基于超短期光伏功率预测的混合储能控制策略  

Hybrid Energy Storage Control Strategy Based on Ultra-short-term Photo-voltaic Power Forecast

作　　者：司孟姣 赵葵银[1] 陈凯杰 林国汉[1] SI Mengjiao;ZHAO Kuiyin;CHEN Kaijie;LIN Guohan(College of Electrical and Information Engineering,Hunan Institute of Engineering,Xiangtan 411104,China)

机构地区：[1]湖南工程学院电气与信息工程学院,湘潭411104

出　　处：《湖南工程学院学报（自然科学版）》2023年第2期22-29,共8页Journal of Hunan Institute of Engineering(Natural Science Edition)

基　　金：湖南省科技创新计划重点项目(2020RC5019).

摘　　要：针对储能系统平抑光伏输出功率波动存在滞后性的问题,提出了一种基于超短期光伏功率预测的混合储能控制策略.在功率预测方面,使用改进的灰狼算法对最小二乘支持向量机(LSSVM)预测模型的超参数进行优化,提高了预测速度与精度.在功率平抑方面,使用基于超级电容荷电状态(SOC)的功率分配策略,提高了平抑速度.仿真结果表明,所提出的控制策略能够有效地提高储能系统平抑速度,缓解储能系统平抑功率波动存在的滞后性问题.Aiming at the problem of lagging in the stabilization of photo-voltaic output power fluctuations in energy storage systems,this paper proposes a hybrid energy storage control strategy based on ultra-short-term photo-voltaic power prediction.In terms of power prediction,this paper uses the improved gray wolf algorithm to optimize the hyper-parameters of the least squares support vector machine(LSSVM)prediction model,which improves the prediction speed and accuracy.In terms of power flatness,this paper uses a power distribution strategy based on the super-capacitor load state(SOC)to improve the smoothing speed.Simulation shows that the proposed control strategy can effectively improve the flattening speed of the energy storage system and alleviate the lag problem of the energy storage system when stabilizeing the power fluctuation.

关 键 词：光伏功率预测 灰狼算法 功率平抑 超级电容 

分 类 号：TM615[电气工程—电力系统及自动化]