A Reinforcement Learning Approach to Parameter Selection for Distributed Optimal Power Flow

TL;DR

This paper introduces a reinforcement learning method to adaptively select penalty parameters in distributed optimal power flow problems, significantly improving convergence speed and robustness over heuristic methods.

Contribution

It develops a deep Q-learning based policy for penalty parameter selection in ADMM for ACOPF, demonstrating substantial acceleration and generalizability.

Findings

Up to 59% reduction in iteration count compared to heuristic methods.

Policy generalizes well to unseen loading and system loss scenarios.

Provides proof-of-concept for RL in parameter tuning for power system optimization.

Abstract

With the increasing penetration of distributed energy resources, distributed optimization algorithms have attracted significant attention for power systems applications due to their potential for superior scalability, privacy, and robustness to a single point-of-failure. The Alternating Direction Method of Multipliers (ADMM) is a popular distributed optimization algorithm; however, its convergence performance is highly dependent on the selection of penalty parameters, which are usually chosen heuristically. In this work, we use reinforcement learning (RL) to develop an adaptive penalty parameter selection policy for the AC optimal power flow (ACOPF) problem solved via ADMM with the goal of minimizing the number of iterations until convergence. We train our RL policy using deep Q-learning, and show that this policy can result in significantly accelerated convergence (up to a 59% reduction in the number of iterations compared to existing, curvature-informed penalty parameter selection methods). Furthermore, we show that our RL policy demonstrates promise for generalizability, performing well under unseen loading schemes as well as under unseen losses of lines and generators (up to a 50% reduction in iterations). This work thus provides a proof-of-concept for using RL for parameter selection in ADMM for power systems applications.