Event-Driven Non-Intrusive Load Monitoring Algorithm Based on Targeted Mining Multidimensional Load Characteristics

被引:2
作者
Xie, Gang [1 ]
Wang, Hongpeng [1 ]
机构
[1] Beijing Univ Posts & Telecommun, Sch Informat & Commun Engn, Beijing 100876, Peoples R China
基金
中国国家自然科学基金;
关键词
non-intrusive load monitoring; learning to ranking; smart grid; electrical characteristics; APPLIANCE IDENTIFICATION; HOME APPLIANCE; CLASSIFICATION;
D O I
10.23919/JCC.2023.00.003
中图分类号
TN [电子技术、通信技术];
学科分类号
0809 ;
摘要
Nowadays, the advancement of non-intrusive load monitoring (NILM) has been hastened by the ever-increasing requirements for the reasonable use of electricity by users and demand side manage-ment. Although existing researches have tried their best to extract a wide variety of load features based on transient or steady state of electrical appliances, it is still very difficult for their algorithm to model the load decomposition problem of different electrical ap-pliance types in a targeted manner to jointly mine their proposed features. This paper presents a very effective event-driven NILM solution, which aims to separately model different appliance types to mine the unique characteristics of appliances from multi-dimensional features, so that all electrical appliances can achieve the best classification performance. First, we convert the multi-classification problem into a serial multiple binary classification problem through a pre-sort model to simplify the original problem. Then, ConTrastive Loss K-Nearest Neighbour (CTLKNN) model with trainable weights is proposed to targeted mine appli-ance load characteristics. The simulation results show the effectiveness and stability of the proposed algo-rithm. Compared with existing algorithms, the pro-posed algorithm has improved the identification performance of all electrical appliance types.
引用
收藏
页码:40 / 56
页数:17
相关论文
共 42 条
[1]   Event-Based Energy Disaggregation Algorithm for Activity Monitoring From a Single-Point Sensor [J].
Alcala, Jose ;
Urena, Jesus ;
Hernandez, Alvaro ;
Gualda, David .
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT, 2017, 66 (10) :2615-2626
[2]  
[Anonymous], 2013, OPEN J ENERGY EFFICI, DOI [10.4236/ojee.2013.21002, DOI 10.4236/OJEE.2013.21002]
[3]  
[Anonymous], 2006, 2006 IEEE COMP SOC C
[4]  
Bucci G., 2020, P IEEE INT INSTR MEA, P1, DOI DOI 10.1109/I2MTC43012.2020.9128599
[5]  
Cevher V, 2008, LECT NOTES COMPUT SC, V5303, P155, DOI 10.1007/978-3-540-88688-4_12
[6]  
Chang H.-H., 2010, 2010 14 INT C COMPUT, P27
[7]   Standby Power Management of a Smart Home Appliance by Using Energy Saving System With Active Loading Feature Identification [J].
Chen, Ming-Tang ;
Lin, Che-Min .
IEEE TRANSACTIONS ON CONSUMER ELECTRONICS, 2019, 65 (01) :11-17
[8]   A New Convolutional Neural Network-Based System for NILM Applications [J].
Ciancetta, Fabrizio ;
Bucci, Giovanni ;
Fiorucci, Edoardo ;
Mari, Simone ;
Fioravanti, Andrea .
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT, 2021, 70 (70)
[9]  
Dean B., 2016, Global status report 2016: towards zero-emission efficient and resilient buildings
[10]   Residential Appliance Identification Based on Spectral Information of Low Frequency Smart Meter Measurements [J].
Dinesh, Chinthaka ;
Nettasinghe, Buddhika W. ;
Godaliyadda, Roshan Indika ;
Ekanayake, Mervyn Parakrama B. ;
Ekanayake, Janaka ;
Wijayakulasooriya, Janaka V. .
IEEE TRANSACTIONS ON SMART GRID, 2016, 7 (06) :2781-2792