电工技术学报  2022, Vol. 37 Issue (23): 5987-5999    DOI: 10.19595/j.cnki.1000-6753.tces.220979
新型储能系统应用关键技术专题(特约主编:李建林 教授 梅生伟 教授 李军徽 教授) |
风储联合电站实时自调度的高效深度确定性策略梯度算法
宋煜浩1, 魏韡1, 黄少伟1, 吴启仁2, 梅生伟1
1.清华大学电机工程与应用电子系 北京 100084;
2.中国三峡新能源(集团)股份有限公司 北京 101100
Efficient Deep Deterministic Policy Gradient Algorithm for Real-Time Self-Dispatch of Wind-Storage Power Plant
Song Yuhao1, Wei Wei1, Huang Shaowei1, Wu Qiren2, Mei Shengwei1
1. Department of Electrical Engineering Tsinghua University Beijing 100084 China;
2. China Three Gorges Renewables (Group) Co. Ltd Beijing 101100 China
全文: PDF (3737 KB)   HTML
输出: BibTeX | EndNote (RIS)      
摘要 发展风电等可再生能源对于实现双碳目标具有重要意义,风储联合电站是未来风电接入电网的主要形式。该文研究发电侧商业化运行的风储联合电站的实时自调度问题,目标是使自身的期望收益最大化。由于场站级风电预测误差较大,独立发电商信息有限,难以准确预测电网电价,风储联合电站实时自调度面临多重不确定性,极具挑战。该文提出高效深度确定性策略梯度(DDPG)算法求取风储联合电站实时自调度策略,实现不依赖预测的场站级在线决策。首先通过Lyapunov优化构建基础策略,得到一个较好的但未必是局部最优的策略;然后,采用基础策略预生成样本,用于初始化经验库,提升搜索效率;接着,应用引入专家机制的DDPG算法,可以训练得到局部最优的自调度策略;最后,算例分析表明,相比于基础调度策略和经典DDPG,该文所提方法能有效提升风储联合电站的平均收益。
服务
把本文推荐给朋友
加入我的书架
加入引用管理器
E-mail Alert
RSS
作者相关文章
宋煜浩
魏韡
黄少伟
吴启仁
梅生伟
关键词 风储联合电站实时自调度Lyapunov优化深度确定性策略梯度(DDPG)    
Abstract:The development of wind power and other renewable energy is of great significance to achieve the dual carbon goal, and the wind-storage power plant is the main form of wind power connected to the power grid in the future. This paper studies the real-time self-dispatch problem of the wind-storage power plant commercialized on the generating side, with the goal of maximizing its expected income. Due to the large prediction error of the field-level wind power and the difficulty in accurately predicting the electricity price of the grid due to the limited information of independent power producers, the real-time self-dispatch of the wind-storage power plant is faced with multiple uncertainties, which is extremely challenging. In this paper, an efficient DDPG algorithm was proposed to solve the real-time self-dispatch strategy of the wind-storage power plant, and realize the field-level online decision-making independent of prediction. Firstly, Lyapunov optimization was used to construct the basic strategy to obtain a good but not necessarily local optimal strategy. Then, samples were pre-generated by the basic strategy to initialize the experience base and improve the search efficiency. Further, DDPG algorithm with expert mechanism was applied to train the locally optimal self-scheduling strategy. Case study shows that compared with the basic dispatch strategy and the classical DDPG, the proposed method can effectively improve the average revenue of the wind-storage power plant.
Key wordsWind-storage power plant    real-time self-dispatch    Lyapunov optimization    deep deterministic policy gradient(DDPG)   
收稿日期: 2022-05-30     
PACS: TM614  
基金资助:中国长江三峡集团有限公司科研项目资助(202003128)
通讯作者: 黄少伟 男,1985年生,博士,副研究员,硕士生导师,研究方向为人工智能在电力系统中的应用。E-mail:huangsw@mail.tsinghua.edu.cn   
作者简介: 宋煜浩 男,1998年生,博士研究生,研究方向为储能技术的应用。E-mail:3160871816@qq.com
引用本文:   
宋煜浩, 魏韡, 黄少伟, 吴启仁, 梅生伟. 风储联合电站实时自调度的高效深度确定性策略梯度算法[J]. 电工技术学报, 2022, 37(23): 5987-5999. Song Yuhao, Wei Wei, Huang Shaowei, Wu Qiren, Mei Shengwei. Efficient Deep Deterministic Policy Gradient Algorithm for Real-Time Self-Dispatch of Wind-Storage Power Plant. Transactions of China Electrotechnical Society, 2022, 37(23): 5987-5999.
链接本文:  
https://dgjsxb.ces-transaction.com/CN/10.19595/j.cnki.1000-6753.tces.220979          https://dgjsxb.ces-transaction.com/CN/Y2022/V37/I23/5987