ML/AI in market designs research use ML methods to construct generative models as inputs to simulation studies, especially power flow, market analysis, and design studies to solve a variety of techniques to solve problems.

In a wider context, Dr Archie Chapman develops and applies principled AI, game theory, optimisation and ML methods to solve large-scale and dynamic allocation, scheduling and queuing problems, including:

  • Approximate dynamic programming, reinforcement learning and policy function approximation used to emulate decision-makers in power systems, from the bidding behaviour of generators down to residential battery scheduling by small customers.

He also applies reinforcement learning to run sample efficient security and stability studies, i.e. to cut down the need to run time-domain simulations.

Project members

Associate Professor Archie Chapman

Associate Professor
School of Electrical Engineering and Computer Science