Real-time security margin control using deep reinforcement learning

Topology-aware reinforcement learning for tertiary voltage control

“…In the context of ACOPF, neural networks can either be trained by imitation (supervised learning) or by interaction with a simulator through Reinforcement Learning (RL) [7]. Recent work explores the application of deep neural networks to ACOPF [8], while others [9], [10], [11], [12] frame the ACOPF problem as a closed-loop RL problem.…”