Deep Learning-based Non-intrusive Load Monitoring: Recent Advances and Perspectives
CSTR:
Author:
  • Article
  • | |
  • Metrics
  • |
  • Reference [89]
  • |
  • Related [20]
  • | | |
  • Comments
    Abstract:

    Non-intrusive load monitoring (NILM) is an important part of intelligent power utilization and energy saving techniques and has attracted extensive attention. Due to the superior performance of newly-developed deep learning methods in various tasks in recent years, some representative deep learning methods have been successfully applied to the load decomposition task in NILM. To systematically summarize the research status and progress of deep learning methods applied to NILM, this study focuses on analyzing and summarizing the research literature on deep learning based NILM in recent years. Firstly, the NILM framework is outlined, and then the feature extraction method and the public data set of NILM are introduced. In addition, the load decomposition methods based on deep learning in NILM are analyzed and summarized. Finally, the study points out several challenges in this field and provides an outlook on its opportunities and future research directions.

    Reference
    [1] Hart GW. Nonintrusive appliance load monitoring. Proceedings of the IEEE, 1992, 80(12): 1870–1891. [doi: 10.1109/5.192069
    [2] Batra N, Singh A, Whitehouse K. If you measure it, can you improve it? Exploring the value of energy disaggregation. Proceedings of the 2nd ACM International Conference on Embedded Systems for Energy-efficient Built Environments. Seoul: ACM, 2015. 191–200.
    [3] Zoha A, Gluhak A, Imran MA, et al. Non-intrusive load monitoring approaches for disaggregated energy sensing: A survey. Sensors, 2012, 12(12): 16838–16866. [doi: 10.3390/s121216838
    [4] Berges ME, Goldman E, Matthews HS, et al. Enhancing electricity audits in residential buildings with nonintrusive load monitoring. Journal of Industrial Ecology, 2010, 14(5): 844–858. [doi: 10.1111/j.1530-9290.2010.00280.x
    [5] Papadopoulos PM, Reppa V, Polycarpou MM, et al. Scalable distributed sensor fault diagnosis for smart buildings. IEEE/CAA Journal of Automatica Sinica, 2020, 7(3): 638–655. [doi: 10.1109/JAS.2020.1003123
    [6] 邓晓平, 张桂青, 魏庆来, 等. 非侵入式负荷监测综述. 自动化学报, 2022, 48(3): 644–663. [doi: 10.16383/j.aas.c200270
    [7] Wild B, Barsim KS, Yang B. A new unsupervised event detector for non-intrusive load monitoring. Proceedings of 2015 IEEE Global Conference on Signal and Information Processing (GlobalSIP). Orlando: IEEE, 2015. 73–77.
    [8] Pereira L. NILMPEds: A performance evaluation dataset for event detection algorithms in non-intrusive load monitoring. Data, 2019, 4(3): 127. [doi: 10.3390/data4030127
    [9] Anderson KD, Bergés ME, Ocneanu A, et al. Event detection for non intrusive load monitoring. Proceedings of the 38th Annual Conference on IEEE Industrial Electronics Society. Montréal: IEEE, 2012. 3312–3317.
    [10] Yang CC, Soh CS, Yap VV. Comparative study of event detection methods for non-intrusive appliance load monitoring. Energy Procedia, 2014, 61: 1840–1843. [doi: 10.1016/j.egypro.2014.12.225
    [11] Hamdi M, Messaoud H, Bouguila N. A new approach of electrical appliance identification in residential buildings. Electric Power Systems Research, 2020, 178: 106037. [doi: 10.1016/j.epsr.2019.106037
    [12] De Baets L, Ruyssinck J, Develder C, et al. On the Bayesian optimization and robustness of event detection methods in NILM. Energy and Buildings, 2017, 145: 57–66. [doi: 10.1016/j.enbuild.2017.03.061
    [13] Ajmera J, McCowan I, Bourlard H. Robust speaker change detection. IEEE Signal Processing Letters, 2004, 11(8): 649–651. [doi: 10.1109/LSP.2004.831666
    [14] Berriri H, Naouar MW, Slama-Belkhodja I. Easy and fast sensor fault detection and isolation algorithm for electrical drives. IEEE Transactions on Power Electronics, 2012, 27(2): 490–499. [doi: 10.1109/TPEL.2011.2140333
    [15] Houidi S, Auger F, Sethom HBA, et al. Statistical assessment of abrupt change detectors for non-intrusive load monitoring. Proceedings of 2018 IEEE International Conference on Industrial Technology (ICIT). Lyon: IEEE, 2018. 1314–1319.
    [16] Rueda L, Cardenas A, Kelouwani S, et al. Transient event classification based on wavelet neuronal network and matched filters. Proceedings of the 44th Annual Conference of the IEEE Industrial Electronics Society. Washington: IEEE, 2018. 832–837.
    [17] Houidi S, Auger F, Sethom HBA, et al. Multivariate event detection methods for non-intrusive load monitoring in smart homes and residential buildings. Energy and Buildings, 2020, 208: 109624. [doi: 10.1016/j.enbuild.2019.109624
    [18] Zheng Z, Chen HN, Luo XW. A supervised event-based non-intrusive load monitoring for non-linear appliances. Sustainability, 2018, 10(4): 1001. [doi: 10.3390/su10041001
    [19] Afzalan M, Jazizadeh F, Wang J. Self-configuring event detection in electricity monitoring for human-building interaction. Energy and Buildings, 2019, 187: 95–109. [doi: 10.1016/j.enbuild.2019.01.036
    [20] Lindahl PA, Ali MT, Armstrong P, et al. Nonintrusive load monitoring of variable speed drive cooling systems. IEEE Access, 2020, 8: 211451–211463. [doi: 10.1109/ACCESS.2020.3039408
    [21] Liu YC, Wang X, You W. Non-intrusive load monitoring by voltage-current trajectory enabled transfer learning. IEEE Transactions on Smart Grid, 2019, 10(5): 5609–5619. [doi: 10.1109/TSG.2018.2888581
    [22] Tayal A, Dewan L, Lather JS. Artificial neural network-based source identification producing harmonic pollution in the electric network. In: Dewan L, Bansal RC, Kalla UK, eds. Advances in Renewable Energy and Sustainable Environment. Singapore: Springer, 2021. 49–58.
    [23] Inagaki S, Egami T, Suzuki T, et al. Nonintrusive appliance load monitoring based on integer programming. Electrical Engineering in Japan, 2011, 174(2): 18–25. [doi: 10.1002/eej.21040
    [24] Leeb SB, Shaw SR, Kirtley JL. Transient event detection in spectral envelope estimates for nonintrusive load monitoring. IEEE Transactions on Power Delivery, 1995, 10(3): 1200–1210. [doi: 10.1109/61.400897
    [25] Popescu F, Enache F, Vizitiu IC, et al. Recurrence plot analysis for characterization of appliance load signature. Proceedings of the 2014 10th International Conference on Communications. Bucharest: IEEE, 2014. 1–4.
    [26] Du L, Yang Y, He DW, et al. Feature extraction for load identification using long-term operating waveforms. IEEE Transactions on Smart Grid, 2015, 6(2): 819–826. [doi: 10.1109/TSG.2014.2373314
    [27] 程祥, 李林芝, 吴浩, 等. 非侵入式负荷监测与分解研究综述. 电网技术, 2016, 40(10): 3108–3117. [doi: 10.13335/j.1000-3673.pst.2016.10.026
    [28] Drouaz M, Colicchio B, Moukadem A, et al. New time-frequency transient features for nonintrusive load monitoring. Energies, 2021, 14(5): 1437. [doi: 10.3390/en14051437
    [29] Hernandez AS, Ballado AH, Heredia APD. Development of a non-intrusive load monitoring (NILM) with unknown loads using support vector machine. Proceedings of 2021 IEEE International Conference on Automatic Control & Intelligent Systems (I2CACIS). Shah Alam: IEEE, 2021. 203–207.
    [30] Liang J, Ng S, Kendall G, et al. Load signature study ?V part I: Basic concept, structure and methodology. Proceedings of IEEE PES General Meeting. Minneapolis: IEEE, 2010. 1.
    [31] Dufour L, Genoud D, Jara A, et al. A non-intrusive model to predict the exible energy in a residential building. Proceedings of 2015 IEEE Wireless Communications and Networking Conference Workshops (WCNCW). New Orleans: IEEE, 2015. 69–74.
    [32] Jiang L, Li JM, Luo SH, et al. Power load event detection and classification based on edge symbol analysis and support vector machine. Applied Computational Intelligence and Soft Computing, 2012, 2012: 742461. [doi: 10.1155/2012/742461
    [33] Jiang L, Luo SH, Li JM. An approach of household power appliance monitoring based on machine learning. Proceedings of the 2012 5th International Conference on Intelligent Computation Technology and Automation. Zhangjiajie: IEEE, 2012. 577–580.
    [34] 汪繁荣, 向堃, 吴铁洲. 基于VMD样本熵与随机森林的非侵入式设备状态检测方法. 现代电子技术, 2021, 44(15): 104–108. [doi: 10.16652/j.issn.1004-373x.2021.15.021
    [35] 宋旭帆, 周明, 涂京, 等. 基于KNN结合核Fisher判别的非侵入式负荷监测方法. 电力系统自动化, 2018, 42(6): 73–80. [doi: 10.7500/AEPS20170627011
    [36] 刘玲. 基于稳态特征的非侵入式负荷监测算法研究[硕士学位论文]. 广州: 华南理工大学, 2019.
    [37] Wu X, Gao YC, Jiao D. Multi-label classification based on random forest algorithm for non-intrusive load monitoring system. Processes, 2019, 7(6): 337. [doi: 10.3390/pr7060337
    [38] Kramer O, Klingenberg T, Sonnenschein M, et al. Non-intrusive appliance load monitoring with bagging classifiers. Logic Journal of the IGPL, 2015, 23(3): 359–368. [doi: 10.1093/jigpal/jzv016
    [39] Hinton GE, Osindero S, Teh YW. A fast learning algorithm for deep belief nets. Neural Computation, 2006, 18(7): 1527–1554. [doi: 10.1162/neco.2006.18.7.1527
    [40] LeCun Y, Bengio Y, Hinton G. Deep learning. Nature, 2015, 521(7553): 436–444. [doi: 10.1038/nature14539
    [41] Pouyanfar S, Sadiq S, Yan YL, et al. A survey on deep learning: Algorithms, techniques, and applications. ACM Computing Surveys, 2018, 51(5): 92
    [42] Zhu CC, Chen FY, Ahmed U, et al. Semantic relation reasoning for shot-stable few-shot object detection. Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Nashville: IEEE, 2021. 8782–8791.
    [43] Lee CC, Sridhar K, Li JL, et al. Deep representation learning for affective speech signal analysis and processing: Preventing unwanted signal disparities. IEEE Signal Processing Magazine, 2021, 38(6): 22–38. [doi: 10.1109/MSP.2021.3105939
    [44] Khurana S, Moritz N, Hori T, et al. Unsupervised domain adaptation for speech recognition via uncertainty driven self-training. Proceedings of 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Toronto: IEEE, 2021. 6553–6557.
    [45] 燕续峰, 翟少鹏, 王治华, 等. 深度神经网络在非侵入式负荷分解中的应用. 电力系统自动化, 2019, 43(1): 126–132, 167. [doi: 10.7500/AEPS20180629004
    [46] 任文龙, 许刚. 基于深度序列翻译模型的非侵入式负荷分解方法. 电网技术, 2020, 44(1): 27–34. [doi: 10.13335/j.1000-3673.pst.2019.0645
    [47] Zhang CY, Zhong MJ, Wang ZZ, et al. Sequence-to-point learning with neural networks for non-intrusive load monitoring. Proceedings of the AAAI Conference on Artificial Intelligence (AAAI-18). Palo Alto: AAAI Press, 2018. 2604–2611.
    [48] Qian YC, Yang QY, Li DH, et al. An improved temporal convolutional network for non-intrusive load monitoring. Proceedings of the 2021 33rd Chinese Control and Decision Conference (CCDC). Kunming: IEEE, 2021. 2557–2562.
    [49] Tongta A, Chooruang K. Long short-term memory (LSTM) neural networks applied to energy disaggregation. Proceedings of the 2020 8th International Electrical Engineering Congress (iEECON). Chiang Mai: IEEE, 2020. 1–4.
    [50] De Diego-Otón L, Fuentes-Jimenez D, Hernández Á, et al. Recurrent LSTM architecture for appliance identification in non-intrusive load monitoring. Proceedings of 2021 IEEE International Instrumentation and Measurement Technology Conference (I2MTC). Glasgow: IEEE, 2021. 1–6.
    [51] Akarsh C, Varma SH, Rao PV. Time series analysis using LSTM for elderly care application. Proceedings of the 2nd International Conference on Advances in Computer Engineering and Communication Systems. Singapore: Springer, 2022. 471–479.
    [52] 刘耀先, 孙毅, 李彬, 等. 基于边缘嵌入深度学习的非侵入式负荷分解方法. 电网技术, 2019, 43(12): 4329–4336. [doi: 10.13335/j.1000-3673.pst.2019.1510
    [53] Duan QY, Zhang F, Ren XY, et al. A non-intrusive loading monitoring method based on attention mechanism and denoising-autoencoder. Journal of Physics: Conference Series, 2021, 2005: 012224. [doi: 10.1088/1742-6596/2005/1/012224
    [54] Kaselimi M, Voulodimos A, Protopapadakis E, et al. EnerGAN: A generative adversarial network for energy disaggregation. Proceedings of 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Barcelona: IEEE, 2020. 1578–1582.
    [55] Zeifman M, Roth K. Nonintrusive appliance load monitoring: Review and outlook. IEEE Transactions on Consumer Electronics, 2011, 57(1): 76–84. [doi: 10.1109/TCE.2011.5735484
    [56] 安国庆, 梁宇飞, 蒋子尧, 等. 基于CF-MF-SE联合特征的非侵入式负荷辨识. 河北科技大学学报, 2021, 42(5): 462–469. [doi: 10.7535/hbkd.2021yx05004
    [57] Wang AL, Chen BX, Wang CG, et al. Non-intrusive load monitoring algorithm based on features of V-I trajectory. Electric Power Systems Research, 2018, 157: 134–144. [doi: 10.1016/j.epsr.2017.12.012
    [58] Kolter JZ, Jaakkola T. Approximate inference in additive factorial HMMs with application to energy disaggregation. Proceedings of the 15th International Conference on Artificial Intelligence and Statistics. La Palma: JMLR.org, 2012. 1472–1482.
    [59] Basu K, Debusschere V, Bacha S, et al. A generic data driven approach for low sampling load disaggregation. Sustainable Energy, Grids and Networks, 2017, 9: 118–127. [doi: 10.1016/j.segan.2016.12.006
    [60] Yu JY, Gao YC, Wu YX, et al. Non-intrusive load disaggregation by linear classifier group considering multi-feature integration. Applied Sciences, 2019, 9(17): 3558. [doi: 10.3390/app9173558
    [61] Tabatabaei SM, Dick S, Xu W. Toward non-intrusive load monitoring via multi-label classification. IEEE Transactions on Smart Grid, 2017, 8(1): 26–40. [doi: 10.1109/TSG.2016.2584581
    [62] Liao J, Elafoudi G, Stankovic L, et al. Non-intrusive appliance load monitoring using low-resolution smart meter data. Proceedings of 2014 IEEE International Conference on Smart Grid Communications (SmartGridComm). Venice: IEEE, 2014. 535–540.
    [63] Zhao BC, Stankovic L, Stankovic V. Blind non-intrusive appliance load monitoring using graph-based signal processing. Proceedings of 2015 IEEE Global Conference on Signal and Information Processing (GlobalSIP). Orlando: IEEE, 2015. 68–72.
    [64] Parson O, Ghosh S, Weal M, et al. Non-intrusive load monitoring using prior models of general appliance types. Proceedings of the 26th AAAI Conference on Artificial Intelligence. Toronto: AAAI Press, 2012. 356–362.
    [65] Racines D, Candelo JE, Montaña J. Non-intrusive electrical load monitoring system applying neural networks with combined steady-state electrical variables. Tehnički Vjesnik, 2018, 25(5): 1321–1329
    [66] Sun W, Pang XF, Geng HN, et al. Non-intrusive residential load decomposition method based on steady state feature extraction. Proceedings of the 2021 33rd Chinese Control and Decision Conference (CCDC). Kunming: IEEE, 2021. 1425–1430.
    [67] 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. 电力系统自动化, 2018, 42(3): 70–76. [doi: 10.7500/AEPS20170103001
    [68] Gray M, Morsi WG. Application of wavelet-based classification in non-intrusive load monitoring. Proceedings of the 2015 IEEE 28th Canadian Conference on Electrical and Computer Engineering (CCECE). Halifax: IEEE, 2015. 41–45.
    [69] Timplalexis C, Angelis GF, Krinidis S, et al. Low frequency residential non-intrusive load monitoring based on a hybrid feature extraction tree-learning approach. Energy Sources, Part A: Recovery, Utilization, and Environmental Effects, 2022, 44(1): 493–514. [doi: 10.1080/15567036.2022.2046663
    [70] De Paula Rodrigues R, Da Silveira PM. Curvature scale space-based signatures for electrical load classification in NILM. Electrical Engineering, 2021, 103(2): 1239–1252. [doi: 10.1007/s00202-020-01183-4
    [71] Djordjevic S, Simic M. Nonintrusive identification of residential appliances using harmonic analysis. Turkish Journal of Electrical Engineering & Computer Sciences, 2018, 26(2): 780–791. [doi: 10.3906/elk-1705-262
    [72] Djordjevic S, Simic M. Appliance level load monitoring based on the steady-state harmonic analysis. Proceedings of XIV International SAUM Conference. Niš, 2018.
    [73] Bouhouras AS, Vaggos M, Poulakis N, et al. Load signatures enhancement via odd-order harmonic currents. Proceedings of the 2016 IEEE 16th International Conference on Environment and Electrical Engineering (EEEIC). Florence: IEEE, 2016. 1–6.
    [74] Huang XQ, Yin B, Zhang R, et al. Study of steady-state feature extraction algorithm based on EMD. IOP Conference Series: Materials Science and Engineering, 2019, 490(6): 062036
    [75] Alcalá J, Ureña J, Hernández Á, et al. Event-based energy disaggregation algorithm for activity monitoring from a single-point sensor. IEEE Transactions on Instrumentation and Measurement, 2017, 66(10): 2615–2626. [doi: 10.1109/TIM.2017.2700987
    [76] Sadeghianpourhamami N, Ruyssinck J, Deschrijver D, et al. Comprehensive feature selection for appliance classification in NILM. Energy and Buildings, 2017, 151: 98–106. [doi: 10.1016/j.enbuild.2017.06.042
    [77] Cole AI, Albicki A. Data extraction for effective non-intrusive identification of residential power loads. Proceedings of IEEE Instrumentation and Measurement Technology Conference. Where Instrumentation is Going (Cat. No. 98CH36222). Paul: IEEE, 1998. 812–815.
    [78] 朱乔木, 党杰, 陈金富, 等. 基于深度置信网络的电力系统暂态稳定评估方法. 中国电机工程学报, 2018, 38(3): 735–743. [doi: 10.13334/j.0258-8013.pcsee.162436
    [79] Lü W, Cai ZQ, Chu JH. Load Identification based on S-transform and (2D)2PCA of transient current. Laser & Optoelectronics Progress, 2018, 55(8): 080701
    [80] Sirojan T, Phung T, Ambikairajah E. Intelligent edge analytics for load identification in smart meters. Proceedings of 2017 IEEE Innovative Smart Grid Technologies-Asia (ISGT-Asia). Auckland: IEEE, 2017. 1–5.
    [81] Gulati M, Ram SS, Singh A. An in depth study into using EMI signatures for appliance identification. Proceedings of the 1st ACM Conference on Embedded Systems for Energy-efficient Buildings. Memphis: ACM, 2014. 70–79.
    [82] Lee D. Phase noise as power characteristic of individual appliance for non-intrusive load monitoring. Electronics Letters, 2018, 54(16): 993–995. [doi: 10.1049/el.2018.5331
    [83] Zhang L, Shi SW. A non-intrusive load monitoring method based on multi-scale wavelet packet optimization and transient feature matching. Proceedings of the 2021 IEEE 12th International Conference on Software Engineering and Service Science (ICSESS). Beijing: IEEE, 2021. 113–117.
    [84] Gillis JM, Alshareef SM, Morsi WG. Nonintrusive load monitoring using wavelet design and machine learning. IEEE Transactions on Smart Grid, 2016, 7(1): 320–328. [doi: 10.1109/TSG.2015.2428706
    [85] Chang HH. Non-intrusive demand monitoring and load identification for energy management systems based on transient feature analyses. Energies, 2012, 5(11): 4569–4589. [doi: 10.3390/en5114569
    [86] Liu B, Luan WP, Yu YX. Dynamic time warping based non-intrusive load transient identification. Applied Energy, 2017, 195: 634–645. [doi: 10.1016/j.apenergy.2017.03.010
    [87] Rathore V, Jain SK. Non intrusive load monitoring and load disaggregation using transient data analysis. Proceedings of 2018 Conference on Information and Communication Technology (CICT). Jabalpur: IEEE, 2018. 1–5.
    [88] Rehman AU, Lie TT, Vallès B, et al. Comparative evaluation of machine learning models and input feature space for non-intrusive load monitoring. Journal of Modern Power Systems and Clean Energy, 2021, 9(5): 1161–1171. [doi: 10.35833/MPCE.2020.000741
    [89] Iksan N, Sembiring J, Haryanto N, et al. Appliances identification method of non-intrusive load monitoring based on load signature of V-I trajectory. Proceedings of 2015 International Conference on Information Technology Systems and Innovation (ICITSI). Bandung: IEEE, 2015. 1–6.
    Cited by
    Comments
    Comments
    分享到微博
    Submit
Get Citation

张石清,王伟,钱亚冠,赵小明,杜磊,章为昆.面向深度学习的非侵入式负荷监测研究进展.计算机系统应用,2023,32(3):25-47

Copy
Share
Article Metrics
  • Abstract:
  • PDF:
  • HTML:
  • Cited by:
History
  • Received:July 17,2022
  • Revised:August 15,2022
  • Online: November 18,2022
Article QR Code
You are the firstVisitors
Copyright: Institute of Software, Chinese Academy of Sciences Beijing ICP No. 05046678-3
Address:4# South Fourth Street, Zhongguancun,Haidian, Beijing,Postal Code:100190
Phone:010-62661041 Fax: Email:csa (a) iscas.ac.cn
Technical Support:Beijing Qinyun Technology Development Co., Ltd.

Beijing Public Network Security No. 11040202500063