基于SSA-SVM的非侵入式负荷识别  

Non-intrusive load identification based on Sparrow Search Algorithm Optimized Support Vector Machine

作　　者：李梓彤 杨超[1] LI Zitong;YANG Chao(School of Electrical Engineering,Guizhou University,Guiyang 550025,China)

机构地区：[1]贵州大学电气工程学院,贵阳550025

出　　处：《智能计算机与应用》2023年第3期143-147,共5页Intelligent Computer and Applications

基　　金：贵州省科学技术基金(黔科合基础[2019]1100)。

摘　　要：针对目前非侵入式负荷监测方法对负荷特征相近的电器识别准确率不高的问题,本文提出了一种基于麻雀搜索算法(sparrow search algorithm, SSA)优化支持向量机(support vector machine, SVM)的负荷识别方法。该方法除了采用传统的有功和无功作为特征外,还采用了基波功率因数和频域电流谐波幅值作为新特征,同时使用麻雀搜索算法对支持向量机的核心参数进行优化,建立负荷识别模型,实现对家用电器的有效监测。进而采用AMPds数据集对算法进行测试,通过对比分析,验证了本文所提方法的有效性。In order to solve the problem of low accuracy of current non-invasive load monitoring methods in identifying electrical products with similar load characteristics,a load identification method based on sparrow search algorithm(SSA)and optimized support vector machine(SVM)is proposed.This method not only uses traditional active power and reactive power as features,but also uses fundamental power factor and harmonic amplitude of current in frequency domain as new features,and then uses sparrow search algorithm to optimize the core parameters of support vector machine.After that,the load identification model is established to realize the effective monitoring of household appliances.Finally,the algorithm is tested with AMPds data set,and the effectiveness of this method is verified by comparative analysis.

关 键 词：非侵入式负荷监测 麻雀搜索算法 支持向量机 参数优化 

分 类 号：TM933[电气工程—电力电子与电力传动] TM925