摘要
针对如何提高风力发电功率预测的准确率,研究设计了一种基于改进乌鸦搜索算法(ICSA)优化支持向量机(SVM)的风电功率预测模型。在乌鸦搜索算法的基础上引入高斯变异算子和差分变异策略,提出改进型乌鸦搜索算法,并将之与支持向量机相结合,搭建ICSA-SVM风电功率预测模型。使用该模型,所得预测结果的均方根误差、平均绝对误差、平均绝对百分比误差等指标的值分别为4.42%、3.56%和5.22%。结果表明ICSA-SVM模型可实现参数优化,并有效提升了预测精度。研究成果可服务于含风能的电力系统日前调度,对推广清洁能源、实现碳达峰和碳中和具有重要意义。
Aiming at how to improve the accuracy of wind power prediction,a wind power prediction model based on improved crow search algorithm(ICSA)optimized support vector machine(SVM)is studied and designed.Based on the crow search algorithm,the Gaussian mutation operator and differential mutation strategy are introduced to propose an improved crow search algorithm and combine it with support vector machines to build a wind power prediction model.Using this model,the values of root mean square error,mean absolute error and mean absolute percentage error of the prediction results are 4.42%,3.56%and 5.22%,respectively.The results indicate that the ICSA-SVM model can achieve the optimization of parameters and effectively improve the prediction accuracy.The research results can serve for the day-ahead dispatch of power systems containing wind energy,which is of great significance for promoting clean energy and achieving the great goals of"carbon peak"and"carbon neutralization".
作者
李国全
高建宇
白天宇
李华
Li Guoquan;Gao Jianyu;Bai Tianyu;Li Hua(Kailuan Energy Chemical Co.,Ltd.,Tangshan 063100,China;Qinggong College,North China University of Science and Technology,Tangshan 063000,China;School of Electronic and Information Engineering,Hebei University of Technology,Tianjin 300401,China;School of Electrical Engineering,Hebei University of Technology,Tianjin 300401,China)
出处
《国外电子测量技术》
北大核心
2022年第2期40-45,共6页
Foreign Electronic Measurement Technology
基金
天津市自然科学基金(19JCZDJC32100)
河北省自然科学基金(E2018202282)项目资助
关键词
风电功率预测
改进型乌鸦搜索算法
高斯变异
差分变异
支持向量机
wind power prediction
improved crow search algorithm
Gauss mutation
differential mutation
support vector machines
作者简介
李国全,硕士,高级工程师,主要研究方向为煤化工机电与智能化控制系统管理。E-mail:liguoquan@kailuan.com.cn;通信作者:高建宇,硕士,讲师,主要研究方向为智能仪器与检测系统。E-mail:aicien@163.com;白天宇,本科生,主要研究方向为电子科学与技术。E-mail:bai.t@outlook.com;李华,硕士,副教授,主要研究方向为新能源发电与智能控制。E-mail:lihua69@hebut.edu.cn
