智能电网中的异常数据修复模型研究  

Research on Abnormal Data Repair Model in Smart Grid

作　　者：林范龙 林昀 黄庆仕 杨晓勇 LIN Fanlong;LIN Yun;HUANG Qingshi;YANG Xiaoyong(Jieyang Power Supply Bureau of Guangdong Power Grid Co.,Ltd.,Jieyang 522000,China;School of Computer Science and Technology,North China Electric Power University,Beijing 100000,China;School of Electrical and Electronic Engineering,North China Electric Power University,Beijing 100000,China;School of Water Resources and Hydropower Engineering,Wuhan University,Wuhan 430062,China;School of Computer Science and Technology,Chongqing University of Technology,Chongqing 400000,China)

机构地区：[1]广东电网有限责任公司揭阳供电局,广东揭阳522000 [2]华北电力大学计算机科学与技术学院,北京100000 [3]华北电力大学电子信息工程学院,北京100000 [4]武汉大学,水利水电学院,湖北武汉430062 [5]重庆理工大学,计算机科学与工程学院,重庆400000

出　　处：《微型电脑应用》2024年第9期134-138,共5页Microcomputer Applications

摘　　要：为进一步提高电力负荷异常数据修复质量,提出一种改进天牛须搜素(IBAS)算法优化径向基核函数(RBF)神经网络参数的异常数据修复方法。在BAS的基础上,引入动态惯性权重和莱维飞行轨迹优化机制,实现IBAS算法的改进;将IBAS用于RBF网络参数优化,并构建IBAS-RBF的异常数据修复模型;进行电力负荷的单点及连续点异常数据的修复,并通过评分指标对修复质量进行评价。实验结果表明,相较于改进前的BAS算法、PSO算法和FPA算法,改进后的IBAS算法的寻优速度和寻优精度显著提升;采用IBAS-RBF模型进行电力负荷数据修复后,无论在单点异常数据的修复,还是在连续点异常数据的修复,其修复效果都要更趋近于真实数据;通过IBAS-RBF对负荷序列数据的修复,其修复前后的准确性和一致性分别提升7.8%和7.6%,趋势性和有效性分别提升了6.6%和2.1%。由此说明,此IBAS-RBF模型可实现电力负荷极值异常消除和连续点异常修复,修复轨迹平滑度显著提升。To further improve the quality of power load abnormal data repair,an improved beetle antennae search(IBAS)algorithm is proposed to optimize the parameters of the radial basis function(RBF)kernel neural network for abnormal data repair.Based on BAS,dynamic inertia weights and Levi’s flight trajectory optimization mechanism are introduced to improve the IBAS algorithm.IBAS is applied to optimize RBF network parameters and an abnormal data repair model for IBAS-RBF is constructed.The abnormal data of single and continuous power load points are repaired,and the repair quality is evaluated through quality evaluation indicators.The experimental results show that compared to the BAS algorithm,PSO algorithm and FPA algorithm,the IBAS algorithm significantly improves its optimization speed and accuracy.After using the IBAS-RBF model for power load data restoration,the accuracy and consistency of the load series are improved by 7.8%and 7.6%,respectively,and the trend and effectiveness are improved by 6.6%and 2.1%,respectively.This indicates that this model can achieve the elimination of extreme power load anomalies and the repair of continuous point anomalies,significantly improves the smoothness of the repair trajectory.

关 键 词：电力负荷 异常检测 IBAS RBF网络 数据修复 

分 类 号：TP392[自动化与计算机技术—计算机应用技术]