{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T16:41:40Z","timestamp":1778604100518,"version":"3.51.4"},"reference-count":77,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2025.3527863","type":"journal-article","created":{"date-parts":[[2025,1,9]],"date-time":"2025-01-09T19:59:15Z","timestamp":1736452755000},"page":"15090-15157","source":"Crossref","is-referenced-by-count":4,"title":["A Novel Approach to Faster Convergence and Improved Accuracy in Deep Learning-Based Electrical Energy Consumption Forecast Models for Large Consumer Groups"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7379-5364","authenticated-orcid":false,"given":"A. Jayanth","family":"Balaji","sequence":"first","affiliation":[{"name":"Department of Electronics and Communication Engineering, Amrita School of Engineering, Amrita Vishwa Vidyapeetham, Coimbatore, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9213-8319","authenticated-orcid":false,"given":"Binoy B.","family":"Nair","sequence":"additional","affiliation":[{"name":"Department of Electronics and Communication Engineering, Amrita School of Engineering, Amrita Vishwa Vidyapeetham, Coimbatore, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6743-2076","authenticated-orcid":false,"given":"D. S. Harish","family":"Ram","sequence":"additional","affiliation":[{"name":"Department of Electronics and Communication Engineering, Amrita School of Engineering, Amrita Vishwa Vidyapeetham, Coimbatore, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-8974-3641","authenticated-orcid":false,"given":"Kuruvachan Kalluvelil","family":"George","sequence":"additional","affiliation":[{"name":"NCS Pte Ltd. (Singtel Group), Ang Mo Kio, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/SURV.2011.101911.00087"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.asej.2020.05.004"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2011.2166794"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.rser.2023.113405"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.3389\/fenrg.2022.959786"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.egyr.2024.05.071"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3374209"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/PES.2008.4596961"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-33389-2_16"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-57264-2_26"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.3233\/JIFS-169965"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICITIIT57246.2023.10068706"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2016.06.052"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/2623330.2623612"},{"key":"ref15","article-title":"Don\u2019t decay the learning rate, increase the batch size","author":"Smith","year":"2017","journal-title":"arXiv:1711.00489"},{"key":"ref16","article-title":"Revisiting small batch training for deep neural networks","author":"Masters","year":"2018","journal-title":"arXiv:1804.07612"},{"key":"ref17","article-title":"AdaBatch: Adaptive batch sizes for training deep neural networks","author":"Devarakonda","year":"2017","journal-title":"arXiv:1712.02029"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevA.33.1134"},{"key":"ref19","volume-title":"CER Smart Metering Project\u2014Electricity Customer Behaviour Trial, Pp. 2009\u20132010 [dataset]. 1st Edition. Irish Social Science Data Archive. SN: 0012\u201300","author":"Avanashilingam","year":"2012"},{"key":"ref20","volume-title":"Real-Time Actual Load","year":"2023"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1111\/j.2517-6161.1969.tb00775.x"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/0304-4076(92)90104-Y"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2020.106825"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2011.2160459"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.3390\/en12010161"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/1941\/1\/012069"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.jhydrol.2021.126800"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-37963-5_53"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2934110"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2018.10.340"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-99-5166-6_36"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ETCM53643.2021.9590681"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21595\/jve.2022.22271"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/INDICON45594.2018.8987125"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-16-2422-3_34"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-35289-8_26"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.physd.2019.132306"},{"key":"ref39","volume-title":"Understanding LSTM Networks\u2014Colah\u2019s Blog","year":"2024"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1406.1078"},{"key":"ref41","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","author":"Chung","year":"2014","journal-title":"arXiv:1412.3555"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/AiDAS53897.2021.9574312"},{"key":"ref43","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"},{"key":"ref44","volume-title":"Tf.keras.optimizers.Adam | TensorFlow V2.16.1","year":"2024"},{"key":"ref45","article-title":"On large-batch training for deep learning: Generalization gap and sharp minima","author":"Shirish Keskar","year":"2016","journal-title":"arXiv:1609.04836"},{"key":"ref46","article-title":"Large batch optimization for deep learning: Training BERT in 76 minutes","author":"You","year":"2019","journal-title":"arXiv:1904.00962"},{"key":"ref47","article-title":"Stagewise enlargement of batch size for SGD-based learning","author":"Zhao","year":"2020","journal-title":"arXiv:2002.11601"},{"key":"ref48","article-title":"The limit of the batch size","author":"You","year":"2020","journal-title":"arXiv:2006.08517"},{"key":"ref49","article-title":"Pipelined backpropagation at scale: Training large models without batches","author":"Kosson","year":"2020","journal-title":"arXiv:2003.11666"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1016\/0925-2312(93)90006-o"},{"key":"ref52","article-title":"AdaBelief optimizer: Adapting stepsizes by the belief in observed gradients","author":"Zhuang","year":"2020","journal-title":"arXiv:2010.07468"},{"key":"ref53","article-title":"ADADELTA: An adaptive learning rate method","author":"Zeiler","year":"2012","journal-title":"arXiv:1212.5701"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1137\/0111030"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1137\/1019005"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.6028\/jres.049.044"},{"key":"ref57","first-page":"2342","article-title":"An empirical exploration of recurrent network architectures","volume-title":"Proc. 32nd Int. Conf. Mach. Learn.","volume":"37","author":"Jozefowicz"},{"issue":"1","key":"ref58","first-page":"305","article-title":"Ian goodfellow, Yoshua Bengio, and Aaron Courville: Deep learning","volume":"19","author":"Goodfellow","year":"2017","journal-title":"Genetic Program. Evolvable Mach."},{"key":"ref59","article-title":"On the training dynamics of deep networks with L2 regularization","author":"Lewkowycz","year":"2020","journal-title":"arXiv:2006.08643"},{"key":"ref60","article-title":"Adaptive low-rank regularization with damping sequences to restrict lazy weights in deep networks","author":"Bejani","year":"2021","journal-title":"arXiv:2106.09677"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1145\/1015330.1015435"},{"issue":"3","key":"ref62","first-page":"543","article-title":"A method for unconstrained convex minimization problem with the rate of convergence O(1\/k2)","volume":"269","author":"Ito","year":"1983","journal-title":"Dokl. Akad. Nauk. SSSR"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1038\/323533a0"},{"key":"ref64","article-title":"An overview of gradient descent optimization algorithms","author":"Ruder","year":"2016","journal-title":"arXiv:1609.04747"},{"key":"ref65","first-page":"2121","article-title":"Adaptive subgradient methods for online learning and stochastic optimization","volume":"12","author":"Duchi","year":"2011","journal-title":"J. Mach. Learn. Res."},{"key":"ref66","article-title":"Descending through a crowded valley\u2013benchmarking deep learning optimizers","author":"Schmidt","year":"2020","journal-title":"arXiv:2007.01547"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1145\/3474124.3474167"},{"key":"ref68","article-title":"LRTuner: A learning rate tuner for deep neural networks","author":"Iyer","year":"2021","journal-title":"arXiv:2105.14526"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/bigdata47090.2019.9006104"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2023.07.043"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/iccad51958.2021.9643567"},{"key":"ref72","article-title":"Reconciling modern deep learning with traditional optimization analyses: The intrinsic learning rate","author":"Li","year":"2020","journal-title":"arXiv:2010.02916"},{"key":"ref73","article-title":"Improving generalization and convergence by enhancing implicit regularization","author":"Wang","year":"2024","journal-title":"arXiv:2405.20763"},{"issue":"8","key":"ref74","first-page":"2","article-title":"Neural networks for machine learning lecture 6a overview of mini\u2013batch gradient descent","volume":"14","author":"Hinton","year":"2012","journal-title":"Cited"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.4271\/2024-26-0484"},{"key":"ref76","volume-title":"Fundamental Research Statistics for the Behavioral Sciences","author":"Roscoe","year":"1975"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1016\/j.jneumeth.2012.08.016"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/10835081.pdf?arnumber=10835081","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,28]],"date-time":"2025-01-28T18:46:25Z","timestamp":1738089985000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10835081\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":77,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3527863","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}