Non-Intrusive Residential Electricity Load Disaggregation Based on Temporal Convolutional Neural Network

doi:10.12204/j.issn.1000-7229.2021.03.012

Abstract

Abstract:

Non-intrusive load disaggregation can accurately portray the user’s power consumption portrait by recovering the information of single electrical equipment on the power consumption side from the total electric meter information, which plays an important role in the refined management of the consumers. Aiming at the problems of low decomposition accuracy and low training efficiency of current artificial neural network models in load decomposition, this paper studies and builds a non-intrusive load disaggregation model based on temporal convolutional neural network. By analyzing the power consumption of the device, the dilated causal convolution is applied to perform convolution operations on the power sequence of electric meter and to expand the receptive field and extract richer features. The network training efficiency is improved by adding residual connections, weight normalization layers and optimizing training data window. Finally, the constructed model is tested on the optimized UKdale data set. The experimental results show that mean absolute error, root mean square error, and relative error are all in a relatively small range, and the time complexity analysis further shows that the model has a shorter training time without losing the load decomposition accuracy.

Key words: smart grid, load disaggregation, temporal convolutional neural network(TCN), sequence to point

CLC Number:

TM73

LIU Zhongmin, HOU Kunfu, GAO Jinggeng, WANG Zhiguo. Non-Intrusive Residential Electricity Load Disaggregation Based on Temporal Convolutional Neural Network[J]. ELECTRIC POWER CONSTRUCTION, 2021, 42(3): 97-106.

Figures/Tables 20

Fig.1 The process of NILM based on temporal convolutional neural network

Fig.2 Comparison of the receptive field between ordinary convolution and dilated causal convolution

Fig.3 Refrigerator operating characteristic

Fig.4 Structure of temporal convolutional neural network

Table 1 Data configuration

Table 2 Experimental results of different window lengths

Fig.5 Schematic diagram of sliding window for data augmentation

Fig.6 Comparison of experimental results of refrigerator load monitoring in household 1

Table 3 Comparison of evaluation indices of refrigerator load monitoring in household 1

Fig.7 Comparison of experimental results of generalization ability of models across households

Table 4 Comparison of evaluation indices of refrigerator load monitoring across households

Table 5 Comparison of training time (3 months training data from household 1)

Fig.A1 Comparison of kettle experiment result

Fig.A2 Comparison of TV experiment results

Table A1 Comparison of kettle evaluation index

Table A2 Comparison of TV evaluation index

Fig.A3 Comparison of washing machine experiment results

Fig.A4 Comparison of dish washer experiment results

Table A3 Comparison of washing machine evaluation index

Table A4 Comparison of dish washer evaluation index

References 20

[1]	余贻鑫, 刘博, 栾文鹏. 非侵入式居民电力负荷监测与分解技术[J]. 南方电网技术, 2013,7(4):1-5.
	YU Yixin, LIU Bo, LUAN Wenpeng. Nonintrusive residential load monitoring and decomposition technology[J]. Southern Power System Technology, 2013,7(4):1-5.
[2]	程祥, 李林芝, 吴浩, 等. 非侵入式负荷监测与分解研究综述[J]. 电网技术, 2016,40(10):3108-3117.
	CHENG Xiang, LI Linzhi, WU Hao, et al. A survey of the research on non-intrusive load monitoring and disaggregation[J]. Power System Technology, 2016,40(10):3108-3117.
[3]	徐大青, 栾文鹏, 王鹏, 等. 智能电表数据分析方法及应用[J]. 供用电, 2015,32(8):25-30.
	XU Daqing, LUAN Wenpeng, WANG Peng, et al. Analysis and applications of smart meter data[J]. Distribution & Utilization, 2015,32(8):25-30.
[4]	阮文骏, 王蓓蓓, 李扬, 等. 峰谷分时电价下的用户响应行为研究[J]. 电网技术, 2012,36(7):86-93.
	RUAN Wenjun, WANG Beibei, LI Yang, et al. Customer response behavior in time-of-use price[J]. Power System Technology, 2012,36(7):86-93.
[5]	庄池杰, 张斌, 胡军, 等. 基于无监督学习的电力用户异常用电模式检测[J]. 中国电机工程学报, 2016,36(2):379-387. doi: 10.13334/j.0258-8013.pcsee.2016.02.008 URL
	ZHUANG Chijie, ZHANG Bin, HU Jun, et al. Anomaly detection for power consumption patterns based on unsupervised learning[J]. Proceedings of the CSEE, 2016,36(2):379-387.
[6]	HART G W. Nonintrusive appliance load monitoring[J]. Proceedings of the IEEE, 1992,80(12):1870-1891. doi: 10.1109/5.192069 URL
[7]	卢天琪. 结合事件检测的HMM非侵入式电力负荷监测算法研究[D]. 武汉: 华中科技大学, 2017.
	LU Tianqi. Research on event-based HMM for non-intrusive electrical load monitoring algorithm[D]. Wuhan: Huazhong University of Science and Technology, 2017.
[8]	吴瑶. 基于因子隐马尔科夫模型的非侵入式负荷分解方法[D]. 北京: 华北电力大学, 2019.
	WU Yao. Non-intrusive load decomposition method based on factorial hidden Markov model[D]. Beijing: North China Electric Power University, 2019.
[9]	孙毅, 李昊洋, 刘耀先, 等. 基于改进隐马尔科夫模型的非侵入式家居负荷识别[J]. 电力建设, 2020,41(4):73-80.
	SUN Yi, LI Haoyang, LIU Yaoxian, et al. Non-intrusive home-load identification based on improved hidden Markov model[J]. Electric Power Construction, 2020,41(4):73-80.
[10]	邓晓平, 张桂青, 魏庆来, 等. 非侵入式负荷监测综述[J/OL]. 自动化学报: 1-20[2020-09-07]. https://doi.org/10.16383/j.aas.c200270.
	DENG Xiaoping, ZHANG Guiqing, WEI Qinglai, et al. A survey on the non-intrusive load monitoring[J/OL]. Acta Automatica Sinica: 1-20[2020-09-07]. https://doi.org/10.16383/j.aas.c200270.
[11]	KELLY J, KNOTTENBELT W. Neural NILM: Deep neural networks applied to energy disaggregation[C]// Proceedings of the 2nd ACM International Conference on Embedded Systems for Energy-Efficient Built Environments. New York,USA: ACM, 2015: 55-64.
[12]	ZHANG C Y, ZHONG M J, WANG Z Z. et al. Sequence-to-point learning with neural networks for nonintrusive load monitoring[DB/OL].[2020-07-10]. http://homepages.inf.ed.ac.uk/csutton/publications/aaai18nilm.pdf.
[13]	WANG K, LI K L, ZHOU L Q, et al. Multiple convolutional neural networks for multivariate time series prediction[J]. Neurocomputing, 2019,360:107-119. doi: 10.1016/j.neucom.2019.05.023 URL
[14]	BAI S, KOLTER J Z, KOLTUN V. An empirical evaluation of generic convolutional and recurrent networks for sequence modeling [db/OL]. [2020-07-10]. https://arxiv.org/pdf/1803.01271.pdf.
[15]	VAN DE OORD A, DIELEMAN S, ZEN H, et al. WaveNet: A generative model for raw audio[DB/OL]. (2016-09-19)[2020-07-10]. https://arxiv.org/abs/1609.03499.
[16]	SALIMANS T, KINGMA D P. Weight normalization: A simple reparameterization to accelerate training of deep neural networks[C]// Proceedings of the 30th International Conference on Neural Information Processing Systems. New York: Curran Associates Inc., 2016: 901-909.
[17]	SRIVASTAVA N, HINTON G, KRIZHEVSKY A, et al. Dropout: A simple way to prevent neural networks from overfitting[J]. Journal of Machine Learning Research, 2014,15:1929-1958.
[18]	HE K M, ZHANG X Y, REN S Q, et al. Deep residual learning for image recognition[C]// 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Las Vegas, NV, USA: IEEE, 2016: 770-778.
[19]	KELLY J, KNOTTENBELT W. The UK-DALE dataset, domestic appliance-level electricity demand and whole-house demand from five UK homes[J]. Scientific Data, 2015,2:150007. doi: 10.1038/sdata.2015.7 URL pmid: 25984347
[20]	BATRA N, KELLY J, PARSON O, et al. NILMTK: An open source toolkit for non-intrusive load monitoring[C]// Proceedings of the 5th International Conference on Future Energy Systems. Cambridge, UK, 2014: 265-276.