储能科学与技术 ›› 2025, Vol. 14 ›› Issue (6): 2439-2441.doi: 10.19799/j.cnki.2095-4239.2025.0504

• 储能系统与工程 • 上一篇    下一篇

基于深度强化学习的储能系统能量管理与优化调度策略

陈勋()   

  1. 赣州师范高等专科学校，江西 赣州 341000
  • 收稿日期:2025-05-28 修回日期:2025-06-04 出版日期:2025-06-28 发布日期:2025-06-27
  • 作者简介:陈勋（1981—），男，硕士，副教授，研究方向为教育教学、数学教育、计算机应用及大数据等，E-mail：xunchen1202@126.com。
  • 基金资助:
    江西省教育厅科学技术研究项目(GJJ2206007)

Energy management and optimal scheduling strategies for energy storage systems based on deep reinforcement learning

Xun CHEN()   

  1. Ganzhou Teachers College, Ganzhou 341000, Jiangxi, China
  • Received:2025-05-28 Revised:2025-06-04 Online:2025-06-28 Published:2025-06-27

RichHTML

1

PDF

2

摘要：

随着“3060”计划的提出以及国家一系列对电力系统改革方案的提出，新能源并网技术得到了大力发展，然而，由于光伏发电随机性较强，使得准确预测光伏发电功率变得较为困难，大规模的光伏电站接入电力系统后，会给电力系统潮流分布和调度运行带来严峻的挑战。本工作提出了基于深度强化学习的优化调度方法，注重其智能性、自调节、动态调整的特点，还对多元目标优化和多层级调度策略做了一些尝试，为储系统高效与可持续发展提供了理论支撑与指导作用。

关键词: 深度强化学习, 储能系统, 能量管理, 优化调度, 多目标优化

Abstract:

With the proposal of the "3060 Plan" and the introduction of a series of reform schemes for the power system, the development of new energy grid connection technology has been vigorously promoted. However, due to the randomness of photovoltaic power generation, accurately predicting photovoltaic power generation has become quite challenging. The large-scale connection of photovoltaic power plants to the power system poses severe challenges to the power system's power flow distribution and scheduling operations. This paper proposes an optimization scheduling method based on deep reinforcement learning, emphasizing its intelligence, self-regulation, and dynamic adjustment characteristics. It also attempts to explore multi-objective optimization and multi-level scheduling strategies, providing theoretical support and guidance for the efficient and sustainable development of energy storage systems.

Key words: deep reinforcement learning, energy storage system, energy management, optimization scheduling, multi-objective optimization

中图分类号: