Load Shedding Scheme with Deep Reinforcement Learning to Improve Short-term Voltage Stability

In this paper, a novel load shedding scheme against voltage instability with deep reinforcement learning (DRL). The convolutional neural networks (CNNs) are chosen to automatically learn the features and exploit the local spatial correlations from TS data of voltages. The DRL load shedding controller interacts with system dynamics through a sequence of observations, actions and rewards with two convolutional neural networks, namely critic and actor networks. The critic network is used to evaluate the quality of the load shedding actions and the actor network to determine the time, location and amounts of load shedding (LS). A global reward function is defined considering the recovery characteristics of voltages and total load shedding amounts to guarantee the coordination of under voltage load shedding (UVLS). The simulation is performed on the modified New England 39-bus system, and the results validate the voltage recovery performance and load shedding amount of the proposed scheme under different scenario.