Towards Trustworthy Energy Disaggregation: A Review of Challenges, Methods, and Perspectives for Non-Intrusive Load Monitoring
Abstract
:1. Introduction
- Provides a short literature review on the existing NILM methods for residential appliances and highlights the trustworthiness aspects of the current state-of-the-art methods.
- Collects the research dilemmas that have appeared in the literature for solving the NILM problem and discusses the advantages and disadvantages of the different approaches.
- Highlights the existing challenges in NILM and discusses the barriers and limitations towards a reliable, practical, and trustworthy NILM framework.
- Discusses the future perspectives on NILM models under a trustworthy framework.
2. Background on NILM
2.1. NILM Problem Formulation
2.2. Challenges to NILM
- “Challenge 1: To create reliable algorithms with good generalization ability”:
- “Challenge 2: To develop hybrid NILM models incorporating user’s feedback and techniques that support continuous learning”:
- “Challenge 3: To provide explainable NILM models with reasoning behind the model estimations”:
- “Challenge 4: To achieve fairness in NILM”:
- “Challenge 5: To provide privacy-preserving outcomes using secure NILM models”:
3. Paper Selection Methodology
4. A Brief NILM Literature Review
4.1. The Early NILM Era (1995–2014)
4.2. Deep-Learning-Based NILM (2015–2019)
4.3. Current Advancements in NILM (2020–Present)
5. Signal Analysis and Feature Extraction
5.1. Outline of the Existing Practices for NILM Data Pre-Processing
5.1.1. Balancing
5.1.2. Handling Sample Rates and Missing Data
5.1.3. Optimal Features’ Extraction and Selection
6. Machine Learning for NILM
6.1. Research Dilemmas and Conflicting Views
6.1.1. Classification or Regression Model
6.1.2. Multi-Target or Single-Target Model
6.1.3. Supervised or Unsupervised Learning
6.1.4. Convolutional or Recurrent Layers
6.1.5. Causal or Non-Causal Models
6.1.6. Sequence-to-Point or Sequence-to-Sequence Techniques
6.1.7. Uni- or N-Dimensional Problem
6.2. Trends in Machine Learning Approaches for Solving NILM
7. Trustworthiness in NILM Algorithms: Can We Trust AI in NILM Problems?
7.1. Reliability
7.2. Scalability
7.3. Robustness
7.4. Precision
7.5. Explainability
7.6. Fairness
7.7. Safety and Privacy
8. Datasets, Performance Evaluation/Validation Strategy, and Open NILM Tools
8.1. Datasets
8.2. NILM Metrics and Evaluation
8.2.1. Classification—Event Detection—Metrics
8.2.2. Regression—Power Estimation—Metrics
8.3. Open NILM Tools towards Commercialization
9. NILM Applications
10. Discussion and Conclusions
10.1. Discussion on Feature Selection and Data Pre-Processing in NILM
10.2. Discussion on NILM Model Implementation
10.3. Discussion on NILM Model Evaluation
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Conflicts of Interest
References
- Rolnick, D.; Donti, P.; Kaack, L.; Kochanski, K.; Lacoste, A.; Sankaran, K.; Ross, A.; Milojevic-Dupont, N.; Jaques, N.; Waldman-Brown, A.; et al. Tackling Climate Change with Machine Learning. arXiv 2019, arXiv:1906.05433. [Google Scholar] [CrossRef]
- Hart, G.W. Nonintrusive appliance load monitoring. Proc. IEEE 1992, 80, 1870–1891. [Google Scholar] [CrossRef]
- Najafi, B.; Moaveninejad, S.; Rinaldi, F. Chapter 17—Data Analytics for Energy Disaggregation: Methods and Applications. In Big Data Application in Power Systems; Elsevier: Amsterdam, The Netherlands, 2018; pp. 377–408. [Google Scholar]
- Ruano, A.; Hernandez, A.; Ureña, J.; Ruano, M.; Garcia, J. NILM techniques for intelligent home energy management and ambient assisted living: A review. Energies 2019, 12, 2203. [Google Scholar] [CrossRef] [Green Version]
- Bousbiat, H.; Klemenjak, C.; Leitner, G.; Elmenreich, W. Augmenting an Assisted Living Lab with Non-Intrusive Load Monitoring. In Proceedings of the 2020 IEEE International Instrumentation and Measurement Technology Conference (I2MTC), Dubrovnik, Croatia, 25–28 May 2020; pp. 1–5. [Google Scholar]
- Hernández, Á.; Ruano, A.; Ureña, J.; Ruano, M.; Garcia, J. Applications of NILM techniques to energy management and assisted living. IFAC-PapersOnLine 2019, 52, 164–171. [Google Scholar] [CrossRef]
- Murray, D.; Stankovic, L.; Stankovic, V.; Espinoza-Orias, N. Appliance electrical consumption modeling at scale using smart meter data. J. Clean. Prod. 2018, 187, 237–249. [Google Scholar] [CrossRef] [Green Version]
- Zhang, Y.; Tang, G.; Huang, Q.; Wang, Y.; Wang, X.; Lou, J. FedNILM: Applying Federated Learning to NILM Applications at the Edge. arXiv 2021, arXiv:2106.07751. [Google Scholar] [CrossRef]
- 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, South, Korea, 4–5 November 2015; pp. 55–64. [Google Scholar]
- Salani, M.; Derboni, M.; Rivola, D.; Medici, V.; Nespoli, L.; Rosato, F.; Rizzoli, A.E. Non intrusive load monitoring for demand side management. Energy Inform. 2020, 3, 1–12. [Google Scholar] [CrossRef]
- Berges, M.; Goldman, E.; Matthews, H.S.; Soibelman, L. Training load monitoring algorithms on highly sub-metered home electricity consumption data. Tsinghua Sci. Technol. 2008, 13, 406–411. [Google Scholar] [CrossRef]
- Lucas, A.; Jansen, L.; Andreadou, N.; Kotsakis, E.; Masera, M. Load flexibility forecast for DR using nonintrusive load monitoring in the residential sector. Energies 2019, 12, 2725. [Google Scholar] [CrossRef] [Green Version]
- Rashid, H.; Singh, P.; Stankovic, V.; Stankovic, L. Can nonintrusive load monitoring be used for identifying an appliance’s anomalous behavior? Appl. Energy 2019, 238, 796–805. [Google Scholar] [CrossRef] [Green Version]
- Bonfigli, R.; Felicetti, A.; Principi, E.; Fagiani, M.; Squartini, S.; Piazza, F. Denoising Autoencoders for Non-Intrusive Load Monitoring: Improvements and Comparative Evaluation. Energy Build. 2017, 158, 1461–1474. [Google Scholar] [CrossRef]
- Samek, W.; Montavon, G.; Vedaldi, A.; Hansen, L.K.; Müller, K. Explainable AI: Interpreting, Explaining and Visualizing Deep Learning; Springer: Berlin/Heidelberg, Germany, 2019; Volume 11700. [Google Scholar]
- Dinesh, C.; Makonin, S.; Bajić, I.V. Residential Power Forecasting Using Load Identification and Graph Spectral Clustering. IEEE Trans. Circuits Syst. II Express Briefs 2019, 66, 1900–1904. [Google Scholar] [CrossRef]
- Basu, K.; Debusschere, V.; Bacha, S. Residential appliance identification and future usage prediction from smart meter. In Proceedings of the IECON 2013—39th Annual Conference of the IEEE Industrial Electronics Society, Vienna, Austria, 10–13 November 2013; pp. 4994–4999. [Google Scholar]
- Kaselimi, M.; Doulamis, N.; Doulamis, A.; Voulodimos, A.; Protopapadakis, E. Bayesian-optimized Bidirectional LSTM Regression Model for Non-intrusive Load Monitoring. In Proceedings of the ICASSP 2019—2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Brighton, UK, 12–17 May 2019; pp. 2747–2751. [Google Scholar]
- Murray, D.; Stankovic, L.; Stankovic, V.; Lulic, S.; Sladojevic, S. Transferability of Neural Network Approaches for Low-rate Energy Disaggregation. In Proceedings of the ICASSP 2019—2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Brighton, UK, 12–17 May 2019; pp. 8330–8334. [Google Scholar]
- D’Incecco, M.; Squartini, S.; Zhong, M. Transfer Learning for Non-Intrusive Load Monitoring. IEEE Trans. Smart Grid 2019, 11, 1419–1429. [Google Scholar] [CrossRef] [Green Version]
- Altrabalsi, H.; Stankovic, V.; Liao, J.; Stankovic, L. Low-complexity energy disaggregation using appliance load modeling. Aims Energy 2016, 4, 884–905. [Google Scholar] [CrossRef]
- Liao, J.; Elafoudi, G.; Stankovic, L.; Stankovic, V. Non-intrusive appliance load monitoring using low-resolution smart meter data. In Proceedings of the 2014 IEEE International Conference on Smart Grid Communications (SmartGridComm), Venice, Italy, 3–6 November 2014; pp. 535–540. [Google Scholar]
- He, K.; Stankovic, L.; Liao, J.; Stankovic, V. Non-Intrusive Load Disaggregation Using Graph Signal Processing. IEEE Trans. Smart Grid 2018, 9, 1739–1747. [Google Scholar] [CrossRef] [Green Version]
- Lin, Y.; Tsai, M. Non-intrusive load monitoring by novel neuro-fuzzy classification considering uncertainties. IEEE Trans. Smart Grid 2014, 5, 2376–2384. [Google Scholar] [CrossRef]
- Elafoudi, G.; Stankovic, L.; Stankovic, V. Power disaggregation of domestic smart meter readings using dynamic time warping. In Proceedings of the 2014 6th International Symposium on Communications, Control and Signal Processing (ISCCSP), Athens, Greece, 21–23 May 2014; pp. 36–39. [Google Scholar]
- Kim, J.; Le, T.; Kim, H. Nonintrusive Load Monitoring Based on Advanced Deep Learning and Novel Signature. Comput. Intell. Neurosci. 2017, 2017, 1–22. [Google Scholar] [CrossRef]
- Zhao, B.; He, K.; Stankovic, L.; Stankovic, V. Improving event-based nonintrusive load monitoring using graph signal processing. IEEE Access 2018, 6, 53944–53959. [Google Scholar] [CrossRef]
- Machlev, R.; Levron, Y.; Beck, Y. Modified cross-entropy method for classification of events in NILM systems. IEEE Trans. Smart Grid 2018, 10, 4962–4973. [Google Scholar] [CrossRef]
- Kolter, J.; Jaakkola, T. Approximate inference in additive factorial hmms with application to energy disaggregation. In Proceedings of the Artificial Intelligence and Statistics, PMLR, Canary Islands, Spain, 21–23 April 2012; pp. 1472–1482. [Google Scholar]
- Kong, W.; Dong, Z.Y.; Hill, D.J.; Ma, J.; Zhao, J.H.; Luo, F.J. A Hierarchical Hidden Markov Model Framework for Home Appliance Modeling. IEEE Trans. Smart Grid 2018, 9, 3079–3090. [Google Scholar] [CrossRef]
- Bajović, D.; He, K.; Stanković, L.; Vukobratović, D.; Stanković, V. Optimal detection and error exponents for hidden semi-Markov models. IEEE J. Sel. Top. Signal Process. 2018, 12, 1077–1092. [Google Scholar] [CrossRef] [Green Version]
- Mauch, L.; Yang, B. 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), Orlando, FL, USA, 14–16 December 2015; pp. 63–67. [Google Scholar]
- Makonin, S.; Popowich, F.; Bajić, I.V.; Gill, B.; Bartram, L. Exploiting HMM sparsity to perform online real-time nonintrusive load monitoring. IEEE Trans. Smart Grid 2015, 7, 2575–2585. [Google Scholar] [CrossRef]
- Rahimpour, A.; Qi, H.; Fugate, D.; Kuruganti, T. Non-Intrusive Energy Disaggregation Using Non-Negative Matrix Factorization with Sum-to-k Constraint. IEEE Trans. Power Syst. 2017, 32, 4430–4441. [Google Scholar] [CrossRef] [Green Version]
- Makonin, S.; Popowich, F.; Bartram, L.; Gill, B.; Bajić, I.V. AMPds: A public dataset for load disaggregation and eco-feedback research. In Proceedings of the 2013 IEEE Electrical Power Energy Conference, Halifax, NS, Canada, 21–23 August 2013; pp. 1–6. [Google Scholar]
- Murray, D.; Stankovic, L.; Stankovic, V. An electrical load measurements dataset of United Kingdom households from a two-year longitudinal study. Sci. Data 2017, 4, 160122. [Google Scholar] [CrossRef] [Green Version]
- Kaselimi, M.; Doulamis, N.; Voulodimos, A.; Protopapadakis, E.; Doulamis, A. Context Aware Energy Disaggregation Using Adaptive Bidirectional LSTM Models. IEEE Trans. Smart Grid 2020, 11, 3054–3067. [Google Scholar] [CrossRef]
- Voulodimos, A.; Doulamis, N.; Doulamis, A.; Protopapadakis, E. Deep learning for computer vision: A brief review. Comput. Intell. Neurosci. 2018, 2018, 7068349. [Google Scholar] [CrossRef]
- Kaselimi, M.; Protopapadakis, E.; Voulodimos, A.; Doulamis, N.; Doulamis, A. Multi-Channel Recurrent Convolutional Neural Networks for Energy Disaggregation. IEEE Access 2019, 7, 81047–81056. [Google Scholar] [CrossRef]
- Harell, A.; Makonin, S.; Bajić, I.V. WaveNILM: A Causal Neural Network for Power Disaggregation from the Complex Power Signal. In Proceedings of the ICASSP 2019—2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Brighton, UK, 12–17 May 2019; pp. 8335–8339. [Google Scholar] [CrossRef] [Green Version]
- Zhang, C.; Zhong, M.; Wang, Z.; Goddard, N.; Sutton, C. Sequence-to-point learning with neural networks for nonintrusive load monitoring. In Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence (AAAI-18), New Orleans, LA, USA, 2–7 February 2018. [Google Scholar]
- Chen, K.; Wang, Q.; He, Z.; Chen, K.; Hu, J.; Jinliang, H. Convolutional Sequence to Sequence Non-intrusive Load Monitoring. J. Eng. 2018, 2018, 1860–1864. [Google Scholar] [CrossRef]
- Bao, K.; Ibrahimov, K.; Wagner, M.; Schmeck, H. Enhancing neural nonintrusive load monitoring with generative adversarial networks. Energy Inform. 2018, 1, 18. [Google Scholar] [CrossRef]
- Kaselimi, M.; Voulodimos, A.; Protopapadakis, E.; Doulamis, N.; Doulamis, A. EnerGAN: A Generative Adversarial Network for Energy Disaggregation. In Proceedings of the ICASSP 2020—2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Barcelona, Spain, 4–8 May 2020; pp. 1578–1582. [Google Scholar]
- Pan, Y.; Liu, K.; Shen, Z.; Cai, X.; Jia, Z. Sequence-to-subsequence learning with conditional GAN for power disaggregation. In Proceedings of the ICASSP 2020—2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Barcelona, Spain, 4–8 May 2020; pp. 3202–3206. [Google Scholar]
- Chen, K.; Zhang, Y.; Wang, Q.; Hu, J.; Fan, H.; Jinliang, H. Scale- and Context-Aware Convolutional Non-Intrusive Load Monitoring. IEEE Trans. Power Syst. 2019, 35, 2362–2373. [Google Scholar] [CrossRef] [Green Version]
- Wang, W.; Wei, F.; Dong, L.; Bao, H.; Yang, N.; Zhou, M. MiNILM: Deep self-attention distillation for task-agnostic compression of pre-trained transformers. arXiv 2020, arXiv:2002.10957. [Google Scholar]
- Yue, Z.; Witzig, C.R.; Jorde, D.; Jacobsen, H. BERT4NILM: A Bidirectional Transformer Model for Non-Intrusive Load Monitoring. In Proceedings of the 5th International Workshop on Non-Intrusive Load Monitoring, Online, 18 November2020; pp. 89–93. [Google Scholar]
- Faustine, A.; Pereira, L.; Bousbiat, H.; Kulkarni, S. 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, Online, 18 November 2020; pp. 84–88. [Google Scholar]
- Vilone, G.; Longo, L. Explainable artificial intelligence: A systematic review. arXiv 2020, arXiv:2006.00093. [Google Scholar]
- Murray, D.; Stankovic, L.; Stankovic, V. Explainable NILM networks. In Proceedings of the 5th International Workshop on Non-Intrusive Load Monitoring, Online, 18 November 2020; pp. 64–69. [Google Scholar]
- Klemenjak, C.; Makonin, S.; Elmenreich, W. Towards comparability in nonintrusive load monitoring: On data and performance evaluation. In Proceedings of the 2020 IEEE Power & Energy Society Innovative Smart Grid Technologies Conference (ISGT), Washington, DC, USA, 17–20 February 2020; pp. 1–5. [Google Scholar]
- De Baets, L.; Develder, C.; Dhaene, T.; Deschrijver, D.; Gao, J.; Berges, M. Handling imbalance in an extended PLAID. In Proceedings of the 2017 Sustainable Internet and ICT for Sustainability (SustainIT), Funchal, Portugal, 6–7 December 2017; pp. 1–5. [Google Scholar]
- Zoha, A.; Gluhak, A.; Imran, M.A.; Rajasegarar, S. Non-intrusive load monitoring approaches for disaggregated energy sensing: A survey. Sensors 2012, 12, 16838–16866. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Schirmer, P.A.; Mporas, I.; Sheikh-Akbari, A. Energy disaggregation using two-stage fusion of binary device detectors. Energies 2020, 13, 2148. [Google Scholar] [CrossRef]
- Pereira, M.; Velosa, N.; Pereira, L. dscleaner: A python library to clean, preprocess and convert nonintrusive load monitoring datasets. Data 2019, 4, 123. [Google Scholar] [CrossRef] [Green Version]
- Bao, S.; Zhang, L.; Li, W.; Sun, D.; Zhang, B.; Han, X. Feature Selection Method for Non-intrusive Load Monitoring with Balanced Redundancy and Relevancy. In Proceedings of the 2020 IEEE/IAS Industrial and Commercial Power System Asia (I CPS Asia), Shanghai, China, 8–11 July 2020; pp. 1641–1648. [Google Scholar]
- Karim, S.B.; Roman, S.; Bin, Y. An Approach for Unsupervised Non-Intrusive Load Monitoring of Residential Appliances. In Proceedings of the 2nd International Workshop on Non-Intrusive Load Monitoring, Austin, TX, USA, 3 June 2014. [Google Scholar]
- Dinesh, C.; Godaliyadda, G.; Ekanayake, M.; Ekanayake, J.; Perera, P. Non-intrusive load monitoring based on low frequency active power measurements. AIMS Energy 2016, 4, 414–443. [Google Scholar] [CrossRef]
- Hassan, T.; Javed, F.; Arshad, N. An empirical investigation of VI trajectory based load signatures for nonintrusive load monitoring. IEEE Trans. Smart Grid 2013, 5, 870–878. [Google Scholar] [CrossRef] [Green Version]
- Sadeghianpourhamami, N.; Ruyssinck, J.; Deschrijver, D.; Dhaene, T.; Develder, C. Comprehensive feature selection for appliance classification in NILM. Energy Build. 2017, 151, 98–106. [Google Scholar] [CrossRef] [Green Version]
- Wu, Q.; Wang, F. Concatenate convolutional neural networks for nonintrusive load monitoring across complex background. Energies 2019, 12, 1572. [Google Scholar] [CrossRef] [Green Version]
- Schirmer, P.A.; Mporas, I. Double Fourier Integral Analysis based Convolutional Neural Network Regression for High-Frequency Energy Disaggregation. IEEE Trans. Emerg. Top. Comput. Intell. 2021, 6, 439–449. [Google Scholar] [CrossRef]
- Himeur, Y.; Alsalemi, A.; Bensaali, F.; Amira, A. An intelligent nonintrusive load monitoring scheme based on 2D phase encoding of power signals. Int. J. Intell. Syst. 2021, 36, 72–93. [Google Scholar] [CrossRef]
- Liu, Y.; Wang, X.; You, W. Non-intrusive load monitoring by voltage–current trajectory enabled transfer learning. IEEE Trans. Smart Grid 2018, 10, 5609–5619. [Google Scholar] [CrossRef]
- Nalmpantis, C.; Vrakas, D. Machine Learning Approaches for Non-Intrusive Load Monitoring: From Qualitative to Quantitative Comparation. Artif. Intell. Rev. 2019, 52, 217–243. [Google Scholar] [CrossRef]
- Kelly, J.; Knottenbelt, W. The UK-DALE dataset, domestic appliance-level electricity demand and whole-house demand from five UK homes. Sci. Data 2015, 2, 1–14. [Google Scholar] [CrossRef] [Green Version]
- Precioso, D.; Gómez-Ullate, D. NILM as a regression versus classification problem: The importance of thresholding. arXiv 2020, arXiv:2010.16050. [Google Scholar]
- Ayub, M.; El-Alfy, E. Multi-Target Energy Disaggregation using Convolutional Neural Networks. Int. J. Adv. Comput. Sci. Appl. 2020, 11, 684–693. [Google Scholar] [CrossRef]
- Jiang, J.; Kong, Q.; Plumbley, M.; Gilbert, N.; Hoogendoorn, M.; Roijers, D. Deep Learning-Based Energy Disaggregation and On/Off Detection of Household Appliances. ACM Trans. Knowl. Discov. Data (TKDD) 2021, 15, 1–21. [Google Scholar] [CrossRef]
- Xia, M.; Liu, W.; Wang, K.; Song, W.; Chen, C.; Li, Y. Non-intrusive load disaggregation based on composite deep long short-term memory network. Expert Syst. Appl. 2020, 160, 113669. [Google Scholar] [CrossRef]
- Jorde, D.; Kriechbaumer, T.; Jacobsen, H. Electrical Appliance Classification using Deep Convolutional Neural Networks on High Frequency Current Measurements. In Proceedings of the 2018 IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids (SmartGridComm), Aalborg, Denmark, 29–31 October 2018; pp. 1–6. [Google Scholar]
- Devlin, M.A.; Hayes, B. Non-Intrusive Load Monitoring and Classification of Activities of Daily Living Using Residential Smart Meter Data. IEEE Trans. Consum. Electron. 2019, 65, 339–348. [Google Scholar] [CrossRef]
- Kim, J.; Lee, B. Appliance classification by power signal analysis based on multi-feature combination multi-layer LSTM. Energies 2019, 12, 2804. [Google Scholar] [CrossRef] [Green Version]
- Li, D.; Dick, S. Residential household nonintrusive load monitoring via graph-based multi-label semi-supervised learning. IEEE Trans. Smart Grid 2018, 10, 4615–4627. [Google Scholar] [CrossRef]
- Singhal, V.; Maggu, J.; Majumdar, A. Simultaneous Detection of Multiple Appliances From Smart-Meter Measurements via Multi-Label Consistent Deep Dictionary Learning and Deep Transform Learning. IEEE Trans. Smart Grid 2019, 10, 2969–2978. [Google Scholar] [CrossRef] [Green Version]
- Singh, S.; Majumdar, A. Non-intrusive load monitoring via multi-label sparse representation-based classification. IEEE Trans. Smart Grid 2019, 11, 1799–1801. [Google Scholar] [CrossRef] [Green Version]
- Kolter, J.; Batra, S.; Ng, A. Energy disaggregation via discriminative sparse coding. Adv. Neural Inf. Process. Syst. 2010, 23, 1153–1161. [Google Scholar]
- He, K.; Jakovetic, D.; Zhao, B.; Stankovic, V.; Stankovic, L.; Cheng, S. A generic optimisation-based approach for improving nonintrusive load monitoring. IEEE Trans. Smart Grid 2019, 10, 6472–6480. [Google Scholar] [CrossRef] [Green Version]
- Buddhahai, B.; Makonin, S. A Nonintrusive Load Monitoring Based on Multi-Target Regression Approach. IEEE Access 2021, 9, 163033–163042. [Google Scholar] [CrossRef]
- Khazaei, M.; Stankovic, L.; Stankovic, V. Evaluation of low-complexity supervised and unsupervised NILM methods and pre-processing for detection of multistate white goods. In Proceedings of the 5th International Workshop on Non-Intrusive Load Monitoring, Online, 18 November 2020; pp. 34–38. [Google Scholar]
- Barsim, K.S.; Yang, B. Toward a semi-supervised nonintrusive load monitoring system for event-based energy disaggregation. In Proceedings of the 2015 IEEE Global Conference on Signal and Information Processing (GlobalSIP), Orlando, FL, USA, 14–16 December 2015; pp. 58–62. [Google Scholar]
- Iwayemi, A.; Zhou, C. SARAA: Semi-Supervised Learning for Automated Residential Appliance Annotation. IEEE Trans. Smart Grid 2017, 8, 779–786. [Google Scholar] [CrossRef]
- Jia, R.; Gao, Y.; Spanos, C.J. A fully unsupervised nonintrusive load monitoring framework. In Proceedings of the 2015 IEEE International Conference on Smart Grid Communications (SmartGridComm), Miami, FL, USA, 2–5 November 2015; pp. 872–878. [Google Scholar]
- Hochreiter, S.; Schmidhuber, J. Long short-term memory. Neural Comput. 1997, 9, 1735–1780. [Google Scholar] [CrossRef]
- Oord, A.; Dieleman, S.; Zen, H.; Simonyan, K.; Vinyals, O.; Graves, A.; Kalchbrenner, N.; Senior, A.; Kavukcuoglu, K. WaveNet: A Generative Model for Raw Audio. In Proceedings of the 9th ISCA Speech Synthesis Workshop, Sunnyvale, CA, USA, 13–15 September 2016; p. 125. [Google Scholar]
- Çavdar, İ.H.; Faryad, V. New design of a supervised energy disaggregation model based on the deep neural network for a smart grid. Energies 2019, 12, 1217. [Google Scholar] [CrossRef] [Green Version]
- Jia, Z.; Yang, L.; Zhang, Z.; Liu, H.; Kong, F. Sequence to point learning based on bidirectional dilated residual network for nonintrusive load monitoring. Int. J. Electr. Power Energy Syst. 2021, 129, 106837. [Google Scholar] [CrossRef]
- Reinhardt, A.; Bouchur, M. On the Impact of the Sequence Length on Sequence-to-Sequence and Sequence-to-Point Learning for NILM. In Proceedings of the 5th International Workshop on Non-Intrusive Load Monitoring; Association for Computing Machinery, NILM’20, New York, NY, USA, 18 November 2020; pp. 75–78. [Google Scholar]
- Bousbiat, H.; Klemenjak, C.; Elmenreich, W. Exploring Time Series Imaging for Load Disaggregation. In Proceedings of the 7th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation, Online, 18–20 November 2020; pp. 254–257. [Google Scholar]
- De Baets, L.; Develder, C.; Dhaene, T.; Deschrijver, D. Detection of unidentified appliances in nonintrusive load monitoring using siamese neural networks. Int. J. Electr. Power Energy Syst. 2019, 104, 645–653. [Google Scholar] [CrossRef]
- Makantasis, K.; Georgogiannis, A.; Voulodimos, A.; Georgoulas, I.; Doulamis, A.; Doulamis, N. Rank-R FNN: A tensor-based learning model for high-order data classification. IEEE Access 2021, 9, 58609–58620. [Google Scholar] [CrossRef]
- Batra, N.; Jia, Y.; Wang, H.; Whitehouse, K. Transferring decomposed tensors for scalable energy breakdown across regions. In Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence, New Orleans, LA, USA, 2–7 February 2018. [Google Scholar]
- Nolasco, L.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. 2022, 22, 501–509. [Google Scholar] [CrossRef]
- Yang, W.; Pang, C.; Huang, J.; Zeng, X. Sequence-to-Point Learning Based on Temporal Convolutional Networks for Nonintrusive Load Monitoring. IEEE Trans. Instrum. Meas. 2021, 70, 1–10. [Google Scholar] [CrossRef]
- Liu, H.; Wang, Y.; Fan, W.; Liu, X.; Li, Y.; Jain, S.; Liu, Y.; Jain, A.K.; Tang, J. Trustworthy ai: A computational perspective. arXiv 2021, arXiv:2107.06641. [Google Scholar] [CrossRef]
- Faustine, A.; Pereira, L.; Klemenjak, C. Adaptive Weighted Recurrence Graphs for Appliance Recognition in Non-Intrusive Load Monitoring. IEEE Trans. Smart Grid 2021, 12, 398–406. [Google Scholar] [CrossRef]
- Jones, R.; Klemenjak, C.; Makonin, S.; Bajić, I. Stop: Exploring Bayesian Surprise to Better Train NILM. In Proceedings of the 5th International Workshop on Non-Intrusive Load Monitoring, Virtual, 18 November 2020; pp. 39–43. [Google Scholar]
- Salem, H.; Sayed-Mouchaweh, M. A semi-supervised and online learning approach for nonintrusive load monitoring. In Proceedings of the Joint European Conference on Machine Learning and Knowledge Discovery in Databases, Würzburg, Germany, 16–20 September 2019; Springer: Berlin/Heidelberg, Germany, 2019; pp. 585–601. [Google Scholar]
- Klemenjak, C.; Faustine, A.; Makonin, S.; Elmenreich, W. On Metrics to Assess the Transferability of Machine Learning Models in Non-Intrusive Load Monitoring. arXiv 2019, arXiv:1912.06200. [Google Scholar]
- Athanasiadis, C.; Doukas, D.; Papadopoulos, T.; Chrysopoulos, A. A Scalable Real-Time Non-Intrusive Load Monitoring System for the Estimation of Household Appliance Power Consumption. Energies 2021, 14, 767. [Google Scholar] [CrossRef]
- Krystalakos, O.; Nalmpantis, C.; Vrakas, D. Sliding Window Approach for Online Energy Disaggregation Using Artificial Neural Networks. In Proceedings of the Proceedings of the 10th Hellenic Conference on Artificial Intelligence, SETN ’18, Patras, Greece, 9–12 July 2018. [Google Scholar]
- Batra, N.; Singh, A.; Whitehouse, K. Neighbourhood NILM: A big-data approach to household energy disaggregation. arXiv 2015, arXiv:1511.02900. [Google Scholar]
- Shin, C.; Rho, S.; Lee, H.; Rhee, W. Data requirements for applying machine learning to energy disaggregation. Energies 2019, 12, 1696. [Google Scholar] [CrossRef] [Green Version]
- Kaselimi, M.; Doulamis, N.; Voulodimos, A.; Doulamis, A.; Protopapadakis, E. EnerGAN++: A Generative Adversarial Gated Recurrent Network for Robust Energy Disaggregation. IEEE Open J. Signal Process. 2021, 2, 1–16. [Google Scholar] [CrossRef]
- Welikala, S.; Dinesh, C.; Godaliyadda, R.I.; Ekanayake, M.P.B.; Ekanayake, J. Robust Non-Intrusive Load Monitoring (NILM) with unknown loads. In Proceedings of the 2016 IEEE International Conference on Information and Automation for Sustainability (ICIAfS), Galle, Sri Lanka, 16–19 December 2016; pp. 1–6. [Google Scholar]
- Rafiq, H.; Shi, X.; Zhang, H.; Li, H.; Ochani, M.K.; Shah, A.A. Generalizability Improvement of Deep Learning-Based Non-Intrusive Load Monitoring System Using Data Augmentation. IEEE Trans. Smart Grid 2021, 12, 3265–3277. [Google Scholar] [CrossRef]
- Du, X.; Wang, T.; Wang, L.; Pan, W.; Chai, C.; Xu, X.; Jiang, B.; Wang, J. CoreBug: Improving effort-aware bug prediction in software systems using generalized k-core decomposition in class dependency networks. Axioms 2022, 11, 205. [Google Scholar] [CrossRef]
- Refaeilzadeh, P.; Tang, L.; Liu, H. Cross-validation. Encycl. Database Syst. 2009, 5, 532–538. [Google Scholar]
- Murray, D.; Stankovic, L.; Stankovic, V. Transparent AI: Explainability of deep learning based load disaggregation. In Proceedings of the 8th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation, Coimbra, Portugal, 17–18 November 2021; pp. 268–271. [Google Scholar]
- Mehrabi, N.; Morstatter, F.; Saxena, N.; Lerman, K.; Galstyan, A. A survey on bias and fairness in machine learning. ACM Comput. Surv. (CSUR) 2021, 54, 1–35. [Google Scholar] [CrossRef]
- Huber, P.; Calatroni, A.; Rumsch, A.; Paice, A. Review on Deep Neural Networks Applied to Low-Frequency NILM. Energies 2021, 14, 2390. [Google Scholar] [CrossRef]
- Kriechbaumer, T.; Jacobsen, H. BLOND, a building-level office environment dataset of typical electrical appliances. Sci. Data 2018, 5, 1–14. [Google Scholar] [CrossRef]
- Jazizadeh, F.; Afzalan, M.; Becerik-Gerber, B.; Soibelman, L. EMBED: A dataset for energy monitoring through building electricity disaggregation. In Proceedings of the Ninth International Conference on Future Energy Systems, Karlsruhe, Germany, 12–15 June 2018; pp. 230–235. [Google Scholar]
- Wenninger, M.; Maier, A.; Schmidt, J. DEDDIAG, a domestic electricity demand dataset of individual appliances in Germany. Sci. Data 2021, 8, 1–15. [Google Scholar] [CrossRef]
- Goddard, N.; Kilgour, J.; Pullinger, M.; Arvind, D.; Lovell, H.; Moore, J.; Shipworth, D.; Sutton, C.; Webb, J.; Berliner, N.; et al. IDEAL Household Energy Dataset. Sci. Data 2021, 8, 1–18. [Google Scholar]
- Kolter, J.Z.; Johnson, M.J. REDD: A public dataset for energy disaggregation research. In Proceedings of the Workshop on data mining applications in sustainability (SIGKDD), San Diego, CA, USA, 21 August 2011; Volume 25, pp. 59–62. [Google Scholar]
- Zimmermann, J.; Evans, M.; Griggs, J.; King, N.; Harding, L.; Roberts, P.; Evans, C. Household Electricity Survey: A Study of Domestic Electrical Product Usage; Intertek Testing & Certification Ltd.: Hong Kong, China, 2012; pp. 213–214. [Google Scholar]
- Gao, J.; Giri, S.; Kara, E.; Bergés, M. PLAID: A public dataset of high-resoultion electrical appliance measurements for load identification research: Demo abstract. In Proceedings of the 1st ACM Conference on Embedded Systems for Energy-Efficient Buildings, Memphis, TN, USA, 4–6 November 2014. [Google Scholar]
- Harell, A.; Jones, R.; Makonin, S.; Bajić, I. TraceGAN: Synthesizing Appliance Power Signatures Using Generative Adversarial Networks. IEEE Trans. Smart Grid 2021, 12, 4553–4563. [Google Scholar] [CrossRef]
- Renaux, D.P.B.; Pottker, F.; Ancelmo, H.; Lazzaretti, A.; Lima, C.R.E.; Linhares, R.R.; Oroski, E.; Nolasco, L.S.; Lima, L.T.; Mulinari, B.M.; et al. A dataset for nonintrusive load monitoring: Design and implementation. Energies 2020, 13, 5371. [Google Scholar] [CrossRef]
- Klemenjak, C.; Kovatsch, C.; Herold, M.; Elmenreich, W. A synthetic energy dataset for nonintrusive load monitoring in households. Sci. Data 2020, 7, 1–17. [Google Scholar] [CrossRef] [Green Version]
- Anderson, K.; Ocneanu, A.; Benitez, D.; Carlson, D.; Rowe, A.; Berges, M. BLUED: A fully labeled public dataset for event-based nonintrusive load monitoring research. In Proceedings of the 2nd KDD Workshop on Data Mining Applications in Sustainability (SustKDD), Beijing, China, 12–16 August 2012; pp. 1–5. [Google Scholar]
- Maasoumy, M.; Sanandaji, B.; Poolla, K.; Vincentelli, A. Berds-berkeley energy disaggregation dataset. In Proceedings of the Workshop on Big Learning at the Conference on Neural Information Processing Systems (NIPS), Lake Tahoe, NV, USA, 5–10 December 2013; pp. 1–6. [Google Scholar]
- Batra, N.; Gulati, M.; Singh, A.; Srivastava, M. It’s Different: Insights into home energy consumption in India. In Proceedings of the 5th ACM Workshop on Embedded Systems For Energy-Efficient Buildings, Roma, Italy, 11–15 November 2013; pp. 1–8. [Google Scholar]
- Uttama Nambi, A.; Reyes Lua, A.; Prasad, V.R. Loced: Location-aware energy disaggregation framework. In Proceedings of the 2nd ACM International Conference on Embedded Systems for Energy-Efficient Built Environments, South, Korea, 4–5 November 2015; pp. 45–54. [Google Scholar]
- Beckel, C.; Kleiminger, W.; Cicchetti, R.; Staake, T.; Santini, S. The ECO dataset and the performance of nonintrusive load monitoring algorithms. In Proceedings of the 1st ACM Conference on Embedded Systems for Energy-Efficient Buildings, Memphis, TN, USA, 4–6 November 2014; pp. 80–89. [Google Scholar]
- Monacchi, A.; Egarter, D.; Elmenreich, W.; D’Alessandro, S.; Tonello, A. GREEND: An energy consumption dataset of households in Italy and Austria. In Proceedings of the 2014 IEEE International Conference on Smart Grid Communications (SmartGridComm), Venice, Italy, 3–6 November 2014; pp. 511–516. [Google Scholar]
- Picon, T.; Meziane, M.; Ravier, P.; Lamarque, G.; Novello, C.; Bunetel, J.; Raingeaud, Y. COOLL: Controlled on/off loads library, a public dataset of high-sampled electrical signals for appliance identification. arXiv 2016, arXiv:1611.05803. [Google Scholar]
- Shin, C.; Joo, S.; Yim, J.; Lee, H.; Moon, T.; Rhee, W. Subtask gated networks for nonintrusive load monitoring. In Proceedings of the AAAI Conference on Artificial Intelligence, Honolulu, HI, USA, 27 January–1 February 2019; Volume 33, pp. 1150–1157. [Google Scholar]
- 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 2021, 13, 280–292. [Google Scholar] [CrossRef]
- Liu, Y.; Zhong, L.; Qiu, J.; Lu, J.; Wang, W. Unsupervised Domain Adaptation for Non-Intrusive Load Monitoring Via Adversarial and Joint Adaptation Network. IEEE Trans. Ind. Inform. 2022, 18, 266–277. [Google Scholar] [CrossRef]
- Makonin, S.; Popowich, F. Nonintrusive load monitoring (NILM) performance evaluation. Energy Effic. 2015, 8, 809–814. [Google Scholar] [CrossRef]
- Pereira, L. NILMPEds: A performance evaluation dataset for event detection algorithms in nonintrusive load monitoring. Data 2019, 4, 127. [Google Scholar] [CrossRef] [Green Version]
- Pereira, L.; Nunes, N. A comparison of performance metrics for event classification in nonintrusive load monitoring. In Proceedings of the 2017 IEEE International Conference on Smart Grid Communications (SmartGridComm), Dresden, Germany, 23–27 October 2017; pp. 159–164. [Google Scholar]
- Batra, N.; Kelly, J.; Parson, O.; Dutta, H.; Knottenbelt, W.; Rogers, A.; Singh, A.; Srivastava, M. NILMTK: An Open Source Toolkit for Non-Intrusive Load Monitoring. In Proceedings of the 5th International Conference on Future Energy Systems, e-Energy ’14, Cambridge, UK, 11–13 June 2014; Association for Computing Machinery: New York, NY, USA, 2014; pp. 265–276. [Google Scholar]
- Kukunuri, R.; Batra, N.; Pandey, A.; Malakar, R.; Kumar, R.; Krystalakos, O.; Zhong, M.; Meira, P.; Parson, O. NILMTK-Contrib: Towards reproducible state-of-the-art energy disaggregation. In Proceedings of the AI Social Good Workshop, Virtual, 20–21 July 2020; pp. 1–5. [Google Scholar]
- Gupta, M.; Majumdar, A. Handling Missing Data and Outliers in Energy Disaggregation. In Proceedings of the Special Section on Current Research Topics in Power, Nuclear and Fuel Energy, SP-CRTPNFE, from the International Conference on Recent Trends in Engineering, Science and Technology, Hyderabad, India, 1 June 2016. [Google Scholar]
- Sykiotis, S.; Kaselimi, M.; Doulamis, A.; Doulamis, N. ELECTRIcity: An Efficient Transformer for Non-Intrusive Load Monitoring. Sensors 2022, 22, 2926. [Google Scholar] [CrossRef]
ID | Author | Title | Classification (C) or Regression (R) Model | Multi- (M) or Single- (S) Target Model | Convolutional- (C) or Recurrent- (R) Based Architecture | Causal (C) or Non-Causal (N) Model | seq2point or seq2seq | Uni- (u) or Multi- (m) Dimensional |
---|---|---|---|---|---|---|---|---|
1 | J. Kelly et al., 2015 [9] | Neural NILM: Deep neural networks applied to energy disaggregation | Classification | Single | Conv./Recur. | Non-causal | seq2seq | Uni |
2 | J. Kim et al. 2017 [26] | Nonintrusive load monitoring based on advanced deep learning and novel signature | Classification | Single | Recurrence | Causal | seq2point | Uni |
3 | C. Zhang e. al., 2018 [41] | Sequence-to-point learning with neural networks for nonintrusive load monitoring | Regression | Single | Convolution | Causal | seq2point | Uni |
4 | K. Chen et al., 2018 [42] | Convolutional sequence-to-sequence nonintrusive load monitoring | Regression | Single | Convolution | Causal | seq2seq | Uni |
5 | M. Kaselimi et al., 2019 [18] | Bayesian-optimized bidirectional LSTM regression model for nonintrusive load monitoring | Regression | Single | Recurrence | Non-causal | seq2seq | Uni |
6 | D. Murray et al., 2019 [19] | Transferability of neural network approaches for low-rate energy disaggregation | Classification | Single | Conv./Recur. | Causal | seq2point | Uni |
7 | M. Kaselimi et al., 2019 [39] | Multi-channel recurrent convolutional neural networks for energy disaggregation | Regression | Single | Convolution | Non-causal | seq2seq | Multi |
8 | A. Harell et al., 2019 [40] | WaveNILM: a causal neural network for power disaggregation from the complex power signal | Classification | Single | Convolution | Causal | seq2point | Multi |
9 | M. Kaselimi et al., 2020 [37] | Context-aware energy disaggregation using adaptive bidirectional LSTM models | Regression | Single | Recurrence | Non-causal | seq2seq | Uni |
10 | A. Faustine et al., 2020 [49] | UNet-NILM: a deep neural network for multi-task appliances’ state detection and power estimation in NILM | Classification/Regr. | Multi | Convolution | Causal | seq2point | Uni |
11 | L. d. S. Nolasco et al., 2021 [94] | DeepDFML-NILM: a new CNN-based architecture for detection, feature extraction, and multi-label classification in NILM signals | Classification | Single | Convolution | Causal | seq2point | Uni |
12 | W. Yang et al., 2021 [95] | Sequence-to-point learning based on temporal convolutional networks for nonintrusive load monitoring | Regression | Single | Convolution | Causal | seq2point | Uni |
Dataset Name | Year | Country | House No. | Duration | Variables | Aggregate Sampling Rate | Appliance Sampling Rate | Comments |
---|---|---|---|---|---|---|---|---|
REDD [117] | 2011 | US | 6 | a few months | current, voltage | 1 Hz, 15 kHz | 1/3 Hz | first released and most-used |
BLUED [123] | 2011 | US | 1 | 8 days | current, voltage | 12 kHz | - | allows for analysis in both the time and the frequency domains |
HES [118] | 2012 | UK | 251 | 1 year | active power | 2–10 min | 2–10 min | number of houses |
AMPds [35] | 2013 | CA | 1 | 1 year | current, voltage, pf, real, reactive, and apparent power | 1 min | 1 min | multiple variables |
BERDS [124] | 2013 | US | 1 | 1 year | active, reactive, and apparent power | 20 s | 20 s | public building of the University |
iAWE [125] | 2013 | IN | 1 | 73 days | current, voltage, active, reactive, and apparent power | 1 s | 1 s | contains electricity, gas, and water consumption data |
DRED [126] | 2014 | NL | 1 | 6 months | active power | 1 Hz | 1 Hz | indoor and outdoor temperature, wind speed, humidity, precipitation, and occupancy information |
ECO [127] | 2014 | CH | 6 | 8 months | active reactive power | 1 Hz | 1 Hz | occupancy information of the monitored household |
GREEND [128] | 2014 | IT/AT | 9 | 1 year | active power | 1 s | 1 s | cross-country dataset |
PLAID [119] | 2014 | US | 60 | summer of 2013 and winter of 2014 | current, voltage | - | 30 kHz | 3 versions PLAID 1 (2014), PLAID 2 (2017), and PLAID 3 (2018), which include also aggregate measurements |
REFIT [36] | 2015 | UK | 20 | 2 years | active power | 8 s | 8 s | corrupted-with-noise version of the dataset |
UK-DALE [67] | 2015 | UK | 5 | 1 to 2.5 years | current, voltage | 6 s, 16 kHz | 6 s | long duration |
COOLL [129] | 2016 | FR | 1 | - | current, voltage | - | 100 kHz | high-frequencysampled electrical signals for appliance identification |
BLOND [113] | 2018 | DE | 1 | 213 | current, voltage | 50 kHz | 6.4 kHz | building-level office environment dataset |
EMBED [114] | 2019 | US | 3 | 14–21 days | active, reactive power | 12 kHz | 12 kHz | aggregate power files, fully labeled appliance event timestamps, and plug load consumption for a variety of monitored appliances |
SynD [122] | 2019 | AT | 1 | 180 days | active power | 5 Hz | 5 Hz | synthetic energy dataset |
DEDDIAG [115] | 2021 | DE | 15 | <3.5 years | active power | 1 Hz | 1 Hz | long duration |
IDEAL [116] | 2021 | UK | 255 | <2 year | active power | 1 s | 1 s | electricity and gas sensor data along with a diverse range of relevant contextual data from additional sensors and surveys |
Top-5 Common Appliances’ MAE (W) | ||||||||
---|---|---|---|---|---|---|---|---|
A/A | Dataset | Dishwasher | Washing Mach. | Fridge | Microwave | Kettle | Overall MAE (W) per Dataset | Unseen House |
[9] | UK | 24.0 | 11.0 | 18.0 | 6.0 | 6.0 | 22.0 | √ |
[41] | RD/UK | 20.0/27.7 | 18.4/12.6 | 28.1/20.9 | 28.2/8.7 | -/7.4 | 15.5 /23.6 | √ |
[42] | RD | 12.8 | 32.0 | - | √ | |||
[18] | AM | 6.4 | 9.2 | - | ||||
[19] | RD/RF | 119.4/82.74 | -/71.9 | 10.1/8.6 | 68.0/35.5 | - | √ | |
[39] | AM | 14.3 | 4.8 | - | ||||
[130] | RD/UK | 15.9/13.5 | 20.6/11.0 | 22.9/15.3 | 15.9/8.6 | 18.8 /10.9 | √ | |
[37] | RD/RF/AM | 7.1/31.3/- | -/21.8/9.2 | 6.9 /-/- | - | √ | ||
[49] | UK | 6.8 | 11.5 | 15.2 | 6.5 | 16.0 | 11.2 | √ |
[20] | RD/UK/RF | 20.0/27.7/12.2 | 18.4/12.6/16.9 | 28.1/20.9/20.0 | 28.2/8.7/12.7 | 23.7/15.5/13.7 | √ | |
[95] | UK | 23.3 | 16.4 | 12.6 | 4.1 | - | √ | |
[45] | UK | 13.5 | 7.1 | 11.9 | 3.1 | 3.6 | 7.8 | √ |
[131] | RD/UK/RF | 23.8/28.4/15.4 | 19.9/15.9/17.9 | 31.3/22.3/23.2 | 29.9/9.7/12.2 | -/7.7/6.9 | - | √ |
[132] | UK/RF | 51.3/28.2 | 25.9/44.0 | 31.1/63.1 | 64.5/20.7 | 13.9/16.7 | - | √ |
[48] | RD/UK | 20.5/16.2 | 34.9/6.9 | 32.4/25.5 | 17.6/6.96 | -/6.8 | 26.4/12.4 | √ |
Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. |
© 2022 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Kaselimi, M.; Protopapadakis, E.; Voulodimos, A.; Doulamis, N.; Doulamis, A. Towards Trustworthy Energy Disaggregation: A Review of Challenges, Methods, and Perspectives for Non-Intrusive Load Monitoring. Sensors 2022, 22, 5872. https://doi.org/10.3390/s22155872
Kaselimi M, Protopapadakis E, Voulodimos A, Doulamis N, Doulamis A. Towards Trustworthy Energy Disaggregation: A Review of Challenges, Methods, and Perspectives for Non-Intrusive Load Monitoring. Sensors. 2022; 22(15):5872. https://doi.org/10.3390/s22155872
Chicago/Turabian StyleKaselimi, Maria, Eftychios Protopapadakis, Athanasios Voulodimos, Nikolaos Doulamis, and Anastasios Doulamis. 2022. "Towards Trustworthy Energy Disaggregation: A Review of Challenges, Methods, and Perspectives for Non-Intrusive Load Monitoring" Sensors 22, no. 15: 5872. https://doi.org/10.3390/s22155872
APA StyleKaselimi, M., Protopapadakis, E., Voulodimos, A., Doulamis, N., & Doulamis, A. (2022). Towards Trustworthy Energy Disaggregation: A Review of Challenges, Methods, and Perspectives for Non-Intrusive Load Monitoring. Sensors, 22(15), 5872. https://doi.org/10.3390/s22155872