基于Stacking算法的特高压直流输电线路合成电场预测方法研究  

Research on total electric field prediction method of UHVDC transmission line based on Stacking algorithm

作　　者：李振华[1,2] 吴慕聪 程紫熠 姚为方 谢辉春 LI Zhenhua;WU Mucong;CHENG Ziyi;YAO Weifang;XIE Huichun(Hubei Provincial Key Laboratory for Operation and Control of Cascaded Hydropower Station(China Three Gorges University),Yichang 443002,China;College of Electrical Engineering and New Energy,China Three Gorges University,Yichang 443002,China;State Grid Anhui Electric Power Corporation Research Institute,Hefei 230601,China;China Electric Power Research Institute Co.,Ltd.,Wuhan Branch,Wuhan 430074,China)

机构地区：[1]梯级水电站运行与控制湖北省重点实验室(三峡大学),湖北宜昌443002 [2]三峡大学电气与新能源学院,湖北宜昌443002 [3]国网安徽省电力有限公司电力科学研究院,安徽合肥230601 [4]中国电力科学研究院有限公司武汉分院,湖北武汉430074

出　　处：《电工电能新技术》2023年第6期88-96,共9页Advanced Technology of Electrical Engineering and Energy

基　　金：国家电网公司科技项目(GYW11201907738)。

摘　　要：特高压输电线路是我国电网重要的组成部分,周围电磁环境复杂多变,地面合成电场是特高压输电线路主要电磁环境指标之一,进行准确预测和长期监测对电网安全运行具有重要意义。本文对宁东-浙江±800 kV特高压直流输电工程(灵绍线)进行了合成电场数据采集,将测量得到的合成电场数据进行了异常值分析及处理,通过实际算例表明:局部离群因子(LOF)异常值剔除算法差值平均值小,优于基于密度的有噪声的应用空间聚类(DBSCAN)和孤立森林剔除算法;使用Stacking算法及多种算法基于两组不同数据对合成电场进行预测,预测结果显示Stacking算法预测精度均优于多种同类预测算法;与传统有限元法预测合成电场进行对比,结果显示该预测方法可有效进行特高压直流输电线路地面合成电场预测、有效监测合成电场、及时发现隐患,保证输电线路安全稳定运行。UHV transmission lines are an important part of the country’s power grid,and the surrounding electromagnetic environment is complex and changeable.The ground synthetic electric field is one of the main electromagnetic environmental indicators of UHV transmission lines.Accurate prediction and long-term monitoring are of great significance to the safe operation of the power grid.In this paper,the synthetic electric field data are collected for the Ningdong-Zhejiang±800 kV UHV DC transmission project(Ling-Shao Line),and the measured synthetic electric field data are analyzed and processed for outliers.The average difference of the culling algorithm is small,which is better than DBSCAN and the isolated forest culling algorithm.Moreover,using Stacking algorithm and a variety of machine learning algorithms based on two different sets of data to predict the total electric field,prediction results show that Stacking algorithm prediction has better accuracy than a variety of similar prediction algorithms.The low prediction error of the Stacking algorithm highlights the superior ability to accurately predict the ground total electric field of UHVDC transmission lines.

关 键 词：有效数据 直流输电线路 800 kV特高压 合成电场 LOF算法 Stacking算法 

分 类 号：TM732[电气工程—电力系统及自动化]