{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,2]],"date-time":"2026-05-02T07:17:47Z","timestamp":1777706267328,"version":"3.51.4"},"reference-count":44,"publisher":"SAGE Publications","issue":"3","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IFS"],"published-print":{"date-parts":[[2022,7,21]]},"abstract":"<jats:p>The coronavirus disease 2019 pandemic has significantly impacted the world. The sudden decline in electricity load demand caused by strict social distancing restrictions has made it difficult for traditional models to forecast the load demand during the pandemic. Therefore, in this study, a novel transfer deep learning model with reinforcement-learning-based hyperparameter optimization is proposed for short-term load forecasting during the pandemic. First, a knowledge base containing mobility data is constructed, which can reflect the changes in visitor volume in different regions and buildings based on mobile services. Therefore, the sudden decline in load can be analyzed according to the socioeconomic behavior changes during the pandemic. Furthermore, a new transfer deep learning model is proposed to address the problem of limited mobility data associated with the pandemic. Moreover, reinforcement learning is employed to optimize the hyperparameters of the proposed model automatically, which avoids the manual adjustment of the hyperparameters, thereby maximizing the forecasting accuracy. To enhance the hyperparameter optimization efficiency of the reinforcement-learning agents, a new advance forecasting method is proposed to forecast the state-action values of the state space that have not been traversed. The experimental results on 12 real-world datasets covering different countries and cities demonstrate that the proposed model achieves high forecasting accuracy during the coronavirus disease 2019 pandemic.<\/jats:p>","DOI":"10.3233\/jifs-213103","type":"journal-article","created":{"date-parts":[[2022,3,29]],"date-time":"2022-03-29T13:55:08Z","timestamp":1648562108000},"page":"2869-2882","source":"Crossref","is-referenced-by-count":2,"title":["A novel transfer deep learning model with reinforcement-learning-based hyperparameter optimization for short-term load forecasting during the COVID-19 pandemic"],"prefix":"10.1177","volume":"43","author":[{"given":"Shuai","family":"Zhang","sequence":"first","affiliation":[{"name":"School of Information Management and Artificial Intelligence, Zhejiang University of Finance and Economics, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qian","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Information Management and Artificial Intelligence, Zhejiang University of Finance and Economics, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenhua","family":"Zeng","sequence":"additional","affiliation":[{"name":"School of Electric Power Engineering, South China University of Technology, Guangzhou, China; Shenzhen Urban Public Safety and Technology Institute, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shanshan","family":"Guo","sequence":"additional","affiliation":[{"name":"Library, Zhejiang University of Finance and Economics, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiyuan","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Information Management and Artificial Intelligence, Zhejiang University of Finance and Economics, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"179","reference":[{"key":"10.3233\/JIFS-213103_ref1","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1016\/j.segan.2016.02.005","article-title":"Deep learning for estimating building energy consumption","volume":"6","author":"Mocanu","year":"2016","journal-title":"Sustainable Energy, Grids and Networks"},{"key":"10.3233\/JIFS-213103_ref2","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.eswa.2017.04.053","article-title":"Convolutional neural network approaches to granite tiles classification","volume":"84","author":"Ferreira","year":"2017","journal-title":"Expert Systems with Applications"},{"key":"10.3233\/JIFS-213103_ref3","doi-asserted-by":"crossref","first-page":"72","DOI":"10.1016\/j.energy.2019.05.230","article-title":"Predicting residential energy consumption using CNN-LSTM neural networks","volume":"182","author":"Kim","year":"2019","journal-title":"Energy"},{"key":"10.3233\/JIFS-213103_ref4","doi-asserted-by":"crossref","first-page":"427","DOI":"10.1016\/j.ins.2020.08.053","article-title":"A novel ensemble deep learning model with dynamic error correction and multi-objective ensemble pruning for time series forecasting","volume":"544","author":"Zhang","year":"2021","journal-title":"Information Sciences"},{"issue":"4","key":"10.3233\/JIFS-213103_ref5","doi-asserted-by":"crossref","first-page":"3943","DOI":"10.1109\/TSG.2018.2844307","article-title":"Short-term load forecasting with deep residual networks","volume":"10","author":"Chen","year":"2018","journal-title":"IEEE Transactions on Smart Grid"},{"issue":"7","key":"10.3233\/JIFS-213103_ref7","doi-asserted-by":"crossref","first-page":"647","DOI":"10.1038\/s41558-020-0797-x","article-title":"Temporary reduction in daily global CO2 emissions during the COVID-19 forced confinement","volume":"10","author":"Le Qu\u00e9r\u00e9","year":"2020","journal-title":"Nature Climate Change"},{"key":"10.3233\/JIFS-213103_ref8","doi-asserted-by":"crossref","first-page":"14","DOI":"10.1016\/j.knosys.2015.01.010","article-title":"Transfer learning using computational intelligence: A survey","volume":"80","author":"Lu","year":"2015","journal-title":"Knowledge-Based Systems"},{"key":"10.3233\/JIFS-213103_ref9","unstructured":"Sutton R.S. and Barto A.G. , Reinforcement Learning: An Introduction, Massachusetts: The MIT Press, (2018)."},{"issue":"4","key":"10.3233\/JIFS-213103_ref10","doi-asserted-by":"crossref","first-page":"3646","DOI":"10.1109\/TSG.2020.2972513","article-title":"Deep-based conditional probability density function forecasting of residential loads","volume":"11","author":"Afrasiabi","year":"2020","journal-title":"IEEE Transactions on Smart Grid"},{"key":"10.3233\/JIFS-213103_ref11","doi-asserted-by":"crossref","first-page":"182","DOI":"10.1016\/j.knosys.2018.01.015","article-title":"Ensemble incremental learning random vector functional link network for short-term electric load forecasting","volume":"145","author":"Qiu","year":"2018","journal-title":"Knowledge-Based Systems"},{"issue":"4","key":"10.3233\/JIFS-213103_ref12","doi-asserted-by":"crossref","first-page":"2261","DOI":"10.3233\/JIFS-171292","article-title":"A novel electric load consumption prediction and feature selection model based on modified clonal selection algorithm","volume":"34","author":"Avatefipour","year":"2018","journal-title":"Journal of Intelligent & Fuzzy Systems"},{"key":"10.3233\/JIFS-213103_ref13","doi-asserted-by":"crossref","first-page":"328","DOI":"10.1016\/j.enbuild.2019.04.034","article-title":"Recurrent inception convolution neural network for multi short-term load forecasting","volume":"194","author":"Kim","year":"2019","journal-title":"Energy and Buildings"},{"issue":"6","key":"10.3233\/JIFS-213103_ref14","doi-asserted-by":"crossref","first-page":"8219","DOI":"10.3233\/JIFS-190658","article-title":"Effective load forecasting for large power consuming industrial customers using long short-term memory recurrent neural networks","volume":"37","author":"Motepe","year":"2019","journal-title":"Journal of Intelligent & Fuzzy Systems"},{"key":"10.3233\/JIFS-213103_ref15","doi-asserted-by":"crossref","first-page":"115410","DOI":"10.1016\/j.apenergy.2020.115410","article-title":"Robust short-term electrical load forecasting framework for commercial buildings using deep recurrent neural networks","volume":"278","author":"Chitalia","year":"2020","journal-title":"Applied Energy"},{"issue":"1","key":"10.3233\/JIFS-213103_ref16","first-page":"73","article-title":"A hybrid RNN model for mid-to-long term electricity demand forecasting incorporating weather influences","volume":"69","author":"Peng","year":"2021","journal-title":"AT-Automatisierungstechnik"},{"issue":"2","key":"10.3233\/JIFS-213103_ref19","doi-asserted-by":"crossref","first-page":"163","DOI":"10.1080\/095400996116866","article-title":"A survey of transfer between connectionist networks","volume":"8","author":"Pratt","year":"1996","journal-title":"Connection Science"},{"key":"10.3233\/JIFS-213103_ref20","doi-asserted-by":"crossref","first-page":"74","DOI":"10.1016\/j.knosys.2018.05.021","article-title":"A novel transfer learning framework for time series forecasting","volume":"156","author":"Ye","year":"2018","journal-title":"Knowledge-Based Systems"},{"key":"10.3233\/JIFS-213103_ref21","unstructured":"Laptev N. , Yu J. and Rajagopal R. , Reconstruction and regression loss for time-series transfer learning, Special Interest Group on Knowledge Discovery and Data Mining (SIGKDD) and Workshop on the Mining and Learning from Time Series (MiLeTS), London, UK, (2018, August)."},{"key":"10.3233\/JIFS-213103_ref22","doi-asserted-by":"crossref","first-page":"352","DOI":"10.1016\/j.enbuild.2018.01.034","article-title":"Transfer learning with seasonal and trend adjustment for cross-building energy forecasting","volume":"165","author":"Ribeiro","year":"2018","journal-title":"Energy and Buildings"},{"issue":"3","key":"10.3233\/JIFS-213103_ref23","doi-asserted-by":"crossref","first-page":"1722","DOI":"10.1109\/TII.2019.2924326","article-title":"Two-layer transfer-learning-based architecture for short-term load forecasting","volume":"16","author":"Cai","year":"2019","journal-title":"IEEE Transactions on Industrial Informatics"},{"issue":"2","key":"10.3233\/JIFS-213103_ref24","doi-asserted-by":"crossref","first-page":"112","DOI":"10.1007\/s41666-019-00062-3","article-title":"Transfer learning for clinical time series analysis using deep neural networks","volume":"4","author":"Gupta","year":"2020","journal-title":"Journal of Healthcare Informatics Research"},{"issue":"16","key":"10.3233\/JIFS-213103_ref25","doi-asserted-by":"crossref","first-page":"6364","DOI":"10.3390\/su12166364","article-title":"Monthly electric load forecasting using transfer learning for smart cities","volume":"12","author":"Jung","year":"2020","journal-title":"Sustainability"},{"key":"10.3233\/JIFS-213103_ref26","doi-asserted-by":"crossref","first-page":"105622","DOI":"10.1016\/j.knosys.2020.105622","article-title":"Predicting concentration levels of air pollutants by transfer learning and recurrent neural network","volume":"192","author":"Fong","year":"2020","journal-title":"Knowledge-Based Systems"},{"key":"10.3233\/JIFS-213103_ref27","doi-asserted-by":"crossref","first-page":"15413","DOI":"10.1109\/ACCESS.2021.3053317","article-title":"Individualized short-term electric load forecasting with deep neural network based transfer learning and meta learning","volume":"9","author":"Lee","year":"2021","journal-title":"IEEE Access"},{"issue":"2","key":"10.3233\/JIFS-213103_ref28","doi-asserted-by":"crossref","first-page":"1377","DOI":"10.1109\/TSG.2019.2937338","article-title":"Reinforced deterministic and probabilistic load forecasting via Q-learning dynamic model selection","volume":"11","author":"Feng","year":"2019","journal-title":"IEEE Transactions on Smart Grid"},{"key":"10.3233\/JIFS-213103_ref29","doi-asserted-by":"crossref","first-page":"51185","DOI":"10.1109\/ACCESS.2019.2911235","article-title":"EmoWare: A context-aware framework for personalized video recommendation using affective video sequences","volume":"7","author":"Tripathi","year":"2019","journal-title":"IEEE Access"},{"key":"10.3233\/JIFS-213103_ref30","doi-asserted-by":"crossref","first-page":"110225","DOI":"10.1016\/j.enbuild.2020.110225","article-title":"Deep reinforcement learning to optimise indoor temperature control and heating energy consumption in buildings","volume":"224","author":"Brandi","year":"2020","journal-title":"Energy and Buildings"},{"key":"10.3233\/JIFS-213103_ref31","doi-asserted-by":"crossref","first-page":"815","DOI":"10.1016\/j.ins.2020.08.101","article-title":"A reinforcement learning approach for dynamic multi-objective optimization","volume":"546","author":"Zou","year":"2021","journal-title":"Information Sciences"},{"issue":"6","key":"10.3233\/JIFS-213103_ref32","doi-asserted-by":"crossref","first-page":"5407","DOI":"10.1109\/TSG.2020.3008730","article-title":"WECC composite load model parameter identification using evolutionary deep reinforcement learning","volume":"11","author":"Bu","year":"2020","journal-title":"IEEE Transactions on Smart Grid"},{"issue":"16","key":"10.3233\/JIFS-213103_ref33","doi-asserted-by":"crossref","first-page":"3171","DOI":"10.1049\/iet-gtd.2019.1468","article-title":"Research on parameter optimisation of dynamic priority scheduling algorithm based on improved reinforcement learning","volume":"14","author":"Meng","year":"2020","journal-title":"IET Generation, Transmission & Distribution"},{"issue":"9","key":"10.3233\/JIFS-213103_ref34","doi-asserted-by":"crossref","first-page":"2142","DOI":"10.1109\/TVLSI.2019.2919609","article-title":"Efficient modular adder designs based on thermometer and One-Hot coding","volume":"27","author":"Jafarzadehpour","year":"2019","journal-title":"IEEE Transactions on Very Large Scale Integration (VLSI) Systems"},{"issue":"10","key":"10.3233\/JIFS-213103_ref35","doi-asserted-by":"crossref","first-page":"1345","DOI":"10.1109\/TKDE.2009.191","article-title":"A survey on transfer learning","volume":"22","author":"Pan","year":"2009","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"10.3233\/JIFS-213103_ref36","doi-asserted-by":"crossref","first-page":"381","DOI":"10.1016\/j.neucom.2020.06.064","article-title":"Efficient hyperparameter optimization through model-based reinforcement learning","volume":"409","author":"Wu","year":"2020","journal-title":"Neurocomputing"},{"issue":"7","key":"10.3233\/JIFS-213103_ref37","doi-asserted-by":"crossref","first-page":"6402","DOI":"10.1109\/JIOT.2020.2974848","article-title":"A deep reinforcement learning based recommender system for occupant-driven energy optimization in commercial buildings","volume":"7","author":"Wei","year":"2020","journal-title":"IEEE Internet of Things Journal"},{"issue":"3-4","key":"10.3233\/JIFS-213103_ref38","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1007\/BF00992698","article-title":"Q-learning","volume":"8","author":"Watkins","year":"1992","journal-title":"Machine Learning"},{"issue":"7","key":"10.3233\/JIFS-213103_ref39","first-page":"2469","article-title":"Deep reinforcement learning for sequence-to-sequence models","volume":"31","author":"Keneshloo","year":"2019","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"issue":"1","key":"10.3233\/JIFS-213103_ref40","doi-asserted-by":"crossref","first-page":"34","DOI":"10.1287\/moor.2018.0970","article-title":"Polynomial time algorithms for branching Markov decision processes and probabilistic min (max) polynomial Bellman equations","volume":"45","author":"Etessami","year":"2020","journal-title":"Mathematics of Operations Research"},{"key":"10.3233\/JIFS-213103_ref41","doi-asserted-by":"crossref","first-page":"113695","DOI":"10.1016\/j.eswa.2020.113695","article-title":"Genetic state-grouping algorithm for deep reinforcement learning","volume":"161","author":"Kim","year":"2020","journal-title":"Expert Systems with Applications"},{"issue":"2","key":"10.3233\/JIFS-213103_ref42","doi-asserted-by":"crossref","first-page":"259","DOI":"10.1016\/j.ijforecast.2009.01.006","article-title":"On forecasting daily stock volatility: The role of intraday information and market conditions","volume":"25","author":"Fuertes","year":"2009","journal-title":"International Journal of Forecasting"},{"key":"10.3233\/JIFS-213103_ref43","doi-asserted-by":"crossref","first-page":"181","DOI":"10.1016\/j.eswa.2019.01.083","article-title":"Combining principal component analysis, discrete wavelet transform and XGBoost to trade in the financial markets","volume":"125","author":"Nobre","year":"2019","journal-title":"Expert Systems with Applications"},{"key":"10.3233\/JIFS-213103_ref44","doi-asserted-by":"crossref","first-page":"117365","DOI":"10.1109\/ACCESS.2020.3004284","article-title":"Forecasting stock prices using a hybrid deep learning model integrating attention mechanism, multi-layer perceptron, and bidirectional long-short term memory neural network","volume":"8","author":"Chen","year":"2020","journal-title":"IEEE Access"},{"key":"10.3233\/JIFS-213103_ref45","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-021-05984-x"},{"issue":"4","key":"10.3233\/JIFS-213103_ref46","doi-asserted-by":"crossref","first-page":"4287","DOI":"10.1109\/TPEL.2020.3024881","article-title":"Research on losses of PCB parasitic capacitance for GaN-based full bridge converters","volume":"36","author":"Meng","year":"2020","journal-title":"IEEE Transactions on Power Electronics"},{"key":"10.3233\/JIFS-213103_ref47","doi-asserted-by":"crossref","first-page":"126133","DOI":"10.1016\/j.jclepro.2021.126133","article-title":"Sustainable economic development in higher education institutions: A global analysis within the SDGs framework","volume":"294","author":"Abad-Segura","year":"2021","journal-title":"Journal of Cleaner Production"}],"container-title":["Journal of Intelligent &amp; Fuzzy Systems"],"original-title":[],"link":[{"URL":"https:\/\/content.iospress.com\/download?id=10.3233\/JIFS-213103","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T09:46:27Z","timestamp":1777455987000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/full\/10.3233\/JIFS-213103"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7,21]]},"references-count":44,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.3233\/jifs-213103","relation":{},"ISSN":["1064-1246","1875-8967"],"issn-type":[{"value":"1064-1246","type":"print"},{"value":"1875-8967","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,7,21]]}}}