PowerNet: Multi-agent Deep Reinforcement Learning for Scalable Powergrid Control

TL;DR

This paper introduces PowerNet, a multi-agent deep reinforcement learning algorithm for scalable, decentralized powergrid control, demonstrating superior performance and efficiency in microgrid simulations compared to traditional methods.

Contribution

PowerNet is a novel on-policy MARL algorithm that incorporates spatial discounting and learned communication for effective decentralized powergrid control.

Findings

Outperforms traditional model-based control methods.

Shows high sample efficiency and scalability in large power grids.

Effective in microgrid simulations with uncertain conditions.

Abstract

This paper develops an efficient multi-agent deep reinforcement learning algorithm for cooperative controls in powergrids. Specifically, we consider the decentralized inverter-based secondary voltage control problem in distributed generators (DGs), which is first formulated as a cooperative multi-agent reinforcement learning (MARL) problem. We then propose a novel on-policy MARL algorithm, PowerNet, in which each agent (DG) learns a control policy based on (sub-)global reward but local states from its neighboring agents. Motivated by the fact that a local control from one agent has limited impact on agents distant from it, we exploit a novel spatial discount factor to reduce the effect from remote agents, to expedite the training process and improve scalability. Furthermore, a differentiable, learning-based communication protocol is employed to foster the collaborations among neighboring agents. In addition, to mitigate the effects of system uncertainty and random noise introduced during on-policy learning, we utilize an action smoothing factor to stabilize the policy execution. To facilitate training and evaluation, we develop PGSim, an efficient, high-fidelity powergrid simulation platform. Experimental results in two microgrid setups show that the developed PowerNet outperforms a conventional model-based control, as well as several state-of-the-art MARL algorithms. The decentralized learning scheme and high sample efficiency also make it viable to large-scale power grids.