基于灰狼算法优化SVR的企业最大需量预测方法  

Optimizing SVR Based on Grey Wolf Algorithm to Predict the Enterprise’s Maximum Demand

作　　者：张跃伟 胡敏 高孝天 ZHANG Yuewei;HU Min;GAO Xiaotian(Shanghai Electrical Apparatus Research Institute(Group)Co.,Ltd.,Shanghai 200063,China;Shanghai Electrical Apparatus Research Institute,Shanghai 200063,China)

机构地区：[1]上海电器科学研究所(集团)有限公司,上海200063 [2]上海电器科学研究院,上海200063

出　　处：《现代建筑电气》2024年第7期17-23,共7页Modern Architecture Electric

基　　金：基于工业互联网的用户端电器设备预测性运维关键技术研究(21XD1431000)。

摘　　要：随着电力供给侧结构性改革,快速准确的电力需量预测有利于企业合理安排生产计划,有助于降低企业用电成本,减少电网侧供电压力,对电网的安全运行和企业的稳定生产具有重要的意义。基于支持向量回归机(SVR)对企业最大需量展开预测模型分析,对模型输入特征进行关联性分析和降维处理,并采用灰狼算法(GWO)优化模型内部的超参数,以达到更好的预测性能。最终结合真实数据,通过MATLAB仿真对比了BPNN、SVR、GWO-SVR的预测性能,验证了所提方法的有效性和准确性。With the structural reform of the power supply side,fast and accurate forecasting of power demand will help enterprises to rationally arrange production plans,reduce the cost of electricity consumption,and reduce the pressure on the power grid side.Significance.Based on support vector regression(SVR),this paper analyzes the prediction model of the enterprise's maximum demand,performs correlation analysis and dimension reduction processing on the input features of the model,and uses the grey wolf optimizer(GWO)to optimize the model.Internal hyperparameters to achieve better prediction performance.Finally,combined with real data,the prediction performance of BPNN,SVR,GWO-SVR three methods is compared through Matlab simulation,and the effectiveness and accuracy of the proposed method are verified.

关 键 词：支持向量机 灰狼算法 关联性分析 降维 

分 类 号：TU852[建筑科学]