{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T01:40:20Z","timestamp":1760060420387,"version":"build-2065373602"},"reference-count":27,"publisher":"MDPI AG","issue":"9","license":[{"start":{"date-parts":[[2025,8,26]],"date-time":"2025-08-26T00:00:00Z","timestamp":1756166400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"General Project of Basic Science Research in Higher Education Institutions in Jiangsu Province","award":["23KJB520008","62206297"],"award-info":[{"award-number":["23KJB520008","62206297"]}]},{"name":"National Natural Science Foundations of China","award":["23KJB520008","62206297"],"award-info":[{"award-number":["23KJB520008","62206297"]}]},{"name":"\u201cQinglan Project\u201d of Jiangsu Higher Education Institutions","award":["23KJB520008","62206297"],"award-info":[{"award-number":["23KJB520008","62206297"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Computers"],"abstract":"<jats:p>Precise electricity consumption forecasting and anomaly detection constitute fundamental requirements for maintaining grid reliability in smart power systems. While consumption patterns demonstrate quasi-periodic behavior with region-specific fluctuations influenced by environmental factors, existing approaches may fail to systematically model these dynamic variations or quantify environmental impacts. This limitation results in a compromised prediction accuracy and ambiguous anomaly identification. To overcome these challenges, we propose a novel Multi-Task Graph Attention Network (MGAT) framework leveraging an adaptive entropy analysis. Our methodology comprises four key innovations: (1) the temporal decomposition of consumption data with entropy-based adaptive clustering into predictable low-entropy components (processed via multi-scale attention networks) and volatile high-entropy components; (2) the graph-based representation of high-entropy fluctuations through numerical correlation encoding, complemented by temporal environmental graphs quantifying external influences; (3) the hierarchical fusion of environmental and fluctuation graphs via a specialized Graph Attention Autoencoder that jointly models dynamic patterns and environmental dependencies; (4) the integrated synthesis of all components for simultaneous consumption prediction and anomaly detection. Experiments verify the MGAT\u2019s performance in both forecasting precision and anomaly identification compared to conventional methods.<\/jats:p>","DOI":"10.3390\/computers14090350","type":"journal-article","created":{"date-parts":[[2025,8,26]],"date-time":"2025-08-26T10:35:17Z","timestamp":1756204517000},"page":"350","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Multi-Task Graph Attention Net for Electricity Consumption Prediction and Anomaly Detection"],"prefix":"10.3390","volume":"14","author":[{"given":"Na","family":"Bai","sequence":"first","affiliation":[{"name":"College of Information and Electrical Engineering, Jiangsu Vocational Institute of Architectural Technology, Xuzhou 221116, China"},{"name":"School of Computer Science and Technology, China University of Mining and Technology, Xuzhou 221116, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jian","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, China University of Mining and Technology, Xuzhou 221116, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhaoli","family":"Wu","sequence":"additional","affiliation":[{"name":"College of Information and Electrical Engineering, Jiangsu Vocational Institute of Architectural Technology, Xuzhou 221116, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2025,8,26]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"1104","DOI":"10.1016\/j.rser.2017.02.023","article-title":"A review and analysis of regression and machine learning models on commercial building electricity load forecasting","volume":"73","author":"Yildiz","year":"2017","journal-title":"Renew. Sustain. Energy Rev."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"13","DOI":"10.1109\/TPWRS.2004.840412","article-title":"Modeling and forecasting electricity prices with input\/output hidden Markov models","volume":"20","author":"Roque","year":"2005","journal-title":"IEEE Trans. Power Syst."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"116180","DOI":"10.1016\/j.apenergy.2020.116180","article-title":"Very short term load forecasting of residential electricity consumption using the Markov-chain mixture distribution (MCM) model","volume":"282","author":"Munkhammar","year":"2021","journal-title":"Appl. Energy"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"123483","DOI":"10.1016\/j.energy.2022.123483","article-title":"Analysis of time series models for Brazilian electricity consumption demand forecasting","volume":"247","author":"Velasquez","year":"2022","journal-title":"Energy"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"3815063","DOI":"10.1155\/2023\/3815063","article-title":"Electricity Load and Price Forecasting Using a Hybrid Method Based Bidirectional Long Short-Term Memory with Attention Mechanism Model","volume":"2023","author":"Gomez","year":"2023","journal-title":"Int. J. Energy Res."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Zhang, X.M., Grolinger, K., Capretz, M.A.M., and Seewald, L. (2018, January 17\u201320). Forecasting Residential Energy Consumption: Single Household Perspective. Proceedings of the 17th IEEE International Conference on Machine Learning and Applications, Orlando, FL, USA.","DOI":"10.1109\/ICMLA.2018.00024"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"120480","DOI":"10.1016\/j.energy.2021.120480","article-title":"Electrical load-temperature CNN for residential load forecasting","volume":"227","author":"Imani","year":"2021","journal-title":"Energy"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"470","DOI":"10.1016\/j.ijepes.2019.02.022","article-title":"Bi-directional long short-term memory method based on attention mechanism and rolling update for short-term load forecasting","volume":"109","author":"Wang","year":"2019","journal-title":"Int. J. Electr. Power Energy Syst."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"10533","DOI":"10.1007\/s00521-021-06773-2","article-title":"A deep LSTM network for the Spanish electricity consumption demand forecasting","volume":"34","author":"Torres","year":"2022","journal-title":"Neural Comput. Appl."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Kim, N., and Choi, J. (2018, January 9\u201312). LSTM Based Short-term Electricity Consumption Forecast with Daily Load Profile Sequences. Proceedings of the IEEE 7th Global Conference on Consumer Electronics, Nara, Japan.","DOI":"10.1109\/GCCE.2018.8574484"},{"key":"ref_11","unstructured":"Zheng, J., Xu, C., Zhang, Z., and Li, X. (2017, January 22\u201324). Electric load forecasting in smart grids using Long-Short-Term-Memory based Recurrent Neural Network. Proceedings of the 51st Annual Conference on Information Sciences and Systems(CISS), Baltimore, MD, USA."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"6061","DOI":"10.1007\/s13042-024-02302-4","article-title":"Multiscale-integrated deep learning approaches for short-term load forecasting","volume":"15","author":"Yang","year":"2024","journal-title":"Int. J. Mach. Learn. Cybern."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"2056","DOI":"10.1109\/TKDE.2023.3319672","article-title":"Multi-scale attention flow for probabilistic time series forecasting","volume":"36","author":"Feng","year":"2023","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"ref_14","first-page":"11","article-title":"Household Electricity Consumption Forecast Based on Bi\u2014LSTM","volume":"33","author":"Xu","year":"2020","journal-title":"Ind. Control. Comput."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"1688","DOI":"10.1016\/j.energy.2016.07.090","article-title":"Deep belief network based electricity load forecasting: An analysis of Macedonian case","volume":"115","author":"Dedinec","year":"2016","journal-title":"Energy"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"301","DOI":"10.1016\/j.enbuild.2016.05.083","article-title":"Polynomial-Fourier series model for analyzing and predicting electricity consumption in buildings","volume":"127","author":"Tsai","year":"2016","journal-title":"Energy Build."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1016\/j.neucom.2015.01.108","article-title":"Modeling time series data with deep Fourier neural networks","volume":"188","author":"Gashler","year":"2016","journal-title":"Neurocomputing"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"131065","DOI":"10.1016\/j.energy.2024.131065","article-title":"A discrete time-varying grey Fourier model with fractional order terms for electricity consumption forecast","volume":"296","author":"Liu","year":"2024","journal-title":"Energy"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Imani, M., and Ghassemian, H. (2019, January 6\u20137). Lagged Load Wavelet Decomposition and LSTM Networks for Short-Term Load Forecasting. Proceedings of the 4th International Conference on Pattern Recognition and Image Analysis, Tehran, Iran.","DOI":"10.1109\/PRIA.2019.8785972"},{"key":"ref_20","first-page":"77","article-title":"Dilated Recurrent Neural Networks","volume":"1","author":"Chang","year":"2017","journal-title":"Annu. Conf. Neural Inf. Process. Syst."},{"key":"ref_21","unstructured":"(2022, August 01). Available online: https:\/\/www.kaggle.com\/datasets\/fedesoriano\/electric-power-consumption."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"120908","DOI":"10.1016\/j.energy.2021.120908","article-title":"Photovoltaic Power Forecasting Based on GA improved Bi-LSTM in Microgrid without Meteorological Information","volume":"231","author":"Zhen","year":"2021","journal-title":"Energy"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"119608","DOI":"10.1016\/j.apenergy.2022.119608","article-title":"A hybrid attention-based deep learning approach for wind power prediction","volume":"323","author":"Ma","year":"2022","journal-title":"Appl. Energy"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Liu, Y., Guan, L., Hou, C., Han, H., Liu, Z., Sun, Y., and Zheng, M. (2019). Wind Power Short-Term Prediction Based on LSTM and Discrete Wavelet Transform. Appl. Sci., 9.","DOI":"10.3390\/app9061108"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"1857","DOI":"10.1007\/s00202-021-01420-4","article-title":"Short-term load forecasting using neural attention model based on EMD","volume":"104","author":"Meng","year":"2022","journal-title":"Electr. Eng."},{"key":"ref_26","first-page":"3096","article-title":"Revisiting vae for unsupervised time series anomaly detection: A frequency perspective","volume":"2024","author":"Wang","year":"2024","journal-title":"Proc. ACM Web Conf."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"506","DOI":"10.1016\/j.cja.2024.03.024","article-title":"An attention graph stacked autoencoder for anomaly detection of electro-mechanical actuator using spatio-temporal multivariate signal","volume":"37","author":"Wu","year":"2024","journal-title":"Chin. J. Aeronaut."}],"container-title":["Computers"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2073-431X\/14\/9\/350\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T18:33:00Z","timestamp":1760034780000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2073-431X\/14\/9\/350"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,26]]},"references-count":27,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2025,9]]}},"alternative-id":["computers14090350"],"URL":"https:\/\/doi.org\/10.3390\/computers14090350","relation":{},"ISSN":["2073-431X"],"issn-type":[{"type":"electronic","value":"2073-431X"}],"subject":[],"published":{"date-parts":[[2025,8,26]]}}}