Graph Data Modeling and Graph Representation Learning Methods and Their Application in Non-intrusive Load Monitoring Problem

被引：0

作者：

Peng B. ^{[1
]}

Pan Z. ^{[1
]}

Yu T. ^{[2
]}

Qiu L. ^{[1
]}

Su X. ^{[1
]}

Chen Z. ^{[1
]}

机构：

[1] School of Electrical Power, South China University of Technology, Guangdong Province, Guangzhou

[2] Guangdong Provincial Key Laboratory of Intelligent Measurement and Advanced Metering of Power Grid, Guangdong Province, Guangzhou

来源：

Zhongguo Dianji Gongcheng Xuebao/Proceedings of the Chinese Society of Electrical Engineering | 2022年 / 42卷 / 17期

基金：

中国国家自然科学基金;

关键词：

graph data modeling; graph representation learning; non-intrusive load monitoring; post-processing technology; time-related characteristics;

D O I：

10.13334/j.0258-8013.pcsee.211116

中图分类号：

学科分类号：

摘要：

Non-intrusive load monitoring can extract the operating state of a single load from the main data of a building, which is of great significance for consumers to adjust their electricity strategies and participate in demand-side response. Existing methods are limited by the sequential input of data in the Euclidean space, and cannot accurately describe the time correlation between different operating states of electrical appliances, which leads to unsatisfactory disaggregation accuracy. Therefore, a novel method of graph data modeling and graph representation learning was proposed. Firstly, the signal to be disaggregated was converted into power graph containing nodes and edges based on graph theory. Secondly, a graph convolutional network with residual mechanism was designed to fully mine the attribute features and time correlation features contained in the data at low sampling frequency. Then, a graph representation learning for load disaggregation was developed. Furthermore, an improved post-processing technology was proposed to solve the problem of the lack of refined correction strategies for dis-aggregation results, thus improving the overall performance of the model. Finally, the proposed method was validated by using public datasets AMPds2 and REDD. The results show that the method has a lower disaggregation error and better generalization performance. ©2022 Chin.Soc.for Elec.Eng.

引用

页码：6260 / 6273

页数：13

共 30 条

[1] DING Tao, Review of energy internet and its operation[J], Proceedings of the CSEE, 38, 15, pp. 4318-4328, (2018)
[2] LING Shunfu, ZHAN Yinfeng, LI Yi, Non-intrusive residential load monitoring method based on CNN-BiLSTM and DTW[J], Power System Technology, 46, 5, pp. 1973-1981, (2022)
[3] GUO Hongxia, LU Jinwei, YANG Ping, Review on key techniques of non-intrusive load monitoring[J], Electric Power Automation Equipment, 41, 1, pp. 135-146, (2021)
[4] ZHOU Run, XIANG Yue, WANG Yang, Non-intrusive identification and load forecasting of household electric vehicle charging behavior based on smart meter data[J], Power System Technology, 46, 5, pp. 1897-1908, (2022)
[5] CHENG Xiang, LI Linzhi, WU Hao, A survey of the research on non-intrusive load monitoring and disaggregation[J], Power System Technology, 40, 10, pp. 3108-3117, (2016)
[6] HART G W．, Nonintrusive appliance load monitoring[J], Proceedings of the IEEE, 80, 12, pp. 1870-1891, (1992)
[7] SUN Yi, ZHANG Lu, ZHAO Honglei, A non-intrusive household load monitoring method based on dynamic adaptive particle swarm optimization algorithm[J], Power System Technology, 42, 6, pp. 1819-1826, (2018)
[8] KOLTER J Z, JAAKKOLA T．, Approximate inference in additive factorial HMMs with application to energy disaggregation[C], Proceedings of the 15th International Conference on Artificial Intelligence and Statistics (AISTATS), pp. 1472-1482, (2012)
[9] HU Yue, HU Wenshan, WANG Xiaowen, A load identification method for event matching based on KM algorithm[J], Electrical Measurement & Instrumentation
[10] Mingyue ZHAI, A new graph learning-based signal processing approach for non-intrusive load disaggregation with active power measurements[J], Neural Computing and Applications, 32, 10, pp. 5495-5504, (2020)

← 1 2 3 →