Completed Clean Energy Engineering

Virtual Power Plant with Artificial Intelligence for Resilience and Decarbonisation (VPP-WARD)

In plain English

AI plain-English summary

The UK power grid could soon face tens of millions of solar panels, home batteries, and electric vehicle chargers all feeding electricity back and forth at once—and current systems are not built to handle it. Network operators today struggle with limited visibility of these distributed energy resources (DERs), unpredictable two-way power flows, and voltage problems that can destabilise local grids. Storms like Dudley, Eunice, and Franklin in February 2022 left over a million homes without power, and extreme weather is becoming more frequent. This project develops physics-informed artificial intelligence to create a Virtual Power Plant—a system that aggregates and coordinates thousands of small energy devices as if they were a single, controllable power station. If successful, the AI could help operators make better decisions during heatwaves and storms, reduce the duration and frequency of power cuts, and lower energy bills for millions of UK households. It would also accelerate the adoption of DERs and support the UK’s progress toward Net Zero by making the grid both cleaner and more resilient.

View original technical description
Distributed Energy Resources (DERs) are small, modular energy generation and storage units, e.g., wind turbines, photovoltaics, batteries, and electric vehicles, that could be connected directly to the power distribution network. DERs play a critical role in achieving Net Zero. Presently there are over 1 million homes with solar panels in the UK. With the green energy transition well under way in the UK, by 2050 there could be tens of millions of DERs connected to the UK power grid. Although DERs have many benefits, e.g., a reduced carbon footprint and improved energy affordability, they present complex challenges for network operators (e.g., low DER visibility, bi-directional power flow, and voltage anomalies), creating a major barrier to Net Zero. Meanwhile, natural hazards and extreme events are an increasing threat not only to humans but also power grid resilience - a direct impact is the power cuts, e.g., Storms "Dudley", "Eunice" and "Franklin" in February 2022 left over a million homes without electricity. How best to manage millions of DERs is still an open question, especially for improving the grid resilience to natural hazards and extreme events, e.g., storms and heatwaves. This project will develop innovative physics-informed Artificial Intelligence (AI) solutions for enabling Virtual Power Plants (VPP), capable of aggregating and managing many diverse DERs; not only improving decision-making for network operators but also enhancing the grid resilience to natural hazards and extreme events. These could also lead to reduced energy bills for millions of UK energy consumers, less power cuts during extreme events, to greater adoption and more efficient management of DERs, and ultimately to enable rapid progress towards Net Zero.

View the original record at the funder ↗

Researchers

Anish Jindal (Co-Investigator)Aristides Kiprakis (Co-Investigator)Asaad Faramarzi (Co-Investigator)Ashraf Osman (Co-Investigator)Behzad Kazemtabrizi (Co-Investigator)Desen Kirli (Co-Investigator)Gagangeet Singh Aujla (Co-Investigator)Hailiang Du (Co-Investigator)Hongjian SUN (Principal Investigator)JING JIANG (Co-Investigator)Mahmoud Shahbazi (Co-Investigator)Md Apel Mahmud (Co-Investigator)Nicole Metje (Co-Investigator)Peter Matthews (Co-Investigator)Sarah Xiao (Co-Investigator)Sotirios Tsaftaris (Co-Investigator)

Related Research

Grants with similar aims, by meaning.

Decentralised Integration of Renewable Energy sources through smart grid Technologies (DIRECT)
Virtual Power Plant (VPP)
Ebbs and Flows of Energy Systems (EFES)
Virtual Power Plant for Interoperable and Smart isLANDS
Towards Joint Power-Communication System Modelling and Optimisation for Smart Grid Application: Virtual Power Plant (TOPMOST)

Original classification

Research Grant

Plain English summaries and category classifications on this site are generated by AI and may not perfectly reflect the original research.