基于随机森林算法的电力工程数据预测分析建模与仿真  

Modeling and simulation of power engineering data prediction and analysis based on Random Forest algorithm

作　　者：周云浩 杨宝杰 刘丹 李海峰[1] 杨鹏飞 ZHOU Yunhao;YANG Baojie;LIU Dan;LI Haifeng;YANG Pengfei(Electric Power Construction Engineering Consulting Branch,State Grid Beijing Electric Power Company,Beijing 100021,China)

机构地区：[1]国网北京市电力公司电力建设工程咨询分公司,北京100021

出　　处：《电子设计工程》2024年第4期103-106,111,共5页Electronic Design Engineering

基　　金：北京电力公司输变电工程应用项目(SGBJJS00XSJS2100639)。

摘　　要：针对电力工程数据量大、种类较多且传统分析模型处理效果不佳等问题,文中构建了一种基于随机森林算法的电力工程数据预测分析模型。该模型通过采集层获取各种工程数据,并在数据分析层运用经灰狼优化算法改进的随机森林算法对各种数据进行深度挖掘及学习,以获得电力工程数据的预测结果,从而满足应用层的业务需求。基于Matlab仿真平台进行数值实验论证的结果表明,所提模型的平均绝对百分比误差与均方根误差分别为4.15%、34.19万元,且均优于其他对比模型。Aiming at the problems of large amount and variety of power engineering data,and the poor processing effect of traditional analysis models,this paper constructs a power engineering data prediction and analysis model based on Random Forest algorithm.The power engineering data analysis system model obtains various engineering data through the collection layer,and uses the random forest algorithm improved by the Gray Wolf Optimizer algorithm to deeply mine and learn various data in the data analysis layer to obtain the prediction results of power engineering data,so as to meet the business needs of the application layer.Based on the Matlab simulation platform,the proposed model is demonstrated by numerical experiments.The results show that the MAPE and RMSE are 4.15% and 341 900 yuan respectively,which are better than other comparison models.

关 键 词：数据预测分析 随机森林算法 灰狼优化算法 平均绝对百分比误差 均方根误差 

分 类 号：TP311.13[自动化与计算机技术—计算机软件与理论]