Safe Reinforcement Learning for Grid Voltage Control

TL;DR

This paper introduces safe reinforcement learning methods for grid voltage control, ensuring safety during emergency voltage recovery, demonstrated through simulations on a standard power system benchmark.

Contribution

It proposes two novel safe RL approaches—constrained optimization and Barrier function-based—for emergency voltage control in power grids.

Findings

Effective voltage recovery demonstrated on IEEE 39-bus system

Safe RL approaches outperform traditional load shedding methods

Methods ensure system safety during emergency control

Abstract

Under voltage load shedding has been considered as a standard approach to recover the voltage stability of the electric power grid under emergency conditions, yet this scheme usually trips a massive amount of load inefficiently. Reinforcement learning (RL) has been adopted as a promising approach to circumvent the issues; however, RL approach usually cannot guarantee the safety of the systems under control. In this paper, we discuss a couple of novel safe RL approaches, namely constrained optimization approach and Barrier function-based approach, that can safely recover voltage under emergency events. This method is general and can be applied to other safety-critical control problems. Numerical simulations on the 39-bus IEEE benchmark are performed to demonstrate the effectiveness of the proposed safe RL emergency control.