SOM-K-means Non-intrusive Load Identification Based on Multi Feature Joint Sparse Expression

doi:10.12204/j.issn.1000-7229.2023.05.007

Abstract

Abstract:

Nonintrusive load monitoring is an effective method for comprehensively perceiving load data and optimizing energy efficiency. At present, the main observation object of nonintrusive load monitoring algorithms is the load with a regulation potential; however, the identification accuracy is poor for electrical appliances with small power and similar load curves. Moreover, the algorithm is highly dependent on prior data. Therefore, an SOM-K-means non-intrusive load identification algorithm based on multi-feature joint sparse expression is proposed in this study. The algorithm uses load features to train the optimal dictionary. The objective function is constructed by combining the optimal dictionary and multi-feature joint sparse representation, and the multi-feature joint sparse matrix is solved, which overcomes the problem of identifying load types limited by single-type load characteristics. Considering the multi-feature joint sparse matrix as the input, combined with the K-means algorithm optimized by a self-organizing map (SOM) neural network and the mean absolute error, the load was quickly identified. Finally, experimental verification using the PLAID dataset shows that the identification accuracy of the proposed algorithm can reach 90% with only 120 iterations, improving the convergence speed of the algorithm and proving that the method can realize load identification accurately and efficiently.

Key words: nonintrusive load identification, joint sparse representation of multiple features, self-organizing map neural network, K-means clustering

CLC Number:

TM714

YAN Meng, YU Yawen, WANG Lingjing, DU Yu, WU Xin. SOM-K-means Non-intrusive Load Identification Based on Multi Feature Joint Sparse Expression[J]. ELECTRIC POWER CONSTRUCTION, 2023, 44(5): 61-71.

Figures/Tables 8

Fig.1 Implementation structure

Fig.2 Flow chart of SOM-K-means algorithm

Table 1 Results of load feature extraction

Fig.3 Comparison between classification statistics and initial gradient data

Fig.4 SOM neural network training classification results

Fig.5 Classification results of 8 types of load

Fig.6 Comparison of different combination features and different algorithms

Table 2 MAEcomparison of different algorithms

References 30

[1]	IPAKCHI A, ALBUYEH F. Grid of the future[J]. IEEE Power and Energy Magazine, 2009, 7(2): 52-62. doi: 10.1109/MPE.2008.931384 URL
[2]	汪四仙, 毕忠勤. 非侵入式电力负荷监测技术研究[J]. 上海电力学院学报, 2017, 33(4): 357-361.
	WANG Sixian, BI Zhongqin. Study on non-intrusive load monitoring technology[J]. Journal of Shanghai University of Electric Power, 2017, 33(4): 357-361.
[3]	CHANG H H, CHEN K L, TSAI Y P, et al. A new measurement method for power signatures of nonintrusive demand monitoring and load identification[J]. IEEE Transactions on Industry Applications, 2012, 48(2): 764-771. doi: 10.1109/TIA.2011.2180497 URL
[4]	CHAO L, AKINTAYO A, JIANG Z. Multivariate exploration of non-intrusive load monitoring via spatiotemporal pattern network[J]. Applied Energy, 2018, 211: 1106-1122. doi: 10.1016/j.apenergy.2017.12.026 URL
[5]	祁兵, 董超, 武昕, 等. 基于DTW算法与稳态电流波形的非侵入式负荷辨识方法[J]. 电力系统自动化, 2018, 42(3): 70-76.
	QI Bing, DONG Chao, WU Xin, et al. Non-intrusive load identification method based on DTW algorithm and steady-state current waveform[J]. Automation of Electric Power Systems, 2018, 42(3): 70-76.
[6]	WELIKALA S, DINESH C, EKANAYAKE M P B, et al. Incorporating appliance usage patterns for non-intrusive load monitoring and load forecasting[J]. IEEE Transactions on Smart Grid, 2017, 10(1): 448-461. doi: 10.1109/TSG.5165411 URL
[7]	WELIKALA S, THELASINGHA N, AKRAM M, et al. Implementation of a robust real-time non-intrusive load monitoring solution[J]. Applied Energy, 2019, 238: 1519-1529. doi: 10.1016/j.apenergy.2019.01.167 URL
[8]	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. November 4 - 5, 2015, Seoul, South Korea. New York: ACM, 2015: 55-64.
[9]	马临超, 杨捷, 肖鹏, 等. 基于新型卷积神经网络的非侵入式负载监测方法[J]. 智慧电力, 2022, 50(4): 96-102.
	MA Linchao, YANG Jie, XIAO Peng, et al. Non-invasive load monitoring method based on novel convolutional neural network[J]. Smart Power, 2022, 50(4): 96-102.
[10]	CHANG H H, LIAN K L, SU Y C, et al. Power-spectrum-based wavelet transform for nonintrusive demand monitoring and load identification[J]. IEEE Transactions on Industry Applications, 2014, 50(3): 2081-2089. doi: 10.1109/TIA.28 URL
[11]	LIU Y C, WANG X, YOU W. Non-intrusive load monitoring by voltage-current trajectory enabled transfer learning[J]. IEEE Transactions on Smart Grid, 2019, 10(5): 5609-5619. doi: 10.1109/TSG.5165411 URL
[12]	IKSAN N, SEMBIRING J, HARYANTO N, et al. Appliances identification method of non-intrusive load monitoring based on load signature of V-I trajectory[C]// 2015 International Conference on Information Technology Systems and Innovation (ICITSI). November 16-19, 2015, Bandung, Indonesia. IEEE, 2016: 1-6.
[13]	WANG A L J, CHEN B X M, WANG C G, et al. Non-intrusive load monitoring algorithm based on features of V-I trajectory[J]. Electric Power Systems Research, 2018, 157: 134-144. doi: 10.1016/j.epsr.2017.12.012 URL
[14]	HAN Y H, XU Y, HUO Y X, et al. Non-intrusive load monitoring by voltage-current trajectory enabled asymmetric deep supervised hashing[J]. IET Generation, Transmission & Distribution, 2021, 15(21): 3066-3080. doi: 10.1049/gtd2.v15.21 URL
[15]	MAKONIN S, POPOWICH F, BAJI? 倢 I V, et al. Exploiting HMM sparsity to perform online real-time nonintrusive load monitoring[J]. IEEE Transactions on Smart Grid, 2016, 7(6): 2575-2585. doi: 10.1109/TSG.2015.2494592 URL
[16]	郭治远, 李志勇, 邵洁, 等. 基于智能用电网络的负荷状态与类型在线辨识[J]. 电力建设, 2022, 43(4): 69-80. doi: 10.12204/j.issn.1000-7229.2022.04.008
	GUO Zhiyuan, LI Zhiyong, SHAO Jie, et al. Online monitoring of load states and types based on smart electric appliance network[J]. Electric Power Construction, 2022, 43(4): 69-80. doi: 10.12204/j.issn.1000-7229.2022.04.008
[17]	FIGUEIREDO M B, DE ALMEIDA A, RIBEIRO B. An experimental study on electrical signature identification of non-intrusive load monitoring (NILM) systems[C]// Adaptive and Natural Computing Algorithms. Berlin, Heidelberg: Springer Berlin Heidelberg, 2011: 31-40.
[18]	POWERS J T, MARGOSSIAN B, SMITH B A. Using a rule-based algorithm to disaggregate end-use load profiles from premise-level data[J]. IEEE Computer Applications in Power, 1991, 4(2): 42-47. doi: 10.1109/67.75875 URL
[19]	武昕, 韩璐, 韩笑, 等. 欠定分离机制下基于特征滤波的居民负荷非侵入辨识算法[J]. 电力系统自动化, 2017, 41(20): 118-125.
	WU Xin, HAN Lu, HAN Xiao, et al. Feature filtering based non-intrusive identification algorithm for residential load in underdetermined separation mechanism[J]. Automation of Electric Power Systems, 2017, 41(20): 118-125.
[20]	TABATABAEI S M, DICK S, XU W. Toward non-intrusive load monitoring via multi-label classification[J]. IEEE Transactions on Smart Grid, 2017, 8(1): 26-40. doi: 10.1109/TSG.2016.2584581 URL
[21]	刘仲民, 侯坤福, 高敬更, 等. 基于时间卷积神经网络的非侵入式居民用电负荷分解方法[J]. 电力建设, 2021, 42(3): 97-106. doi: 10.12204/j.issn.1000-7229.2021.03.012
	LIU Zhongmin, HOU Kunfu, GAO Jinggeng, et al. Non-intrusive residential electricity load disaggregation based on temporal convolutional neural network[J]. Electric Power Construction, 2021, 42(3): 97-106. doi: 10.12204/j.issn.1000-7229.2021.03.012
[22]	余登武, 刘敏, 汪元芹. 基于GRNN与注意力机制模型的非侵入式家用负荷分解[J]. 智慧电力, 2021, 49(3): 74-79.
	YU Dengwu, LIU Min, WANG Yuanqin. Non-invasive household load decomposition based on GRNN and attention mechanism model[J]. Smart Power, 2021, 49(3): 74-79.
[23]	DRENKER S, KADER A. Nonintrusive monitoring of electric loads[J]. IEEE Computer Applications in Power, 1999, 12(4): 47-51. doi: 10.1109/67.795138 URL
[24]	仝瑞宁, 李鹏, 郎恂, 等. 基于Fisher主元分析和核极限学习机的非侵入式电力负荷辨识模型[J]. 电力建设, 2021, 42(2): 85-92. doi: 10.12204/j.issn.1000-7229.2021.02.011
	TONG Ruining, LI Peng, LANG Xun, et al. Non-intrusive power load identification model based on FPCA and KELM[J]. Electric Power Construction, 2021, 42(2): 85-92. doi: 10.12204/j.issn.1000-7229.2021.02.011
[25]	武昕, 焦点, 高宇辰. 基于非侵入式用电数据分解的自适应特征库构建与负荷辨识[J]. 电力系统自动化, 2020, 44(4): 101-109.
	WU Xin, JIAO Dian, GAO Yuchen. Construction of adaptive feature library and load identification based on decomposition of non-intrusive power consumption data[J]. Automation of Electric Power Systems, 2020, 44(4): 101-109.
[26]	GAO J K, GIRI S, KARA E C, et al. PLAID: a public dataset of high-resoultion electrical appliance measurements for load identification research: demo abstract[C]// Proceedings of the 1st ACM Conference on Embedded Systems for Energy-Efficient Buildings. November 3 - 6, 2014, Memphis, Tennessee. New York: ACM, 2014: 198-199.
[27]	王守相, 郭陆阳, 陈海文, 等. 基于特征融合与深度学习的非侵入式负荷辨识算法[J]. 电力系统自动化, 2020, 44(9): 103-110.
	WANG Shouxiang, GUO Luyang, CHEN Haiwen, et al. Non-intrusive load identification algorithm based on feature fusion and deep learning[J]. Automation of Electric Power Systems, 2020, 44(9): 103-110.
[28]	KRYSTALAKOS O, NALMPANTIS C, VRAKAS D. Sliding window approach for online energy disaggregation using artificial neural networks[C]// Proceedings of the 10th Hellenic Conference on Artificial Intelligence. July 9 - 12, 2018, Patras, Greece. New York: ACM, 2018: 1-6.
[29]	ZHANG C Y, ZHONG M J, WANG Z Z, et al. Sequence-to-point learning with neural networks for nonintrusive load monitoring[C]// Thirty-Second AAAI Conference on Artificial Intelligence (AAAI-18). USA: AAAI, 2018: 2604-2611.
[30]	徐晓会, 赵书涛, 崔克彬. 基于卷积块注意力模型的非侵入式负荷分解算法[J]. 电网技术, 2021, 45(9): 3700-3706.
	XU Xiaohui, ZHAO Shutao, CUI Kebin. Non-intrusive load disaggregate algorithm based on convolutional block attention module[J]. Power System Technology, 2021, 45(9): 3700-3706.