摘要
为了提高输电线路覆冰预测精度,采用差分进化算法对灰狼优化算法进行改进,形成差分灰狼算法,采用差分灰狼算法(Differential Evolution Grey Wolf Optimization,DEGWO)对最小二乘支持向量机(Least Squares Support Vector Machine,LSSVM)进行优化,建立基于DEGWO-LSSVM的输电线路覆冰厚度预测模型。采用两组实际运行线路的覆冰增长数据进行算例分析,并与其他覆冰预测方法对比,结果表明,DEGWO-LSSVM模型的误差波动更小,预测精度更高,验证了文章所提覆冰预测模型的正确性和实用性。
In order to improve the prediction accuracy of transmission line icing,the differential evolution algorithm is used to improve the grey wolf optimization algorithm and form the differential grey wolf algorithm,which is then used to optimize the least square support vector machine,and the prediction model of transmission line icing thickness based on DEGWO-LSSVM is established.Two sets of icing growth data of actual operation lines are used for analysis and comparison with other icing prediction methods.The results show that the error fluctuation of DEGWO-LSSVM model is smaller and the prediction accuracy is higher,which verifies the correctness and practicability of the proposed icing prediction model.
作者
吴宇峰
雷希童
陈海旭
张翮
李巧玲
WU Yufeng;LEI Xitong;CHEN Haixu;ZHANG He;LI Qiaoling(Fuzhou Yili Power Engineering Co.,Ltd.,Fuzhou 350000,China;Fuzhou Power Supply Company of State Grid Fujian Electric Power Co.,Ltd.,Fuzhou 350000,China;Putian Power Supply Company of State Grid Fujian Electric Power Co.,Ltd.,Putian 351100,China;Jingmen Power Supply Company of State Grid Hubei Electric Power Co.,Ltd.,Jingmen 448000,China)
出处
《安徽电气工程职业技术学院学报》
2023年第1期24-30,共7页
Journal of Anhui Electrical Engineering Professional Technique College
关键词
输电线路
覆冰厚度
预测
差分灰狼算法
transmission line
icing thickness
forecast
differential evolution grey wolf optimization
