Scholarlink

<p>This paper proposes a deep reinforcement learning-based framework for optimizing photovoltaic (PV) and energy storage system scheduling. By modeling the control task as a Markov Decision Process and employing the Soft Actor-Critic (SAC) algorithm, the system learns adaptive charge/discharge policies under uncertain solar generation and dynamic load conditions. Experiments conducted on three datasets demonstrate that the proposed method consistently outperforms rule-based and model predictive control baselines in cost reduction, peak load minimization, and operational safety. The results confirm SAC’s robustness, generalization capability, and suitability for real-world smart grid energy management.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

An integrated scheduling and optimization approach for photovoltaic-storage systems using deep reinforcement learning

  • 期刊论文

  • 发表日期：

    2025年10月13日

查看全文
  • Zeyu Yang

摘要

This paper proposes a deep reinforcement learning-based framework for optimizing photovoltaic (PV) and energy storage system scheduling. By modeling the control task as a Markov Decision Process and employing the Soft Actor-Critic (SAC) algorithm, the system learns adaptive charge/discharge policies under uncertain solar generation and dynamic load conditions. Experiments conducted on three datasets demonstrate that the proposed method consistently outperforms rule-based and model predictive control baselines in cost reduction, peak load minimization, and operational safety. The results confirm SAC’s robustness, generalization capability, and suitability for real-world smart grid energy management.