Learning to run a power network challenge for training topology controllers

Abstract

For power grid operations, a large body of research focuses on using generation redispatching, load shedding or demand side management flexibilities. However, a less costly and potentially more flexible option would be grid topology reconfiguration, as already partially exploited by Coreso (European RSC) and RTE (French TSO) operations. Beyond previous work on branch switching, bus reconfigurations are a broader class of action and could provide some substantial benefits to route electricity and optimize the grid capacity to keep it within safety margins. Because of its non-linear and combinatorial nature, no existing optimal power flow solver can yet tackle this problem. We here propose a new framework to learn topology controllers through imitation and reinforcement learning. We present the design and the results of the first "Learning to Run a Power Network" challenge released with this framework. We finally develop a method providing performance upper-bounds (oracle), which highlights remaining unsolved challenges and suggests future directions of improvement.

References in corpus (2)

• Safe and Nested Subgame Solving for Imperfect-Information Games
• Hierarchical Decision Making In Electricity Grid Management

Cited by in corpus (10)

• Managing power grids through topology actions: A comparative study between advanced rule-based and reinforcement learning agents
• Learning to run a Power Network Challenge: a Retrospective Analysis
• Large-scale Grid Optimization: The Workhorse of Future Grid Computations
• PowerGym: A Reinforcement Learning Environment for Volt-Var Control in Power Distribution Systems
• HUGO -- Highlighting Unseen Grid Options: Combining Deep Reinforcement Learning with a Heuristic Target Topology Approach
• Reinforcement Learning for Electricity Network Operation
• Exploring grid topology reconfiguration using a simple deep reinforcement learning approach
• Understanding the Safety Requirements for Learning-based Power Systems Operations
• Learning Topology Actions for Power Grid Control: A Graph-Based Soft-Label Imitation Learning Approach
• Action Set Based Policy Optimization for Safe Power Grid Management