Learning Topology Actions for Power Grid Control: A Graph-Based Soft-Label Imitation Learning Approach

2025-03-19

AI Summary

To address the challenges of transmission congestion management under high renewable energy penetration and the poor generalizability of conventional single-solution topology control policies, this paper proposes a graph-structured soft-label imitation learning method. The approach leverages power system simulations to generate soft labels—probabilistic action outcomes—thereby modeling a distribution over multiple feasible topology actions for each system state, relaxing the restrictive assumptions of hard labels and single-optimal-action policies. Incorporating domain-specific topological priors, it employs a Graph Neural Network (GNN) to jointly embed system states and topology actions. Experimental results demonstrate that the proposed method significantly outperforms state-of-the-art baselines: it achieves superior generalization and robustness in topology control tasks and improves performance by 17% over a greedy expert agent.

Technology Category

• Machine Learning: Imitation Learning & Inverse Reinforcement Learning
• Search and Optimization: Sampling/Simulation-based Search
• Planning, Routing, and Scheduling: Learning for Planning and Scheduling

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Energy management for devices in mobile Web and WoT environments
• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems

Abstract

The rising proportion of renewable energy in the electricity mix introduces significant operational challenges for power grid operators. Effective power grid management demands adaptive decision-making strategies capable of handling dynamic conditions. With the increase in complexity, more and more Deep Learning (DL) approaches have been proposed to find suitable grid topologies for congestion management. In this work, we contribute to this research by introducing a novel Imitation Learning (IL) approach that leverages soft labels derived from simulated topological action outcomes, thereby capturing multiple viable actions per state. Unlike traditional IL methods that rely on hard labels to enforce a single optimal action, our method constructs soft labels over actions, by leveraging effective actions that prove suitable in resolving grid congestion. To further enhance decision-making, we integrate Graph Neural Networks (GNNs) to encode the structural properties of power grids, ensuring that the topology-aware representations contribute to better agent performance. Our approach significantly outperforms state-of-the-art baselines, all of which use only topological actions, as well as feedforward and GNN-based architectures with hard labels. Most notably, it achieves a 17% better performance compared to the greedy expert agent from which the imitation targets were derived.

Problem

• Addresses power grid congestion management challenges
• Proposes soft-label imitation learning for adaptive grid control
• Integrates Graph Neural Networks for topology-aware decision-making

Innovation

• Soft-label Imitation Learning for grid control
• Graph Neural Networks encode grid structures
• Multiple viable actions captured per state