Deep Reinforcement Learning for Long-Term Voltage Stability Control

Deep reinforcement learning (DRL) is a machine learning-based method suited for complex and high-dimensional control problems. In this study, a real-time control system based on DRL is developed for long-term voltage stability events. The possibility of using system services from demand response (DR) and energy storage systems (ESS) as control measures to stabilize the system is investigated. The performance of the DRL control is evaluated on a modified Nordic32 test system. The results show that the DRL control quickly learns an effective control policy that can handle the uncertainty involved when using DR and ESS. The DRL control is compared to a rule-based load shedding scheme and the DRL control is shown to stabilize the system both significantly faster and with lesser load curtailment. Finally, when testing and evaluating the performance on load and disturbance scenarios that were not included in the training data, the robustness and generalization capability of the control were shown to be effective