Exploring grid topology reconfiguration using a simple deep reinforcement learning approach

TL;DR

This paper presents a simple reinforcement learning approach for grid topology reconfiguration, enabling an agent to effectively manage power flows in a test case across diverse scenarios, demonstrating promising adaptability and diversity.

Contribution

A straightforward RL baseline is developed for grid topology control, trained on a single scenario, and shown to operate effectively across multiple demand and generation scenarios.

Findings

Agent operated successfully in 965 out of 1000 scenarios

Demonstrated diverse and efficient topology switching behavior

Effective control with minimal training data

Abstract

System operators are faced with increasingly volatile operating conditions. In order to manage system reliability in a cost-effective manner, control room operators are turning to computerised decision support tools based on AI and machine learning. Specifically, Reinforcement Learning (RL) is a promising technique to train agents that suggest grid control actions to operators. In this paper, a simple baseline approach is presented using RL to represent an artificial control room operator that can operate a IEEE 14-bus test case for a duration of 1 week. This agent takes topological switching actions to control power flows on the grid, and is trained on only a single well-chosen scenario. The behaviour of this agent is tested on different time-series of generation and demand, demonstrating its ability to operate the grid successfully in 965 out of 1000 scenarios. The type and variability of topologies suggested by the agent are analysed across the test scenarios, demonstrating efficient and diverse agent behaviour.