{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T22:45:52Z","timestamp":1784069152256,"version":"3.55.0"},"reference-count":32,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2024,9,23]],"date-time":"2024-09-23T00:00:00Z","timestamp":1727049600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Neurorobot."],"abstract":"<jats:sec><jats:title>Introduction<\/jats:title><jats:p>Residential load forecasting is a challenging task due to the random fluctuations caused by complex correlations and individual differences. The existing short-term load forecasting models usually introduce external influencing factors such as climate and date. However, these additional information not only bring computational burden to the model, but also have uncertainty. To address these issues, we propose a novel multi-level feature fusion model based on graph attention temporal convolutional network (MLFGCN) for short-term residential load forecasting.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>The proposed MLFGCN model fully considers the potential long-term dependencies in a single load series and the correlations between multiple load series, and does not require any additional information to be added. Temporal convolutional network (TCN) with gating mechanism is introduced to learn potential long-term dependencies in the original load series. In addition, we design two graph attentive convolutional modules to capture potential multi-level dependencies in load data. Finally, the outputs of each module are fused through an information fusion layer to obtain the highly accurate forecasting results.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>We conduct validation experiments on two real-world datasets. The results show that the proposed MLFGCN model achieves 0.25, 7.58% and 0.50 for MAE, MAPE and RMSE, respectively. These values are significantly better than those of baseline models.<\/jats:p><\/jats:sec><jats:sec><jats:title>Discussion<\/jats:title><jats:p>The MLFGCN algorithm proposed in this paper can significantly improve the accuracy of short-term residential load forecasting. This is achieved through high-quality feature reconstruction, comprehensive information graph construction and spatiotemporal features capture.<\/jats:p><\/jats:sec>","DOI":"10.3389\/fnbot.2024.1461403","type":"journal-article","created":{"date-parts":[[2024,9,23]],"date-time":"2024-09-23T11:23:06Z","timestamp":1727090586000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":7,"title":["MLFGCN: short-term residential load forecasting via graph attention temporal convolution network"],"prefix":"10.3389","volume":"18","author":[{"given":"Ding","family":"Feng","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dengao","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2024,9,23]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"113693","DOI":"10.1016\/j.apenergy.2019.113693","article-title":"Residential loads flexibility potential for demand response using energy consumption patterns and user segments","volume":"254","author":"Afzalan","year":"2019","journal-title":"Appl. Energy"},{"key":"ref2","first-page":"1","article-title":"A time-series distribution test system based on real utility data","author":"Bu","year":"2019"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"103484","DOI":"10.1016\/j.scs.2021.103484","article-title":"MultiCycleNet: multiple cycles self-boosted neural network for short-term electric household load forecasting","volume":"76","author":"Chen","year":"2022","journal-title":"Sustain. Cities Soc."},{"key":"ref4","first-page":"159","article-title":"Leveraging spatial information in smart grids using STGCN for short-term load forecasting","author":"Cheung","year":"2021"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"17835","DOI":"10.1109\/TITS.2022.3151925","article-title":"Traffic data recovery from corrupted and incomplete observations via spatial-temporal TRPCA","volume":"23","author":"Feng","year":"2022","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref6","doi-asserted-by":"publisher","first-page":"115503","DOI":"10.1016\/j.apenergy.2020.115503","article-title":"Short-term electricity price and load forecasting in isolated power grids based on composite neural network and gravitational search optimization algorithm","volume":"277","author":"Heydari","year":"2020","journal-title":"Appl. Energy"},{"key":"ref7","volume-title":"World energy outlook 2023","year":"2023"},{"key":"ref8","doi-asserted-by":"publisher","first-page":"8243","DOI":"10.1109\/TII.2021.3065718","article-title":"A novel evolutionary-based deep convolutional neural network model for intelligent load forecasting","volume":"17","author":"Jalali","year":"2021","journal-title":"IEEE Trans. Ind. Inform."},{"key":"ref9","doi-asserted-by":"publisher","first-page":"109423","DOI":"10.1016\/j.patcog.2023.109423","article-title":"Dynamic graph structure learning for multivariate time series forecasting","volume":"138","author":"Li","year":"2023","journal-title":"Pattern Recognit."},{"key":"ref10","doi-asserted-by":"publisher","first-page":"5373","DOI":"10.1109\/TSG.2021.3093515","article-title":"Spatial-temporal residential short-term load forecasting via graph neural networks","volume":"12","author":"Lin","year":"2021","journal-title":"IEEE Trans. Smart Grid"},{"key":"ref11","doi-asserted-by":"publisher","first-page":"012051","DOI":"10.1088\/17426596\/2078\/1\/012051","article-title":"Attention based spatial-temporal graph convolutional networks for short-term load forecasting","volume":"2078","author":"Liu","year":"2021","journal-title":"J. Phys.Conf. Ser."},{"key":"ref12","first-page":"1","article-title":"Forecasting electricity consumption using ARIMA model","author":"Mahia","year":"2019"},{"key":"ref13","doi-asserted-by":"publisher","first-page":"108026","DOI":"10.1016\/j.sigpro.2021.108026","article-title":"AR and ARMA model order selection for time-series modeling with ImageNet classification","volume":"183","author":"Moon","year":"2021","journal-title":"Signal Process."},{"key":"ref14","article-title":"Commercial and residential hourly load profiles for all TMY3 locations in the United States [data set]","year":"2014"},{"key":"ref22","first-page":"13","article-title":"WaveNet: A generative model for raw audio","volume":"125","author":"Oord","year":"2016","journal-title":"Proceedings of the 9th ISCA on speech synthesis workshop (SSW)"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"117511","DOI":"10.1016\/j.energy.2020.117511","article-title":"An efficient hour-ahead electrical load forecasting method based on innovative features","volume":"201","author":"Rafati","year":"2020","journal-title":"Energy"},{"key":"ref16","doi-asserted-by":"publisher","first-page":"108885","DOI":"10.1016\/j.epsr.2022.108885","article-title":"Short-term load forecasting based on CEEMDAN and transformer","volume":"214","author":"Ran","year":"2023","journal-title":"Electr. Power Syst. Res."},{"key":"ref17","doi-asserted-by":"publisher","first-page":"143759","DOI":"10.1109\/ACCESS.2020.3009537","article-title":"A novel CNN-GRU-based hybrid approach for short-term residential load forecasting","volume":"8","author":"Sajjad","year":"2020","journal-title":"IEEE Access"},{"key":"ref18","doi-asserted-by":"publisher","first-page":"5271","DOI":"10.1109\/TSG.2017.2686012","article-title":"Deep learning for household load forecasting-a novel pooling deep RNN","volume":"9","author":"Shi","year":"2017","journal-title":"IEEE Trans. Smart Grid"},{"key":"ref19","doi-asserted-by":"publisher","first-page":"107730","DOI":"10.1016\/j.asoc.2021.107730","article-title":"Data driven day-ahead electrical load forecasting through repeated wavelet transform assisted SVM mode","volume":"111","author":"Singh","year":"2021","journal-title":"Appl. Soft Comput."},{"key":"ref20","doi-asserted-by":"publisher","first-page":"121177","DOI":"10.1016\/j.apenergy.2023.121177","article-title":"A multi-task learning method for multi-energy load forecasting based on synthesis correlation analysis and load participation factor","volume":"343","author":"Tan","year":"2023","journal-title":"Appl. Energy"},{"key":"ref21","doi-asserted-by":"publisher","first-page":"380","DOI":"10.1016\/j.enbuild.2015.11.068","article-title":"Short-term residential electric load forecasting: a compressive spatio-temporal approach","volume":"111","author":"Tascikaraoglu","year":"2016","journal-title":"Energ. Buildings"},{"key":"ref23","article-title":"Graph attention networks","author":"Veli\u010dkovi\u0107","year":"2018","journal-title":"Proceedings of the international conference on learning representations (ICLR)"},{"key":"ref24","doi-asserted-by":"publisher","first-page":"12191","DOI":"10.1609\/aaai.v36i11.21479","article-title":"Causalgnn: causal-based graph neural networks for spatio-temporal epidemic forecasting","volume":"36","author":"Wang","year":"2022","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"ref25","doi-asserted-by":"publisher","first-page":"16137","DOI":"10.1109\/TITS.2022.3148105","article-title":"Hierarchical traffic flow prediction based on spatial-temporal graph convolutional network","volume":"23","author":"Wang","year":"2022","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref26","doi-asserted-by":"publisher","first-page":"109873","DOI":"10.1016\/j.epsr.2023.109873","article-title":"Short-term load forecasting using spatial-temporal embedding graph neural network","volume":"225","author":"Wei","year":"2023","journal-title":"Electr. Power Syst. Res."},{"key":"ref27","doi-asserted-by":"publisher","first-page":"105776","DOI":"10.1016\/j.engappai.2022.105776","article-title":"Combined framework based on data preprocessing and multi-objective optimizer for electricity load forecasting","volume":"119","author":"Xia","year":"2023","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref28","doi-asserted-by":"publisher","first-page":"109579","DOI":"10.1016\/j.ijepes.2023.109579","article-title":"Optimized hybrid ensemble learning approaches applied to very short-term load forecasting","volume":"155","author":"Yamasaki","year":"2024","journal-title":"Int. J. Electr. Power Energy Syst."},{"key":"ref29","doi-asserted-by":"publisher","first-page":"118197","DOI":"10.1016\/j.apenergy.2021.118197","article-title":"A combined deep learning load forecasting model of single household resident user considering multi-time scale electricity consumption behavior","volume":"307","author":"Yang","year":"2022","journal-title":"Appl. Energy"},{"key":"ref30","doi-asserted-by":"publisher","first-page":"1951","DOI":"10.1109\/TFUZZ.2023.3338565","article-title":"Fuzzy-based deep attributed graph clustering","volume":"32","author":"Yang","year":"2023","journal-title":"IEEE Trans. Fuzzy Syst."},{"key":"ref31","doi-asserted-by":"publisher","first-page":"116328","DOI":"10.1016\/j.apenergy.2020.116328","article-title":"Multi-temporal-spatial-scale temporal convolution network for short-term load forecasting of power systems","volume":"283","author":"Yin","year":"2021","journal-title":"Appl. Energy"},{"key":"ref32","doi-asserted-by":"publisher","first-page":"882","DOI":"10.1016\/j.apenergy.2019.05.102","article-title":"A Kalman filter-based bottom-up approach for household short-term load forecast","volume":"250","author":"Zheng","year":"2019","journal-title":"Appl. Energy"}],"container-title":["Frontiers in Neurorobotics"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnbot.2024.1461403\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,23]],"date-time":"2024-09-23T11:23:08Z","timestamp":1727090588000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnbot.2024.1461403\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,23]]},"references-count":32,"alternative-id":["10.3389\/fnbot.2024.1461403"],"URL":"https:\/\/doi.org\/10.3389\/fnbot.2024.1461403","relation":{},"ISSN":["1662-5218"],"issn-type":[{"value":"1662-5218","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,9,23]]},"article-number":"1461403"}}