储能科学与技术

• XXXX • 上一篇    下一篇

基于深度强化学习和多目标粒子群优化的储能容量配置方法

牟雪鹏1,2(✉)，蔡权2,3，周依然2,3，李庆生1,2，张裕1,2(✉)   

  1. 1. 贵州电网公司电网规划研究中心，贵州贵阳550002
    2. 贵州省新型电力系统运行控制全省重点实验室，贵州贵阳550000
    3. 贵州电网公司电网规划研究中心人才工作站，贵州贵阳550002
  • 收稿日期:2025-10-15 修回日期:2025-11-27
  • 通讯作者: 张裕 E-mail:19166871@qq.com;zhangyu830906@163.com
  • 作者简介:牟雪鹏（1982-），男，硕士学位，高级工程师，主要研究方向：从事电力系统继电保护、新型电力系统技术研究，E-mail：19166871@qq.com 张裕（1983-），男，硕士学位，工程师，主要从事电网新技术应用研究、电网规划设计。E-mail：zhangyu830906@163.com
  • 基金资助:

    南方电网公司重点科技项目，（GZKJXM20220031）

    贵州省科技计划项目，（ZSYS（2025）007）

Energy Storage Capacity Configuration Method Based on Deep Reinforcement Learning and Multi-Objective Particle Swarm Optimization

MOU Xuepeng1,2(✉)，CAI Quan2,3，ZHOU Yiran2,3，LI Qingsheng1,2，ZHANG Yu1,2(✉)   

  1. 1. Power Network Planning Research Center of Guizhou Power Grid Corporation, Guiyang 550002,China
    2. Guizhou Provincial Key Laboratory of New Power System Operation Control ,Guiyang 550000 , China
    3. Guizhou Power Grid Company Power Grid Planning Research Center Talent Workstation,Guiyang 550002, China
  • Received:2025-10-15 Revised:2025-11-27
  • Contact: ZHANG Yu E-mail:19166871@qq.com;zhangyu830906@163.com

摘要： 随着新能源大规模并网，其出力的间歇性与随机性给电力系统稳定运行带来挑战，储能合理容量配置对提升系统可靠性、促进新能源消纳至关重要。本文提出基于深度强化学习（DRL）与多目标粒子群优化（MOPSO）的储能容量配置方法：首先分析电力系统运行特性与储能接入需求，构建含风光、负荷的系统模型，明确配置约束与多目标优化目标；其次利用DRL学习复杂环境下储能运行策略，通过DRL智能体与电网环境交互输出充放电时序控制建议，将该建议作为MOPSO的粒子初始化边界与搜索方向引导，结合MOPSO对储能容量组合的全局搜索能力，实现多目标寻优过程中经济性、可靠性与新能源消纳目标的冲突平衡。以实际电网为例的案例分析表明，该方法相较传统方法，能在满足系统约束下优化储能配置方案，提升经济性、可靠性与新能源消纳能力，为大规模新能源接入下的储能规划提供可行技术手段，助力电力系统低碳高效转型。

关键词: 深度强化学习, 多目标粒子群优化, 储能系统, 全局搜索, 容量配置

Abstract: With the large-scale integration of new energy into power grids, the intermittency and randomness of their output pose significant challenges to the stable operation of power systems. The rational capacity configuration of energy storage systems plays a crucial role in enhancing system reliability and promoting new energy consumption. This paper proposes an energy storage capacity configuration method based on Deep Reinforcement Learning (DRL) and Multi-Objective Particle Swarm Optimization (MOPSO). Firstly, it analyzes the operational characteristics of power systems and the access requirements of energy storage, constructs a system model incorporating wind power, solar power, and loads, and clarifies the configuration constraints and multi-objective optimization goals. Secondly, it utilizes DRL to learn energy storage operation strategies in complex environments; through the interaction between the DRL agent and the power grid environment, the agent outputs charging/discharging timing control recommendations. These recommendations are used as the particle initialization boundaries and search direction guidance for MOPSO. Combined with MOPSO's global search capability for energy storage capacity combinations, the method achieves a balance between the conflicts among economic, reliability, and new energy consumption objectives during the multi-objective optimization process. Case analysis based on an actual power grid shows that, compared with traditional methods, this approach can optimize the energy storage configuration scheme while satisfying system constraints, improve economic efficiency, reliability, and new energy consumption capacity. It provides a feasible technical means for energy storage planning under large-scale new energy integration and contributes to the low-carbon and efficient transformation of power systems.

Key words: deep reinforcement learning, multi-objective particle swarm optimization, energy storage system, global search capacity configuration

中图分类号: