Abstract
Non-intrusive Load Monitoring refers to the techniques for providing detailed information on appliances’ states or their energy consumption by measuring only aggregate electrical parameters. Supervised deep neural networks have reached the state-of-the-art in this task, and to improve the performance when training and test data domains differ, transfer learning techniques have been successfully applied. However, these techniques rely on data labeled sample-by-sample (strong labels) to be effective, which can be particularly costly in transfer learning since it requires collecting and annotating data in the target domain. To mitigate this issue, this work proposes a cross-domain transfer learning approach based on weak supervision and Convolutional Recurrent Neural Networks for multi-label appliance classification. The proposed method is based on the concept of inexact supervision by modeling NILM as a Multiple Instance Learning problem, exploiting different and less costly annotations called weak labels. The learning strategy is able to exploit weak labels both for pre-training and fine-tuning the models.
UK-DALE and REFIT are used in the experiments as source and target domain datasets to train, fine-tune, and evaluate the networks. The results demonstrate the effectiveness of the proposed method compared to the related pre-trained models. In particular, when the model is pre-trained on strongly and weakly labeled data of UK-DALE and then fine-tuned only on REFIT weak labels, the performance improves by 20.3%.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Batra, N., et al.: Towards reproducible state-of-the-art energy disaggregation. In: Proceedings of BuildSys, pp. 193–202 (2019)
Bonfigli, R., et al.: Denoising autoencoders for non-intrusive load monitoring: improvements and comparative evaluation. Energy Build. 158, 1461–1474 (2018)
Cho, K., et al.: Learning phrase representations using RNN encoder-decoder for statistical machine translation. In: Proceedings of EMNL, pp. 1724–1734 (2014)
Dietterich, T.G., Lathrop, R.H., Lozano-Pérez, T.: Solving the multiple instance problem with axis-parallel rectangles. Artif. Intell. 89(1), 31–71 (1997)
D’Incecco, M., Squartini, S., Zhong, M.: Transfer learning for non-intrusive load monitoring. IEEE Trans. Smart Grid 11(2), 1419–1429 (2020)
Dinkel, H., et al.: The smallrice submission to the DCASE2021 task 4 challenge: a lightweight approach for semi-supervised sound event detection with unsupervised data augmentation. In: Proceedings of DCASE (2021)
Hart, G.: Nonintrusive appliance load monitoring. Proc. IEEE 80(12), 1870–1891 (1992)
Çimen, H., et al.: A dual-input multi-label classification approach for non-intrusive load monitoring via deep learning. In: Proceedings of ZINC, pp. 259–263 (2020)
Kelly, J., Knottenbelt, W.: Neural NILM: deep neural networks applied to energy disaggregation. In: Proceedings of the 2nd ACM International Conference on Embedded Systems for Energy-Efficient Built Environment, New York, USA, pp. 55–64 (2015)
Kelly, J., Knottenbelt, W.: The UK-DALE dataset, domestic appliance-level electricity demand and whole-house demand from five UK homes. Sci. Data 2(150007) (2015)
Kingma, D., Ba, J.: Adam: a method for stochastic optimization. In: Proceedings of ICLR (2014)
Li, D., Sawyer, K., Dick, S.: Disaggregating household loads via semi-supervised multi-label classification. In: Proceedings of NAFIPS, pp. 1–5 (2015)
Li, L., et al.: Hyperband: a novel bandit-based approach to hyperparameter optimization. J. Mach. Learn. Res. 18(1), 6765–6816 (2017)
Li, Y.F., Zhou, Z.H.: Towards making unlabeled data never hurt. IEEE Trans. Pattern Anal. Mach. Intell. 37(1), 175–188 (2015)
Lin, J., Ma, J., Zhu, J., Liang, H.: Deep domain adaptation for non-intrusive load monitoring based on a knowledge transfer learning network. IEEE Trans. Smart Grid 13(1), 280–292 (2022)
Massidda, L., et al.: Non-intrusive load disaggregation by convolutional neural network and multilabel classification. Appl. Sci. 10, 1454 (2020)
Miao, N., et al.: Non-intrusive load disaggregation using semi-supervised learning method. In: SPAC, pp. 17–22 (2019)
Murray, D., et al.: An electrical load measurements dataset of United Kingdom households from a two-year longitudinal study. Sci. Data 4(1), 160122 (2017)
Murray, D., et al.: Transferability of neural network approaches for low-rate energy disaggregation. In: Proceedings of ICASSP, Brighton, UK, pp. 8330–8334 (2019)
Nolasco, L.D.S., Lazzaretti, A.E., Mulinari, B.M.: DeepDFML-NILM: a new CNN-based architecture for detection, feature extraction and multi-label classification in NILM signals. IEEE Sens. J. 22(1), 501–509 (2022)
Panigrahi, S., Nanda, A., Swarnkar, T.: A survey on transfer learning. Smart Innov. Syst. Technol. 194, 781–789 (2021)
Serafini, L., Tanoni, G., Principi, E., Squartini, S.: A multiple instance regression approach to electrical load disaggregation. In: Proceedings of EUSIPCO (2022)
Singh, S., et al.: Non-intrusive load monitoring via multi-label sparse representation-based classification. IEEE Trans. Smart Grid 11(2), 1799–1801 (2020)
Singh, S., et al.: Multi-label deep blind compressed sensing for low-frequency non-intrusive load monitoring. IEEE Trans. Smart Grid 13(1), 4–7 (2022)
Singhal, V., et al.: Simultaneous detection of multiple appliances from smart-meter measurements via multi-label consistent deep dictionary learning and deep transform learning. IEEE Trans. Smart Grid 10(3), 2969–2978 (2019)
Sun, M., et al.: Non-intrusive load monitoring system framework and load disaggregation algorithms: a survey. In: Proceedings of ICAMechS, pp. 284–288 (2019)
Tabatabaei, S.M., Dick, S., Xu, W.: Toward non-intrusive load monitoring via multi-label classification. IEEE Trans. Smart Grid 8(1), 26–40 (2017)
Tanoni, G., Principi, E., Squartini, S.: Multilabel appliance classification with weakly labeled data for non-intrusive load monitoring. IEEE Trans. Smart Grid 14(1), 440–452 (2023). https://doi.org/10.1109/TSG.2022.3191908
Verma, S., Singh, S., Majumdar, A.: Multi label restricted Boltzmann machine for non-intrusive load monitoring. In: Proceedings of ICASSP, pp. 8345–8349 (2019)
Verma, S., Singh, S., Majumdar, A.: Multi-label LSTM autoencoder for non-intrusive appliance load monitoring. Electr. Power Syst. Res. 199, 107414 (2021)
Wang, L., et al.: Pre-trained models for non-intrusive appliance load monitoring. IEEE Trans. Green Commun. and Netw. 2400, 1 (2021)
Wang, Y., et al.: A comparison of five multiple instance learning pooling functions for sound event detection with weak labeling. In: Proceedings of ICASSP, pp. 31–35 (2019)
Yang, Y., Zhong, J., Li, W., Gulliver, T.A., Li, S.: Semisupervised multilabel deep learning based nonintrusive load monitoring in smart grids. IEEE Trans. Ind. Inf. 16(11), 6892–6902 (2020)
Zhang, C., et al.: Sequence-to-point learning with neural networks for non-intrusive load monitoring. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 32, no. 1 (2018)
Zhao, B., et al.: Improving event-based non-intrusive load monitoring using graph signal processing. IEEE Access 6, 53944–53959 (2018)
Zhou, X., et al.: Non-intrusive load monitoring using a CNN-LSTM-RF model considering label correlation and class-imbalance. IEEE Access 9, 84306–84315 (2021)
Zhou, Z.H.: A brief introduction to weakly supervised learning. Natl. Sci. Rev. 5(1), 44–53 (2018)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Tanoni, G., Principi, E., Mandolini, L., Squartini, S. (2022). Weakly Supervised Transfer Learning for Multi-label Appliance Classification. In: Mahmud, M., Ieracitano, C., Kaiser, M.S., Mammone, N., Morabito, F.C. (eds) Applied Intelligence and Informatics. AII 2022. Communications in Computer and Information Science, vol 1724. Springer, Cham. https://doi.org/10.1007/978-3-031-24801-6_26
Download citation
DOI: https://doi.org/10.1007/978-3-031-24801-6_26
Publisher Name: Springer, Cham
Online ISBN: 978-3-031-24801-6
eBook Packages: Computer ScienceComputer Science (R0)