Graph Convolutional Network-Based Topology Embedded Deep Reinforcement Learning for Voltage Stability Control

Abstract

Topology changes happen frequently in power systems and can impose significant challenges to traditional controllers of power systems. Recent studies revealed the strength of deep reinforcement learning (DRL) based approaches in power system preventive and corrective control. But topological variations are difficult to capture using classical fully connected neural network (FCN) model and has not been explicitly modeled in previous work. Hence, we develop a Graph Convolutional Network (GCN) based DRL framework to tackle topology changes in power system voltage stability control design. The GCN model helps the DRL agent to better capture topology changes and spatial correlations in nodal features. Our GCN based approach is evaluated using the IEEE-39 bus system and it outperforms the FCN-based DRL scheme in terms of training convergence and control performance considering grid topology changes.