{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T07:36:19Z","timestamp":1781076979710,"version":"3.54.1"},"reference-count":27,"publisher":"MDPI AG","issue":"3","license":[{"start":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T00:00:00Z","timestamp":1773705600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Entropy"],"abstract":"<jats:p>High-frequency non-intrusive load monitoring provides detailed harmonic information for appliances\u2019 power disaggregation, and machine-learning approaches have demonstrated good performance in this task. However, these methods provide little transparency regarding the information structure of the aggregate signal. To address this, this paper models NILM as a coding-decoding process and applies information-theoretic measures to quantify uncertainty, recoverability, temporal contribution, and inter-appliance masking effects in aggregate signals. In the analyzed dataset, transfer entropy suggests negligible temporal gains, which is consistent with the observed effectiveness of pointwise models such as Random Forest. Moreover, conditional mutual information emphasizes the asymmetric masking relationships between appliances, with the laptop charger acting as a dominant interferer in the considered measurements. These findings are validated through a Random Forest regression model with minimum Redundancy Maximum Relevance feature selection. The results show that the mutual information between an appliance and the aggregate is a good predictor of disaggregation performance in the examined data, as appliances with high mutual information, such as hair dryer and electric water heater, achieve lower estimation errors, while others, such as iron, are difficult to recover despite stable distributions. This relationship is statistically supported by a strong negative monotonic correlation between normalized mutual information and the disaggregation error (Spearman rs=\u22120.81, p=0.015). Hence, this work demonstrates how information-theoretic analysis can help characterize disaggregation difficulty prior to model training and assess the observability of appliances in high-frequency NILM.<\/jats:p>","DOI":"10.3390\/e28030334","type":"journal-article","created":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T09:35:57Z","timestamp":1773740157000},"page":"334","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["An Information-Theoretic Analysis of High-Frequency Load Disaggregation"],"prefix":"10.3390","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4502-2153","authenticated-orcid":false,"given":"Gabriel Arquelau Pimenta","family":"Rodrigues","sequence":"first","affiliation":[{"name":"Department of Electrical Engineering, University of Brasilia, Bras\u00edlia 70910-900, Brazil"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5182-0496","authenticated-orcid":false,"given":"Andr\u00e9 Luiz Marques","family":"Serrano","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering, University of Brasilia, Bras\u00edlia 70910-900, Brazil"},{"name":"Institute of Mathematical and Computer Sciences, University of S\u00e3o Paulo, S\u00e3o Carlos 13566-590, SP, Brazil"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6795-2768","authenticated-orcid":false,"given":"Geraldo Pereira Rocha","family":"Filho","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering, University of Brasilia, Bras\u00edlia 70910-900, Brazil"},{"name":"Department of Exact and Technological Sciences, State University of Southwest Bahia, Vit\u00f3ria da Conquista 45083-900, BA, Brazil"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3771-2605","authenticated-orcid":false,"given":"Vin\u00edcius Pereira","family":"Gon\u00e7alves","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering, University of Brasilia, Bras\u00edlia 70910-900, Brazil"},{"name":"Institute of Mathematical and Computer Sciences, University of S\u00e3o Paulo, S\u00e3o Carlos 13566-590, SP, Brazil"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2982-4006","authenticated-orcid":false,"given":"Rodolfo Ipolito","family":"Meneguette","sequence":"additional","affiliation":[{"name":"Institute of Mathematical and Computer Sciences, University of S\u00e3o Paulo, S\u00e3o Carlos 13566-590, SP, Brazil"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,3,17]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Rehman, A.U., Tito, S.R., Nieuwoudt, P., Imran, G., Lie, T.T., Vall\u00e8s, B., and Ahmad, W. (2019). Applications of Non-Intrusive Load Monitoring Towards Smart and Sustainable Power Grids: A System Perspective. Proceedings of the 2019 29th Australasian Universities Power Engineering Conference (AUPEC), IEEE.","DOI":"10.1109\/AUPEC48547.2019.211897"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"100384","DOI":"10.1016\/j.egyai.2024.100384","article-title":"Comparing four machine learning algorithms for household non-intrusive load monitoring","volume":"17","author":"Young","year":"2024","journal-title":"Energy AI"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"121703","DOI":"10.1016\/j.apenergy.2023.121703","article-title":"A novel non-intrusive load monitoring method based on ResNet-seq2seq networks for energy disaggregation of distributed energy resources integrated with residential houses","volume":"349","author":"Zhang","year":"2023","journal-title":"Appl. Energy"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"6505312","DOI":"10.1109\/TIM.2025.3570355","article-title":"A generalizable load recognition method in NILM based on transferable random forest","volume":"74","author":"Yan","year":"2025","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Kaselimi, M., Protopapadakis, E., Voulodimos, A., Doulamis, N., and Doulamis, A. (2022). Towards trustworthy energy disaggregation: A review of challenges, methods, and perspectives for non-intrusive load monitoring. Sensors, 22.","DOI":"10.3390\/s22155872"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"111308","DOI":"10.1016\/j.enbuild.2021.111308","article-title":"Practical limits to the use of non-intrusive load monitoring in commercial buildings","volume":"251","author":"Meier","year":"2021","journal-title":"Energy Build."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"4184","DOI":"10.1007\/s10618-024-01070-7","article-title":"Model-agnostic variable importance for predictive uncertainty: An entropy-based approach","volume":"38","author":"Wood","year":"2024","journal-title":"Data Min. Knowl. Discov."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Dinar, F., Paris, S., and Busvelle, \u00c9. (2025). Capturing High-Frequency Harmonic Signatures for NILM: Building a Dataset for Load Disaggregation. Sensors, 25.","DOI":"10.3390\/s25154601"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Massidda, L., and Marrocu, M. (2022). A bayesian approach to unsupervised, non-intrusive load disaggregation. Sensors, 22.","DOI":"10.3390\/s22124481"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"3627","DOI":"10.1109\/TSG.2023.3245019","article-title":"A time efficient factorial hidden Markov model-based approach for non-intrusive load monitoring","volume":"14","author":"Kumar","year":"2023","journal-title":"IEEE Trans. Smart Grid"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"6227","DOI":"10.1007\/s10489-021-02690-y","article-title":"Non-intrusive load monitoring method with inception structured CNN","volume":"52","author":"Ding","year":"2022","journal-title":"Appl. Intell."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"5762","DOI":"10.1016\/j.egyr.2021.09.001","article-title":"Non-intrusive load decomposition based on CNN\u2013LSTM hybrid deep learning model","volume":"7","author":"Zhou","year":"2021","journal-title":"Energy Rep."},{"key":"ref_13","first-page":"46","article-title":"Proficiency of power values for load disaggregation","volume":"65","author":"Egarter","year":"2015","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Schirmer, P.A., Mporas, I., and Paraskevas, M. (2020). Energy disaggregation using elastic matching algorithms. Entropy, 22.","DOI":"10.3390\/e22010071"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"3841","DOI":"10.1109\/TSG.2023.3239598","article-title":"A learnable image-based load signature construction approach in NILM for appliances identification","volume":"14","author":"Zhang","year":"2023","journal-title":"IEEE Trans. Smart Grid"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Houidi, S., Fourer, D., and Auger, F. (2020). On the use of concentrated time\u2013frequency representations as input to a deep convolutional neural network: Application to non intrusive load monitoring. Entropy, 22.","DOI":"10.3390\/e22090911"},{"key":"ref_17","first-page":"1119","article-title":"Event-based two-stage non-intrusive load monitoring method involving multi-dimensional features","volume":"9","author":"Zhou","year":"2022","journal-title":"CSEE J. Power Energy Syst."},{"key":"ref_18","first-page":"3443","article-title":"Nonintrusive appliance identification with appliance-specific networks","volume":"56","author":"Fang","year":"2020","journal-title":"IEEE Trans. Ind. Appl."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"13696","DOI":"10.1109\/TMC.2025.3590765","article-title":"Preventing non-intrusive load monitoring privacy invasion: A precise adversarial attack scheme for networked smart meters","volume":"24","author":"He","year":"2025","journal-title":"IEEE Trans. Mob. Comput."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"2507612","DOI":"10.1109\/TIM.2025.3542871","article-title":"Privacy-preserving NILM: A self-alignment source-aware domain adaptation approach","volume":"74","author":"Hao","year":"2025","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"114091","DOI":"10.1016\/j.rser.2023.114091","article-title":"DP2-NILM: A distributed and privacy-preserving framework for non-intrusive load monitoring","volume":"191","author":"Dai","year":"2024","journal-title":"Renew. Sustain. Energy Rev."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Mari\u00f1o, C., Masquil, E., Marchesoni, F., Fernandez, A., and Massaferro, P. (2021). NILM: Multivariate DNN performance analysis with high frequency features. Proceedings of the 2021 IEEE PES Innovative Smart Grid Technologies Conference-Latin America (ISGT Latin America), IEEE.","DOI":"10.1109\/ISGTLatinAmerica52371.2021.9543016"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"163","DOI":"10.1109\/TIA.2021.3128469","article-title":"Feature selection method for nonintrusive load monitoring with balanced redundancy and relevancy","volume":"58","author":"Bao","year":"2021","journal-title":"IEEE Trans. Ind. Appl."},{"key":"ref_24","first-page":"2502514","article-title":"Adaptive multitimescale event detection in nonintrusive load monitoring based on minimum description length principle","volume":"73","author":"Liu","year":"2023","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Liu, Y., You, W., and Yang, M. (2025). Non-Intrusive Load Identification Based on Multivariate Features and Information Entropy-Weighted Ensemble. Energies, 18.","DOI":"10.3390\/en18092369"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"1148","DOI":"10.1109\/TDSC.2025.3614253","article-title":"Charging Into Your Privacy: Indirect Privacy Leakage Attack Using a Laptop Charger","volume":"23","author":"Kim","year":"2025","journal-title":"IEEE Trans. Dependable Secur. Comput."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"55937","DOI":"10.1109\/ACCESS.2020.2981969","article-title":"Household appliance classification using lower odd-numbered harmonics and the bagging decision tree","volume":"8","author":"Kang","year":"2020","journal-title":"IEEE Access"}],"container-title":["Entropy"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1099-4300\/28\/3\/334\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T05:17:01Z","timestamp":1773897421000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1099-4300\/28\/3\/334"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,17]]},"references-count":27,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2026,3]]}},"alternative-id":["e28030334"],"URL":"https:\/\/doi.org\/10.3390\/e28030334","relation":{},"ISSN":["1099-4300"],"issn-type":[{"value":"1099-4300","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,17]]}}}