Fast Searching of Extreme Operating Conditions for Relay Protection Setting Calculation Based on Graph Neural Network and Reinforcement Learning

2025-01-16

AI Summary

To address the low efficiency of extreme operating condition (EOC) search for relay protection under high renewable energy penetration, this paper formulates the EOC search as a Markov decision process and proposes a graph neural network (GNN)-based deep reinforcement learning method. We introduce a novel graph-structured Dueling Double DQN architecture that jointly encodes power grid topology and real-time operational states. Furthermore, we design a two-stage guided learning and free exploration (GLFE) training framework to accelerate convergence and enhance generalization. Evaluated on IEEE 39-bus and 118-bus systems, our approach reduces computation time for maximum fault current EOC search by one to three orders of magnitude—while maintaining 100% accuracy. This work establishes an efficient, reliable paradigm for real-time protective relay setting calculation in highly dynamic power systems.

Technology Category

• Search and Optimization: Learning to Search
• Machine Learning: Graph-based Machine Learning
• Planning, Routing, and Scheduling: Planning with Markov Models (MDPs, POMDPs)

Application Category

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

Abstract

Searching for the Extreme Operating Conditions (EOCs) is one of the core problems of power system relay protection setting calculation. The current methods based on brute-force search, heuristic algorithms, and mathematical programming can hardly meet the requirements of today's power systems in terms of computation speed due to the drastic changes in operating conditions induced by renewables and power electronics. This paper proposes an EOC fast search method, named Graph Dueling Double Deep Q Network (Graph D3QN), which combines graph neural network and deep reinforcement learning to address this challenge. First, the EOC search problem is modeled as a Markov decision process, where the information of the underlying power system is extracted using graph neural networks, so that the EOC of the system can be found via deep reinforcement learning. Then, a two-stage Guided Learning and Free Exploration (GLFE) training framework is constructed to accelerate the convergence speed of reinforcement learning. Finally, the proposed Graph D3QN method is validated through case studies of searching maximum fault current for relay protection setting calculation on the IEEE 39-bus and 118-bus systems. The experimental results demonstrate that Graph D3QN can reduce the computation time by 10 to 1000 times while guaranteeing the accuracy of the selected EOCs.

Problem

• Power System
• Renewable Energy
• Computational Speed

Innovation

• Graph D3QN
• Two-stage Training Strategy
• Extreme Case Detection in Power Systems