基于SVM的非侵入式负荷识别  

Non-intrusive Load Identification Based a SVM

作　　者：蔡高成 程丽娟 CAI Gaocheng;CHENG Lijuan(School of Mathematics and Statistics, Lingnan Normal University, Zhanjiang, Guangdong 524048, China)

机构地区：[1]岭南师范学院数学与统计学院,广东湛江524048

出　　处：《岭南师范学院学报》2018年第6期40-45,共6页Journal of Lingnan Normal University

基　　金：岭南师范学院自然科学青年项目(QL1407);大学生创新创业训练计划校级课题(201810579717)

摘　　要：非侵入式负荷监测技术是电力能耗监测的一种手段,通过传感器采集负荷电流和功率等运行特征参数,对设备耗能进行独立计量,预测用户设备的用电情况和规律,以提高电力系统的稳定性和可靠性,为电力公司科学制定电网调度方案,提供科学依据.选取电流、有功功率和谐波电流等稳态数据作为设备的运行特征,基于对偶树复小波变换对数据去噪,建立基于SVM分类识别模型进行负荷识别.Non-intrusive load monitoring technology is a means of monitoring energy consumption.To predict the power consumption and rules of the user equipment,the sensor collects operating characteristic parameters such as load current and power,and the energy consumption of the equipment is measured.It can provide scientific evidence to develop a grid dispatching plan for the power company.The steady-state data of current,active power and harmonic current are selected as the operating characteristics of the equipment.Based on the dual-tree complex wavelet transform,the data is denoised,and the SVM classification recognition models are established for load identification.

关 键 词：对偶树复小波变换 非侵入式负荷 SVM 

分 类 号：C812[社会学—统计学]