Physical Informed-Inspired Deep Reinforcement Learning Based Bi-Level Programming for Microgrid Scheduling

TL;DR

This paper introduces a novel deep reinforcement learning-based bi-level programming approach for microgrid scheduling, effectively managing stakeholder interests and flexibility resources under complex conditions.

Contribution

It proposes a new DRL-inspired bi-level optimization method that overcomes non-convex limitations of traditional approaches, integrating AutoML and advanced RL techniques for improved performance.

Findings

Successfully balances stakeholder interests in microgrid operations.

Outperforms existing RL methods in economic and computational metrics.

Effectively exploits flexibility resources for better scheduling.

Abstract

To coordinate the interests of operator and users in a microgrid under complex and changeable operating conditions, this paper proposes a microgrid scheduling model considering the thermal flexibility of thermostatically controlled loads and demand response by leveraging physical informed-inspired deep reinforcement learning (DRL) based bi-level programming. To overcome the non-convex limitations of karush-kuhn-tucker (KKT)-based methods, a novel optimization solution method based on DRL theory is proposed to handle the bi-level programming through alternate iterations between levels. Specifically, by combining a DRL algorithm named asynchronous advantage actor-critic (A3C) and automated machine learning-prioritized experience replay (AutoML-PER) strategy to improve the generalization performance of A3C to address the above problems, an improved A3C algorithm, called AutoML-PER-A3C, is designed to solve the upper-level problem; while the DOCPLEX optimizer is adopted to address the lower-level problem. In this solution process, AutoML is used to automatically optimize hyperparameters and PER improves learning efficiency and quality by extracting the most valuable samples. The test results demonstrate that the presented approach manages to reconcile the interests between multiple stakeholders in MG by fully exploiting various flexibility resources. Furthermore, in terms of economic viability and computational efficiency, the proposal vastly exceeds other advanced reinforcement learning methods.