Abstract
Non-Intrusive Load Monitoring (NILM) technique or energy disaggregation is a technique used to detect the appliance’s states and estimate their individual energy consumption, given the aggregated data through the main smart meter. Indeed, energy efficiency is the main goal of the NILM techniques, which can be achieved by providing energy disaggregation feedback to the consumers. Unlike single models where training must be performed for each appliance, this work proposes multi-target disaggregation which is more appropriate due to the drastic reduction of resources when training is performed for all target appliances simultaneously. For this purpose, new hybrid models are proposed by combining well-known deep learning models: Convolutional Neural Network (CNN), Denoising Autoencoder (DAE), Recurrent Neural Network (RNN), and Long Short-Term Memory network (LSTM). An implementation and detailed comparative study is then suggested between the proposed hybrid deep learning models and conventional single models in terms of various performance metrics on the UK-Domestic Appliance-Level Electricity (UKDALE) benchmarking database. The experimental results show that the proposed hybrid models provide the best disaggregation performances for multi-target disaggregation compared to single models. Specifically, the CNN-LSTM and the DAE-LSTM are the best hybrid models with the highest overall F1-score of 78.90% and 72.94% respectively.
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs12053-023-10161-1/MediaObjects/12053_2023_10161_Fig1_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs12053-023-10161-1/MediaObjects/12053_2023_10161_Fig2_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs12053-023-10161-1/MediaObjects/12053_2023_10161_Fig3_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs12053-023-10161-1/MediaObjects/12053_2023_10161_Fig4_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs12053-023-10161-1/MediaObjects/12053_2023_10161_Fig5_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs12053-023-10161-1/MediaObjects/12053_2023_10161_Fig6_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs12053-023-10161-1/MediaObjects/12053_2023_10161_Fig7_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs12053-023-10161-1/MediaObjects/12053_2023_10161_Fig8_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs12053-023-10161-1/MediaObjects/12053_2023_10161_Fig9_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs12053-023-10161-1/MediaObjects/12053_2023_10161_Fig10_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs12053-023-10161-1/MediaObjects/12053_2023_10161_Fig11_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs12053-023-10161-1/MediaObjects/12053_2023_10161_Fig12_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs12053-023-10161-1/MediaObjects/12053_2023_10161_Fig13_HTML.png)
Similar content being viewed by others
Abbreviations
- NILM :
-
Non-intrusive Load Monitoring
- ILM :
-
Intrusive load monitoring
- ALM :
-
Appliance load monitoring
- IAMs :
-
Individual appliance monitors
- ANN :
-
Artificial neural network
- DNN :
-
Deep neural networks
- DL :
-
Deep learning
- GA :
-
Genetic algorithm
- CNN :
-
Convolutional neural network
- RNN :
-
Recurrent neural network
- LSTM :
-
Long short-term memory
- GRU :
-
Gated recurrent unit
- DAE :
-
Denoising autoencoder
- SRN :
-
Simple recurrent network
- RCNN :
-
Recurrent convolutional neural network
- UKDALE :
-
UK-domestic appliance-level electricity
- AMPds :
-
Almanac of minutely power database
- REDD :
-
Reference energy disaggregation database
- ReLU :
-
Rectified linear unit
- MAE :
-
Mean absolute error
- R :
-
Recall
- P :
-
Precision
- F 1 :
-
F1-score
- HMM :
-
Hidden Markov Model
References
Abuimara, T., Hobson, B. W., Gunay, B., & Brien, W. O. (2022). A Data-Driven Workflow to Improve Energy Efficient Operation of Commercial Buildings : A Review with Real-World Examples. Building Services Engineering Research and Technology, 43(4), 517–534. https://doi.org/10.1177/01436244211069655
Alkhulaifi, A., & Aljohani, A. J. (2020). Investigation of Deep Learning-Based Techniques for Load Disaggregation, Low-Frequency Approach. International Journal of Advanced Computer Science and Applications, 11(1).
Athanasiadis, C. L., Papadopoulos, T. A., & Doukas, D. I. (2021). Real-Time Non-Intrusive Load Monitoring : A Light-Weight and Scalable Approach. Energy & Buildings, 253, 111523. https://doi.org/10.1016/j.enbuild.2021.111523
Ayub, M., & El-Alfy, E.-S. (2020). Multi-Target Energy Disaggregation Using Convolutional Neural Networks. International Journal of Advanced Computer Science and Applications, 11(10), 684–693.
Bonfigli, R., Principi, E., Fagiani, M., Severini, M., & Squartini, S. (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
Bonfigli, R., Felicetti, A., Principi, E., Fagiani, M., Squartini, S., & Piazza, F. (2018). Denoising Autoencoders for Non-Intrusive Load Monitoring: Improvements and Comparative Evaluation. Energy and Buildings, 158, 1461–1474. https://doi.org/10.1016/j.enbuild.2017.11.054
Buddhahai, B., & Makonin, S. (2021). A Nonintrusive Load Monitoring Based on Multi-Target Regression Approach. IEEE Access, 9, 163033–163042. https://doi.org/10.1109/ACCESS.2021.3133292
Chen, K., Wang, Q., He, Z., Chen, K., Jun, Hu., & He, J. (2018). Convolutional Sequence to Sequence Non-intrusive Load Monitoring. The Journal of Engineering, 2018(17), 1860–1864. https://doi.org/10.1049/joe.2018.8352
Chen, K., Zhang, Yu., Wang, Q., Jun, Hu., Fan, H., & He, J. (2019). Scale- and Context-Aware Convolutional Non-Intrusive Load Monitoring. IEEE Transactions on Power Systems, 35, 2362–2373. https://doi.org/10.1109/TPWRS.2019.2953225
Chen, C., Gao, P., Jiang, J., Wang, H., Li, P., & Wan, S. (2021). A Deep Learning Based Non-Intrusive Household Load Identification for Smart Grid in China. Computer Communications, 177, 176–84. https://doi.org/10.1016/j.comcom.2021.06.023
Chen, H., Hsien, Y., Chun, W., & Fan, H. (2021b). A Convolutional Autoencoder - Based Approach with Batch Normalization for Energy Disaggregation. The Journal of Supercomputing, 77(3), 2961–2978. https://doi.org/10.1007/s11227-020-03375-y
Çimen, H., Çetinkaya, N., Vasquez, J. C., Member, S., & Guerrero, J. M. (2020). A Microgrid Energy Management System Based on Non-Intrusive Load Monitoring via Multitask Learning. IEEE Transactions on Smart Grid, 12(2), 977–987. https://doi.org/10.1109/TSG.2020.3027491
Cui, G., Liu, Bo., Luan, W., & Yixin, Yu. (2019). Estimation of Target Appliance Electricity Consumption Using Background Filtering. IEEE Transactions on Smart Grid, 10(6), 5920–5929. https://doi.org/10.1109/TSG.2019.2892841
Gopinath, R., Mukesh Kumar, C., Chandra, P., & Srinivas, K. (2020). Energy Management Using Non-Intrusive Load Monitoring Techniques – State- of-the-Art and Future Research Directions. Sustainable Cities and Society, 62, 102411. https://doi.org/10.1016/j.scs.2020.102411
Hart, G. W. (1992). Nonintrusive Appliance Load Monitoring. Proceedings of the IEEE, 80(12), 1870–1891. https://doi.org/10.1109/5.192069
He, K., Stankovic, L., Liao, J., & Stankovic, V. (2018). Non-Intrusive Load Disaggregation Using Graph Signal Processing. IEEE Transactions on Smart Grid, 9(3), 1739–1747. https://doi.org/10.1109/TSG.2016.2598872
Himeur, Y., Alsalemi, A., Bensaali, F., & Amira, A. (2020). Building Power Consumption Datasets : Survey, Taxonomy and Future Directions. Energy & Buildings, 227, 110404. https://doi.org/10.1016/j.enbuild.2020.110404
Hosseini, S. S., Agbossou, K., Kelouwani, S., & Cardenas, A. (2017). Non-Intrusive Load Monitoring through Home Energy Management Systems: A Comprehensive Review. Renewable and Sustainable Energy Reviews, 79, 1266–1274. https://doi.org/10.1016/j.rser.2017.05.096
Houidi, S., Fourer, D., & Auger, F. (2020). On the Use of Concentrated Time – Frequency Representations as Input to a Deep Convolutional Neural Network : Application to Non Intrusive. Entropy, 22, 911. https://doi.org/10.3390/e22090911
Ji, T. Y., Liu, L., Wang, T. S., Lin, W. B., Li, M. S., & Wu, Q. H. (2019). Non-Intrusive Load Monitoring Using Additive Factorial Approximate Maximum a Posteriori Based on Iterative Fuzzy C-Means. IEEE Transactions on Smart Grid, 10, 6667–6677. https://doi.org/10.1109/TSG.2019.2909931
Jia, Z., Yang, L., Zhang, Z., Liu, H., & Kong, F. (2021). Sequence to Point Learning Based on Bidirectional Dilated Residual Network for Non-Intrusive Load Monitoring. Electrical Power and Energy Systems, 129, 106837.
Jiang, J., Kong, Q., Plumbley, M. D., Gilbert, N., Hoogendoorn, M., & Roijers, D. M. (2021). Deep Learning-Based Energy Disaggregation and On/Off Detection of Household Appliances. ACM Transactions on Knowledge Discovery from Data, 15(3), 1–21. https://doi.org/10.1145/3441300
Kaselimi, M., Doulamis, N., Voulodimos, A., Protopapadakis, E., & Doulamis, A. (2020). Context Aware Energy Disaggregation Using Adaptive Bidirectional LSTM Models. IEEE Transactions on Smart Grid, 11(4), 3054–3067. https://doi.org/10.1109/TSG.2020.2974347
Kaselimi, M., Protopapadakis, E., Voulodimos, A. V., Doulamis, N., & Doulamis, A. D. (2022). Towards Trustworthy Energy Disaggregation : A Review of Load Monitoring. Sensors, 22(15), 5872.
Kelly, J., Gate, Q., & Knottenbelt W. (2015). Neural NILM : Deep Neural Networks Applied to Energy Disaggregation. Proceedings of the 2nd ACM International Conference on Embedded Systems for Energy-Efficient Built Environments, 55–64. https://doi.org/10.1145/2821650.2821672.
Kelly, J., & Knottenbelt, W. (2015). The UK-DALE Dataset, Domestic Appliance-Level Electricity Demand and Whole-House Demand from Fi ve UK Homes. Scientific Data, 2(1), 1–14. https://doi.org/10.1038/sdata.2015.7
Kim, J., Le, T-t-h., & Kim, H. (2017). Nonintrusive Load Monitoring Based on Advanced Deep Learning and Novel Signature. Computational Intelligence and Neuroscience, 2017. https://doi.org/10.1155/2017/4216281
Kim, J. G., & Lee, B. (2019). Appliance Classification by Power Signal Analysis Based on Multi-Feature Combination Multi-Layer LSTM. Energies, 12(14), 2804. https://doi.org/10.3390/en12142804
Kong, W., Dong, Z. Y., Wang, Bo., & Zhao, J. (2019). A Practical Solution for Non-Intrusive Type II Load Monitoring Based on Deep Learning and. Post-Processing. IEEE Transactions on Smart Grid, 11(1), 148–160. https://doi.org/10.1109/TSG.2019.2918330
Krizhevsky, B. A., Sutskever, I., & Hinton, G. E. (2012). ImageNet Classification with Deep Convolutional Neural Networks. Communications of the ACM, 60(6), 84–90.
Li, C., Liang, G., Zhao, H., & Chen, G. (2021. A Demand-Side Load Event Detection Algorithm Based on Wide-Deep Neural Networks and Randomized Sparse Backpropagation. Frontiers in Energy Research, 856. https://doi.org/10.3389/fenrg.2021.720831
Lin, Y.-H. (2020). A Parallel Evolutionary Computing-Embodied Artificial Neural Network Applied to Non-Intrusive Load Monitoring for Demand-Side Management in a Smart Home : Towards Deep Learning. Sensors, 20(6), 1649.
Lin, Y. H., & Tsai, MS. (2011). Applications of Hierarchical Support Vector Machines for Identifying Load Operation in Nonintrusive Load Monitoring Systems. In 2011 9th World Congress on Intelligent Control and Automation (pp. 688–93). https://doi.org/10.1109/WCICA.2011.5970603
Liu, W., Weng, L., Xia, M., & Wang, Ke. (2019). Multi-Scale Residual Network for Energy Disaggregation Yiqing Xu Zhuhan Qiao. Intrnational Journal of Sensor Networks, 30(3), 172–183.
Liu, Qi., Zhang, J., Liu, X., Zhang, Y., Xiaolong, Xu., Khosravi, M., & Bilal, M. (2022). Improving Wireless Indoor Non-Intrusive Load Disaggregation Using Attention-Based Deep Learning Networks. Physical Communication, 51, 101584. https://doi.org/10.1016/j.phycom.2021.101584
Makonin, S., Popowich, F., Bajic, I. V., Gill, B., & Bartram, L. (2016). Exploiting HMM Sparsity to Perform Online Real-Time Nonintrusive Load Monitoring. IEEE Transactions on Smart Grid, 7(6), 2575–2585. https://doi.org/10.1109/TSG.2015.2494592
Massidda, L., Marrocu, M., & Manca, S. (2020). Non-Intrusive Load Disaggregation by Convolutional Neural Network and Multilabel Classification. Applied Sciences, 10(4), 1454. https://doi.org/10.3390/app10041454
Min, C., & Wen, G. (2019). Non-Intrusive Load Monitoring System Based on Convolution Neural Network and Adaptive Linear Programming Boosting. Energies, 12, 2882.
Monteiro, R. V. A., De Santana, J. C. R., Teixeira, R. F. S., Bretas, A. S., Aguiar, R., & Poma, P. (2021). Non-Intrusive Load Monitoring Using Artificial Intelligence Classifiers : Performance Analysis of Machine Learning Techniques. Electric Power Systems Research, 198, 107347. https://doi.org/10.1016/j.epsr.2021.107347
Moradzadeh, A., Mohammadi, B., Abapour, M., & Anvari, A. (2021). A Practical Solution Based on Convolutional Neural Network for Non - Intrusive Load Monitoring. Journal of Ambient Intelligence and Humanized Computing, 12(10), 9775–9789. https://doi.org/10.1007/s12652-020-02720-6
Passricha, V., & Aggarwal, R. K. (2014). Convolutional Neural Networks for Raw Speech Recognition. From Natural to Artificial Intelligence - Algorithms and Applications, 22(10), 1533–1545. https://doi.org/10.5772/intechopen.80026
Peng, Ce., Lin, G., Zhai, S., Ding, Yi., & He, G. (2020). Non-Intrusive Load Monitoring via Deep Learning Based User Model and Appliance Group Model. Energies, 13(21), 5629. https://doi.org/10.3390/en13215629
Prasad, R. S., & Semwal, D. (2014). Multi Point Sensing (MPS): A Solution for Resolving Complexity in NIALM Applications for Indian Domestic Consumers. In 2014 IEEE International Conference on Power Electronics, Drives and Energy Systems, PEDES 2014, 1–6. https://doi.org/10.1109/PEDES.2014.7042066.
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. Energies, 13(9), 2195.
Rafiq, H., Shi, X., Zhang, H., Li, H., Ochani, M. K., & Shah, A. A. (2021). Generalizability Improvement of Deep Learning-Based Non-Intrusive Load Monitoring System Using Data Augmentation. IEEE Transactions on Smart Grid, 12(4), 3265–3277. https://doi.org/10.1109/TSG.2021.3082622
Ramadan, R., Huang, Qi., Bamisile, O., & Zalhaf, A. S. (2022b). Intelligent Home Energy Management Using Internet of Things Platform Based on NILM Technique. Sustainable Energy, Grids and Networks, 31, 100785. https://doi.org/10.1016/j.segan.2022.100785
Ramadan, R., Huang, Q., & Bamisile, O. (2022). Non-Intrusive Load Monitoring for Household Energy Disaggregation: A State-of-the-Art. In 2022 IEEE 6th IEEE Conference on Energy Internet and Energy System Integration, 1397–1403. https://doi.org/10.1109/EI256261.2022.10116809
Ramadan, R., Huang, Q., Bamisile, O., Zalhaf, A. S., Mahmoud, K., Lehtonen, M., & M. M. F. Darwish, M. M. F. (2023). Towards Energy-Efficient Smart Homes via Precise Nonintrusive Load Disaggregation Based on Hybrid ANN–PSO. Energy Science and Engineering, 2535–51. https://doi.org/10.1002/ese3.1472
Ranjan, S., Jayashree, D., Venkatesan, K. G. S., & Budaraju, H. (2021). Non-Intrusive Load Monitoring Technique Using Deep Neural Networks for Energy Disaggregation. Materials Today: Proceedings. https://doi.org/10.1016/j.matpr.2021.01.192
Semwal, S., Singh, M., & Prasad, R. S. (2015). Group Control and Identification of Residential Appliances Using a Nonintrusive Method. Turkish Journal of Electrical Engineering and Computer Sciences, 23(6), 1805–1816. https://doi.org/10.3906/elk-1404-59
Song, J., & Wang, H. (2021). Non-Intrusive Load Identification Method Based on Improved Long Short Term Memory Network. Energies, 14(03), 684.
Verma, S., Singh, S., & Majumdar, A. (2021). Multi-Label LSTM Autoencoder for Non-Intrusive Appliance Load Monitoring. Electric Power Systems Research, 199, 107414. https://doi.org/10.1016/j.epsr.2021.107414
Wang, J., & Srikantha, P. (2021). Stealthy Black-Box Attacks on Deep Learning Non-Intrusive Load Monitoring Models. IEEE Transactions on Smart Grid, 12, 3479–3492.
Wu, H., & Liu, H. (2021). Non-Intrusive Load Transient Identification Based on Multivariate LSTM Neural Network and Time Series Data Augmentation. Sustainable Energy, Grids and Networks, 27, 100490. https://doi.org/10.1016/j.segan.2021.100490
Xia, M., Wang, K., Zhang, X., & Xu, Y. (2019). Non-Intrusive Load Disaggregation Based on Deep Dilated Residual Network. Electric Power Systems Research, 170, 277–85. https://doi.org/10.1016/j.epsr.2019.01.034
Xia, M., Wang, Ke., Song, W., Chen, C., & Li, Y. (2020). Non-Intrusive Load Disaggregation Based on Composite Deep Long Short-Term Memory Network. Expert Systems with Applications, 160, 113669. https://doi.org/10.1016/j.eswa.2020.113669
Yang, C. C., Soh, C. S., & Yap, V. V. (2017). A Systematic Approach in Appliance Disaggregation Using K-Nearest Neighbours and Naive Bayes Classifiers for Energy Efficiency. Energy Efficiency, 11(1), 239–256. https://doi.org/10.1007/s12053-017-9561-0
Yang, D., Gao, X., Kong, L., Pang, Y., & Zhou, B. (2020). An Event-Driven Convolutional Neural Architecture for Non-Intrusive Load Monitoring of Residential Appliance. IEEE Transactions on Consumer Electronics, 66(2), 173–182. https://doi.org/10.1109/TCE.2020.2977964
Yin, Bo., Zhao, L., Huang, X., Zhang, Y., & Zehua, Du. (2021). Research on Non-Intrusive Unknown Load Identification Technology Based on Deep Learning. International Journal of Electrical Power and Energy Systems, 131, 107016. https://doi.org/10.1016/j.ijepes.2021.107016
Zhang, G., Gary Wang, G., Farhangi, H., & Palizban, A. (2017). Data Mining of Smart Meters for Load Category Based Disaggregation of Residential Power Consumption. Sustainable Energy, Grids and Networks, 10, 92–103. https://doi.org/10.1016/j.segan.2017.03.006
Zhang, Y., Yin, Bo., Cong, Y., & Zehua, Du. (2020). Multi-State Household Appliance Identification Based on Convolutional Neural Networks and Clustring. Energies, 13(04), 792.
Zhou, X., Feng, J., & Li, Y. (2021). Non-Intrusive Load Decomposition Based on CNN – LSTM Hybrid Deep Learning Model. Energy Reports, 7, 5762–5771. https://doi.org/10.1016/j.egyr.2021.09.001
Acknowledgements
The authors thank the anonymous reviewers for their helpful comments.
Author information
Authors and Affiliations
Contributions
Jamila Ouzine: Conceptualization, Writing—original draft, Methodology, Writing – review and editing, Software. Manal Marzouq: Conceptualization, Writing—original draft, Methodology, review and Validation. Saad Dosse Bennani: Conceptualization, Investigation, Supervision, Validation. Khadija Lahrech: Conceptualization, Investigation, Supervision, Validation. Hakim EL Fadili: Conceptualization, Investigation, Supervision, Validation.
Corresponding author
Ethics declarations
Conflict of interest
The authors declare no competing interests.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Ouzine, J., Marzouq, M., Dosse Bennani , S. et al. New hybrid deep learning models for multi-target NILM disaggregation. Energy Efficiency 16, 82 (2023). https://doi.org/10.1007/s12053-023-10161-1
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s12053-023-10161-1