Skip to main content

Data-driven control and coordination of smart converters for sustainable power system using deep reinforcement learning

About the project
The goal of this project is to address the voltage instability caused by a high ratio of renewables in sustainable power grids by making the control and coordination of converters of distributed energy resources more intelligent. To that end, we will leverage deep reinforcement learning to train data-driven and communication-efficiently control policies that are able to adapt to the fast fluctuation of renewable energy resources. We will train policies on advanced simulation environments and implement our AI algorithms on real microgrids in our lab at KTH. The developed control policies will allow converters to automatically learn to optimize their interactions with the complex grid environment and achieve a smooth integration of renewables without voltage security violation, thus promoting a climate-neutral society.


Background
Moving towards sustainability and climate security, electric power systems are going through a major paradigm shift with wide integration of distributed energy resources, such as solar PV, wind power, energy storage and electric vehicles. However, today’s grid cannot handle the voltage rise and fast voltage fluctuations from the high penetration of renewables, which will cause a violation of grid security. Power converters of distributed energy resources have full controllability that is promising to be utilized to address this challenge, while it is widely recognized that the lack of adequate control mechanisms to regulate the voltages is a key hindrance. Our belief is that AI and machine learning will play a key role in improving control strategies for converters by making them more adaptive and intelligent to stabilize the complex and changing power grids.

Crossdisciplinary collaboration
This project is a collaboration among KTH EECS, Stockholm University and UC Berkeley.

Follow us on social media to stay updated with our current research

Contacts

Picture of Qianwen Xu

Qianwen Xu

Assistant Professor at KTH, PI of research project Autonomous coordination and control of smart converters for sustainable power systems, PI of research project Data-Driven Control and Coordination of Smart Converters for Sustainable Power System Using Deep Reinforcement Learning at Digital Futures

+46 8 790 63 56
qianwenx@kth.se
Picture of Sindri Magnússon

Sindri Magnússon

Associate professor, Department of Computer and Systems Sciences at Stockholm University, Vice Chair Working group Cooperate at Digital Futures, Co-PI of research project Decision-making in Critical Societal Infrastructures (DEMOCRITUS) at Digital Futures, Co-PI of research project Data-Driven Control and Coordination of Smart Converters for Sustainable Power System Using Deep Reinforcement Learning at C3.ai DTI, Co-Supervisor for postdoc project Distributed Optimization and Federated Learning in Emerging Smart Networks at Digital Futures

+46 8 16 11 15
sindri.magnusson@dsv.su.se
Picture of Robert Pilawa-Podgurski

Robert Pilawa-Podgurski

Associate Professor, Electrical Engineering and Computer Sciences University of California, Berkeley

pilawa@berkeley.edu