{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T16:22:23Z","timestamp":1774369343496,"version":"3.50.1"},"reference-count":43,"publisher":"SAGE Publications","issue":"5","license":[{"start":{"date-parts":[[2021,4,12]],"date-time":"2021-04-12T00:00:00Z","timestamp":1618185600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/journals.sagepub.com\/page\/policies\/text-and-data-mining-license"}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":["Journal of Intelligent &amp; Fuzzy Systems"],"published-print":{"date-parts":[[2021,11,17]]},"abstract":"<jats:p>Short-term electricity load forecasting (STLF) plays a key role in operating the power system of a nation. A challenging problem in STLF is to deal with real-time data. This paper aims to address the problem using a hybrid online model. Online learning methods are becoming essential in STLF because load data often show complex seasonality (daily, weekly, annual) and changing patterns. Online models such as Online AutoRegressive Integrated Moving Average (Online ARIMA) and Online Recurrent neural network (Online RNN) can modify their parameters on the fly to adapt to the changes of real-time data. However, Online RNN alone cannot handle seasonality directly and ARIMA can only handle a single seasonal pattern (Seasonal ARIMA). In this study, we propose a hybrid online model that combines Online ARIMA, Online RNN, and Multi-seasonal decomposition to forecast real-time time series with multiple seasonal patterns. First, we decompose the original time series into three components: trend, seasonality, and residual. The seasonal patterns are modeled using Fourier series. This approach is flexible, allowing us to incorporate multiple periods. For trend and residual components, we employ Online ARIMA and Online RNN respectively to obtain the predictions. We use hourly load data of Vietnam and daily load data of Australia as case studies to verify our proposed model. The experimental results show that our model has better performance than single online models. The proposed model is robust and can be applied in many other fields with real-time time series.<\/jats:p>","DOI":"10.3233\/jifs-189884","type":"journal-article","created":{"date-parts":[[2021,4,13]],"date-time":"2021-04-13T22:10:39Z","timestamp":1618351839000},"page":"5639-5652","update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":16,"title":["Hybrid online model based multi seasonal decompose for short-term electricity load forecasting using ARIMA and online RNN"],"prefix":"10.1177","volume":"41","author":[{"given":"Nguyen Quang","family":"Dat","sequence":"first","affiliation":[{"name":"School of Applied Mathematics and Informatics, HUST, Hanoi, Vietnam"}]},{"given":"Nguyen Thi","family":"Ngoc Anh","sequence":"additional","affiliation":[{"name":"School of Applied Mathematics and Informatics, HUST, Hanoi, Vietnam"}]},{"given":"Nguyen","family":"Nhat Anh","sequence":"additional","affiliation":[{"name":"CMC Corporation, Hanoi, Vietnam"}]},{"given":"Vijender Kumar","family":"Solanki","sequence":"additional","affiliation":[{"name":"Department of Computer Science &amp; Engineering CMR Institute of Technology, Hyderabad, India"}]}],"member":"179","published-online":{"date-parts":[[2021,4,12]]},"reference":[{"key":"e_1_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.energy.2018.10.076"},{"key":"e_1_3_2_3_2","first-page":"2922","article-title":"Short-term load forecasts using lstm networks","volume":"158","author":"Muzaffar S.","year":"2019","unstructured":"MuzaffarS., AfshariA., Short-term load forecasts using lstm networks, Innovative Solutions for Energy Transitions158 (2019), 2922\u20132927.","journal-title":"Innovative Solutions for Energy Transitions"},{"key":"e_1_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2015.01.122"},{"key":"e_1_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2018.09.082"},{"key":"e_1_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.energy.2014.06.104"},{"key":"e_1_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2016.06.133"},{"key":"e_1_3_2_8_2","first-page":"399","article-title":"Modelling and forecasting of rainfall time series using sarima","volume":"33","author":"Milenkovi\u0107 M.","year":"2018","unstructured":"Milenkovi\u0107M., \u0160vadlenkaL., MelicharV., Bojovi\u0107N. and Avramovi\u0107Z., Modelling and forecasting of rainfall time series using sarima, Transport33 (2018), 399\u2013419.","journal-title":"Transport"},{"key":"e_1_3_2_9_2","first-page":"399","article-title":"Modelling and forecasting of rainfall time series using sarima, Environ","volume":"4","author":"P. D.P.","year":"2017","unstructured":"P.D.P., Z.M.M., Modelling and forecasting of rainfall time series using sarima, Environ, Process4 (2017), 399\u2013419.","journal-title":"Process"},{"key":"e_1_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.tre.2018.12.005"},{"key":"e_1_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1016\/S0925-2312(01)00702-0"},{"key":"e_1_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2014.05.028"},{"key":"e_1_3_2_13_2","first-page":"63","article-title":"Arima-wnn hybrid model for forecasting wheat yield time-series data","volume":"70","author":"Ray M.","year":"2016","unstructured":"RayM., RaiA., SinghR.V.K., Arima-wnn hybrid model for forecasting wheat yield time-series data, Journal of the Indian Society of Agricultural Statistics70 (2016), 63\u201370.","journal-title":"Journal of the Indian Society of Agricultural Statistics"},{"key":"e_1_3_2_14_2","first-page":"369","article-title":"A novel hybrid approach for time series data forecasting using moving average filter and arima-svm, Emerging Technologies in Data Mining and Information Security","volume":"183","author":"Aradhye G.","year":"2018","unstructured":"AradhyeG., RaoA.C.S., MohammedM.D.M., A novel hybrid approach for time series data forecasting using moving average filter and arima-svm, Emerging Technologies in Data Mining and Information Security, Advances in Intelligent Systems and Computing183 (2018), 369\u2013381.","journal-title":"Advances in Intelligent Systems and Computing"},{"key":"e_1_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2018.10.009"},{"key":"e_1_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.renene.2019.01.031"},{"key":"e_1_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"e_1_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1162\/089976600300015015"},{"key":"e_1_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2015.06.092"},{"key":"e_1_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-018-1163-9"},{"key":"e_1_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.energy.2018.05.052"},{"key":"e_1_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.renene.2016.02.003"},{"issue":"13","key":"e_1_3_2_23_2","first-page":"2342","article-title":"Time series prediction with recurrent neural networks trained by a hybrid pso\u2013ea algorithm","volume":"70","author":"Cai X.","year":"2007","unstructured":"CaiX., ZhangN., VenayagamoorthyG.K., WunschD.C., Time series prediction with recurrent neural networks trained by a hybrid pso\u2013ea algorithm, Neurocomputing selected papers from the 3rd International Conference on Development and Learning (ICDL 2004) Time series prediction competition: the CATS benchmark70(13) (2007), 2342\u20132353.","journal-title":"Neurocomputing selected papers from the 3rd International Conference on Development and Learning (ICDL 2004) Time series prediction competition: the CATS benchmark"},{"issue":"11","key":"e_1_3_2_24_2","first-page":"1936","article-title":"Som time series clustering and prediction with recurrent neural networks","volume":"74","author":"Cherif A.","year":"2011","unstructured":"CherifA., CardotH., Bon\u00e9R., Som time series clustering and prediction with recurrent neural networks, Neurocomputing adaptive Incremental Learning in Neural Networks Learning Algorithm and Mathematic Modelling Selected papers from the International Conference on Neural Information Processing 2009 (ICONIP 2009)74(11) (2011), 1936\u20131944.","journal-title":"Neurocomputing adaptive Incremental Learning in Neural Networks Learning Algorithm and Mathematic Modelling Selected papers from the International Conference on Neural Information Processing 2009 (ICONIP 2009)"},{"key":"e_1_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2012.01.014"},{"key":"e_1_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2014.05.062"},{"key":"e_1_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2015.2404823"},{"key":"e_1_3_2_28_2","article-title":"Wavelet-artificial neural network model for water level forecasting","author":"Anh N.T.N.","year":"2018","unstructured":"AnhN.T.N., DatN.Q., VanN.T., DoanhN.N., AnN.L., Wavelet-artificial neural network model for water level forecasting, 2018 International Conference on Research in Intelligent and Computing in Engineering (RICE) (2018).","journal-title":"2018 International Conference on Research in Intelligent and Computing in Engineering (RICE)"},{"issue":"03","key":"e_1_3_2_29_2","article-title":"Prediction of water level using time series, wavelet and neural network approaches","volume":"10","author":"Anh N.T.N.","year":"2020","unstructured":"AnhN.T.N., DatN.Q., SolankiV.K., AnN.L., Prediction of water level using time series, wavelet and neural network approaches, International Journal of Information Retrieval Research, IGI-Global (03) 10 (2020).","journal-title":"International Journal of Information Retrieval Research, IGI-Global"},{"key":"e_1_3_2_30_2","article-title":"Online arima algorithms for time series prediction","author":"Liu C.","year":"2016","unstructured":"LiuC., HoiS.C., ZhaoP., SunJ., Online arima algorithms for time series prediction, Thirtieth AAAI Conference on Artificial Intelligence (2016).","journal-title":"Thirtieth AAAI Conference on Artificial Intelligence"},{"key":"e_1_3_2_31_2","first-page":"1","article-title":"Renewable energy management in cellular networks: An online strategy based on arima forecasting and a markov chain model","author":"Leithon J.","year":"2016","unstructured":"LeithonJ., LimT.J., SunS., Renewable energy management in cellular networks: An online strategy based on arima forecasting and a markov chain model, 2016 IEEE Wireless Communications and Networking Conference (2016), 1\u20136.","journal-title":"2016 IEEE Wireless Communications and Networking Conference"},{"key":"e_1_3_2_32_2","article-title":"Spiral recurrent neural network for online learning","author":"Gao H.","year":"2007","unstructured":"GaoH., SollacherR., KriegelH.-P., Spiral recurrent neural network for online learning, ESANN\u20192007 proceedings (2007).","journal-title":"ESANN\u20192007 proceedings"},{"key":"e_1_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939759"},{"key":"e_1_3_2_34_2","first-page":"816","article-title":"Robust online time series prediction with recurrent neural networks","author":"Guo T.","year":"2016","unstructured":"GuoT., XuZ., YaoX., ChenH., AbererK., FunayaK., Robust online time series prediction with recurrent neural networks, 2016 IEEE International Conference on Data Science and Advanced Analytics (2016), 816\u2013825.","journal-title":"2016 IEEE International Conference on Data Science and Advanced Analytics"},{"key":"e_1_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.1162\/neco_a_01228"},{"key":"e_1_3_2_36_2","article-title":"Time series analysis, forecasting and control","author":"Box G.","year":"1970","unstructured":"BoxG., JenkinsG., Time series analysis, forecasting and control, Holden-Day, San Francisco, CA (1970).","journal-title":"Holden-Day, San Francisco"},{"key":"e_1_3_2_37_2","article-title":"Online learning for time series prediction","volume":"2013","author":"Anava O.","year":"2013","unstructured":"AnavaO., HazanE., MannorS., ShamirO., Online learning for time series prediction, JMLR: Workshop and Conference Proceedings2013 (2013).","journal-title":"JMLR: Workshop and Conference Proceedings"},{"key":"e_1_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-007-5016-8"},{"key":"e_1_3_2_39_2","doi-asserted-by":"crossref","unstructured":"HazanE. KalaiA. KaleS. AgarwalA. Logarithmic regret algorithms for online convex optimization (2006) 499\u2013513.","DOI":"10.1007\/11776420_37"},{"key":"e_1_3_2_40_2","unstructured":"PascanuR. MikolovT. BengioY. On the difficulty of training recurrent neural networks (2013) 1310\u20131318."},{"key":"e_1_3_2_41_2","doi-asserted-by":"publisher","DOI":"10.1109\/72.737503"},{"key":"e_1_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.1109\/THMS.2016.2634921"},{"key":"e_1_3_2_43_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.agrformet.2019.107796"},{"key":"e_1_3_2_44_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2017.06.035"}],"container-title":["Journal of Intelligent &amp; Fuzzy Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.3233\/JIFS-189884","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.3233\/JIFS-189884","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.3233\/JIFS-189884","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,2]],"date-time":"2026-02-02T04:25:26Z","timestamp":1770006326000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.3233\/JIFS-189884"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,4,12]]},"references-count":43,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2021,11,17]]}},"alternative-id":["10.3233\/JIFS-189884"],"URL":"https:\/\/doi.org\/10.3233\/jifs-189884","relation":{},"ISSN":["1064-1246","1875-8967"],"issn-type":[{"value":"1064-1246","type":"print"},{"value":"1875-8967","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,4,12]]}}}