![Behind-the-meter power systems allow energy-intensive facilities – such as data centres, industrial plants and large commercial campuses – to generate or store electricity directly on-site rather than relying exclusively on the public grid. By integrating local energy sources such as natural gas cogeneration, solar PV, battery storage or, where feasible, hydrogen-ready turbines, organizations can reduce exposure to grid congestion and improve operational reliability during peak demand. Behind-the-meter assets also help facilities align consumption with on-site renewables, cutting emissions and strengthening resilience. Analysis by the International Energy Agency (IEA) indicates that decentralized energy resources can support system reliability and improve resilience to grid disturbances.[1] The International Renewable Energy Agency (IRENA) notes that on-site generation paired with storage enhances operational flexibility and mitigates stress on regional grids.[2]Main outcomes of the solution Sustainability: Enables the use of on-site cleaner energy sources, lowering emissions and reducing reliance on carbon-intensive grid electricity; support integration of low-carbon fuels and emerging technologies into industrial and data center operations. Affordability: Reduces exposure to wholesale price volatility and provides greater long-term cost predictability for mission-critical facilities; avoids costly transmission upgrades, connection-queue delays and certain tariff components (e.g., demand charges, transmission fees), improving economics where grid congestion or high connection costs would otherwise increase total energy costs. Reliability & Flexibility: Improves resilience during peak demand, outages or grid congestion by allowing facilities to rely on on-site generation or storage; supports continuity of operations in mission-critical facilities such as data centers, advanced manufacturing sites and logistics hubs. Key implementation and scaling factors Conduct early assessments of load profiles, site constraints, permitting requirements and environmental regulations to confirm the feasibility of on-site generation or storage. Use modular, standardized designs and ensure seamless integration with existing and future facility infrastructure, including mission-critical equipment. Implement rigorous safety, compliance and maintenance frameworks that address hydrogen handling, battery safety codes, emissions standards and operational reliability. Secure resilient fuel-supply and logistics arrangements for natural gas, hydrogen or other clean fuels to ensure uninterrupted behind-the-meter operation. Deploy advanced digital control and energy-management systems to coordinate on-site generation, storage and grid interactions in real time. Address regulatory and market conditions – including tariff structures, standby charges, private-wire rights and self-generation rules – that determine project viability. Manage applicable interconnection, protection and metering requirements to remain compliant with grid-code obligations even when operating primarily behind the meter. Case Study Energy Abundance Development Corp. (under development, 2026 onwards), USAIn Texas, Energy Abundance Development Corp. (formerly Green Hydrogen International) is developing Data City – what it describes as “the world’s largest behind-the-meter data center”– designed to operate independently of the public grid and to be powered by dedicated on-site and local clean fuel generation. The planned 50,000-acre campus near Laredo will initially rely on locally sourced natural-gas generation, with a phased transition to 100% green hydrogen stored in nearby salt-dome caverns.[3]According to the developer, the project will be built in phases, beginning with 300 MW of data-center capacity and 1 million square feet of data-center space targeted for 2026, with an envisaged long-term expansion pathway of up to 5 GW and more than 15 million square feet of leasable space as demand grows. A related green energy hub near Corpus Christi is expected to produce approximately 280,000 tons of green hydrogen and 1 million tons of green ammonia per year, using wind and solar power. As a forward-looking development, the Texas project illustrates how large industrial and data center facilities may use behind-the-meter generation and dedicated clean-fuel supply to secure power availability, stabilize long-term energy costs and bypass grid-connection constraints while supporting the growth of high-density operations. References: Unlocking the Potential of Distributed Energy Resources I IEA (May 2022) Innovation Landscape for a Renewable-Powered Future I IRENA (2019)Energy Abundance Announces Data City, Texas - The World's Largest Behind-the-Meter Data Center Hub Powered by 100% 24/7 Green Energy I PR Newswire (March 2025)](https://fws.weforum.org/images/casestudies/aJYTG00000012ML4AY/standard)
Behind-the-meter
![Behind-the-meter batteries installed at homes, commercial buildings, or industrial sites store electricity on the customer side of the meter, allowing users to manage when and how they consume or export energy. By shifting load, shaving peaks, and supporting self-consumption of on-site renewables, these systems reduce strain on the grid and help smooth local demand profiles. When paired with digital controls, behind-the-meter batteries can also participate in demand-response programs, aggregation schemes and virtual power plants (VPPs). As electrification of end uses increases and renewable output becomes more variable, grid operators face rising challenges from peak loads, local congestion and system balancing. Analysis by the International Energy Agency (IEA) highlights that distributed batteries can provide fast and flexible response and support system stability without major grid upgrades.[1] When integrated into VPPs, behind-the-meter batteries can deliver services such as frequency regulation, peak reduction, reserve capacity and congestion management. Main outcomes of the solution Affordability: Lowers energy costs by reducing peak-demand charges, enabling time-shifting to lower-priced hours, and helping avoid or defer costly grid upgrades where local constraints would otherwise increase system costs. Reliability & Flexibility: Enhances operational continuity by providing fast-response backup during outages or congestion, while enabling flexible dispatch of stored energy for self-consumption, load shifting and local balancing. System Resilience: When aggregated and digitally coordinated, functions as distributed flexibility assets that support frequency stabilization, manage local constraints and reduce reliance on thermal peaker plants during extreme-weather events. Key deployment and scaling factors Analyze load profiles, tariff structures and usage patterns to size batteries correctly and maximize value streams. Use standardized metering and communication protocols for seamless integration with energy-management systems, aggregators and grid operators. Deploy advanced control systems to optimize charging and discharging in real time and coordinate safely with on-site renewables. Ensure compliance with fire-safety codes, permitting requirements and interconnection standards for distributed batteries. Create supportive regulatory frameworks enabling BTM batteries to participate in demand-response and grid-service markets. Establish modular system designs and strong vendor partnerships to streamline rollout and asset management. Address interconnection, protection and metering rules to enable safe import/export capability and VPP participation. Case Studies California Energy Commission and California Independent System Operator (CAISO) (2025), USA California’s Demand-Side Grid Support (DSGS) program compensates households and aggregators that discharge behind-the-meter home batteries during grid stress events, such as heatwaves. DSGS has become a key element of California’s demand-side reliability strategy, complementing CAISO’s resource adequacy framework.[2] In 2025, DSGS recorded its largest activation to date: over 100,000 home batteries delivered approximately 539 MW over two hours, demonstrating the scale and responsiveness of aggregated behind-the-meter resources.[3] Programme guidelines expanded available capacity to around 500 MW, enabling participation from aggregators including Sunrun, Tesla Energy, OhmConnect and others. Under the program framework, aggregators coordinate battery dispatch, CAISO validates performance, and the program administrator Olivine manages settlement and compliance. DSGS is expected to deliver net system savings of approximately USD 28 million to USD 206 million over 2025–2028, depending on market conditions.[3] These savings are driven by avoided procurement of high-cost peak-generation resources and reduced reliance on emergency capacity measures during grid-stress events. Iron Mountain Data Centers (2024), USA In 2024, Iron Mountain Data Centers, in collaboration with the Virginia Department of Energy and with funding from the U.S. Department of Energy, initiated a project to deploy behind-the-meter battery energy storage at its Prince William County data center campus in Virginia. The project is supported by an award of approximately USD 50 million under DOE’s Grid Resilience and Innovation Partnerships (GRIP) program, with additional cost-sharing from private partners. The battery system is installed on the customer side of the meter and is designed to support load management at a large, power-intensive data center site. The system will enable Iron Mountain to shift electricity consumption by charging during lower-cost periods and discharging during peak demand, reducing stress on the local distribution network and supporting more efficient use of grid infrastructure as on-site power demand grows. In addition to load shifting, the battery is intended to improve site-level resilience by supporting critical IT operations during grid disturbances and reducing reliance on diesel backup generation during outages. The project is being used to assess how digitally controlled, behind-the-meter storage at hyperscale and enterprise data centers can contribute to both operational continuity and broader grid-flexibility objectives. The initiative is structured as a replicable deployment model for other data-intensive campuses, providing insights into technical integration, regulatory coordination and the role of large behind-the-meter assets in supporting system reliability as electrification and data-center demand continue to expand.[4, 5] References: Unlocking the Potential of Distributed Energy Resources I IEA (May 2022) Demand Side Grid Support Program I California Energy Commission Calfornia's home batteries are replacing gas plants and saving hundreds of millions I PV Magazine (September 2025) Innovative transmission, energy storage projects in 18 states get USD 2.2B from DOE I Utility Dive (August 2024)IMDC gets grant of USD 50M for developing on site battery storage by VA DoE I Iron Mountain (August 2024)](https://fws.weforum.org/images/casestudies/aJYTG00000012Nx4AI/standard)
Behind-the-meter battery integration
![Carbon capture, utilization and storage (CCUS) encompasses technologies that capture CO₂ emissions from industrial facilities, gas processing plants and fossil-fuel power stations before they enter the atmosphere. Once captured, CO₂ is compressed and transported by pipelines or ships for permanent storage in deep geological formations, or used as feedstock for products such as synthetic fuels, chemicals or construction materials. The International Energy Agency (IEA) highlights CCUS as a critical lever for reducing emissions in hard-to-abate sectors such as cement, steel, chemicals and gas processing.[1] According to the International Renewable Energy Agency (IRENA), achieving global net-zero emission by 2050 would require around 6 Gt of CO₂ per year to be captured and stored by 2040 and more than 8 Gt per year by 2050, across industrial carbon capture and storage (CCS), bioenergy with CCS (BECCS), direct air capture with storage (DACCS) and other carbon-removal pathways. IRENA characterizes the role of carbon capture as “moderate but indispensable” in 1.5°C global energy transition scenario.[2]Main outcomes of the solution Sustainability: Delivers durable emissions reductions by capturing CO₂ at industrial sites and storing it permanently in suitable geological formations, while enabling utilization pathways that provide verifiable long-term climate value. System Resilience: Provides a predictable, infrastructure-based abatement route that supports industrial compliance with tightening climate policies, offering stable, weather-independent emissions mitigation where appropriate geological storage is available. Reliability & Flexibility: Enables reliable production of low-carbon hydrogen, ammonia and natural gas, and supports scalable multi-emitter cluster-based participation through shared CO₂ transport and storage systems that help distribute costs and risks. Key deployment and scaling factors Conduct reservoir characterization and injection-capacity assessments, and develop monitoring frameworks to assess long-term storage integrity, capacity and permanence. Develop shared CO₂ pipeline, compression and storage hubs to reduce costs and streamline multi-emitter participation. Develop and implement regulatory frameworks covering permitting, long-term liability, reporting requirements and cross-border CO₂ transportation. Use modular capture technologies to reduce installation timelines and standardize integration with industrial processes. Establish commercial models for long-term offtake, transport and storage services to enable cost-sharing across clusters. Coordinate closely among industrial operators, pipeline developers, technology vendors and geological agencies to accelerate project delivery. Deploy digital monitoring systems and advanced subsurface modelling to ensure safe, permanent storage performance over time. Advance credible standards for emissions accounting and reporting for CCS power generation projects. Case Studies Petronas, MMHE, NPCC, McDermott and Baker Hughes (Expected 2026), Malaysia Petronas’ Kasawari CCS project in the SK316 gas field offshore Sarawak is designed to capture and store up to 3.3 million tonnes of CO₂ per year, making it one of the largest offshore CCS developments in Asia and globally. CO₂ separated during gas production will be compressed and transported through a subsea pipeline to the depleted M1 reservoir for permanent geological storage. The project is being developed by Petronas Carigali, with engineering contributions from MMHE, NPCC, McDermott and Baker Hughes. Kasawari forms a central element of Malaysia’s strategy to build regional CO₂ storage capacity by leveraging existing offshore assets and favorable geological potential. It demonstrates how large natural-gas operations in Southeast Asia can integrate CCUS at scale, supporting emissions reduction while laying foundation for future multi-emitter transport and storage networks. [3,4,5,8]Low Carbon Infrastructure and Google (2025), USA The Broadwing Energy project in Decatur, Illinois is a natural-gas cogeneration power plant of over 400 MW and greater than 1,500,000 lbs. steam per hour under development by Low Carbon Infrastructure (LCI) and designed with integrated post-combustion carbon capture targeting around 90% CO₂ removal. The Broadwing plant will produce power for Google as well as power and steam for Archer Daniels Midland (ADM). The captured CO₂ is expected to be transported to EPA Class VI geological storage wells operated by ADM, which has already carried out nearly a decade of commercial-scale CO₂ injection, storage and monitoring at their Decatur site. Under a long-term agreement to procure clean, firm electricity, Google intends to use Broadwing as part of its strategy to secure round-the-clock decarbonized power for its data-center operations. The project will also incorporate a new standard for CCS-specific Energy Attribute Certificates (EACs), developed by industry experts to ensure CSS projects can be accurately quantified in emissions reporting. [6] The project shows how CCS can be paired with dispatchable gas generation to support reliable, lower-carbon supply in systems with rising electricity demand. Broadwing is the first project in a longer-term collaboration between Google and LCI highlighting an emerging replicable procurement model in which corporate clean power commitments help enable investment in firm low-carbon assets and early development of next-generation CCS projects in the US power sector.[7]Pertamina, J-Power, JANUS, JGC and ITB (2025), Indonesia The Gundih CCS pilot in Central Java is Indonesia’s first planned onshore carbon-capture and storage project. The design targets the capture of around 300,000 tons of CO₂ per year from the natural-gas processing stream at the Gundih Gas Field, with compression and injection into the nearby Kedungtuban geological structure for permanent storage. The project is being developed by Pertamina in collaboration with J-Power, JGC Corporation, JANUS, and the Institut Teknologi Bandung (ITB), building on feasibility work supported through Japan’s Joint Crediting Mechanism.[8,9]Technical studies to date include reservoir characterization, seismic surveying and front-end engineering design for capture, compression and monitoring systems. While injection operations have not yet begun, the feasibility work indicates an estimated total storage potential of around 3 million tons of CO₂ over a 10-year injection period, subject to reservoir performance and regulatory approvals.[8,9]Gundih is intended to demonstrate the technical and regulatory foundations for CCS deployment in Indonesia following the issuance of Presidential Regulation No. 14/2024 on CCS/CCUS.[10] The project is expected to help build domestic storage expertise, validate Indonesia’s onshore storage capacity and provide an early model for integrating CCS into natural-gas operations across the ASEAN region. References: Net Zero Roadmap: A Global Pathway to Keep the 1.5C Goal in Reach I IEA (2023) Carbon Capture I IRENA McDermott Secures Offshore Contract for the Kasawari Carbon Capture and Storage Project in Malaysia I McDermott (January 2024) Kasawari Gas Development Project, Sarawak, Malaysia I Offshore Technology (February 2023) PETRONAS Carigali Reaches Final Investment Decision for Kasawari CCS Project Offshore Sarawak I Petronas (November 2022) Carbon Capture and Storage Energy Attribute CertificatesOur first carbon capture and storage project I Google (October 2025)CCUS Activities in Indonesia (October 2020) Innovation can accelerate Southeast Asia's energy transition I Atlantic Council (October 2024) Indonesia Moves to Provide Solid Legal Basis for Carbon Capture & Storage I ABNR (April 2024)](https://fws.weforum.org/images/casestudies/aJYTG00000012PZ4AY/standard)
Carbon capture, utilization and storage (CCUS)
![Community-owned geothermal development models are joint structures in which local residents, landholders, or resource-rights owners share ownership and/or governance with a professional project developer. These models can be implemented through a jointly owned Special-Purpose Company (SPC), or through a community-owned company that outsources development and operations. The defining feature is that the community retains rights to the lands and wells and has meaningful influence over decision-making, investment, operations, and long-term revenue allocation. Conventional geothermal development is typically led by commercial developers, with local communities and landowners merely selling their land during the project’s initial stages. The community ownership models differs in that authority and ownership remain with the original owners – the local communities and landowners. Traditional projects may encounter social acceptance challenges, slower permitting and limited local benefit flows. In contrast, community-owned models embed shared governance, transparent financial structures and reinvestment mechanisms that can strengthen trust, improve permitting efficiency and expand local economic value. This supports broader rural development and long-term project stability alongside firm clean energy deployment. Main outcomes of the solution Reliability & Flexibility: Provides firm, weather-independent renewable heat and power that stabilizes supply and reduces reliance on fossil peaking assets. Affordability: Supports lower long-run system costs by adding high-capacity-factor baseload generation and enabling efficient utilization of co-produced heat across local industries. Socioeconomic Impact: Expands equitable energy access and regional economic development through a locally-led structure that optimizes ownership and usage rights, reinvestment of profits, and job creation in geothermal operations, thermal utilization, and regional tourism. Key deployment and scaling factors Establish clear governance and equity structures that guarantee community representation and long-term benefit-sharing from the outset.Deploy targeted public risk-mitigation tools (e.g. exploration guarantees and contingent grants) to address early-stage geothermal drilling risk and attract private capital. Secure bankable revenue streams through long-term electricity and heat off-take agreements that stabilize cash flow for both community and developer. Integrate direct-use heat applications (agriculture, agro-processing, district heating, tourism) to strengthen local economic value and improve overall project economics. Apply transparent digital monitoring and reporting systems that give community shareholders visibility into production, revenues and reinvestment flows. Case Study Baseload Capital and Furusato Netsuden (2011), JapanThe Waita Model is a community-centred geothermal development approach that formalises shared ownership between local landholding stakeholders and a professional developer. The model was developed in connection with the establishment of the 2 MW Waita No. 1 Power Plant in Oguni Town, Kumamoto Prefecture. In 2011, a community-owned limited liability company, Waita-kai, was formed and outsourced the operation of the power plant to the developer Furusato Netsuden. Waita No. 1 began commercial operations in 2015. Through recurring meetings, representatives of Waita-kai and Furusato Netsuden share information and make joint decisions regarding power plant operations, development activities, and budget allocation. The 5 MW Waita No. 2 Power Plant, scheduled for commissioning in 2026, was established via a Special-Purpose Company (SPC) where Furusato Netsuden is the sole shareholder. However, Waita-kai retains the rights to the lands and wells and plans to operate the plant in line with the principles applied at Waita No. 1, including revenue distribution and information sharing. The Waita Model is thus based on two power plants in which local land remains in the hands of its original owners, and the rights to the wells drilled there are held by the local community. The model also enables geothermal heat to be used for local greenhouses, household hot water, food processing, tourism facilities, and wood drying – aiming to diversify income streams and strengthen local economic resilience. Operational progress demonstrates the model’s viability. A 30 MW+ pipeline of additional sites is planned across several regions, applying similar governance and development principles. With only a small share of Japan’s 23 GW geothermal potential currently developed, the Waita Model illustrates how structured community participation and benefit-sharing mechanisms can support socially accepted, scalable geothermal deployment aligned with national clean energy objectives.[1,2,3] References: Global-local alliance powers a new era in Japan’s geothermal energy I Baseload Capital (September 2025) Geothermal energy for the People, by the People I Baseload Capital (October 2025) Furusato Netsuden Company Website](https://fws.weforum.org/images/casestudies/aJYTG00000012fh4AA/standard)
Community-owned geothermal development models
![These types of frameworks define how operators can strategically leverage large electricity consumers during declared emergency conditions and require participating facilities to operate on pre-verified onsite generation. These frameworks are designed for critical events and help stabilize the system by providing rapid load relief when reserves are exhausted. Eligible facilities typically have substantial backup generation – increasingly adopting green hydrogen systems, fuel cells, or battery energy storage – and must demonstrate that essential loads can continue operating safely during disconnection. These frameworks establish standardized technical, commercial and governance procedures for operator-directed curtailment, including requirements for certified remote operation equipment, telemetry, and regular testing. ensuring clear obligations and predictable procedures for both utilities and high-load customers. They also define participation rules, coordination protocols and triggers that align emergency actions with broader reliability objectives, while providing clarity for industrial users on their obligations during scarcity events. Main outcomes of the solution Reliability & Flexibility: Provides operator-directed load relief from large industrial users with proven backup generation, enabling precise and immediate balancing during scarcity events. This stabilizes frequency and voltage, improves system controllability, and supports secure operation under variable and peak-stress conditions. System Resilience: Reduces the likelihood of uncontrolled blackouts by enabling high-load facilities to transition to onsite generation during extreme weather, supply disruptions or sudden demand spikes. Standardized procedures enhance emergency response and reduce the likelihood of cascading outages. Institutional Efficiency & Transparency: Establishes clear rules for participation, disconnection triggers, technical requirements and operator–customer coordination. This improves governance quality, strengthens regulatory trust, and ensures transparent decision-making that aligns long-term reliability obligations with efficient system planning. Key implementation and scaling factorsIntegration of controlled disconnection protocols into grid emergency operations and market rules Mandatory installation of certified shutoff and control equipment at qualifying facilities Transparency and coordination between grid operators, regulators, and large consumers on disconnection triggers and sequencing Incentive-based participation programs for voluntary load reduction or transfer to backup onsite generation Regulatory mechanisms to validate and certify backup power systems (e.g., green hydrogen, fuel cells, BESS) and ensure compliance through testing Cross-sector collaboration between energy, technology, and manufacturing stakeholders to scale resilient energy infrastructure Cybersecurity and data-governance requirements for remote-operation interfaces and control signals Case Study ERCOT and State of Texas (2024), USA In 2024, the State of Texas strengthened ERCOT’s authority through Senate Bill 6, enabling the operator to disconnect or curtail large electricity consumers – including data centers and large industrial facilities – during declared grid emergencies. The regulation targets loads of 75 MW or greater, requiring operators to install certified automated shut-off systems and to register the capabilities and fuel types of their onsite backup generation and provide telemetry to ERCOT. Backup systems deployed by these facilities range from diesel gensets to battery storage and fuel-cell solutions. Disconnection actions are governed by ERCOT’s firm load-shed protocol, which specifies triggers and procedures during Energy Emergency Alert (EEA) conditions. Facilities participating in the framework must integrate remote-operation interfaces to enable ERCOT to curtail load within minutes and participate in regular testing to verify compliance. A parallel voluntary participation program administered by the Public Utility Commission of Texas (PUCT) offers contractual incentives for facilities that agree to reduce load or operate on on-site generation during forecasted shortages. Interconnection agreements and compliance audits ensure visibility of high-load customers and align new large-load requests with ERCOT’s transmission planning and emergency response frameworks.[1]References: Texas law gives grid operator power to disconnect data centers during crisis | Utility Dive (June 2025)](https://fws.weforum.org/images/casestudies/aJYTG00000012hJ4AQ/standard)
Frameworks for turning large loads into strategic grid resources
![Cross-border power trading frameworks allow countries to exchange electricity through interconnected transmission systems and harmonized market mechanisms. By coordinating generation, demand and reserves, these frameworks improve system-wide dispatch efficiency. They also reduce the need for redundant backup capacity by enabling countries to share reserves and balance renewable variability. In turn, this helps limit renewable curtailment by allowing surplus clean energy to flow to neighboring markets when domestic demand is low. Regional integration also promotes competition and transparency through shared rules and coordinated scheduling and common settlement systems that enable cost-reflective pricing and access to a more diversified supply mix. Over time, such cooperation builds trust among national utilities and regulators, enabling progressively deeper market integration and the eventual formation of regional power pools. In an increasingly electrified energy landscape, cross-border trading is a cornerstone of both reliability and decarbonization, transforming fragmented national systems into cohesive and optimized networks. Main outcomes of the solution Sustainability: Enables power to flow across borders, reducing curtailment and supporting decarbonization Reliability & Flexibility: Enhanced system security through reserve sharing, regional balancing and access to a more diversified supply mix Institutional Efficiency & Transparency: Trust built through harmonized governance, transparent market rules and coordinated operations Key deployment and scaling factors Expansion and reinforcement of cross-border transmission interconnectors – including capacity upgrades, synchronous/asynchronous links and secure cross-border transfer capability – to support reliable power flows. Coordinated approaches for financing interconnectors and regional balancing assets, including allocation of capital costs, regulated returns, risk-sharing frameworks and long-term cross-border agreements. Alignment of grid codes, market rules, tariff structures, scheduling procedures, and system-operator protocols across participating countries. Effective multilateral bodies (e.g., regional coordination centers, system operators or market operators) to oversee implementation and compliance. Robust digital systems for power product trading, cross-border capacity booking, coordinated reserve dispatch, common settlement systems and cybersecurity safeguards. Real-time data exchange, forecasting and contingency analysis systems that maintain visibility, security and efficiency of cross-border operations. Political commitment and agreements among governments and regulators that sustain cross-border initiatives over time and provide confidence to investors. Case StudiesLao PDR–Thailand–Malaysia–Singapore Power Integration Project (2022), Southeast Asia The Lao PDR–Thailand–Malaysia–Singapore Power Integration Project (LTMS–PIP) is Southeast Asia’s first multi-country framework for coordinated electricity transfers, enabling hydropower generated in Laos to be transmitted through Thailand and Malaysia to Singapore.[1] The initiative establishes harmonized technical, regulatory and settlement arrangements across four national grids, creating a foundation for rules-based cross-border power trading in the region. Operational since 2022, LTMS–PIP enables up to 200 MW of cross-border electricity flows under its most recent Phase II framework.[1] By mid-2023, over 265 GWh had been traded, demonstrating technical feasibility and institutional cooperation across participating system operators.[2]LTMS-PIP represents a significant institutional innovation for ASEAN, offering a replicable model for phased regional integration and advancing the long-term ASEAN Power Grid vision.[3] The project was developed by Électricité du Laos (EDL), EGAT (Thailand), Tenaga Nasional Berhad (Malaysia), and Keppel (Singapore), under a license issued by Singapore’s Energy Market Authority.[1] Nord Pool (1996), Northern Europe Nord Pool is the world’s first multinational power exchange and a leading example of deep, long-term cross-border market integration. It operates as a Nominated Electricity Market Operator (NEMO) in 16 European countries1, providing unified day-ahead and intraday trading supported by harmonized market rules, coordinated capacity allocation and interoperable digital systems. Today, Nord Pool facilitates more than 1,100 TWh of annual trading volumes across its bidding zones, underscoring its role as one of the largest and most liquid electricity markets globally. In recent years, Nord Pool has continued to shape some of Europe’s most advanced cross-border market frameworks. As a key NEMO in both the Single Day-Ahead Coupling2 (SDAC) and Single Intraday Coupling (SIDC) systems, it participates in market arrangements that now connect 20 European countries into a single price-formation process. Nord Pool has played a central role in the implementation of flow-based market coupling, which allocates cross-border capacity based on detailed network constraints; multi-NEMO arrangements, allowing multiple power exchanges to operate within the same bidding zone; and successive expansions of SIDC, enabling continuous intraday trading across an increasingly integrated European system. Additional enhancements – including strengthened clearing and collateral frameworks and improved digital interoperability – support stable cross-border operation amid rising renewable penetration, increased price volatility and higher intraday balancing needs. Nord Pool’s evolution illustrates how advanced market integration can scale over time through shared platforms, transparent governance and systematic rule harmonization. It remains a global reference point for regions seeking to develop or deepen power-pooling arrangements and cross-border electricity markets.[5,6,7] References: Singapore Doubles Power Import Capacity Under LTMS-PIP Phase 2 I Energy Market Authority (September 2024) Status of Southeast Asia Interconnectivity under ASEAN Power Grid I ASEAN Centre for Energy (October 2023) Unlocking Regional Power Trade: Policy Pathways for the ASEAN Power Grid I ASEAN Business Advisory Council (July 2025) Our business | Nord Pool Company Website Nord Pool reports robust trading figures for 2023 | Nord Pool (January 2024) Nord Pool Connection Power Futures Deal Moves Forward I Nord Pool (June 2025)](https://fws.weforum.org/images/casestudies/aJYTG00000012iv4AA/standard)
Cross-border power trading and regional integration
![Demand response programs use price incentives, grid-stress notifications and increasingly automated controls to shift or reduce electricity consumption during peak periods. These mechanisms balance supply and demand more efficiently than traditional network reinforcement, lower system costs and enable households and businesses to participate directly in grid stability. Modern demand-side management differs from earlier, seasonal peak-shaving schemes by operating year-round, integrating digital metering and enabling verifiable load flexibility across residential, commercial and industrial customers. Policy and regulatory reforms play a central role: dynamic pricing rules, standardized baseline methodologies, aggregator licensing and market-access provisions allow flexible demand to participate alongside generation in wholesale, balancing and capacity markets. These frameworks mark a shift from treating consumers as passive recipients to recognizing flexible demand as a formal system resource that improves system efficiency and supports higher levels of renewable integration.[1,2]Main outcomes of the solution Reliability & Flexibility: Provides fast, dispatchable load adjustments that help system operators balance renewable variability, manage peak constraints and stabilize frequency and voltage. Automated controls and digital metering make flexible demand a predictable, verifiable resource in routine system operations. Affordability: Reduces peak demand, lowering wholesale price spikes and deferring grid and generation investment. More efficient asset utilization reduces system operating costs and supports lower consumer bills over time. Sustainability: Absorbs surplus renewable generation and reduces dependence on carbon-intensive peak supply, decreasing curtailment and supporting electrification while limiting the environmental impacts of grid expansion. Key deployment and scaling factors Clear regulatory frameworks to ensure predictable market access and support consistent procurement of demand-side resources. Dynamic pricing structures to encourage customers to shift demand away from peak periods. Automated controls to deliver fast and verifiable flexibility across residential, commercial, and industrial loads. Aggregation models to expand participation by combining small, distributed loads into market-ready resources. Interoperable data and device standards to reduce integration complexity and enable broader scaling of flexible demand. Transparent incentives and consumer protections to strengthen participation and long-term engagement. Digital readiness at household and business level, including smart meters and interoperable devices that support automated response. Case Study National Energy System Operator (NESO) (2022), United Kingdom The UK’s Demand Flexibility Service (DFS) enables households, businesses and aggregators to be rewarded for reducing or shifting electricity consumption during grid-stress periods. Launched in winter 2022/23 as a contingency tool, DFS evolved into a year-round “merit-based margin” mechanism in 2024. In the 2024/25 winter period, approximately 1.98 million customer connections (MPANs) were registered, and DFS events delivered around 3,917.7 MWh of reduced or shifted demand at a cost of £1.2 million (≈ USD 1.5 million) for contracted capacity. NESO estimates system-balancing savings of roughly £500,000 (≈ USD 650,000) across the season. During activation windows, the aggregated response was sufficient to momentarily meet the equivalent demand of over 12 million homes, illustrating the scale of flexible demand available through coordinated participation. DFS allows NESO to procure demand-side flexibility in competition with generation, reducing reliance on expensive peaking resources, lowering balancing costs and improving the integration of renewable generation.[3]References: World Energy Outlook 2025 I IEA (2025) Innovation landscape for smart electrification I IRENA (June 2023) Nearly 2 million households and businesses registered for Demand Flexibility Service (DFS) last winter | NESO (July 2025)](https://fws.weforum.org/images/casestudies/aJYTG00000012kX4AQ/standard)
Demand response programs
Megawatt-scale EV charging
![A standardized remote-island hybrid microgrid is a repeatable solution for modernizing isolated power systems that still rely heavily on diesel generation. It combines solar photovoltaic generation, battery energy storage, an energy management system, and dispatchable backup generation within a standardized engineering design and delivery approach that can be adapted to different island load profiles and operating conditions. This matters because small and remote islands often face some of the highest electricity costs in the world, while also dealing with limited grid infrastructure, fuel import dependence, and high exposure to outages and extreme weather. A standardized approach reduces the need to redesign each project from the ground up, which can shorten development timelines, simplify procurement and installation, and improve consistency in performance across sites. Technically, the hybrid architecture uses solar power to reduce fuel consumption, batteries to manage variability and provide short-duration balancing, and dispatchable backup generation to maintain security of supply when renewable output is low or demand spikes. These systems are typically operated as isolated or weak-grid microgrids coordinated through an energy management system that optimizes generation, storage, and load in real time. Strategically, this approach shifts remote-island decarbonization from bespoke engineering toward a more scalable deployment model. This can support expansion of clean power access, reduce long-run operating costs, improve resilience, and enable replication across island and off-grid communities.[1,2] Main outcomes of the solution Reliability & Flexibility: The combination of solar photovoltaic, battery storage, and dispatchable backup generation improves supply stability, enables higher penetration, and enhances operational flexibility in isolated systems. System Resilience: Reduced dependence on imported fuels and diversified generation sources strengthen the ability of island systems to withstand and recover from disruptions, including extreme weather events. Affordability: Lower diesel consumption reduces fuel import costs, transport logistics, and maintenance requirements, while standardized designs reduce engineering and procurement costs. Sustainability: Increased integration of renewable generation lowers greenhouse gas emissions and local air pollution associated with diesel-based power systems. Key implementation and scaling factors Conduct targeted site assessments to map existing diesel configurations, load profiles, and operating constraints to ensure appropriate system sizing and integration. Optimize integration of solar photovoltaic, battery storage, and backup generation to balance renewable penetration, system stability, and lifecycle cost in stand-alone operation. Establish standardized engineering, procurement, and construction frameworks to improve delivery efficiency, quality control, and replicability across sites. Implement remote monitoring, testing, and maintenance protocols to ensure system performance where local technical capacity and site access are constrained. Design modular system architectures to enable incremental capacity expansion as demand evolves. Develop scalable financing and procurement models, including aggregation across multiple sites, to improve bankability and reduce transaction costs. Build local technical and operational capacity to support long-term system management, maintenance, and resilience. Case study Trinasolar (2020), Maldives In 2020, Trinasolar implemented a solar–storage–diesel hybrid microgrid program in the Maldives as an example of modernizing remote island power systems. The deployment spans multiple islands and combines solar photovoltaic generation, battery energy storage systems, diesel generators, and a centralized energy management platform to reduce reliance on imported fuel while maintaining secure electricity supply. The program applies a standardized delivery approach across sites with different load conditions, integrating engineering, procurement, and installation processes. This model is suited to island contexts, where limited infrastructure, fuel logistics, and exposure to disruption increase the cost and vulnerability of conventional power supply. According to Trinasolar3, the program spans 27 islands and achieves approximately 1.3 million liters of annual diesel savings, alongside improved stability of electricity supply for residents and public services. This example illustrates how standardized hybrid microgrid models can support the transition of diesel-dependent island systems toward cleaner and more flexible configurations, while maintaining dispatchable backup capacity and enabling replication across similar geographies. Solution and insights developed with contributions from CESA. References: Islands need resilient power systems more than ever. Clean energy can deliver – Analysis - IEA Batteries and Secure Energy Transitions – Analysis - IEA From Shore to Grid, Trinasolar Lights Up Island Communities - Trinasolar](https://fws.weforum.org/images/casestudies/aJYTG0000001FJZ4A2/standard)
Standardized remote-island hybrid microgrid
Hybrid multi-duration BESS for fast response and long-duration flexibility
![AI-driven price forecasting uses advanced machine learning and AI models to predict short-, medium- and long-term wholesale electricity prices with higher accuracy and faster processing than traditional statistical approaches. As power systems become more volatile – due to high renewable penetration, extreme-weather events, storage participation and shifting demand patters – price signals fluctuate more rapidly and are harder to anticipate. AI systems can process large volumes of historical, meteorological, market and asset-level data to identify complex, non-linear relationships that conventional approaches may miss. These models may include methods such as gradient boosting, random forests and neural networks, which are widely used to capture complex relationships across multiple forecasting horizons. These models typically combine engineered inputs (e.g. detailed weather forecasts, interconnector flows, outages, congestion indicators) with algorithms designed to capture patterns across multiple time horizons. Many AI tools also generate probabilistic forecasts, helping users understand expected price distributions rather than relying on single point predictions. By improving the precision of wholesale market forecasts, AI tools support more informed investment planning, risk management and operational decision making for utilities, traders, renewable developers and storage operators. They help market participants anticipate price spikes, congestion events and renewable-generation swings, strengthening financial performance and improving the bankability of clean-energy projects. Main outcomes of the solution Business Value: Enhances risk management and revenue optimization through more accurate price forecasts, enabling more confident renewable energy investment decisions, hedging strategies and storage-dispatch planning. Reliability & Flexibility: Supports more efficient system balancing by helping participants anticipate variability, congestion and renewable intermittency, enabling improved bidding strategies and operational planning. Key deployment and scaling factors Develop robust data pipelines integrating market, weather, demand, generation, transmission and congestion datasets across multiple timescales, supported by strong data quality and governance processes. Test, back test and validate multiple machine learning algorithms to identify the most accurate and stable method for each market and forecasting horizon, using transparent error metrics and performance evaluation across historical periods. Implement explainability and transparency tools so users can understand key forecast drivers, build trust in model outputs and support regulatory acceptance. Ensure interoperability with trading, risk management and operational planning platforms, allowing seamless integration into day-ahead, intraday and futures trading processes. Establish continuous retraining and performance monitoring processes to maintain accuracy as market fundamentals evolve (renewable penetration, policy shifts, new flexibility resources, weather trends). Assess regulatory or compliance requirements where AI-based forecasts influence market-facing activities, ensuring alignment with accepted standards for risk and data use. Case Study Hitachi Energy (2023), Switzerland Hitachi Energy launched Nostradamus AI, a machine-learning-based forecasting system designed to improve electricity price predictions across global wholesale markets. According to the International Energy Agency (IEA) Energy & AI Observatory and Hitachi Energy, the system evaluates more than ten machine-learning algorithms and selects the best-performing model for each market and forecasting horizon.[1,2] It can generate forecasts for a range of energy-specific variables, including system load, wind and solar generation, and market prices, and allows users to integrate their own datasets and parameters to produce customized forecasts. A 2023 case study using datasets from CAISO and MISO (United States) and AEMO (Australia) indicates that Nostradamus AI achieved forecast accuracies of up to 93% for selected horizons, based on performance metrics presented by Hitachi Energy within the scope of that case study.[3] This case illustrates how AI-based forecasting tools are being applied to compare multiple modelling approaches and produce market-specific price predictions, reflecting growing interest in purpose-built forecasting systems for increasingly variable power markets. References: Energy and AI Observatory I IEA (June 2025) Nostradamus®AI Energy Forecasting Software Solution I Hitachi Hitachi Energy advances predictability of energy investments forecasting with new AI-powered solution I Hitachi (November 2024) Nostradamus AI: How Hitachi Secures Renewables in the Grid I AI Magazine (November 2024)](https://fws.weforum.org/images/casestudies/aJYTG00000012Cf4AI/standard)
AI-driven electricity price forecasting
![AI-enhanced digital technologies combine advanced analytics, machine learning and automated data processing tools to support optimization of nuclear construction and plant operations. These approaches use large engineering datasets, real-time sensor information and structured digital models to improve how construction activities are sequenced, how equipment health is monitored and how operational decisions are supported. Deployed at scale, these tools can turn nuclear project delivery and operations into more standardized, repeatable industrial processes. In nuclear construction, AI can assist with generating work packages, identifying workflow dependencies and improving schedule planning. In operations, AI models support the detection of abnormal conditions, estimation of equipment degradation and maintenance planning. As the nuclear sector introduces more standardized reactor designs, digital platforms incorporating AI can help coordinate supply chain activities and improve consistency across projects. They can also enhance knowledge transfer between projects by capturing lessons learned in digital twins and design platforms. These tools can also support regulatory documentation by structuring data and maintaining traceable, auditable records. Overall, AI-enabled digital systems provide utilities and developers with enhanced analytical capabilities but remain dependent on integration with established nuclear engineering practices, safety cases and regulatory oversight processes.[1] [2]Main outcomes of the solution Business Value: Improves project execution discipline and delivery predictability by supporting more repeatable construction processes and data-driven operational decision-making. This strengthens confidence in nuclear project delivery and supports scalable deployment of standardized reactor designs. Greater predictability helps attract capital and reduce perceived risk. Affordability: Reduces project development and operational costs by automating elements of construction planning, lowering manual engineering effort and supporting maintenance actions that help prevent equipment failures. These efficiencies can limit rework, reduce schedule risk and lower unplanned maintenance costs. Over time, these gains can drive down the cost of new nuclear capacity and life extension. Key deployment and scaling factors Establish access to structured, high-quality engineering and construction datasets suitable for AI model training and validation. Integrate AI tools with digital plant design platforms, construction management systems and operational data environments. Implement robust cybersecurity, data integrity and regulatory compliance frameworks appropriate for nuclear facilities. Develop workforce capabilities spanning AI and data science, nuclear engineering and digital engineering, supported by change management practices. Case Study Westinghouse Electric Company and Google Cloud, (2024), USA Westinghouse and Google Cloud announced a collaboration to apply AI-enabled digital tools to accelerate nuclear plant construction and enhance the operation of existing nuclear facilities. Westinghouse’s HiVE system, introduced in 2024 and built on more than 75 years of proprietary nuclear engineering data, incorporates a nuclear-specific large language model known as Bertha. As part of the collaboration, Westinghouse paired its HiVE and Bertha platforms with Google Cloud technologies, including Vertex AI, Gemini and BigQuery. A first-of-a-kind proof of concept was demonstrated using Westinghouse’s WNEXUS digital plant design platform to autonomously generate and optimize modular construction work packages for the AP1000 reactor. The collaboration is intended to support more repeatable construction processes for advanced reactor designs, including the AP1000, AP300 small modular reactor and eVinci microreactor concepts, while also extending AI-enabled analytics to plant operations such as predictive maintenance and equipment-health monitoring. The case illustrates how AI-enabled digital systems can strengthen execution discipline and operational insight in nuclear projects, while remaining subject to established nuclear safety, quality and regulatory requirements.[1][2]Solution and insights developed with contributions from the World Nuclear Association. References: Westinghouse, Google aim to speed up reactor construction with AI I World Nuclear News (July 2025) Westinghouse and Google Cloud partner on AI platform](https://fws.weforum.org/images/casestudies/aJYTG00000012Ft4AI/standard)
AI-enhanced digital technologies for nuclear supply chain and operational optimization
![Heating, ventilation and air conditioning (HVAC) systems are typically among the most energy-intensive components of commercial and public buildings, often accounting for 35–65% of total energy use depending on building type and climate. AI-powered HVAC systems enhance efficiency by combining digital sensors, predictive analytics and adaptive control. As highlighted by the International Energy Agency (IEA), AI can model a building’s thermal behavior, forecast occupancy patterns and anticipate shifts in weather conditions – enabling HVAC systems to adjust proactively rather than reactively.[1]Instead of relying on fixed rule sets, AI-enabled systems continuously evaluate real-time indoor conditions, external temperatures, historical data and user behavior to determine the lowest-energy configuration that maintains comfort. Over time, the algorithm refines its understanding of the building’s dynamics, improving energy performance, extending equipment lifespan and reducing operational oversight requirements. This makes AI-powered HVAC a practical tool for improving efficiency and supporting low-carbon building operations.[2]Main outcomes of the solution Sustainability: Optimizes energy consumption by dynamically adjusting heating and cooling to actual demand, reducing electricity and district-heating use and supporting lower operational emissions. Affordability: Energy bills by forecasting occupancy and thermal loads, reducing unnecessary heating and cooling, and improving HVAC equipment efficiency throughout the year. Key implementation and scaling factors Ensure robust sensor infrastructure and high-quality data collection to support accurate AI training, continuous optimization and fault detection. Integrate AI tools with existing building-management systems (BMS) to enable scalable deployment across large building portfolios without major hardware replacement. Implement clear governance, data-protection and cybersecurity measures to safeguard operational data and build trust in automated decision-making. Equip facility managers and operational teams with training to interpret AI recommendations, oversee performance and embed insights into routine maintenance and optimization practices. Case Study Schneider Electric's Sustainability Research Institute and Skolfastigheter i Stockholm AB (SISAB)(2018), SwedenThe Schneider Electric partnered with Skolfastigheter i Stockholm AB (SISAB) – which oversees more than 600 educational buildings – to deploy an AI-powered HVAC optimization system integrated with the existing building management system. The platform combined real-time data from indoor sensors, weather forecasts and occupancy-related patterns with adaptive control algorithms that continuously adjusted HVAC operations to maintain comfort while reducing energy use. Across the evaluation period, the deployment delivered measurable efficiency gains: electricity consumption decreased by 8.93% and district-heating use by 3.12%, after weather normalization. The system achieved an average annual carbon saving of 64.8 tCO₂e, and the study reports a carbon cost–benefit ratio of 1:60 per year, meaning each unit of carbon associated with implementation resulted in sixty units avoided annually. By applying AI-based HVAC optimization consistently across SISAB’s large and diverse building portfolio, SISAB identified statistically robust reductions in both energy consumption and associated carbon emissions, while indoor comfort conditions were maintained. These outcomes illustrate how digital approaches can translate into measurable sustainability improvements when implemented at scale. The analysis also highlighted practical integration considerations, including computational demands and interactions with legacy HVAC systems, emphasizing the importance of digital readiness for scaling AI applications in buildings. Overall, the project demonstrates how AI-powered HVAC optimization can support sustainability and affordability objectives across large public-sector building portfolios.[3]References:Energy and AI World Energy Outlook Special Report I IEA (2023) Artificial Intelligence and Big Data I IRENA (2019) AI-Powered HVAC in Educational Buildings I Schneider Electric (December 2024)](https://fws.weforum.org/images/casestudies/aJYTG00000012HV4AY/standard)
AI-powered HVAC
![AI-enabled microgrids integrate onsite renewable generation, battery energy storage systems (BESS) and intelligent energy management algorithms to optimize local energy use, strengthen resilience and support flexible operation in both grid-connected and islanded modes. These systems typically combine machine learning forecasting with model-predictive or optimization-based control, using short scheduling intervals to determine when to consume, store or export electricity based on expected demand, renewable availability and tariff signals. A cloud edge architecture is often used, with forecasting and optimization performed centrally and real-time dispatch executed locally by the microgrid controller. By coordinating solar PV, batteries and backup generation with advanced supervisory controls, AI-informed microgrids support continuity of supply during grid disturbances, reduce energy costs through peak-shaving and tariff optimization, and increase utilization of onsite renewable energy. Environmental benefits depend on local grid mix characteristics, tariff design and available flexibility, but AI can help align economic and sustainability outcomes where regulatory and system conditions are supportive. AI-enabled microgrids are increasingly deployed in commercial facilities, airports, industrial sites, campuses and remote or underserved regions, where they provide cleaner and more reliable power without extensive grid upgrades. Main outcomes of the solution Reliability & Flexibility: Supports more stable operation by enabling controlled transitions between grid-connected and islanded modes, and by applying predictive or optimization-based control to maintain balanced microgrid performance under variable renewable output and demand. System Resilience: Enables real-time local balancing and supports autonomous operation during outages or extreme events, helping maintain priority loads and critical services when the main grid is compromised. Business Value: Helps reduce energy costs through peak shaving and time-of-use optimization, increases the effective use of onsite solar and storage assets and may enable participation in demand-response or export programs where permitted. Key deployment and scaling factors Integrate onsite DERs (solar PV, BESS, backup generators and flexible loads) with an energy-management system incorporating forecasting and optimization capabilities. Implement predictive or optimization-based control to schedule generation, storage and load operation in accordance with tariffs, demand patterns and resilience priorities. Ensure robust real-time control and protection, cybersecurity measures and support for controlled transitions between grid-connected and islanded modes. Use modular or pre-engineered microgrid designs to simplify deployment and enable replication across commercial, industrial or remote applications. Define operational strategies and configuration settings for resilience, including islanding procedures, renewable-first dispatch, peak-shaving logic and DER prioritization. Ensure interoperability with utility and DER communication standards to support integration with grid operations. Align tariff structures and grid mix characteristics to ensure that cost-optimized dispatch supports low-carbon operation where system conditions allow. Case study Schneider Electric (2023), Global In 2023, Schneider Electric began a two-year empirical assessment of 11 operational microgrids across Europe, North America and Australia to evaluate how AI-based optimization affects operating costs and greenhouse gas emissions. Using the EcoStruxure™ Microgrid Advisor platform, the study tested whether economic optimization alone can deliver emissions reductions under real-world tariff and grid conditions. Results show that AI can reduce both costs and emissions where price signals reflect carbon intensity, but can increase emissions where those signals diverge. AI therefore amplifies existing market incentives rather than acting as an independent decarbonization mechanism. A 24/7 agrifood cold-storage logistics facility in South Australia demonstrated the strongest alignment between cost and emissions outcomes. The site operates 2.5 MW of solar PV (14.7:1 PV-to-load ratio), supported by battery storage and high thermal inertia from refrigeration. Compared with heuristic control, AI-based dispatch reduced annual electricity costs by €124,500 (–21.6%) and emissions by 328.6 tCO₂e, yielding an abatement cost of – €379/tCO₂e. The optimization objective was purely economic, with no explicit carbon constraints. Three implementation features enabled this outcome. First, high PV penetration with export capability allowed surplus solar generation to be consumed onsite or exported, displacing higher-carbon grid generation. Second, thermo-electrical flexibility enabled pre-cooling during low-carbon midday periods and reduced grid reliance during evening peaks. Third, alignment between time-of-use prices and carbon intensity ensured that cost-minimizing dispatch avoided high-emissions periods: low-price midday electricity coincided with low carbon intensity, while high-price evening periods coincided with higher emissions. The same AI logic produced different outcomes in other regions. In California sites, where prices reflected capacity scarcity rather than emissions intensity, AI optimization reduced costs by ~€27,500 but increased emissions by 51 tCO₂e. Across the portfolio, successful replication required four conditions: tariffs correlated with carbon intensity, sufficient onsite renewables, operational flexibility (battery and/or thermal), and permission to export electricity. Where these conditions were absent, AI improved economics but did not support emissions reduction.[1,2] References: Accelerating Microgrid Projects: From Start to Finish I Schneider Electric (June 2025) AI-Powered Microgrids: The Path Toward Coupling Economic and Environmental Benefits I Schneider Electric (October 2025)](https://fws.weforum.org/images/casestudies/aJYTG00000012J74AI/standard)
AI-powered microgrids
![Extreme weather events – including large hail – are becoming more frequent and severe, creating new operational risks for utility-scale solar assets. Traditional manual risk-mitigation approaches often cannot respond quickly enough to rapidly forming convective storms. Automated, data-driven climate-resilience systems use predictive meteorology, engineering insights and machine-to-machine automation to anticipate potential impacts and initiate protective actions ahead of damaging events. These systems combine long-range weather monitoring, short-range storm prediction and automated tracker control to reduce exposure to hail-related damage and support asset availability. By embedding meteorological intelligence directly into operational workflows, operators can move from reactive, manual intervention toward more proactive, automated protection strategies that help preserve generation output and extend asset lifetimes. Main outcomes of the solution Reliability & Flexibility: Reduces the likelihood of unplanned outages and asset damage by automatically positioning PV trackers in defensive stow configurations ahead of hazardous weather events. System Resilience: Improves the ability of solar plants to withstand extreme hail conditions through predictive weather modelling, rapid automation and enhanced operational standards. Business Value: Avoids or limits costly equipment damage and replacement, reduces post-event downtime and supports continuity of energy production during extreme-weather events. Key deployment and scaling factors Integrate long-range and short-range meteorological intelligence to provide early situational awareness and precise storm-cell forecasting. Deploy automated tracker-control systems capable of receiving digital hazard signals and autonomously moving PV modules into predefined defensive stow positions. Develop geospatial visualization tools to support real-time monitoring, operator oversight and rapid event response. Embed engineering research and procurement specifications that reduce hail vulnerability at the module-design and operational-standards level. Establish operational protocols that link predictive alerts to automated actions while maintaining availability outside defined hazard windows. Case StudyLightsource bp (2021), USA Lightsource bp developed Project Whiskeyball to address increasing hail risk for utility-scale PV assets. The program combines engineering research, predictive meteorology and automated control to shift hail-response operations from manual and reactive processes toward digital, anticipatory protection. The system uses a multi-layered defense approach. Long-term storm pattern monitoring provides early awareness, enabling operations teams to proactively schedule defensive measures. Short-range automation approach where, if storms develop unexpectedly, predictive algorithms assess whether approaching cells will produce hail and calculate potential impact trajectories relative to solar assets. When credible risk is identified, PV trackers automatically move to a defensive stow position, typically 30 minutes before projected impact. Advanced geospatial visualization tools accelerate monitoring and response times, ensuring complete situational awareness during rapidly evolving weather events. Finally, ongoing collaboration with research laboratories continuously refines procurement specifications and operational standards, strengthening the system's resilience. The system’s performance was demonstrated during a severe hail event in Pueblo, Colorado in July 2023. While surrounding areas experienced damage, the automated stow procedure was executed as designed and no material damage was reported at the protected site. Lightsource bp has also indicated that the presence of a documented, automated hail-mitigation framework supports risk discussions with insurers, although outcomes remain asset- and market-specific.[1]References:Company information provided to World Economic Forum I Lightsource bp (December 2025)](https://fws.weforum.org/images/casestudies/aJYTG00000012Kj4AI/standard)
Automated climate-resilience systems for PV assets
![Early Framework Agreements (EFAs) are modular contracting structures that create stable, repeatable partnerships between utilities, suppliers and public authorities to accelerate grid expansion and modernization. They define consistent commercial, technical and governance terms across multiple projects, enabling earlier initiation of engineering, procurement and permitting activities while maintaining flexibility to adapt to system needs as they evolve. Traditional project-by-project contracting often results in fragmented delivery, duplicated risk assessment and long procurement cycles. EFAs replace these short-cycle tenders with programmatic delivery models that allow standardized designs, clearer risk allocation and economies of scale. This supports more predictable scheduling, improves supply-chain visibility and enables faster build-out of transmission and distribution assets needed for renewable integration and electrification. By introducing consistent delivery frameworks, EFAs help reduce total program costs, improve coordination among stakeholders and strengthen supply-chain resilience. They provide more predictable investment flows and clearer execution pathways for large-scale infrastructure programs. Main outcomes of the solution Reliability & Flexibility: Accelerates delivery of multiple grid projects under consistent technical and commercial frameworks, improving the ability to integrate variable renewables and meet rising network-capacity needs. Affordability: Standardized designs, long-term contracting and early procurement enhance economies of scale, lower total system cost and provide more predictable expenditure profiles. Institutional Efficiency & Transparency: Strengthens coordination between utilities, regulators and suppliers through structured governance, shared risk mechanisms and transparent program oversight. Key implementation and scaling factors Initiate early engineering and procurement to secure manufacturing slots, reduce schedule risk and align permitting activities across multiple projects. Adopt common technical specifications and template designs to reduce interface risks and allow suppliers to deliver repeatable components across multiple projects. Establish clear governance structures to manage multi-party coordination, risk allocation and accountability. Ensure regulatory alignment so that framework models fit within existing approval and cost-recovery structures. Case StudiesTenneT, GE Vernova and Seatrium (2025), Germany In December 2025, TenneT awarded a contract to a consortium comprising GE Vernova and Seatrium for the delivery of BalWin5, a 2.2 GW high-voltage direct current (HVDC) offshore grid connection designed to transmit electricity from wind farms in the German North Sea to the onshore grid at Bremen-Werderland. BalWin5 forms part of TenneT’s programme to expand offshore grid connections using a standardized 2 GW+ design. GE Vernova and Seatrium will also realize the 2 GW offshore grid connections of three Dutch TenneT projects to the onshore grid at Maasvlakte, Port of Rotterdam. The award is the fourth project granted to the GE Vernova–Seatrium consortium under a five-year Framework Cooperation Agreement announced in March 2023, and the first under this framework for TenneT’s German 2 GW projects. The framework establishes common technical specifications, delivery models and commercial terms to support repeatable execution across multiple offshore grid connections. Under the contract, GE Vernova’s Electrification Systems business will deliver the complete HVDC technology, including the onshore and offshore converter stations and associated control and protection systems. Seatrium will design, build, transport and install the offshore converter platform, with fabrication planned at its facilities in Singapore and Batam. Construction is scheduled to commence in January 2026, with commissioning planned for 2032. In parallel, TenneT has also put in place its largest framework arrangement for 2 GW offshore grid projects with Hitachi Energy and Larsen & Toubro and with Siemens Energy and Dragados, covering multiple HVDC converter stations across the North Sea. Together, these arrangements underline TenneT’s strategy of using early framework agreements and standardized designs to ensure supplier continuity, industrial scale-up and more predictable delivery of complex offshore transmission infrastructure.[1,2]RTE (2024), FranceIn 2024, RTE, France's transmission system operator, contracted with five European suppliers – Prysmian, Nexans, NKT-SolidAl and Hellenic Cables – to secure high-voltage underground cable supplies through 2028. The nearly €1 billion (USD 1.15 billion as of Sep 2026) commitment covers the supply and installation of approximately 5,200 km of 90-400 kV cables. RTE's procurement strategy combines earlier demand anticipation, equipment standardization, larger purchasing volumes and framework contracts extended from five to eight years, with the aim of providing manufacturers with greater visibility over future demand. The contracts reserve almost all French cable production capacity still available through 2028, including production of more than 1,700 km of cables in France. RTE reported that the greater demand visibility enabled Prysmian to invest in a new cable production line in Seine-et-Marne, illustrating how longer-term procurement commitments can support additional manufacturing capacity while securing strategic equipment for grid expansion. [3]References: GE Vernova and Seatrium secure a major contract from TenneT to connect North Sea wind power to Germany’s grid | GE Vernova (December 2025) L&T Joins Hitachi Energy to Support TenneT’s 2GW Offshore Wind Grid Scheme I Energy News (October 2025) RTE strengthens its strategic supplies and contributes to developing French industry | Prysmian](https://fws.weforum.org/images/casestudies/aJYTG00000012m94AA/standard)
Early framework agreements
![Investment-origination and acceleration models create a repeatable commercial pathway for scaling early-stage climate-smart enterprises by structuring how business-development support, risk assessment and capital mobilization are delivered as a coordinated service offering across an impact capital continuum - from early-stage validation through investment readiness to blended and commercial finance. Rather than treating technical assistance, pipeline development and investor matchmaking as separate activities, the model bundles them into an integrated, revenue-backed framework that sequences support over time, improving investment readiness and enabling enterprises to progress from early innovation support to blended and, where viable, commercial capital more reliably. The innovation lies in formalizing the business processes that convert early-stage ventures – often lacking financial systems, ESG compliance or bankable plans – into investable opportunities. Providers build a pipeline, apply standardized diagnostics, offer tailored enterprise development services, structure de-risking instruments and package opportunities for investors through sequenced support and partnerships that align concessional, blended and commercial capital. This reduces transaction costs for financiers and creates a predictable flow of viable projects in markets where investment pipelines are typically fragmented or thin. By turning origination and readiness support into a structured business model – with defined service tiers, performance metrics and investment outcomes – the approach helps scale climate-smart technologies such as solar irrigation, cold chains and energy efficient processing, while strengthening productive-use power systems and local value creation in underserved markets. Main outcomes of the solution Business Value: Strengthens early-stage enterprises by improving their investment readiness and enabling access to blended or commercial finance at appropriate stages of maturity, unlocking capital for climate-smart technologies and supporting commercially viable growth in underserved markets. Socioeconomic Impact: Supports inclusive development by enabling enterprises to scale solutions that improve livelihoods, strengthen resilience and expand access to sustainable energy and productive-use technologies, including across agri-food and water systems. Key deployment and scaling factors Expertise in technical assistance and market-readiness support to prepare early-stage ventures for investment, including financial modelling, ESG compliance and operational standardization. Ability to mobilize and blend concessional capital, guarantees or other risk mitigation instruments with private-sector investment across an impact capital continuum, ensuring continuity between early-stage support and later-stage finance. Cross-sector capability (energy, agri-food, water) to support diverse climate-smart and low-carbon business models where power for productive use is a key enabler of resilience and economic viability. Local presence and partnerships in emerging-market contexts to navigate regulatory, social and market complexity and sustain enterprise support over time. Clear governance and monitoring frameworks for pipeline management, ensuring transparency for investors and donors. Case Study SNV (scaling announced 2026), GlobalImplemented across Africa and Asia, the OASIS approach builds on SNV programs such as Innovations Against Poverty (IAP), 2SCALE, Climate Resilient Agribusiness for Tomorrow (CRAFT), the Dutch Fund for Climate and Development (DFCD) and EEP Africa, linking early-stage innovators to blended and commercial investors through a structured origination and acceleration model that enables progression across the impact capital continuum. As aid budgets tighten, grant funding must increasingly act as catalytic capital - bridging the persistent gap between early-stage innovation and blended or commercial finance SNV’s approach streamlines diagnostics, technical assistance and risk-mitigation tools to improve investment readiness for enterprises in sectors where climate-smart technologies require clearer commercial and ESG evidence to attract capital. A recent example is Solar Green Energy (SOGE), Cambodia’s largest solar irrigation provider. Solar Green Energy (SOGE) was initially supported through early-stage, grant-based technical assistance under Innovations Against Poverty (IAP), before progressing into DFCD-supported origination and investment readiness as the business matured and capital needs increased. Prior to engagement, SOGE faced constraints typical of early-stage distributed-energy enterprises: limited financial documentation, unclear revenue structures and gaps in environmental and social safeguards. Through the OASIS model, SOGE received support to improve financial systems, strengthen ESG procedures and prepare investment materials for a proposed USD 13 million expansion. This second phase focused on investment-grade financial structuring, ESG strengthening and targeted de-risking, positioning the company for blended and commercial finance. The technical assistance focused on the design of 18 new solar-powered irrigation stations expected to serve over 18,000 hectares of rice farmland. The model also helped refine SOGE’s commercial structure, including standard water service contracts and cost recovery plans, improving visibility on cash flows and operational risks. These changes strengthened the case for blended financing and helped de-risk the project for investors, demonstrating how targeted technical assistance and origination can bridge the gap between early innovation and scalable investment. SOGE operates 19 existing solar stations and has installed more than 3,000 solar units with farmers. The expansion supported under the origination model is expected to reach 10,800 farming families, increase yields and incomes by up to 50 percent, and reduce greenhouse-gas emissions by roughly 50 percent relative to diesel-based irrigation. The project demonstrates how structured origination and investment-preparation processes can expand the investable pipeline for distributed renewable-energy solutions in markets where early-stage ventures often lack the systems and documentation required to access blended or commercial capital by providing continuity between early innovation grants and later-stage finance.[1]References: Powering Cambodia’s future: solar irrigation for climate resilience | SNV (May 2025)](https://fws.weforum.org/images/casestudies/aJYTG00000012xR4AQ/standard)
Investment origination and acceleration model
![Short-term electricity prices can change quickly, and many parts of the energy system rely on accurate price forecasts to plan operations, trade power and manage risk. Foundation model–based probabilistic price forecasting uses a pre-trained time-series model to generate short-term wholesale electricity price distributions. Instead of training a bespoke forecasting model for each market, the method adapts a large time-series model that has already learned general temporal patterns from diverse datasets. The forecasting workflow involves two distinct steps. First, the model is applied to reconstruct missing values in historical price series, producing a consistent input dataset. Second, the same model generates probabilistic forecasts that describe a range of plausible future prices rather than a single point estimate. Because the model relies on representations learned during pre-training, it can remain robust during periods of elevated volatility, when price behavior deviates from historical norms. This reduces the need for extensive feature engineering and hyperparameter tuning while supporting faster deployment across markets.[1,2] Main Outcomes of the Solution Reliability & Flexibility: Supports consistent short-term price forecasting during volatile market conditions by leveraging generalized temporal patterns learned during large-scale pre-training, reducing sensitivity to regime shifts. Business Value: Shortens model development and deployment timelines for price forecasting, enabling trading, hedging and operational planning without requiring large, highly specialized modelling teams. Key Deployment and Scaling Factors Ensure clean and complete wholesale price datasets aligned with official market index definitions. Apply robust missing-data reconstruction methods to produce a consistent historical price series. Use systematic back-testing approaches, such as daily walk-forward evaluation, to assess performance under changing market conditions. Design deployment architectures that allow extension to additional markets through configuration changes and limited fine-tuning. Provision appropriate compute resources to support efficient inference, with stable numerical precision suitable for probabilistic outputs. Case Study Accenture (2025), United Kingdom For anonymous client. The forecasting system was evaluated using Great Britain’s Market Index Data (MID), a half-hourly wholesale electricity price series published under the Market Index Definition Statement. The dataset covered the period from late 2016 through October 2025 and included price data only, without supplementary inputs such as demand, weather or fuel prices. The foundation model was adapted to this dataset and assessed using a daily walk-forward evaluation framework. Performance remained stable across the full sample, including the highly volatile market conditions observed during 2021–2022. The implementation was operationally lightweight: training, fine tuning and full-day inference were executed on a single consumer-grade GPU, enabling integration into trading, hedging and operational planning workflows without significant infrastructure requirements. While further development is underway to incorporate additional explanatory variables and deeper fine-tuning, the price-only configuration provides a transparent and reproducible baseline for probabilistic short-term electricity price forecasting.[3]References:API Documentation I Exelon Probabilistic Price Forecasting for Day-Ahead and Intraday Markets: Beyond the Statistical Model I Sustainability Vol. 9 Issue 11 (October 2017)Information provided to World Economic Forum (November 2025)](https://fws.weforum.org/images/casestudies/aJYTG000000133t4AA/standard)
Foundation model-based short-term electricity price probabilistic forecasting
![Data-driven geospatial planning is redefining how countries pursue universal electrification. By combining satellite imagery, population mapping, infrastructure datasets, and renewable resource assessments, these tools calculate least-cost electrification pathways for underserved communities. Rather than relying solely on conventional network expansion, governments and utilities can simulate investment scenarios and coordinate grid, mini-grid, and off-grid options with spatial precision. These platforms allow planners to assess updated geospatial access gaps, renewable potential, and connection costs. The approach turns electrification planning into an evidence-based, spatially optimized process – reducing planning uncertainty, improving transparency, and supporting more equitable access expansion. Main outcomes of the solutionAffordability: Identifies least-cost grid, mini-grid, and off-grid pathways, lowering total investment needs and reducing cost per connection. Socioeconomic Impact: Helps governments and developers target underserved and low-income regions, expanding access for households, schools, and enterprises. Institutional Efficiency & Transparency: Uses open-data platforms and transparent modelling frameworks to improve coordination among public agencies, investors, and civil society. Key deployment and scaling factors Availability of high-resolution geospatial data covering population, demand, and infrastructure. Integration of grid, mini-grid, and off-grid systems in least-cost modelling. National adoption of data-driven electrification plans supported by clear policy frameworks. Open-data standards and stakeholder engagement to promote transparency and coordination. Skilled personnel in GIS analysis and energy modelling across utilities and planning agencies. Robust data governance and interoperability standards to harmonize datasets across institutions. Case StudiesWorld Resources Institute (WRI) (2023), Kenya, Uganda, Tanzania The Energy Access Explorer (EAE), developed by the World Resources Institute (WRI), is an open-source geospatial platform designed to strengthen evidence-based energy planning. The tool aggregates datasets on energy supply, demand, environment, infrastructure, and socioeconomic factors to identify priority areas for expanding modern energy services. Initially implemented in Kenya, Uganda, and Tanzania, EAE was co-developed with national and local governments, utilities, and civil society to improve data accessibility and coordination. According to WRI and analysis from partners such as the International Growth Centre, the platform has reached more than 23,000 users and broadened access to consolidated planning data. It has helped reduce manual data-collection requirements for national planners and accelerated preparation of electrification scenarios and renewable-energy plans. By consolidating fragmented datasets into a single open-access interface, EAE has supported more timely decision-making and improved institutional collaboration toward expanding energy access in East Africa.[1]World Bank Group (2020), Sub-Saharan African countries The World Bank’s Energy Sector Management Assistance Program (ESMAP) has supported least-cost geospatial electrification planning across nine Sub-Saharan African countries, including Kenya, Malawi, Mozambique, Uganda, and Zambia, with further countries added in subsequent cycles. The program has also informed national electrification strategies in Ethiopia, Kenya, Mozambique, Myanmar, and Malawi. Its freely accessible web-based planning tool enables users to model multiple scenarios for achieving universal access, combining open data with country-specific inputs. ESMAP complements this with training, technical assistance, and grants that strengthen GIS-based planning capacity and harmonize data standards across participating governments.[2,3,4,5]References: Electricity Access Explorer: An open access tool to enable data-driven energy planning I State Fragility Initiative (2024) The Global Electrification Platform 3.0 I World Bank Blogs (July 2024) Integrated Electrification Strategies and Planning I ESMAP New Open-Source Tool a Breakthrough in Electrification Planning I World Bank Group (July 2017) Integrated Electrification Planning Accelerating Progress towards SDG7 I World Bank Group (November 2020)](https://fws.weforum.org/images/casestudies/aJYTG000000135V4AQ/standard)
Geospatial least-cost electrification planning
![The grid edge comprises secondary substations, feeders, distribution transformers and customer-side connection points where real-time operational decisions increasingly need to be made. Advanced edge-compute platforms run key automation and operational functions directly at these locations, enabling low-latency actions—such as voltage regulation, congestion relief and fault mitigation – that cannot be delivered efficiently through fully centralized architectures. These systems virtualize functions that traditionally required dedicated hardware, improving situational awareness and supporting rapid, automated interventions as network conditions evolve. Traditional architecture depends on slower, centralized analytics with limited visibility at the grid edge, limiting their ability to manage rapid fluctuations from distributed renewables, EV charging, and dynamic loads. Edge-based systems address these constraints by executing compute-intensive functions closer to the network periphery while maintaining coordination with a central platform. Advanced optimization algorithms – including quantum-inspired techniques where appropriate for complex decision problems – can support localized demand adjustments, feeder reconfiguration and congestion relief. This hybrid architecture preserves system-wide visibility while enabling faster and more reliable operational responses across highly distributed grids. Main outcomes of the solution Reliability & Flexibility: Distributed intelligence at the grid edge improves responsiveness to rapid changes in demand, voltage and congestion conditions by enabling low-latency local control actions and automated decision support. System Resilience: Edge devices maintain local operational continuity during disturbances by supporting fast demand adjustments, secure remote switching and coordinated actions that help contain disruptions and restore service more quickly. Affordability: Virtualizing multiple automation functions on a single edge-compute platform can reduce substation hardware requirements, optimize local resource use, defer selected reinforcements and target only the minimal number of participants needed for system relief. Key implementation and scaling factors Define priority grid-edge use cases with clear operational outcomes to guide investment focus and ensure measurable value from early deployments. Establish a scalable hybrid architecture that allocates system-wide analytics to the core platform while delegating real-time decisions to distributed edge nodes. Implement robust data governance and cybersecurity measures to safeguard sensitive operational data and maintain confidence in digital decision-support tools. Integrate interoperability standards and open APIs to ensure seamless coordination among field devices, platforms, and external flexibility providers. Align regulatory and financial frameworks to recognize digital and distributed intelligence as approved cost components and to incentivize performance-based outcomes. Benchmark quantum-inspired or advanced optimization methods against classical approaches to verify where they provide operational advantages Case Study Gridspertise (2025), Colombia In 2025, Gridspertise launched a deployment of its Quantum Edge® devices in Colombia leveraging distributed intelligence to improve operational flexibility and strengthen the grid’s ability to manage stress conditions. The device is a multipurpose edge-computing platform that virtualizes key automation functions at secondary substations, enabling real-time monitoring, automated fault detection and remote control of network assets. According to project reporting, during a significant peak-stress event the system used advanced optimization logic to initiate a targeted demand-reduction action. Participation from 21 commercial and industrial users—around 0.01% of the customer base – contributed to a load reduction exceeding 12%, helping avoid service disruptions for an area serving more than 300,000 customers.[1,2,3]The pilot demonstrates how distributed intelligence at the grid edge can improve responsiveness and operational flexibility, reducing the need for widespread customer participation while supporting resilience under rapidly evolving grid conditions. References: Advancing Latin America's Power System Transformation I World Economic Forum (October 2025) Our technology for smarter, resilient power systems in Latin America | Gridspertise (October 2025) QEd - Quantum Edge® device I Gridspertise](https://fws.weforum.org/images/casestudies/aJYTG00000013774AA/standard)
Grid-edge intelligence and automation