Skip to main content
Back to KTH start page

AI for Energy

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 and electric vehicles. However, today’s grid cannot handle high penetration of renewables and electric vehiclese, which will cause a violation of grid security. We have developed safe multi-agent deep reinforcement learning algrithms to coordinate inverter interfaced distributed energy resources by making them more adaptive and intelligent to stabilize complex and changing power grids.

Part of our solution is published in Github as open source, and tested in our microgrid hardware platform. Our solution achieves decentralized optimal control without real-time communiation. We are currently collaborating with power converter suppliers and grid operators for practical applications. 

Link: Interview AI protects power grid from fluctuations caus | EurekAlert!  

Part of the solution: Open-source AI based control tool

 

Smart converter figure

 

Funding support:

Swedish Research Council

Swedish Energy Agency

Digital Futures

C3 ai Digital Transformation Institute