非侵入式負載監控 (Non-Intrusive Load Monitoring, 下稱NILM) 之發展已久，透過監控、分析場域（如：住家、工廠、辦公室...等等）內部之總用電量，得到場域中各式負載或電器的耗電資訊（如：電器開關狀態、耗電量資訊...等等），無須再對場域內部的負載或電器個別安裝電表監控其耗電資訊，除了提供場域負載監控優良的可擴充性（Scalability）以外，非侵入式監控的特性也使 NILM 成為具有隱私保護特性的居家監控方案。
儘管 NILM 演算法之發展已久，但目前的方法在可解釋性（Explainability） 上仍有發展的空間；近年來雖有部分學者嘗試使用一些視覺化方法，解釋基於神經網路實現之非侵入式負載監控演算法，但其結果仍需經過專家分析才能使結果具有明確的可解釋性。因此，本論文使用規則分類器（Rule Classifier）實現 NILM 負載狀態辨識，透過辨識特定負載或電器之狀態的規則提供具有明確可解釋性的方法。在規則分類器的產生使用基因演算法（Genetic Algorithm）訓練，藉以從大量的規則池中選出最佳的辨識規則，並將這些最佳規則組成規則分類器。
經過本論文的實驗顯示，使用規則分類器實現的 NILM 演算法，其辨識效能與傳統 NILM 演算法相當，雖然效能上沒有非常明顯的改善，但辨識的規則可為總用電量之變化提供明確的依據，使每一負載或電器之狀態判定均有明確原因作為解釋；除此之外，透過規則分類器內的規則分析，可推測出場域之電器使用習慣，並基於分析結果可再進一步作為人類活動分析之參考。

Non-Intrusive Load Monitoring (NILM) has been developed for a long time. Within monitoring and analyzing the total usage of specific fields such as households, buildings, factories, offices...etc., the status or electricity usage of each load or appliance can be obtained without deploying power meter for each load or appliance in a specific field. Based on the solution above, the NILM provides not only outstanding scalability for load monitoring but also privacy protection for a specific field.
Although NILM has been developed for a long time, the explainability for NILM is not provided for most NILM solutions. In recent years, there have been some visualization techniques which try to explain the result of Neural-Network-based NILM, but the visualization result still needs advanced analysis by experts to explain the result more straightforward. Hence, we utilize the rule classifier to implement NILM load identification. The method provides a straightforward explainability based on rules which identify specific status of specific load or appliance. The rule classifier is trained by Genetic Algorithm to figure out the best rule from the rule pool. Finally, the rule classifier is composed of rules which perform better.
The experimental result shows that the performance between baselines and the rule classifier has no significant improvement. However, the rule classifier can provide clear evidence based on the change in total electricity usage. In addition, the habit of load or appliance usage can be inferred through rule analysis. The result can be a reference to human activity analysis in advance.

S. S. Hosseini, K. Agbossou, S. Kelouwani, and A. Cardenas, “Non-intrusive load monitoring through home energy management systems: A comprehensive review,” Renewable and Sustainable Energy Reviews, vol. 79, pp. 1266–1274, 2017.
G.-F. Angelis, C. Timplalexis, S. Krinidis, D. Ioannidis, and D. Tzovaras, “Nilm applications: Literature review of learning approaches, recent developments and challenges,” Energy and Buildings, p. 111951, 2022.
A. Ridi, C. Gisler, and J. Hennebert, “A survey on intrusive load monitoring for appliance recognition,” in 2014 22nd international conference on pattern recognition. IEEE, 2014, pp. 3702–3707.
A. Hernandez, A. Ruano, J. Ure˜na, M. Ruano, and J. Garcia, “Applications of nilm techniques to energy management and assisted living,” IFAC-PapersOnLine, vol. 52, no. 11, pp. 164–171, 2019.
A. Ruano, A. Hernandez, J. Ure˜na, M. Ruano, and J. Garcia, “Nilm techniques for intelligent home energy management and ambient assisted living: A review,” Energies, vol. 12, no. 11, p. 2203, 2019.
S. Giri and M. Berg´es, “An energy estimation framework for event-based methods in nonintrusive load monitoring,” Energy Conversion and Management, vol. 90, pp. 488–498, 2015.
S. Mohamad, D. Arifoglu, C. Mansouri, and A. Bouchachia, “Deep online hierarchical unsupervised learning for pattern mining from utility usage data,” in UK Workshop on Computational Intelligence. Springer, 2018, pp. 276–290.
G. W. Hart, “Nonintrusive appliance load monitoring,” Proceedings of the IEEE, vol. 80, no. 12, pp. 1870–1891, 1992.
R. Machlev, L. Heistrene, M. Perl, K. Levy, J. Belikov, S. Mannor, and Y. Levron, “Explainable artificial intelligence (xai) techniques for energy and power systems: Review, challenges and opportunities,” Energy and AI, p. 100169, 2022.
D. Murray, L. Stankovic, and V. Stankovic, “Explainable nilm networks,” in Proceedings of the 5th International Workshop on non-intrusive load monitoring, 2020, pp. 64–69.
D. Murray, L. Stankovic, and V. Stankovic, “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, 2021, pp. 268–271.
N. Hudson, M. J. Hossain, M. Hosseinzadeh, H. Khamfroush, M. Rahnamay-Naeini, and N. Ghani, “A framework for edge intelligent smart distribution grids via federated learning,” in 2021 International Conference on Computer Communications and Networks (ICCCN). IEEE, 2021, pp. 1–9.
Y. Liu, Y. Sun, and B. Li, “A modified ip-based nilm approach using appliance characteristics extracted by 2-sax,” IEEE Access, vol. 7, pp. 48 119–48 128, 2019.
K. D. Anderson, M. E. Berges, A. Ocneanu, D. Benitez, and J. M. Moura, “Event detection for non intrusive load monitoring,” in IECON 2012-38th Annual Conference on IEEE Industrial Electronics Society. IEEE, 2012, pp. 3312–3317.
J. Alcala, J. Ure˜na, A. Hernandez, and D. Gualda, “Event-based energy disaggregation algorithm for activity monitoring from a single-point sensor,” IEEE Transactions on Instrumentation and Measurement, vol. 66, no. 10, pp. 2615–2626, 2017.
A. Ridi, C. Gisler, and J. Hennebert, “Unseen appliances identification,” in Iberoamerican Congress on Pattern Recognition. Springer, 2013, pp. 75–82.
A. Ridi, C. Gisler, and J. Hennebert, “Automatic identification of electrical appliances using smart plugs,” in 2013 8th International Workshop on Systems, Signal Processing and their Applications (WoSSPA). IEEE, 2013, pp. 301–305.
A. Reinhardt, P. Baumann, D. Burgstahler, M. Hollick, H. Chonov, M. Werner, and R. Steinmetz, “On the accuracy of appliance identification based on distributed load metering data,” in 2012 Sustainable Internet and ICT for Sustainability (SustainIT). IEEE, 2012, pp. 1–9.
A. A. Zaidi, F. Kupzog, T. Zia, and P. Palensky, “Load recognition for automated demand response in microgrids,” in IECON 2010-36th Annual Conference on IEEE Industrial Electronics Society. IEEE, 2010, pp. 2442–2447.
T. Kato, H. S. Cho, D. Lee, T. Toyomura, and T. Yamazaki, “Appliance recognition from electric current signals for information-energy integrated network in home environments,” in International Conference on Smart Homes and Health Telematics. Springer, 2009, pp. 150–157.
N. Lin, B. Zhou, G. Yang, and S. Ma, “Multi-head attention networks for nonintrusive load monitoring,” in 2020 IEEE International Conference on Signal Processing, Communications and Computing (ICSPCC). IEEE, 2020, pp. 1–5.
S. Ghosh, A. Chatterjee, and D. Chatterjee, “An improved load feature extraction technique for smart homes using fuzzy-based nilm,” IEEE Transactions on Instrumentation and Measurement, vol. 70, pp. 1–9, 2021.
P. Nandy, Hidden Markov model based non-intrusive load monitoring using active and reactive power consumption. Missouri University of Science and Technology, 2016.
R. Bonfigli, E. Principi, M. Fagiani, M. Severini, S. Squartini, and F. Piazza, “Nonintrusive load monitoring by using active and reactive power in additive factorial hidden markov models,” Applied Energy, vol. 208, pp. 1590–1607, 2017.
G. A. Raiker, S. B. Reddy, L. Umanand, A. Yadav, and M. M. Shaikh, “Approach to non-intrusive load monitoring using factorial hidden markov model,” in 2018 IEEE 13th International Conference on Industrial and Information Systems (ICIIS). IEEE, 2018, pp. 381–386.
W. Kong, Z. Y. Dong, D. J. Hill, J. Ma, J. Zhao, and F. Luo, “A hierarchical hidden markov model framework for home appliance modeling,” IEEE Transactions on Smart Grid, vol. 9, no. 4, pp. 3079–3090, 2016.
R. Machlev, J. Belikov, Y. Beck, and Y. Levron, “Mo-nilm: A multi-objective evolutionary algorithm for nilm classification,” Energy and Buildings, vol. 199, pp. 134–144, 2019.
K. He, L. Stankovic, J. Liao, and V. Stankovic, “Non-intrusive load disaggregation using graph signal processing,” IEEE Transactions on Smart Grid, vol. 9, no. 3, pp. 1739–1747, 2016.
M. Figueiredo, B. Ribeiro, and A. de Almeida, “Electrical signal source separation via nonnegative tensor factorization using on site measurements in a smart home,” IEEE Transactions on Instrumentation and Measurement, vol. 63, no. 2, pp. 364–373, 2013.
M. Nguyen, S. Alshareef, A. Gilani, and W. G. Morsi, “A novel feature extraction and classification algorithm based on power components using single-point monitoring for nilm,” in 2015 IEEE 28th Canadian Conference on Electrical and Computer Engineering (CCECE). IEEE, 2015, pp. 37–40.
H. Kang, H. Kim et al., “Household appliance classification using lower odd-numbered harmonics and the bagging decision tree,” IEEE Access, vol. 8, pp. 55 937–55 952, 2020.
F. B. Gurbuz, R. Bayindir, and S. Vadi, “Comprehensive non-intrusive load monitoring process: Device event detection, device feature extraction and device identification using knn, random forest and decision tree,” in 2021 10th International Conference on Renewable Energy Research and Application (ICRERA). IEEE, 2021, pp. 447–452.
M. Figueiredo, A. De Almeida, and B. Ribeiro, “Home electrical signal disaggregation for non-intrusive load monitoring (nilm) systems,” Neurocomputing, vol. 96, pp. 66–73, 2012.
F. Gong, N. Han, Y. Zhou, S. Chen, D. Li, and S. Tian, “A svm optimized by particle swarm optimization approach to load disaggregation in non-intrusive load monitoring in smart homes,” in 2019 IEEE 3rd Conference on Energy Internet and Energy System Integration (EI2). IEEE, 2019, pp. 1793–1797.
F. Hidiyanto and A. Halim, “Knn methods with varied k, distance and training data to disaggregate nilm with similar load characteristic,” in Proceedings of the 3rd Asia Pacific Conference on Research in Industrial and Systems Engineering 2020, 2020, pp. 93–99.
S. Sahrane, M. Adnane, and M. Haddadi, “A clustering event detection approach for nonintrusive load monitoring,” in 2020 6th International Symposium on New and Renewable Energy (SIENR). IEEE, 2021, pp. 1–7.
X. Wu, Y. Gao, and D. Jiao, “Multi-label classification based on random forest algorithm for non-intrusive load monitoring system,” Processes, vol. 7, no. 6, p. 337, 2019.
Z. Chen, J. Chen, X. Xu, S. Peng, J. Xiao, and H. Qiao, “Non-intrusive load monitoring based on feature extraction of change-point and xgboost classifier,” in 2020 IEEE 4th Conference on Energy Internet and Energy System Integration (EI2). IEEE, 2020, pp. 2652–2656.
D. Yang, X. Gao, L. Kong, Y. Pang, and B. Zhou, “An event-driven convolutional neural architecture for non-intrusive load monitoring of residential appliance,” IEEE Transactions on Consumer Electronics, vol. 66, no. 2, pp. 173–182, 2020.
L. Mauch and B. Yang, “A new approach for supervised power disaggregation by using a deep recurrent lstm network,” in 2015 IEEE Global Conference on Signal and Information Processing (GlobalSIP). IEEE, 2015, pp. 63–67.
T.Wang, T. Ji, and M. Li, “A new approach for supervised power disaggregation by using a denoising autoencoder and recurrent lstm network,” in 2019 IEEE 12th International symposium on diagnostics for electrical machines, power electronics and drives (SDEMPED). IEEE, 2019, pp. 507–512.
H. Shastri and N. Batra, “Neural network approaches and dataset parser for nilm toolkit,” in Proceedings of the 8th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation, 2021, pp. 172–175.
Z. Yue, C. R. Witzig, D. Jorde, and H.-A. Jacobsen, “Bert4nilm: A bidirectional transformer model for non-intrusive load monitoring,” in Proceedings of the 5th International Workshop on Non-Intrusive Load Monitoring, 2020, pp. 89–93.
T. Sirojan, B. T. Phung, and E. Ambikairajah, “Deep neural network based energy disaggregation,” in 2018 IEEE International Conference on Smart Energy Grid Engineering (SEGE). IEEE, 2018, pp. 73–77.
G. Bejarano, D. DeFazio, and A. Ramesh, “Deep latent generative models for energy disaggregation,” in Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, no. 01, 2019, pp. 850–857.
M. Kaselimi, A. Voulodimos, E. Protopapadakis, N. Doulamis, and A. Doulamis, “Energan: A generative adversarial network for energy disaggregation,” in ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2020, pp. 1578–1582.
M. Kaselimi, N. Doulamis, A. Voulodimos, A. Doulamis, and E. Protopapadakis, “Energan++: A generative adversarial gated recurrent network for robust energy disaggregation,” IEEE Open Journal of Signal Processing, vol. 2, pp. 1–16, 2020.
Y. Pan, K. Liu, Z. Shen, X. Cai, and Z. Jia, “Sequence-to-subsequence learning with conditional gan for power disaggregation,” in ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2020, pp. 3202–3206.
A. M. Ahmed, Y. Zhang, and F. Eliassen, “Generative adversarial networks and transfer learning for non-intrusive load monitoring in smart grids,” in 2020 IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids (SmartGridComm). IEEE, 2020, pp. 1–7.
D. Murray, L. Stankovic, V. Stankovic, S. Lulic, and S. Sladojevic, “Transferability of neural network approaches for low-rate energy disaggregation,” in ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2019, pp. 8330–8334.
N. Batra, R. Kukunuri, A. Pandey, R. Malakar, R. Kumar, O. Krystalakos, M. Zhong, P. Meira, and O. Parson, “Towards reproducible state-of-the-art energy disaggregation,” in Proceedings of the 6th ACM international conference on systems for energy-efficient buildings, cities, and transportation, 2019, pp. 193–202.
H. P¨otter, S. Lee, and D. Moss´e, “Towards privacy-preserving framework for non-intrusive load monitoring,” in Proceedings of the Twelfth ACM International Conference on Future Energy Systems, 2021, pp. 259–263.
A. Adadi and M. Berrada, “Peeking inside the black-box: a survey on explainable artificial intelligence (xai),” IEEE access, vol. 6, pp. 52 138–52 160, 2018.
Groceries market basket dataset — kaggle. [Online]. Available: https://www.kaggle.com/datasets/irfanasrullah/groceries?select=groceries+-+groceries.csv
A. Cano, A. Zafra, and S. Ventura, “An interpretable classification rule mining algorithm,” Information Sciences, vol. 240, pp. 1–20, 2013.
F. Thabtah, P. Cowling, and Y. Peng, “Mcar: multi-class classification based on association rule,” in The 3rd ACS/IEEE International Conference onComputer Systems and Applications, 2005. IEEE, 2005, p. 33.
J. Z. Kolter and M. J. Johnson, “Redd: A public data set for energy disaggregation research,” in Workshop on data mining applications in sustainability (SIGKDD), San Diego, CA, vol. 25, no. Citeseer, 2011, pp. 59–62.
C. Beckel, W. Kleiminger, R. Cicchetti, T. Staake, and S. Santini, “The eco data set and the performance of non-intrusive load monitoring algorithms,” in Proceedings of the 1st ACM conference on embedded systems for energy-efficient buildings, 2014, pp. 80–89.
W. Kleiminger, C. Beckel, and S. Santini, “Household occupancy monitoring using electricity meters,” in Proceedings of the 2015 ACM international joint conference on pervasive and ubiquitous computing, 2015, pp. 975–986. 39