ESATED: Leveraging Extra-weak Supervision with Auxiliary Task for Enhanced Non-intrusiveness in Energy Disaggregation
Authors: 
Peng Xia, Hao Zhou, Tianjian Yang, Wangqiu Zhou, Zhi Liu, Xiaoyan Wang, Xiang-Yang LiAuthors Info & Claims
Article No.: 194, Pages 1 - 32
Abstract
Non-intrusive load monitoring (NILM) is crucial to smart grid, which enables applications such as energy conservation and human activity recognition. As a typical task of NILM, energy disaggregation is to decompose total power consumption into appliance-level ones. Despite the remarkable achievements of deep-learning-based methods, their training phase still requires intrusively collected appliance-level power data as strong labels, which are directly used for supervising predictions.
In this paper, we present ESATED, a novel energy disaggregation system which instead utilizes non-intrusively collected binary on-off states of appliances as labels, thus enhancing non-intrusiveness throughout the life cycle. However, our labels are inherently weak labels due to the weak correlation between labels (binary states) and predictions (real-valued power), thus making our model struggle in terms of feasible supervision and acceptable performance. To tackle this challenge, we first explore the feasibility of binary-state-based weak supervision, and then integrate it into an auxiliary learning system, where an auxiliary subtask (i.e., state classification) is introduced to further enhance the performance of the primary task (i.e., energy disaggregation). We conduct extensive experiments on two real-world public datasets, and also implement the prototype system in a practical scenario. Corresponding results reveal that even using weak labels, ESATED could achieve performance and transferability second only to the state-of-the-art model. This result demonstrates the effectiveness of the proposed approach to extract information and train the model from extra weak labels.
References
[1]
Georgios-Fotios Angelis, Christos Timplalexis, Stelios Krinidis, Dimosthenis Ioannidis, and Dimitrios Tzovaras. 2022. NILM applications: Literature review of learning approaches, recent developments and challenges. Energy and Buildings (2022), 111951.
[2]
Kunjin Chen, Yu Zhang, Qin Wang, Jun Hu, Hang Fan, and Jinliang He. 2019. Scale-and context-aware convolutional non-intrusive load monitoring. IEEE Transactions on Power Systems 35, 3 (2019), 2362--2373.
[3]
Halil Çimen, Nurettin Çetinkaya, Juan C Vasquez, and Josep M Guerrero. 2020. A microgrid energy management system based on non-intrusive load monitoring via multitask learning. IEEE Transactions on Smart Grid 12, 2 (2020), 977--987.
[4]
Anthony Faustine, Lucas Pereira, Hafsa Bousbiat, and Shridhar Kulkarni. 2020. UNet-NILM: A deep neural network for multi-tasks appliances state detection and power estimation in NILM. In Proceedings of the 5th International Workshop on Non-Intrusive Load Monitoring. 84--88.
[5]
Jian Feng, Keqin Li, Huaguang Zhang, Xinbo Zhang, and Yu Yao. 2022. Multichannel Spatio-Temporal Feature Fusion Method for NILM. IEEE Transactions on Industrial Informatics 18, 12 (2022), 8735--8744.
[6]
Ting Gong, Tyler Lee, Cory Stephenson, Venkata Renduchintala, Suchismita Padhy, Anthony Ndirango, Gokce Keskin, and Oguz H Elibol. 2019. A comparison of loss weighting strategies for multi task learning in deep neural networks. IEEE Access 7 (2019), 141627--141632.
[7]
George William Hart. 1992. Nonintrusive appliance load monitoring. Proc. IEEE 80, 12 (1992), 1870--1891.
[8]
J Jiang, Q Kong, M Plumbley, and N Gilbert. [n. d.]. Deep Learning Based Energy Disaggregation and On/Off Detection of Household Appliances. arXiv 2019. arXiv preprint arXiv:1908.00941 ([n. d.]).
[9]
Maria Kaselimi, Eftychios Protopapadakis, Athanasios Voulodimos, Nikolaos Doulamis, and Anastasios Doulamis. 2019. Multi-channel recurrent convolutional neural networks for energy disaggregation. IEEE Access 7 (2019), 81047--81056.
[10]
Jack Kelly and William Knottenbelt. 2015. Neural nilm: Deep neural networks applied to energy disaggregation. In Proceedings of the 2nd ACM international conference on embedded systems for energy-efficient built environments. 55--64.
[11]
Jack Kelly and William Knottenbelt. 2015. The UK-DALE dataset, domestic appliance-level electricity demand and whole-house demand from five UK homes. Scientific data 2, 1 (2015), 1--14.
[12]
Alex Kendall, Yarin Gal, and Roberto Cipolla. 2018. Multi-task learning using uncertainty to weigh losses for scene geometry and semantics. In Proceedings of the IEEE conference on computer vision and pattern recognition. 7482--7491.
[13]
Younghun Kim, Thomas Schmid, Zainul M Charbiwala, and Mani B Srivastava. 2009. ViridiScope: design and implementation of a fine grained power monitoring system for homes. In Proceedings of the 11th international conference on Ubiquitous computing. 245--254.
[14]
J Zico Kolter and Matthew J Johnson. 2011. REDD: A public data set for energy disaggregation research. In Workshop on data mining applications in sustainability (SIGKDD), San Diego, CA, Vol. 25. Citeseer, 59--62.
[15]
Odysseas Krystalakos, Christoforos Nalmpantis, and Dimitris Vrakas. 2018. Sliding window approach for online energy disaggregation using artificial neural networks. In Proceedings of the 10th Hellenic Conference on Artificial Intelligence. 1--6.
[16]
Yiming Li and Liao Qu. [n. d.]. NeuralNILM Pytorch. https://github.com/Ming-er/NeuralNILM_Pytorch.
[17]
Lukas Liebel and Marco Körner. 2018. Auxiliary tasks in multi-task learning. arXiv preprint arXiv.1805.06334 (2018).
[18]
Shikun Liu, Andrew Davison, and Edward Johns. 2019. Self-supervised generalisation with meta auxiliary learning. Advances in Neural Information Processing Systems 32 (2019).
[19]
Yinyan Liu, Jing Qiu, and Jin Ma. 2021. Samnet: Toward latency-free non-intrusive load monitoring via multi-task deep learning. IEEE Transactions on Smart Grid 13, 3 (2021), 2412--2424.
[20]
Ram Machlev, Yoash Levron, and Yuval Beck. 2018. Modified cross-entropy method for classification of events in NILM systems. IEEE Transactions on Smart Grid 10, 5 (2018), 4962--4973.
[21]
Nan Miao, Shengjie Zhao, Qingjiang Shi, and Rongqing Zhang. 2019. Non-intrusive load disaggregation using semi-supervised learning method. In 2019 International Conference on Security, Pattern Analysis, and Cybernetics (SPAC). IEEE, 17--22.
[22]
David Murray, Lina Stankovic, Vladimir Stankovic, Srdjan Lulic, and Srdjan Sladojevic. 2019. Transferability of Neural Network Approaches for Low-rate Energy Disaggregation. In ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). 8330--8334.
[23]
Aviv Navon, Idan Achituve, Haggai Maron, Gal Chechik, and Ethan Fetaya. 2020. Auxiliary learning by implicit differentiation. arXiv preprint arXiv:2007.02693 (2020).
[24]
Dennis E Phillips, Rui Tan, Mohammad-Mahdi Moazzami, Guoliang Xing, Jinzhu Chen, and David KY Yau. 2013. Supero: A sensor system for unsupervised residential power usage monitoring. In 2013 IEEE International Conference on Pervasive Computing and Communications (PerCom). IEEE, 66--75.
[25]
Antonio Ridi, Christophe Gisler, and Jean Hennebert. 2014. A survey on intrusive load monitoring for appliance recognition. In 2014 22nd international conference on pattern recognition. IEEE, 3702--3707.
[26]
Sebastian Ruder. 2017. An overview of multi-task learning in deep neural networks. arXiv preprint arXiv.1706.05098 (2017).
[27]
Nasrin Sadeghianpourhamami, Joeri Ruyssinck, Dirk Deschrijver, Tom Dhaene, and Chris Develder. 2017. Comprehensive feature selection for appliance classification in NILM. Energy and Buildings 151 (2017), 98--106.
[28]
Manaswi Saha, Shailja Thakur, Amarjeet Singh, and Yuvraj Agarwal. 2014. Energylens: Combining smartphones with electricity meter for accurate activity detection and user annotation. In Proceedings of the 5th international conference on Future energy systems. 289--300.
[29]
Pascal A Schirmer and Iosif Mporas. 2022. Non-Intrusive Load Monitoring: A Review. IEEE Transactions on Smart Grid (2022).
[30]
Ozan Sener and Vladlen Koltun. 2018. Multi-task learning as multi-objective optimization. Advances in neural information processing systems 31 (2018).
[31]
Luca Serafini, Giulia Tanoni, Emanuele Principi, Susanna Spinsante, and Stefano Squartini. 2022. A multiple instance regression approach to electrical load disaggregation. In 2022 30th European Signal Processing Conference (EUSIPCO). IEEE, 1666--1670.
[32]
Changho Shin, Sunghwan Joo, Jaeryun Yim, Hyoseop Lee, Taesup Moon, and Wonjong Rhee. 2019. Subtask gated networks for non-intrusive load monitoring. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 33. 1150--1157.
[33]
Tharmakulasingam Sirojan, B Toan Phung, and Eliathamby Ambikairajah. 2018. Deep neural network based energy disaggregation. In 2018 IEEE international conference on smart energy grid engineering (SEGE). IEEE, 73--77.
[34]
David Snyder, Daniel Garcia-Romero, Gregory Sell, Alan McCree, Daniel Povey, and Sanjeev Khudanpur. 2019. Speaker recognition for multi-speaker conversations using x-vectors. In ICASSP 2019-2019 IEEE International conference on acoustics, speech and signal processing (ICASSP). IEEE, 5796--5800.
[35]
Ilya Sutskever, Oriol Vinyals, and Quoc V Le. 2014. Sequence to sequence learning with neural networks. Advances in neural information processing systems 27 (2014).
[36]
Seyed Mostafa Tabatabaei, Scott Dick, and Wilsun Xu. 2016. Toward non-intrusive load monitoring via multi-label classification. IEEE Transactions on Smart Grid 8, 1 (2016), 26--40.
[37]
Giulia Tanoni, Emanuele Principi, Luigi Mandolini, and Stefano Squartini. 2022. Weakly Supervised Transfer Learning for Multi-label Appliance Classification. In International Conference on Applied Intelligence and Informatics. Springer, 360--375.
[38]
Giulia Tanoni, Emanuele Principi, and Stefano Squartini. 2022. Multilabel appliance classification with weakly labeled data for non-intrusive load monitoring. IEEE Transactions on Smart Grid 14, 1 (2022), 440--452.
[39]
Yingjie Tian, Xiaotong Yu, and Saiji Fu. 2023. Partial label learning: Taxonomy, analysis and outlook. Neural Networks (2023).
[40]
Akriti Verma, Adnan Anwar, MA Mahmud, Mohiuddin Ahmed, and Abbas Kouzani. 2021. A comprehensive review on the nilm algorithms for energy disaggregation. arXiv preprint arXiv:2102.12578 (2021).
[41]
XiaoYu Wang, Hao Zhou, Nikolaos M Freris, Wangqiu Zhou, Xing Guo, and Xiang-Yang Li. 2021. CALM: Contactless Accurate Load Monitoring via Modality Distillation. In 2021 18th Annual IEEE International Conference on Sensing, Communication, and Networking (SECON). IEEE, 1--9.
[42]
XiaoYu Wang, Hao Zhou, Nikolaos M Freris, Wangqiu Zhou, Xing Guo, Zhi Liu, Yusheng Ji, and Xiang-Yang Li. 2021. LCL: Light Contactless Low-delay Load Monitoring via Compressive Attentional Multi-label Learning. In 2021 IEEE/ACM 29th International Symposium on Quality of Service (IWQOS). IEEE, 1--6.
[43]
Yandong Yang, Jing Zhong, Wei Li, T Aaron Gulliver, and Shufang Li. 2019. Semisupervised multilabel deep learning based nonintrusive load monitoring in smart grids. IEEE Transactions on Industrial Informatics 16, 11 (2019), 6892--6902.
[44]
Chaoyun Zhang, Mingjun Zhong, Zongzuo Wang, Nigel Goddard, and Charles Sutton. 2018. Sequence-to-point learning with neural networks for non-intrusive load monitoring. In Proceedings of the AAAI conference on artificial intelligence, Vol. 32.
[45]
Zheng Zhang, Mao Tan, Rui Pan, Jun Xiao, Chengchen Liao, and Zibin Li. 2022. A Multi-Task Learning Method Integrating Multi-Information Fusion for Non-Intrusive Load Monitoring. In 2022 6th Asian Conference on Artificial Intelligence Technology (ACAIT). 1--6.
[46]
Xiao Zhou, Shujian Li, Chengxi Liu, Haojun Zhu, Nan Dong, and Tianying Xiao. 2021. Non-intrusive load monitoring using a CNN-LSTM-RF model considering label correlation and class-imbalance. IEEE Access 9 (2021), 84306--84315.
[47]
Zhi-Hua Zhou. 2018. A brief introduction to weakly supervised learning. National science review 5, 1 (2018), 44--53.
[48]
Guanzhou Zhu, Dong Zhao, Kuo Tian, Zhengyuan Zhang, Rui Yuan, and Huadong Ma. 2023. Combining Smart Speaker and Smart Meter to Infer Your Residential Power Usage by Self-supervised Cross-modal Learning. Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies 7, 3 (2023), 1--26.
Index Terms
- ESATED: Leveraging Extra-weak Supervision with Auxiliary Task for Enhanced Non-intrusiveness in Energy Disaggregation
Recommendations
Intra and Inter-User Data Augmentation Methods for Energy Disaggregation
Advanced Data Mining and ApplicationsAbstractEnergy disaggregation, also known as Non-Intrusive Load Monitoring (NILM), aims to analyze the aggregate energy consumption of a user, such as a household, to infer the energy usage of individual appliances. Deep learning methods have become ...
Fine-grained label learning in object detection with weak supervision of captions
AbstractThis paper addresses the task of fine-grained label learning in object detection with the weak supervision of auxiliary information attached to images. Most of the recent work focused on the label prediction for objects in the same category space ...
Deep Learning-Based Energy Disaggregation and On/Off Detection of Household Appliances
Energy disaggregation, a.k.a. Non-Intrusive Load Monitoring, aims to separate the energy consumption of individual appliances from the readings of a mains power meter measuring the total energy consumption of, e.g., a whole house. Energy consumption of ...
Comments
Please enable JavaScript to view thecomments powered by Disqus.Information & Contributors
Information
Published In
Copyright © 2024 ACM.
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 21 November 2024
Published in IMWUT Volume 8, Issue 4
Check for updates
Author Tags
Qualifiers
- Research-article
- Research
- Refereed
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 41Total Downloads
- Downloads (Last 12 months)41
- Downloads (Last 6 weeks)6
Reflects downloads up to 07 Mar 2025
Other Metrics
Citations
View Options
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in