International Journal of Intelligent Systems and Applications (IJISA)
IJISA Vol. 17, No. 6, 8 Dec. 2025
Cover page and Table of Contents: PDF (size: 1329KB)
Non-intrusive Load Monitoring for Home Appliance Using Sequence-to-point Convolutional Neural Networks
PDF (1329KB), PP.75-93
Views: 0 Downloads: 0
Author(s)
John Oluwasegun Memud
1
Brendan Chijioke Ubochi
1,*
Michael Rotimi Adu
1
Nnamdi Nwulu
2
Index Terms
Non-intrusive Load Monitoring, Deep Learning, CNN, Energy Disaggregation, Feature Learning, Energy Conservation
Abstract
Non-intrusive load monitoring (NILM) aims to estimate the operational states and power consumption of individual household appliances, providing real-time insights into energy usage for effective energy management and improved demand side response strategies. This study addresses the challenge of accurate energy disaggregation of household energy consumption data into individual appliances’ consumption, an important requirement for effective energy management in smart homes. Traditional energy monitoring systems provide only aggregate data, limiting the ability to optimize energy consumption. To overcome these difficulties, this study proposes a Convolutional Neural Network (CNN)-based model for Non-Intrusive Load Monitoring (NILM) that disaggregates total energy usage into appliance-specific consumption for five key appliances: kettle, microwave, fridge, dishwasher, and washing machine. Unlike the previous approaches, our model integrates a hybrid dataset from UK-DALE and REFIT, leveraging data fusion techniques to enhance generalization. The CNN architecture employed uses five convolutional layers for effective feature extraction, capturing temporal dependencies in appliance usage patterns and thus results in an improved MAE and SAE when compared to similar published results. The preprocessing and hybridization stage involves such processes as missing data imputation, appliance state labelling, feature normalization and merging of the datasets. The developed model achieved an overall accuracy of 98.3% and an F1-score of 81.7% in seen scenarios, while in unseen environments, it attained 96.5% accuracy and an F1-score of 58.1% when tested on the UK-DALE dataset. The seen scenario refers to testing using UK-DALE House 1 and REFIT House 2 data of the validation dataset, whereas the unseen scenario involves entirely new house data not used during training and validation. It is shown that post-processing techniques reduce errors, highlighting its effectiveness, which help to enhance the model's predictive accuracy. This study contributes to the advancement of NILM technologies by combining datasets, offering a robust and scalable solution for individual appliace energy monitoring, with significant implications on energy conservation and smart home efficiency.
Cite This Paper
John Oluwasegun Memud, Brendan Chijioke Ubochi, Michael Rotimi Adu, Nnamdi Nwulu, "Non-intrusive Load Monitoring for Home Appliance Using Sequence-to-point Convolutional Neural Networks", International Journal of Intelligent Systems and Applications(IJISA), Vol.17, No.6, pp.75-93, 2025. DOI:10.5815/ijisa.2025.06.06
Reference
[1]Zoha, A.; Gluhak, A.; Imran, M.A.; Rajasegarar, S. (2012). Non-Intrusive Load Monitoring Approaches for Disaggregated Energy Sensing: A Survey. Sensors, 12, 16838–16866. https://dx.doi.org/10.3390/s121216838
[2]Zeifman, M.; Roth, K. (2011). Nonintrusive Appliance Load Monitoring: Review and Outlook. IEEE Trans. Consum. Electron., 57, 76–84. https://dx.doi.org/10.1109/TCE.2011.5735484
[3]Kelly, J.; Knottenbelt, W. (2015a). 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).
[4]Kolter, J. Z.; Jaakkola, T. (2012). Approximate inference in additive factorial HMMs with application to energy disaggregation. In Artificial Intelligence and Statistics, 1472-1482. Retrieved from http://proceedings.mlr.press/v22/zico12.html
[5]He, W.; Chai, Y. (2016). An Empirical Study on Energy Disaggregation via Deep Learning. In 2nd International Conference on Artificial Intelligence and Industrial Engineering, 338–342. https://www.atlantis-press.com/proceedings/aiie-16/25866379
[6]Zhang, Y.; Yin, B.; Cong, Y.; Du, Z. (2020). Multi-state Household Appliance Identification Based on Convolutional Neural Networks and Clustering. Energies, 13 (4), 792. https://dx.doi.org/10.3390/en13040792
[7]Aghera, R.; Chilana, S.; Garg, V.; Reddy, R. (2021). A Deep Learning Technique Using Low Sampling Rate for Residential Non-Intrusive Load Monitoring. arXiv preprint arXiv:2111.05120. https://doi.org/10.48550/arXiv.2111.05120
[8]Jiao, X.; Chen, G.; Liu, J. (2023). A non-intrusive load monitoring model based on graph neural networks. In 2023 IEEE 2nd International Conference on Electrical Engineering, Big Data and Algorithms (EEBDA) (pp. 245–250). IEEE. https://doi.org/10.1109/EEBDA56825.2023.10090820
[9]Song, J.; Wang, H.; Du, M.; Peng, L.; Zhang, S.; Xu, G. (2021). Non-Intrusive Load Identification Method Based on Improved Long Short-Term Memory Network. Energies, 14 (3), 684. https://doi.org/10.3390/en14030684
[10]Zhang, C.; Zhong, M.; Wang, Z.; Goddard, N.; Sutton, C. (2018). Sequence-to-point learning with neural networks for non-intrusive load monitoring. In Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence (AAAI-18), 32(1) https://doi.org/10.1609/aaai.v32i1.11873
[11]Hart, G. W. (1992). Non-intrusive appliance load monitoring. Proceedings of the IEEE, 80 (12), 1870-1891.
[12]Bonfigli, R.; Principi, E.; Fagiani, M.; Severini, M.; Squartini, S.; Piazza, F. (2017). Non-Intrusive Load Monitoring by Using Active and Reactive Power in Additive Factorial Hidden Markov Models. Applied Energy, 208, 1590–1607. https://doi.org/10.1016/j.apenergy.2017.08.203
[13]Zoha, A.; Gluhak, A.; Nati, M.; Imran, M.A. (2013). Low-Power Appliance Monitoring Using Factorial Hidden Markov Models. In Proceedings of the 2013 IEEE 8th International Conference on Intelligent Sensors, Sensor Networks and Information Processing: Sensing the Future, ISSNIP 2013, Melbourne, Australia, 2–5 April 2013; Volume 1, pp. 527–532. https://dx.doi.org/10.1109/ISSNIP.2013.6529845
[14]Lin, G. Y.; Lee, S. C.; Hsu, J. Y. J.; Jih, W. R. (2010). Applying Power Meters for Appliance Recognition on the Electric Panel. In Proceedings of the 2010 5th IEEE Conference on Industrial Electronics and Applications (ICIEA 2010) (pp. 2254–2259). https://doi.org/10.1109/ICIEA.2010.5515385
[15]Mauch, L.; Yang, B. (2015). A New Approach for Supervised Power Disaggregation by Using a Deep Recurrent LSTM Network. In Proceedings of the 2015 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2015, Orlando, FL, USA, 14–16 December 2015; pp. 63–67. https://dx.doi.org/10.1109/GlobalSIP.2015.7418157
[16]Varanasi, L. N. S.; Karri, S. P. K. (2024). Enhancing non-intrusive load monitoring with channel attention guided bi-directional temporal convolutional network for sequence-to-point learning. Electric Power Systems Research, 228, 110088.
[17]Xiong, C.; Cai, Z.; Liu, S.; Luo, J.; Tu, G. (2023). An improved sequence-to-point learning for non-intrusive load monitoring based on Discrete Wavelet Transform. IEEE Transactions on Instrumentation and Measurement, 72, 1-16.
[18]D’Incecco, M.; Squartini, S.; Zhong, M. (2020). Transfer Learning for Non-Intrusive Load Monitoring. IEEE Trans. Smart Grid, 11 (2), 1419–1429. https://dx.doi.org/10.1109/TSG.2019.2938068
[19]Rafiq, H.; Shi, X.; Zhang, H.; Li, H.; Ochani, M. K. (2020). A deep recurrent neural network for non-intrusive load monitoring based on multi-feature input space and post-processing. Energies, 13 (9), 2195. https://doi.org/10.3390/en13092195
[20]Le, T.-T.-H.; Kim, H. (2018). Non-intrusive load monitoring based on novel transient signal in household appliances with low sampling rate. Energies, 11(12), 3409. https://doi.org/10.3390/en11123409
[21]Manca, M. M.; Massidda, L. (2022). Deep learning based non-intrusive load monitoring with low resolution data from smart meters. Communications in Applied and Industrial Mathematics, 13(1), 39-56. https://doi.org/10.2478/caim-2022-0004
[22]Kelly, J.; Knottenbelt, W. (2015b). The UK-DALE dataset, domestic appliance-level electricity demand and whole-house demand from five UK homes. Scientific Data, 2 (1), 150007. https://doi.org/10.1038/sdata.2015.7
[23]Johnson, M. J.; Kolter, J. Z. (2011). REDD: A public data set for energy disaggregation research. In Workshop on Data Mining Applications in Sustainability (SIGKDD) 25: 59–62. https://www.cs.cmu.edu/afs/cs.cmu.edu/Web/People/zkolter/pubs/kolter-kddsust11.pdf
[24]Murray, D.; Stankovic, L. (2016). REFIT: Electrical load measurements (Cleaned) [Dataset]. Zenodo. https://doi.org/10.5281/zenodo.5063428
[25]Pereira, L.; Nunes, N. (2018). Performance evaluation in non-intrusive load monitoring: Datasets, metrics, and tools—A review. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery, 8(6), e1265. https://doi.org/10.1002/widm.1265
[26]Klemenjak, C.; Makonin, S.; Elmenreich, W. (2020). A synthetic energy dataset for non-intrusive load monitoring in households. Scientific Data, 7(1), 1-12. https://doi.org/10.1038/s41597-020-0434-6
[27]Reddy, R.; Garg, V.; Pudi, V. (2020). A feature fusion technique for improved non-intrusive load monitoring. Energy Informatics, 3 (1), 9. https://doi.org/10.1186/s42162-020-00112-w
[28]Laouali, I.; Ruano, A.; Ruano, M. D. G.; Bennani, S.D.; Fadili, H. E. (2022). Non-intrusive load monitoring of household devices using a hybrid deep learning model through convex hull-based data selection. Energies, 15 (3), 1215. https://doi.org/10.3390/en15031215