{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T15:11:54Z","timestamp":1782313914112,"version":"3.54.5"},"reference-count":35,"publisher":"MDPI AG","issue":"1","license":[{"start":{"date-parts":[[2025,12,22]],"date-time":"2025-12-22T00:00:00Z","timestamp":1766361600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Information"],"abstract":"<jats:p>Short-term load forecasting is essential for optimizing power system operations and supporting renewable energy integration. However, accurately capturing the complex nonlinear features in load data remains challenging. To improve forecasting accuracy, this paper proposes a hybrid CNN-BiGRU-Attention model optimized by the Beluga Whale Optimization (BWO) algorithm. The proposed method integrates deep learning with metaheuristic optimization in four steps: First, a Convolutional Neural Network (CNN) is used to extract spatial features from input data, including historical load and weather variables. Second, a Bidirectional Gated Recurrent Unit (BiGRU) network is employed to learn temporal dependencies from both forward and backward directions. Third, an Attention mechanism is introduced to focus on key features and reduce the influence of redundant information. Finally, the BWO algorithm is applied to automatically optimize the model\u2019s hyperparameters, avoiding the problem of falling into local optima. Comparative experiments against five baseline models (BP, GRU, BiGRU, BiGRU-Attention, and CNN-BiGRU-Attention) demonstrate the effectiveness of the proposed model. The experimental results indicate that the optimized model achieves superior predictive performance with significantly reduced error rates in terms of Mean Absolute Percentage Error (MAPE) and Root Mean Square Error (RMSE), along with a higher Coefficient of Determination (R2) compared to the benchmarks, confirming its high accuracy and reliability for power load forecasting.<\/jats:p>","DOI":"10.3390\/info17010006","type":"journal-article","created":{"date-parts":[[2025,12,23]],"date-time":"2025-12-23T14:27:47Z","timestamp":1766500067000},"page":"6","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["BWO-Optimized CNN-BiGRU-Attention Model for Short-Term Load Forecasting"],"prefix":"10.3390","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-3400-2001","authenticated-orcid":false,"given":"Ruihan","family":"Wu","sequence":"first","affiliation":[{"name":"School of Software, Taiyuan University of Technology, Taiyuan 030600, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2363-1190","authenticated-orcid":false,"given":"Xin","family":"Wen","sequence":"additional","affiliation":[{"name":"School of Software, Taiyuan University of Technology, Taiyuan 030600, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2025,12,22]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"110980","DOI":"10.1016\/j.engappai.2025.110980","article-title":"Short-Term Electricity-Load Forecasting by deep learning: A comprehensive survey","volume":"154","author":"Dong","year":"2025","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref_2","first-page":"6395","article-title":"Metaheuristic Optimization with Deep Learning Enabled Smart Grid Stability Prediction","volume":"75","year":"2023","journal-title":"Comput. Mater. Contin."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Aguilar Madrid, E., and Antonio, N. (2021). Short-term electricity load forecasting with machine learning. Information, 12.","DOI":"10.3390\/info12020050"},{"key":"ref_4","first-page":"344","article-title":"Short-term Power Load Forecasting Based on CNN-BiGRU-Attention","volume":"19","author":"Shuang","year":"2024","journal-title":"J. Electr. Eng."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Liu, X., Song, J., Tao, H., Wang, P., Mo, H., and Du, W. (2025). Quarter-Hourly Power Load Forecasting Based on a Hybrid CNN-BiLSTM-Attention Model with CEEMDAN, K-Means, and VMD. Energies, 18.","DOI":"10.3390\/en18112675"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Mumtahina, U., Alahakoon, S., and Wolfs, P. (2024). Hyperparameter tuning of load-forecasting models using metaheuristic optimization algorithms\u2014a systematic review. Mathematics, 12.","DOI":"10.3390\/math12213353"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Yang, J., and Xing, C. (2019). Data source selection based on an improved greedy genetic algorithm. Symmetry, 11.","DOI":"10.3390\/sym11020273"},{"key":"ref_8","first-page":"85","article-title":"Enhancing Accuracy in Wind and Photovoltaic Power Forecasting Through Neutral Network and Beluga Whale Optimization Algorithm","volume":"18","author":"Chen","year":"2024","journal-title":"Int. J. Multiphys."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"28831","DOI":"10.1109\/ACCESS.2024.3367446","article-title":"Exploring LBWO and BWO algorithms for demand side optimization and cost efficiency: Innovative approaches to smart home energy management","volume":"12","author":"Youssef","year":"2024","journal-title":"IEEE Access"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"120492","DOI":"10.1016\/j.energy.2021.120492","article-title":"Short-term offshore wind speed forecast by seasonal ARIMA-A comparison against GRU and LSTM","volume":"227","author":"Liu","year":"2021","journal-title":"Energy"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"108065","DOI":"10.1016\/j.epsr.2022.108065","article-title":"Deep learning based short term load forecasting with hybrid feature selection","volume":"210","author":"Subbiah","year":"2022","journal-title":"Electr. Power Syst. Res."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"109792","DOI":"10.1016\/j.epsr.2023.109792","article-title":"State-of-the-art review on energy and load forecasting in microgrids using artificial neural networks, machine learning, and deep learning techniques","volume":"225","author":"Wazirali","year":"2023","journal-title":"Electr. Power Syst. Res."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"9","DOI":"10.1016\/j.gloei.2022.04.002","article-title":"A comprehensive review for wind, solar, and electrical load forecasting methods","volume":"5","author":"Wang","year":"2022","journal-title":"Glob. Energy Interconnect."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"118801","DOI":"10.1016\/j.apenergy.2022.118801","article-title":"Short-term multi-energy load forecasting for integrated energy systems based on CNN-BiGRU optimized by attention mechanism","volume":"313","author":"Niu","year":"2022","journal-title":"Appl. Energy"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"130184","DOI":"10.1016\/j.energy.2023.130184","article-title":"TimeNet: Time2Vec attention-based CNN-BiGRU neural network for predicting production in shale and sandstone gas reservoirs","volume":"290","author":"Fargalla","year":"2024","journal-title":"Energy"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"117446","DOI":"10.1016\/j.apenergy.2021.117446","article-title":"Review of meta-heuristic algorithms for wind power prediction: Methodologies, applications and challenges","volume":"301","author":"Lu","year":"2021","journal-title":"Appl. Energy"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"109215","DOI":"10.1016\/j.knosys.2022.109215","article-title":"Beluga whale optimization: A novel nature-inspired metaheuristic algorithm","volume":"251","author":"Zhong","year":"2022","journal-title":"Knowl.-Based Syst."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"23504","DOI":"10.1109\/ACCESS.2024.3358182","article-title":"Short-term load forecasting in smart grids using hybrid deep learning","volume":"12","author":"Asiri","year":"2024","journal-title":"IEEE Access"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"113942","DOI":"10.1016\/j.enbuild.2024.113942","article-title":"Optimal loading distribution of chillers based on an improved beluga whale optimization for reducing energy consumption","volume":"307","author":"Li","year":"2024","journal-title":"Energy Build."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"106389","DOI":"10.1016\/j.asoc.2020.106389","article-title":"Short-term photovoltaic power generation forecasting based on random forest feature selection and CEEMD: A case study","volume":"93","author":"Niu","year":"2020","journal-title":"Appl. Soft Comput."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"106773","DOI":"10.1016\/j.engappai.2023.106773","article-title":"Short-term electric load forecasting using particle swarm optimization-based convolutional neural network","volume":"126","author":"Hong","year":"2023","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"117902","DOI":"10.1016\/j.energy.2020.117902","article-title":"An improved convolutional neural network with load range discretization for probabilistic load forecasting","volume":"203","author":"Huang","year":"2020","journal-title":"Energy"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"14992","DOI":"10.1109\/ACCESS.2021.3053069","article-title":"A pyramid-CNN based deep learning model for power load forecasting of similar-profile energy customers based on clustering","volume":"9","author":"Aurangzeb","year":"2021","journal-title":"IEEE Access"},{"key":"ref_24","first-page":"4370","article-title":"A short-term power load forecasting method based on attention mechanism of CNN-GRU","volume":"43","author":"Zhao","year":"2019","journal-title":"Power Syst. Technol."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"042055","DOI":"10.1088\/1742-6596\/1624\/4\/042055","article-title":"Piggery ammonia concentration prediction method based on CNN-GRU","volume":"1624","author":"Wang","year":"2020","journal-title":"J. Phys. Conf. Ser."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"96221","DOI":"10.1109\/ACCESS.2021.3093481","article-title":"A novel technique for short-term load forecasting using sequential models and feature engineering","volume":"9","author":"Wahab","year":"2021","journal-title":"IEEE Access"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"285","DOI":"10.1016\/j.gloei.2023.06.003","article-title":"Load-forecasting method for IES based on LSTM and dynamic similar days with multi-features","volume":"6","author":"Sun","year":"2023","journal-title":"Glob. Energy Interconnect."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Aurangzeb, K., and Alhussein, M. (2020, January 10). Deep learning framework for short term power load forecasting, a case study of individual household energy customer. Proceedings of the 2019 International Conference on Advances in the Emerging Computing Technologies (AECT), Al Madinah Al Munawwarah, Saudi Arabia.","DOI":"10.1109\/AECT47998.2020.9194153"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"141","DOI":"10.1126\/science.abq6851","article-title":"Data sharing and community-engaged research","volume":"378","author":"Sabatello","year":"2022","journal-title":"Science"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Du, L., Zhang, L., and Wang, X. (2020). Spatiotemporal feature learning based hour-ahead load forecasting for energy internet. Electronics, 9.","DOI":"10.3390\/electronics9010196"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"1895","DOI":"10.1016\/j.renene.2020.10.119","article-title":"Wind power forecasting\u2013A data-driven method along with gated recurrent neural network","volume":"163","author":"Kisvari","year":"2021","journal-title":"Renew. Energy"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"129753","DOI":"10.1016\/j.energy.2023.129753","article-title":"High and low frequency wind power prediction based on Transformer and BiGRU-Attention","volume":"288","author":"Wang","year":"2024","journal-title":"Energy"},{"key":"ref_33","first-page":"81","article-title":"Short-term power load forecasting method based on Attention-BiLSTM-LSTM neural network","volume":"41","author":"Gong","year":"2021","journal-title":"J. Comput. Appl."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"128986","DOI":"10.1016\/j.energy.2023.128986","article-title":"A novel algorithm system for wind power prediction based on RANSAC data screening and Seq2Seq-Attention-BiGRU model","volume":"283","author":"Zhou","year":"2023","journal-title":"Energy"},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Horng, S.C., and Lin, S.S. (2023). Improved beluga whale optimization for solving the simulation optimization problems with stochastic constraints. Mathematics, 11.","DOI":"10.3390\/math11081854"}],"container-title":["Information"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2078-2489\/17\/1\/6\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,23]],"date-time":"2025-12-23T14:40:44Z","timestamp":1766500844000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2078-2489\/17\/1\/6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,22]]},"references-count":35,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,1]]}},"alternative-id":["info17010006"],"URL":"https:\/\/doi.org\/10.3390\/info17010006","relation":{},"ISSN":["2078-2489"],"issn-type":[{"value":"2078-2489","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,22]]}}}