Multi-Agent Safe Policy Learning for Power Management of Networked Microgrids

TL;DR

This paper introduces a supervised multi-agent safe policy learning method for power management in networked microgrids, ensuring operational safety and feasibility through constraint-aware training and distributed optimization.

Contribution

It proposes a novel constrained policy learning approach that incorporates grid operational constraints and privacy-preserving distributed training for microgrid management.

Findings

The method guarantees safe and feasible power dispatch decisions.

Distributed training preserves microgrid privacy and data ownership.

Numerical experiments validate the effectiveness of the proposed approach.

Abstract

This paper presents a supervised multi-agent safe policy learning (SMAS-PL) method for optimal power management of networked microgrids (MGs) in distribution systems. While conventional reinforcement learning (RL) algorithms are black-box decision models that could fail to satisfy grid operational constraints, our proposed method is constrained by AC power flow equations and other operational limits. Accordingly, the training process employs the gradient information of operational constraints to ensure that the optimal control policy functions generate safe and feasible decisions. Furthermore, we have developed a distributed consensus-based optimization approach to train the agents' policy functions while maintaining MGs' privacy and data ownership boundaries. After training, the learned optimal policy functions can be safely used by the MGs to dispatch their local resources, without the need to solve a complex optimization problem from scratch. Numerical experiments have been devised to verify the performance of the proposed method.