摘要
为了提高输电线路覆冰预测精度,采用主成分分析确定输电线路覆冰的关键影响因子为温度、湿度和风速,以此作为覆冰预测模型的输入量。采用布谷鸟算法对支持向量机的惩罚因子和核参数进行优化,建立基于CS-SVM的输电线路覆冰厚度预测模型。采用实际运行线路的覆冰数据进行仿真分析,结果表明,基于CS-SVM的输电线路覆冰厚度预测模型的平均相对误差、均方根误差和全局最大误差分别为5.254%、0.952%、5.827%,均小于其他几种常用覆冰预测模型,验证了模型的正确性和有效性。
In order to improve the accuracy of transmission line icing prediction, principal component analysis is used to determine that the key influencing factors of transmission line icing are temperature, humidity and wind speed, which can be used as the input of icing prediction model.Cuckoo algorithm is used to optimize the penalty factor and kernel parameters of support vector machine, and a transmission line icing thickness prediction model based on CS-SVM is established.The simulation results show that the average relative error, root mean square error and global maximum error of the transmission line icing thickness prediction model based on CS-SVM are 5.254%,0.952% and 5.827% respectively, which are less than other common icing prediction models, which verifies the correctness and effectiveness of the model.
作者
黄飞龙
李杰明
HUANG Fei-long;LI Jie-ming(China Energy Construction Group Guangdong Electric Power Engineering Bureau Co.Ltd.,Guangzhou 510000,China)
出处
《电气开关》
2022年第6期63-67,共5页
Electric Switchgear
关键词
布谷鸟搜索算法
支持向量机
输电线路
覆冰厚度
预测
cuckoo search algorithm
support vector machine
transmission line
icing thickness
forecast
