Supervised Reinforcement Learning for the Coordination of Distributed Energy Resources

Unofficial AI-generated summary based on the public title and abstract. Not an official translation.

🔬研究者:This paper introduces a novel SRL framework that combines supervised pre-training and RL fine-tuning for DER coordination, offering a new training paradigm for multi-agent energy systems.

🏢実務担当者:The framework can be applied by utilities or aggregators to improve DER management and reduce operational costs, with high sample efficiency making it feasible for real-world deployment.

🏛政策担当者:Policymakers should note the potential of AI-driven DER coordination to enhance grid reliability and support renewable integration, which could inform regulations on DER market participation.

The increasing integration of distributed energy resources (DERs) is crucial for power system decarbonization, yet unlocking DERs' flexibility is challenged by their inherent uncertainties and modelling complexity. As traditional optimization methods struggle with such uncertainty and complexity of DERs, reinforcement learning (RL) has emerged as a promising alternative for DER management. However, standard RL methods suffer from sample inefficiency and sub-optimality when trained from scratch. Inspired by the training paradigms in large language models, this paper proposes a Supervised Reinforcement Learning (SRL) framework for learning DER coordination policies. This framework first pre-trains a policy on demonstration data in a supervised-learning fashion, which is then further fine-tuned using RL. Furthermore, we propose a two-step fine-tuning process: offline fine-tuning for enhancing policy performance and online fine-tuning for adapting it to the real-world dynamics. Experiments demonstrate that RL implementations based on the proposed framework significantly outperform all benchmarks, achieving high cost efficiency even under low-quality demonstration data.

• arXiv https://arxiv.org/abs/2606.24947first seen 2026-06-25 04:11:52