一种基于倒谱分析的非侵入式负荷监测方法  

A cepstrum analysis based non-intrusive load monitoring method

作　　者：詹航 竺红卫[1] 朱领军 Zhan Hang;Zhu hong-wei;Zhu ling-jun(School of Electrical Engineering, Zhejiang University, Hangzhou 310027, China)

机构地区：[1]浙江大学电气工程学院,浙江省杭州市310027

出　　处：《电子技术（上海）》2018年第5期37-40,共4页Electronic Technology

摘　　要：针对现有负荷监测算法难以识别多负荷同时动作的情况,提出了一种基于倒谱分析的非侵入式负荷监测算法。将负荷电流波形的倒谱系数作为用电设备的负荷印记,使用决策树算法对运行的用电设备进行识别。此外,根据家庭负荷元件双向对称的特点对倒谱分析算法进行了改进。实验结果表明,所提出的改进倒谱分析方法能够对多负荷同时动作的情况进行有效的识别。a cepstrum analysis based non-intrusive load monitoring method was proposed to tackle the problem that simultaneous operation of multiple appliances is difficult to identify. The cepstrum coefficients of load current waveform was used as load signature in a decision tree algorithm to identify working applications. In addition, an improvement of cepstrum analysis algorithm was made based on the bidirectional symmetry characteristic of household applications. The experiment results showed that the proposed cepstrum analysis method can identify simultaneous operation of multiple appliances efficiently.

关 键 词：非侵入式负荷监测 负荷分解 倒谱分析 负荷印记 

分 类 号：TM714[电气工程—电力系统及自动化]