Abstract
Non-Intrusive Load Monitoring (NILM) remains a critical issue in both commercial and residential energy management, with a key challenge being the requirement for individual appliance-specific deep learning models. These models often disregard the interconnected nature of loads and usage patterns, stemming from diverse user behavior. To address this, we introduce GraphNILM, an innovative end-to-end model that leverages graph neural networks to deliver appliance-level energy usage analysis for an entire home. In its initial phase, GraphNILM employs Gaussian random variables to depict the graph edges, later enhancing prediction accuracy by substituting these edges with observations of appliance interrelationships, stripping the individual load enery from the aggregated main energy all at one time, resulting in reduced memory usage, especially with more than three loads involved, thus presenting a time and space-efficient solution for real-world implementation. Comprehensive testing on popular NILM datasets confirms that our model outperforms existing benchmarks in both accuracy and memory consumption, suggesting its considerable promise for future deployment in edge devices.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Armel, C., Gupta, A., Shrimali, G., Albert, A.: Is disaggregation the holy grail of energy efficiency? the case of electricity. Energy Policy 52, 213–234 (2013)
Batic, D., Tanoni, G., Stankovic, L., Stankovic, V., Principi, E.: Improving knowledge distillation for non-intrusive load monitoring through explainability guided learning. In: 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (ICASSP 2023), pp. 1–5 (2023)
Batra, N., et al.: Nilmtk: an open source toolkit for non-intrusive load monitoring (2014)
Çimen, H., Çetinkaya, N., Vasquez, J.C., Guerrero, J.M.: A microgrid energy management system based on non-intrusive load monitoring via multitask learning. IEEE Trans. Smart Grid 12(2), 977–987 (2020)
De Baets, L., Ruyssinck, J., Develder, C., Dhaene, T., Deschrijver, D.: Appliance classification using VI trajectories and convolutional neural networks. Energy Build. 158, 32–36 (2018). https://doi.org/10.1016/j.enbuild.2017.09.087
Dong, H., Wang, B., Lu, C.T.: Deep sparse coding based recursive disaggregation model for water conservation. In: Twenty-Third International Joint Conference on Artificial Intelligence (2013)
Faustine, A., Mvungi, N.H., Kaijage, S.F., Kisangiri, M.: A survey on non-intrusive load monitoring methodies and techniques for energy disaggregation problem. arXiv preprint arXiv:1703.00785 (2017)
Ferraz, F.C., Monteiro, R.V.A., Teixeira, R.F.S., Bretas, A.S.: A siamese CNN + KNN-based classification framework for non-intrusive load monitoring. J. Control Automat. Electric. Syst.
Ghosh, S., Chatterjee, A., Chatterjee, D.: Extraction of statistical features for type-2 fuzzy Nilm with IoT enabled control in a smart home. Exp. Syst. Appl. 212, 118750 (2023)
Hart, G.W.: Prototype nonintrusive appliance load monitor. Tech. Rep. Progress Report 2, MIT Energy Laboratory (1985)
He, K., Stankovic, V., Stankovic, L.: Building a graph signal processing model using dynamic time warping for load disaggregation. Sensors 20, 6628 (2020)
Huber, P., Calatroni, A., Rumsch, A., Paice, A.: Review on deep neural networks applied to low-frequency Nilm (2021)
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 Environments, pp. 55–64 (2015)
Kelly, J., Knottenbelt, W.J.: The UK-DALE: a dataset recording UK domestic appliance-level electricity demand and whole-house demand. arXiv preprint arXiv:1404.0284 (2014)
Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks (2016)
Kolter, J., Johnson, M.: Redd: a public data set for energy disaggregation research. Artif. Intell. 25 (2011)
Kolter, J., Jaakkola, T.: Approximate inference in additive factorial HMMs with application to energy disaggregation. In: International Conference on Artificial Intelligence and Statistics, pp. 1472–1482 (2012)
Liu, B., Zhang, J., Luan, W.: Load oscillation pattern detection for nilm based on scale space decomposition. In: 2023 8th Asia Conference on Power and Electrical Engineering (ACPEE), pp. 1590–1595 (2023)
Liu, Y., Xu, Q., Yang, Y., Zhang, W.: Detection of electric bicycle indoor charging for electrical safety: a NILM Approach. IEEE Trans. Smart Grid 14(5), 3862–3875 (2023)
Mauch, L., Yang, B.: A New Approach for Supervised Power Disaggregation by Using a Deep Recurrent LSTM Network, pp. 63–67 (2015)
Oord, A.v.d., et al.: Wavenet: a generative model for raw audio (2016)
Parson, O., Ghosh, S., Weal, M., Rogers, A.: Non-intrusive load monitoring using prior models of general appliance types (2012)
Sykiotis, S., et al.: Performance-aware NILM model optimization for edge deployment. IEEE Trans. Green Commun. Netw. 7(3), 1434–1446 (2023). https://doi.org/10.1109/TGCN.2023.3244278
Vine, D., Buys, L., Morris, P.: The effectiveness of energy feedback for conservation and peak demand: a literature review. Open J. Energy Efficiency 2, 2013 (2013)
Zhang, B., Zhao, S., Shi, Q., Zhang, R.: Low-rate non-intrusive appliance load monitoring based on graph signal processing. In: 2019 International Conference on Security, Pattern Analysis, and Cybernetics (SPAC) (2019)
Zhang, C., Zhong, M., Wang, Z., Goddard, N., Sutton, C.: Sequence-to-point learning with neural networks for nonintrusive load monitoring (2016)
Zhao, B., Stankovic, L., Stankovic, V.: Blind non-intrusive appliance load monitoring using graph-based signal processing. In: 2015 IEEE Global Conference on Signal and Information Processing (GlobalSIP) (2015)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Shang, R., Chen, S., Chen, Z., Lu, CT. (2024). GraphNILM: A Graph Neural Network for Energy Disaggregation. In: Yang, DN., Xie, X., Tseng, V.S., Pei, J., Huang, JW., Lin, J.CW. (eds) Advances in Knowledge Discovery and Data Mining. PAKDD 2024. Lecture Notes in Computer Science(), vol 14646. Springer, Singapore. https://doi.org/10.1007/978-981-97-2253-2_34
Download citation
DOI: https://doi.org/10.1007/978-981-97-2253-2_34
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-97-2252-5
Online ISBN: 978-981-97-2253-2
eBook Packages: Computer ScienceComputer Science (R0)