{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,14]],"date-time":"2026-04-14T15:50:38Z","timestamp":1776181838832,"version":"3.50.1"},"reference-count":101,"publisher":"Institution of Engineering and Technology (IET)","issue":"1","license":[{"start":{"date-parts":[[2021,9,22]],"date-time":"2021-09-22T00:00:00Z","timestamp":1632268800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100013348","name":"Innosuisse - Schweizerische Agentur f\u00fcr Innovationsf\u00f6rderung","doi-asserted-by":"publisher","award":["1155002544"],"award-info":[{"award-number":["1155002544"]}],"id":[{"id":"10.13039\/501100013348","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["ietresearch.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["CAAI Trans on Intel Tech"],"published-print":{"date-parts":[[2022,3]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Management and efficient operations in critical infrastructures such as smart grids take huge advantage of accurate power load forecasting, which, due to its non\u2010linear nature, remains a challenging task. Recently, deep learning has emerged in the machine learning field achieving impressive performance in a vast range of tasks, from image classification to machine translation. Applications of deep learning models to the electric load forecasting problem are gaining interest among researchers as well as the industry, but a comprehensive and sound comparison among different\u2014also traditional\u2014architectures is not yet available in the literature. This work aims at filling the gap by reviewing and experimentally evaluating four real world datasets on the most recent trends in electric load forecasting, by contrasting deep learning architectures on short\u2010term forecast (one\u2010day\u2010ahead prediction). Specifically, the focus is on feedforward and recurrent neural networks, sequence\u2010to\u2010sequence models and temporal convolutional neural networks along with architectural variants, which are known in the signal processing community but are novel to the load forecasting one.<\/jats:p>","DOI":"10.1049\/cit2.12060","type":"journal-article","created":{"date-parts":[[2021,9,23]],"date-time":"2021-09-23T01:29:40Z","timestamp":1632360580000},"page":"1-25","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":216,"title":["Deep learning for time series forecasting: The electric load case"],"prefix":"10.1049","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3350-3168","authenticated-orcid":false,"given":"Alberto","family":"Gasparin","sequence":"first","affiliation":[{"name":"Faculty of Informatics Universit\u00e0 della Svizzera Italiana  Lugano Switzerland"}]},{"given":"Slobodan","family":"Lukovic","sequence":"additional","affiliation":[{"name":"Faculty of Informatics Universit\u00e0 della Svizzera Italiana  Lugano Switzerland"}]},{"given":"Cesare","family":"Alippi","sequence":"additional","affiliation":[{"name":"Faculty of Informatics Universit\u00e0 della Svizzera Italiana  Lugano Switzerland"},{"name":"Department of Electronics, Information, and Bioengineering Politecnico di Milano  Milan Italy"}]}],"member":"265","published-online":{"date-parts":[[2021,9,22]]},"reference":[{"key":"e_1_2_11_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/SURV.2011.101911.00087"},{"key":"e_1_2_11_3_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.aej.2011.01.015"},{"key":"e_1_2_11_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/59.910780"},{"key":"e_1_2_11_5_1","doi-asserted-by":"publisher","DOI":"10.1016\/0378-7796(95)00977-1"},{"key":"e_1_2_11_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRS.2003.811010"},{"key":"e_1_2_11_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRS.1987.4335210"},{"key":"e_1_2_11_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRS.2005.846106"},{"key":"e_1_2_11_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/PICA.1995.515202"},{"key":"e_1_2_11_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/1878431.1878435"},{"key":"e_1_2_11_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/59.141695"},{"key":"e_1_2_11_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/59.76685"},{"key":"e_1_2_11_13_1","doi-asserted-by":"publisher","DOI":"10.1016\/0378-7796(94)90037-X"},{"key":"e_1_2_11_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/59.780894"},{"key":"e_1_2_11_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2018.2844307"},{"key":"e_1_2_11_16_1","doi-asserted-by":"publisher","DOI":"10.3390\/en11010213"},{"key":"e_1_2_11_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISIE.2017.8001465"},{"key":"e_1_2_11_18_1","first-page":"351","volume-title":"2010 International Conference on Advances in Recent Technologies in Communication and Computing","author":"Nayaka S.","year":"2010"},{"key":"e_1_2_11_19_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-70338-1"},{"key":"e_1_2_11_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2015.2485943"},{"key":"e_1_2_11_21_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.segan.2016.02.005"},{"key":"e_1_2_11_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CISS.2017.7926112"},{"key":"e_1_2_11_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2017.2753802"},{"key":"e_1_2_11_24_1","doi-asserted-by":"publisher","DOI":"10.3390\/en11071636"},{"key":"e_1_2_11_25_1","doi-asserted-by":"publisher","DOI":"10.3390\/en11051138"},{"key":"e_1_2_11_26_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2017.11.374"},{"key":"e_1_2_11_27_1","doi-asserted-by":"publisher","DOI":"10.3390\/en11123493"},{"key":"e_1_2_11_28_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijforecast.2013.07.001"},{"key":"e_1_2_11_29_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.egypro.2011.12.895"},{"key":"e_1_2_11_30_1","unstructured":"Dheeru D. Karra Taniskidou E.: UCI machine learning repository.http:\/\/archive.ics.uci.edu\/ml(2017). Accessed 15 Sept2021"},{"key":"e_1_2_11_31_1","unstructured":"Smart grid smart city Australian govern Australia Canberray.http:\/\/www.industry.gov.au\/ENERGY\/PROGRAMMES\/SMARTGRIDSMARTCITY\/Pages\/default.aspx. Accessed 15 Sept 2021"},{"key":"e_1_2_11_32_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-69179-4_51"},{"key":"e_1_2_11_33_1","unstructured":"Umass smart dataset. (2017).http:\/\/traces.cs.umass.edu\/index.php\/Smart\/Smart. Accessed 15 Sept 2021"},{"key":"e_1_2_11_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/IECON.2016.7793413"},{"key":"e_1_2_11_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/INDIN.2018.8471953"},{"key":"e_1_2_11_36_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijforecast.2016.02.001"},{"key":"e_1_2_11_37_1","doi-asserted-by":"publisher","DOI":"10.3390\/en14061596"},{"key":"e_1_2_11_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICIOT.2019.00029"},{"key":"e_1_2_11_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2975738"},{"key":"e_1_2_11_40_1","doi-asserted-by":"publisher","DOI":"10.3390\/en14092524"},{"key":"e_1_2_11_41_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.03.011"},{"key":"e_1_2_11_42_1","unstructured":"Trindade A.: ElectricityLoadDiagrams20112014 data set.https:\/\/archive.ics.uci.edu\/ml\/datasets\/ElectricityLoadDiagrams20112014#(2015). Accessed 15 Sept 2021"},{"key":"e_1_2_11_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA.2017.0-110"},{"key":"e_1_2_11_44_1","unstructured":"Cs\u00e1ji B.C.:Approximation with artificial neural networks. Faculty of Sciences vol. 24 p. 7. Etvs Lornd University Hungary (2001)"},{"key":"e_1_2_11_45_1","unstructured":"Hinton G. Srivastava N. Swersky K.:Neural networks for machine learning.https:\/\/www.cs.toronto.edu\/~tijmen\/csc321\/slides\/lecture_slides_lec6.pdf. Accessed 15 Sept 2021"},{"key":"e_1_2_11_46_1","unstructured":"Zeiler M.D.: Adadelta: an adaptive learning rate method. vol.1212 pp.\u00a012. (2012)"},{"key":"e_1_2_11_47_1","volume-title":"3rd International Conference on Learning Representations, ICLR 2015","author":"Kingma D.P.","year":"2015"},{"key":"e_1_2_11_48_1","first-page":"8","article-title":"Weather sensitive short\u2010term load forecasting using nonfully connected artificial neural network","volume":"3","author":"Chen S.","year":"1992","journal-title":"IEEE Trans. Power Syst"},{"key":"e_1_2_11_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_2_11_50_1","doi-asserted-by":"publisher","DOI":"10.1207\/s15516709cog1402_1"},{"key":"e_1_2_11_51_1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"e_1_2_11_52_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"e_1_2_11_53_1","doi-asserted-by":"crossref","unstructured":"Werbos P.J.: Backpropagation through time: what it does and how to do it. In: Proceedings of the IEEE. vol. 78 pp.1550\u20131560(1990).http:\/\/doi.org\/10.1109\/5.58337","DOI":"10.1109\/5.58337"},{"key":"e_1_2_11_54_1","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/5236.001.0001"},{"key":"e_1_2_11_55_1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1990.2.4.490"},{"key":"e_1_2_11_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/72.279181"},{"key":"e_1_2_11_57_1","first-page":"1310","volume-title":"Proceedings of the 30th International Conference on International Conference on Machine Learning \u2013 vol. 28","author":"Pascanu R.","year":"2013"},{"key":"e_1_2_11_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2582924"},{"key":"e_1_2_11_59_1","unstructured":"Chung J. et\u00a0al.: Empirical evaluation of gated recurrent neural networks on sequence modeling.CoRR vol. abs\/1412.3555 (2014)"},{"key":"e_1_2_11_60_1","unstructured":"Yin W. et\u00a0al.: Comparative study of cnn and rnn for natural language processing.arXiv preprint arXiv:1702.01923(2017)"},{"key":"e_1_2_11_61_1","volume-title":"Proceedings of the Second International Conference on Learning Representations (ICLR 2014)","author":"Pascanu R.","year":"2014"},{"key":"e_1_2_11_62_1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1992.4.2.234"},{"key":"e_1_2_11_63_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"e_1_2_11_64_1","first-page":"190","volume-title":"Advances in Neural Information Processing Systems 26","author":"Hermans M.","year":"2013"},{"key":"e_1_2_11_65_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2012.01.039"},{"key":"e_1_2_11_66_1","first-page":"143","volume-title":"European Symposium on Artificial Neural Networks","author":"Sorjamaa A.","year":"2006"},{"key":"e_1_2_11_67_1","volume-title":"Proceedings of the 2nd European Symposium on Time Series Prediction (TSP) ESTSP08","author":"Bontempi G.","year":"2008"},{"key":"e_1_2_11_68_1","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2009.5178802"},{"key":"e_1_2_11_69_1","first-page":"3104","volume-title":"Advances in Neural Information Processing Systems 27: Annual Conference on Neural Information Processing Systems 2014","author":"Sutskever I.","year":"2014"},{"key":"e_1_2_11_70_1","unstructured":"Bahdanau D. Cho K. Bengio Y.: Neural machine translation by\u00a0jointly\u00a0learning to align and translate.CoRR vol. abs\/1409.0473 (2014)"},{"key":"e_1_2_11_71_1","unstructured":"Wu Y. et al.: Google's neural machine translation system: Bridging the gap between human and machine translation arXiv preprint arXiv:1609.08144 (2016)"},{"key":"e_1_2_11_72_1","first-page":"577","volume-title":"Advances in Neural Information Processing Systems 28","author":"Chorowski J.K.","year":"2015"},{"key":"e_1_2_11_73_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472618"},{"key":"e_1_2_11_74_1","first-page":"2048","volume-title":"Proceedings of the 32nd International Conference on Machine Learning","author":"Xu K.","year":"2015"},{"key":"e_1_2_11_75_1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1989.1.2.270"},{"key":"e_1_2_11_76_1","volume-title":"4th International Conference on Learning Representations, ICLR 2016","author":"Ranzato M.","year":"2016"},{"key":"e_1_2_11_77_1","first-page":"1171","volume-title":"Proceedings of the 28th International Conference on Neural Information Processing Systems \u2013 vol. 1","author":"Bengio S.","year":"2015"},{"key":"e_1_2_11_78_1","volume-title":"NIPS","author":"Lamb A.","year":"2016"},{"issue":"7","key":"e_1_2_11_79_1","first-page":"2469","article-title":"Deep reinforcement learning for sequence\u2010to\u2010sequence models","volume":"31","author":"Keneshloo Y.","year":"2020","journal-title":"IEEE Trans. Neural Network. Learn. Syst"},{"key":"e_1_2_11_80_1","doi-asserted-by":"crossref","unstructured":"Wilms H. Cupelli M. Monti A.: Combining auto\u2010regression with exogenous variables in sequence\u2010to\u2010sequence recurrent neural networks for short\u2010term load forecasting. In: 2018 IEEE 16th International Conference on Industrial Informatics (INDIN) pp.673\u2010679.https:\/\/doi.org\/10.1109\/INDIN.2018.8471953","DOI":"10.1109\/INDIN.2018.8471953"},{"key":"e_1_2_11_81_1","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"e_1_2_11_82_1","first-page":"1097","volume-title":"Advances in Neural Information Processing Systems 25","author":"Krizhevsky A.","year":"2012"},{"key":"e_1_2_11_83_1","volume-title":"3rd International Conference on Learning Representations, ICLR 2015","author":"Simonyan K.","year":"2015"},{"key":"e_1_2_11_84_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"e_1_2_11_85_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"e_1_2_11_86_1","first-page":"91","volume-title":"Advances in Neural Information Processing Systems","author":"Ren S.","year":"2015"},{"key":"e_1_2_11_87_1","first-page":"2017","volume-title":"Advances in Neural Information Processing Systems","author":"Jaderberg M.","year":"2015"},{"key":"e_1_2_11_88_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.581"},{"key":"e_1_2_11_89_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.19"},{"key":"e_1_2_11_90_1","volume-title":"A generative model for raw audio. Arxiv","author":"den Oord A.","year":"2016"},{"key":"e_1_2_11_91_1","first-page":"1243","volume-title":"Proceedings of the 34th International Conference on Machine Learning","author":"Gehring J.","year":"2017"},{"key":"e_1_2_11_92_1","first-page":"729","volume-title":"Lecture Notes in Computer Science\/Lecture Notes in Artificial Intelligence","author":"Borovykh A.","year":"2017"},{"key":"e_1_2_11_93_1","unstructured":"Dumoulin V. Visin F.: A guide to convolution arithmetic for deep learning.CoRR vol. abs\/160307285. (2016).http:\/\/arxiv.org\/abs\/1603.07285"},{"key":"e_1_2_11_94_1","unstructured":"Bai S. Kolter J.Z. Koltun V.: An empirical evaluation of generic convolutional and recurrent networks for sequence modeling. arXiv preprint arXiv:1803.01271 (2018)"},{"key":"e_1_2_11_95_1","unstructured":"Chollet F. et\u00a0al.: Keras. (2015).https:\/\/github.com\/fchollet\/keras"},{"key":"e_1_2_11_96_1","unstructured":"Abadi M. et\u00a0al.: TensorFlow: large\u2010scale machine learning on heterogeneous systems. Software available from tensorflow.org. (2015).https:\/\/www.tensorflow.org\/"},{"key":"e_1_2_11_97_1","unstructured":"Commission for Energy Regulation (CER). Cer smart metering project \u2010 electricity customer behaviour trial 2009\u20102010. 1st edn. Irish Social Science Data Archive. SN: 0012\u201000. (2012).https:\/\/www.ucd.ie\/issda\/data\/commissionforenergyregulationcer\/"},{"key":"e_1_2_11_98_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-45528-0"},{"key":"e_1_2_11_99_1","unstructured":"Li S. et\u00a0al.: Demystifying Resnet.arXiv preprint arXiv:1611.01186(2016)"},{"key":"e_1_2_11_100_1","unstructured":"Ioffe S. Szegedy C.: Batch normalization: accelerating deep network training by reducing internal covariate shift pp.448\u2013456. (2015).http:\/\/jmlr.org\/proceedings\/papers\/v37\/ioffe15.pdf"},{"key":"e_1_2_11_101_1","doi-asserted-by":"publisher","DOI":"10.1109\/SE4SG.2013.6596108"},{"key":"e_1_2_11_102_1","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN48605.2020.9207503"}],"container-title":["CAAI Transactions on Intelligence Technology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1049\/cit2.12060","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1049\/cit2.12060","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/pdf\/10.1049\/cit2.12060","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,27]],"date-time":"2025-10-27T09:24:12Z","timestamp":1761557052000},"score":1,"resource":{"primary":{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/10.1049\/cit2.12060"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,9,22]]},"references-count":101,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2022,3]]}},"alternative-id":["10.1049\/cit2.12060"],"URL":"https:\/\/doi.org\/10.1049\/cit2.12060","archive":["Portico"],"relation":{},"ISSN":["2468-6557","2468-2322"],"issn-type":[{"value":"2468-6557","type":"print"},{"value":"2468-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,9,22]]},"assertion":[{"value":"2020-12-28","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-07-05","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-09-22","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}