SAVER: Safe Learning-Based Controller for Real-Time Voltage Regulation

TL;DR

SAVER is a novel safe reinforcement learning-based voltage regulator that ensures system voltages stay within safe bounds in real-time, addressing the challenge of operational constraint satisfaction in uncertain power grids.

Contribution

The paper introduces SAVER, a safe RL controller with a safety projection layer, guaranteeing voltage safety in real-time power grid regulation, a significant improvement over existing data-driven methods.

Findings

SAVER maintains voltage within safe bounds in simulations.

The safety projection layer guarantees operational constraints.

Numerical results validate the effectiveness of SAVER.

Abstract

Fast and safe voltage regulation algorithms can serve as fundamental schemes for achieving a high level of renewable penetration in the modern distribution power grids. Faced with uncertain or even unknown distribution grid models and fast-changing power injections, model-free deep reinforcement learning (DRL) algorithms have been proposed to find the reactive power injections for inverters while optimizing the voltage profiles. However, such data-driven controllers can not guarantee satisfaction of the hard operational constraints, such as maintaining voltage profiles within a certain range of the nominal value. To this end, we propose SAVER: SAfe VoltagE Regulator, which is composed of an RL learner and a specifically designed, computational efficient safety projection layer. SAVER provides a plug-and-play interface for a set of DRL algorithms that guarantees the system voltages to be within safe bounds. Numerical simulations on real-world data validate the performance of the proposed algorithm.