基于改进RBF神经网络的线损不良数据辨别  

Identification of bad line loss data based on Improved RBF neural networknetwork

作　　者：胡行涛 刘大明 Hu XingTao;Liu Daming(Shanghai University of Electric Power,Shanghai,201300)

机构地区：[1]上海电力大学,上海201300

出　　处：《电子测试》2021年第16期37-39,共3页Electronic Test

摘　　要：配电系统中线损的减少对有效利用电力以及配电系统的经济运行非常重要。为了更好地发现有效的降损方法,并为科学规划电网结构收缩目标奠定基础。同时由于海量的电网数据中往往包含错误数据,这些错误数据对线路损耗的计算及预测有很严重的负面影响。针对这些问题,提出一种基于改进RBF神经网络的不良数据辨识模型,可以有效辨识线路损耗的数据中的不良数据,并进行剔除。以上海市某变电站数据为例,验证了该模型的适用性。The reduction of line loss in distribution system is very important for the effective utilization of power and the economic operation of distribution system.In order to better find effective loss reduction methods,and lay the foundation for scientific planning of power grid structure contraction target.At the same time,the massive power grid data often contains error data,which has a serious negative impact on the calculation and prediction of line loss.To solve these problems,a bad data identification model based on Improved RBF neural network is proposed,which can effectively identify and eliminate the bad data in the data of line loss.Taking the data of a substation in Shanghai as an example,the applicability of the model is verified.

关 键 词：线路损耗 不良数据辨识 粒子群算法 RBF神经网络 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程] TM73[自动化与计算机技术—控制科学与工程]