{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,24]],"date-time":"2025-12-24T12:39:46Z","timestamp":1766579986237,"version":"3.48.0"},"reference-count":59,"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":["Future Internet"],"abstract":"<jats:p>Accurate short-term wind speed forecasting is essential for mitigating wind power variability and supporting stable grid operation. This study proposes a model selection forecasting system (MSFS) that dynamically integrates six deep learning models to enhance predictive accuracy and robustness. Using multi-turbine data from a wind farm in northwest China, the framework identifies the optimal model at each time step through iterative evaluation and retrains the selected models to further improve performance. The Kruskal\u2013Wallis test shows that all forecasting models, including MSFS, maintain statistical consistency with the real wind speed distribution at the 95% confidence level. Uncertainty analysis demonstrates that MSFS more reliable forecasting interval. By coupling MSFS-derived wind speed forecasts with turbine-specific power curves, the system enables reliable theoretical power estimation, offering critical reference information for dispatch planning, reserve allocation, and distinguishing resource-driven variability from turbine performance deviations. The slightly conservative yet highly stable forecasting behavior of MSFS reduces overestimation risks and enhances decision reliability. Overall, the proposed MSFS framework provides a robust, interpretable, and operationally valuable solution for short-term wind energy forecasting, with strong potential for wind farm operation and power system management.<\/jats:p>","DOI":"10.3390\/fi18010007","type":"journal-article","created":{"date-parts":[[2025,12,24]],"date-time":"2025-12-24T12:22:27Z","timestamp":1766578947000},"page":"7","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Research and Application of a Model Selection Forecasting System for Wind Speed and Theoretical Power Generation"],"prefix":"10.3390","volume":"18","author":[{"given":"Ming","family":"Zeng","sequence":"first","affiliation":[{"name":"Guangzhou Power Supply Bureau, Guangdong Power Grid Co., Ltd., Guangzhou 510520, China"}]},{"given":"Qianqian","family":"Jia","sequence":"additional","affiliation":[{"name":"Guangzhou Power Supply Bureau, Guangdong Power Grid Co., Ltd., Guangzhou 510520, China"}]},{"given":"Zhenming","family":"Wen","sequence":"additional","affiliation":[{"name":"School of Mechatronic Engineering, Guangdong Polytechnic Normal University, Guangzhou 510450, China"}]},{"given":"Fang","family":"Mao","sequence":"additional","affiliation":[{"name":"Guangzhou Power Supply Bureau, Guangdong Power Grid Co., Ltd., Guangzhou 510520, China"}]},{"given":"Haotao","family":"Huang","sequence":"additional","affiliation":[{"name":"Guangzhou Power Supply Bureau, Guangdong Power Grid Co., Ltd., Guangzhou 510520, China"}]},{"given":"Jingyuan","family":"Pan","sequence":"additional","affiliation":[{"name":"Guangzhou Power Supply Bureau, Guangdong Power Grid Co., Ltd., Guangzhou 510520, China"}]}],"member":"1968","published-online":{"date-parts":[[2025,12,22]]},"reference":[{"key":"ref_1","unstructured":"Global Wind Energy Council (2024). Global Wind Report 2024, Global Wind Energy Council (GWEC)."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"263","DOI":"10.1016\/j.solener.2021.12.011","article-title":"A historical weather forecast dataset from the European centre for medium-range weather forecasts (ecmwf) for energy forecasting","volume":"232","author":"Yang","year":"2022","journal-title":"Sol. Energy"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"1727","DOI":"10.1177\/01445987241248201","article-title":"Performance analysis of arima model for wind speed forecasting in Jerusalem, Palestine","volume":"42","author":"Alsamamra","year":"2024","journal-title":"Energy Explor. Exploit."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"553","DOI":"10.5194\/npg-30-553-2023","article-title":"Downscaling of surface wind forecasts using convolutional neural networks","volume":"30","author":"Dupuy","year":"2023","journal-title":"Nonlin. Process. Geophys."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"1137","DOI":"10.5194\/wes-10-1137-2025","article-title":"Spatio-temporal graph neural networks for power prediction in offshore wind farms using scada data","volume":"10","author":"Daenens","year":"2025","journal-title":"Wind Energy Sci."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"124273","DOI":"10.1016\/j.apenergy.2024.124273","article-title":"Can we trust explainable artificial intelligence in wind power forecasting?","volume":"376","author":"Liao","year":"2024","journal-title":"Appl. Energy"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Liu, Z., Guo, H., Zhang, Y., and Zuo, Z. (2025). A comprehensive review of wind power prediction based on machine learning: Models, applications, and challenges. Energies, 18.","DOI":"10.3390\/en18020350"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"126234","DOI":"10.1016\/j.apenergy.2025.126234","article-title":"A review of predictive uncertainty modeling techniques and evaluation metrics in probabilistic wind speed and wind power forecasting","volume":"396","author":"Wang","year":"2025","journal-title":"Appl. Energy"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"125052","DOI":"10.1016\/j.apenergy.2024.125052","article-title":"Data-augmented trend-fluctuation representations by interpretable contrastive learning for wind power forecasting","volume":"380","author":"Zhao","year":"2025","journal-title":"Appl. Energy"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"145590","DOI":"10.1016\/j.jclepro.2025.145590","article-title":"Deep fuzzy inference system fused with probability density function control for wind power forecasting with asymmetric error distribution","volume":"511","author":"Li","year":"2025","journal-title":"J. Clean. Prod."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"123966","DOI":"10.1016\/j.renene.2025.123966","article-title":"Enhancing probabilistic wind speed forecasting by integrating self-adaptive bayesian wavelet denoising with deep gaussian process regression under uncertainties","volume":"256","author":"Chen","year":"2026","journal-title":"Renew. Energy"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"126318","DOI":"10.1016\/j.apenergy.2025.126318","article-title":"Online probability density prediction of wind power considering virtual and real concept drift detection","volume":"396","author":"He","year":"2025","journal-title":"Appl. Energy"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"125295","DOI":"10.1016\/j.apenergy.2025.125295","article-title":"Physics-constrained wind power forecasting aligned with probability distributions for noise-resilient deep learning\u2606","volume":"383","author":"Gao","year":"2025","journal-title":"Appl. Energy"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"2200","DOI":"10.1109\/TCE.2023.3343821","article-title":"Privacy-preserving smart energy management by consumer-electronic chips and federated learning","volume":"70","author":"Huang","year":"2024","journal-title":"IEEE Trans. Consum. Electron."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"126177","DOI":"10.1016\/j.apenergy.2025.126177","article-title":"Privacy-preserving probabilistic wind power forecasting: An adaptive federated approach","volume":"396","author":"Wang","year":"2025","journal-title":"Appl. Energy"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"119142","DOI":"10.1016\/j.enconman.2024.119142","article-title":"Probabilistic online learning framework for short-term wind power forecasting using ensemble bagging regression model","volume":"323","author":"Nayak","year":"2025","journal-title":"Energy Convers. Manag."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"125286","DOI":"10.1016\/j.apenergy.2025.125286","article-title":"Probabilistic wind speed forecasting via bayesian dlms and its application in green hydrogen production","volume":"382","author":"Leal","year":"2025","journal-title":"Appl. Energy"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"140217","DOI":"10.1016\/j.jclepro.2023.140217","article-title":"A novel wind model downscaling with statistical regression and forecast for the cleaner energy","volume":"434","author":"Chen","year":"2024","journal-title":"J. Clean. Prod."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"119627","DOI":"10.1016\/j.enconman.2025.119627","article-title":"A location-centric transformer framework for multi-location short-term wind speed forecasting","volume":"328","author":"Zhao","year":"2025","journal-title":"Energy Convers. Manag."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"137229","DOI":"10.1016\/j.energy.2025.137229","article-title":"Multi-feature extraction spatio-temporal interaction graph network for wind speed forecasting in windfarm","volume":"333","author":"Ma","year":"2025","journal-title":"Energy"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"136356","DOI":"10.1016\/j.energy.2025.136356","article-title":"A novel deep learning approach for regional high-resolution spatio-temporal wind speed forecasting for energy applications","volume":"328","author":"Resifi","year":"2025","journal-title":"Energy"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"137751","DOI":"10.1016\/j.energy.2025.137751","article-title":"Incremental principal component analysis based depthwise separable unet model for complex wind system forecasting","volume":"334","author":"Zhang","year":"2025","journal-title":"Energy"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"137670","DOI":"10.1016\/j.energy.2025.137670","article-title":"Multi-step prediction of spatio-temporal wind speed based on the multimodal coupled st-dfnet model","volume":"334","author":"Zhang","year":"2025","journal-title":"Energy"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"137521","DOI":"10.1016\/j.energy.2025.137521","article-title":"Dbann: Dual-branch attention neural networks with hierarchical spatiotemporal-perception for multi-node offshore wind power forecasting","volume":"334","author":"Hu","year":"2025","journal-title":"Energy"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"124954","DOI":"10.1016\/j.apenergy.2024.124954","article-title":"Interpreting lasso regression model by feature space matching analysis for spatio-temporal correlation based wind power forecasting","volume":"380","author":"Zhao","year":"2025","journal-title":"Appl. Energy"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"126016","DOI":"10.1016\/j.apenergy.2025.126016","article-title":"A review of solar and wind energy forecasting: From single-site to multi-site paradigm","volume":"392","author":"Verdone","year":"2025","journal-title":"Appl. Energy"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"123618","DOI":"10.1016\/j.renene.2025.123618","article-title":"Addressing intermittency in medium-term photovoltaic and wind power forecasting using a hybrid xlstm-tccnn model with numerical weather predictions","volume":"253","author":"Wan","year":"2025","journal-title":"Renew. Energy"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"123200","DOI":"10.1016\/j.renene.2025.123200","article-title":"Development of a hybrid model for medium-term wind farm power output forecasting","volume":"249","author":"Ignatev","year":"2025","journal-title":"Renew. Energy"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"124008","DOI":"10.1016\/j.renene.2025.124008","article-title":"Hybrid short-term wind power forecasting model using theoretical power curves and temporal fusion transformers","volume":"256","author":"Michalakopoulos","year":"2026","journal-title":"Renew. Energy"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"123463","DOI":"10.1016\/j.renene.2025.123463","article-title":"A cross-dataset benchmark for neural network-based wind power forecasting","volume":"254","author":"Xu","year":"2025","journal-title":"Renew. Energy"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"123550","DOI":"10.1016\/j.renene.2025.123550","article-title":"A deep time-frequency augmented wind power forecasting model","volume":"256","author":"Dong","year":"2026","journal-title":"Renew. Energy"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"136739","DOI":"10.1016\/j.energy.2025.136739","article-title":"A novel hybrid ensemble approach for wind speed forecasting with dual-stage decomposition strategy using optimized gru and transformer models","volume":"329","author":"Ullah","year":"2025","journal-title":"Energy"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"123965","DOI":"10.1016\/j.renene.2025.123965","article-title":"Short-term multi-step wind speed forecasting with multi-feature inputs using variational mode decomposition, a novel artificial intelligence network, and the polar lights optimizer","volume":"256","author":"Li","year":"2026","journal-title":"Renew. Energy"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"119819","DOI":"10.1016\/j.enconman.2025.119819","article-title":"Enhancement of wind speed forecasting using optimized decomposition technique, entropy-based reconstruction, and evolutionary patchtst","volume":"333","author":"Ma","year":"2025","journal-title":"Energy Convers. Manag."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"136660","DOI":"10.1016\/j.energy.2025.136660","article-title":"Ceemdan-se-hdbscan-vmd-tcn-bigru: A two-stage decomposition-based parallel model for multi-altitude ultra-short-term wind speed forecasting","volume":"330","author":"Wu","year":"2025","journal-title":"Energy"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"137225","DOI":"10.1016\/j.energy.2025.137225","article-title":"Dual-path frequency mamba-transformer model for wind power forecasting","volume":"332","author":"Hong","year":"2025","journal-title":"Energy"},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"124028","DOI":"10.1016\/j.renene.2025.124028","article-title":"A multi-dimensional interpretable wind speed forecasting model with two-stage feature exploring","volume":"256","author":"Wu","year":"2026","journal-title":"Renew. Energy"},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"126015","DOI":"10.1016\/j.apenergy.2025.126015","article-title":"Interpretable wind speed forecasting through two-stage decomposition with comprehensive relative importance analysis","volume":"392","author":"Zeng","year":"2025","journal-title":"Appl. Energy"},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"136497","DOI":"10.1016\/j.energy.2025.136497","article-title":"A novel interpretable wind speed forecasting based on the multivariate variational mode decomposition and temporal fusion transformer","volume":"331","author":"Xu","year":"2025","journal-title":"Energy"},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"119752","DOI":"10.1016\/j.enconman.2025.119752","article-title":"Isi net: A novel paradigm integrating interpretability and intelligent selection in ensemble learning for accurate wind power forecasting","volume":"332","author":"Liang","year":"2025","journal-title":"Energy Convers. Manag."},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Wang, Q., Xu, F., He, J., Luo, K., and Fan, J. (2026). A new fusion model for enhanced ultra-short-term offshore wind power forecasting. Renew. Energy, 256.","DOI":"10.1016\/j.renene.2025.123876"},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"137335","DOI":"10.1016\/j.energy.2025.137335","article-title":"An offshore wind speed forecasting system based on feature enhancement, deep time series clustering, and extended lstm","volume":"333","author":"Li","year":"2025","journal-title":"Energy"},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"126348","DOI":"10.1016\/j.apenergy.2025.126348","article-title":"A novel data-driven multi-step wind power point-interval prediction framework integrating sliding window-based two-layer adaptive decomposition and multi-objective optimization for balancing prediction accuracy and stability","volume":"397","author":"Cui","year":"2025","journal-title":"Appl. Energy"},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"106622","DOI":"10.1016\/j.knosys.2020.106622","article-title":"AutoML: A survey of the state-of-the-art","volume":"212","author":"He","year":"2021","journal-title":"Knowl.-Based Syst."},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"409","DOI":"10.1613\/jair.1.11854","article-title":"Benchmark and survey of automated machine learning frameworks","volume":"70","author":"Huber","year":"2021","journal-title":"J. Artif. Intell. Res."},{"key":"ref_46","unstructured":"Zhou, Y., Wu, X., Wu, J., Feng, L., and Tan, K.C. (2024). HM3: Hierarchical multi-objective model merging for pretrained models. arXiv."},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3467477","article-title":"Evolutionary machine learning: A survey","volume":"54","author":"Telikani","year":"2021","journal-title":"ACM Comput. Surv."},{"key":"ref_48","first-page":"271","article-title":"Arbitrated ensembles for time series forecasting in online learning scenarios","volume":"118","author":"Cerqueira","year":"2019","journal-title":"Expert Syst. Appl."},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"122155","DOI":"10.1016\/j.apenergy.2023.122155","article-title":"Applicability analysis of transformer to wind speed forecasting by a novel deep learning framework with multiple atmospheric variables","volume":"353","author":"Jiang","year":"2024","journal-title":"Appl. Energy"},{"key":"ref_50","doi-asserted-by":"crossref","first-page":"129681","DOI":"10.1016\/j.energy.2023.129681","article-title":"Enhancing real-time degradation prediction of lithium-ion battery: A digital twin framework with cnn-lstm-attention model","volume":"286","author":"Li","year":"2024","journal-title":"Energy"},{"key":"ref_51","doi-asserted-by":"crossref","first-page":"948","DOI":"10.1016\/j.renene.2023.05.006","article-title":"A unified multi-step wind speed forecasting framework based on numerical weather prediction grids and wind farm monitoring data","volume":"211","author":"Liu","year":"2023","journal-title":"Renew. Energy"},{"key":"ref_52","doi-asserted-by":"crossref","first-page":"115033","DOI":"10.1016\/j.oceaneng.2023.115033","article-title":"Optimal maintenance planning for offshore wind farms under an uncertain environment","volume":"283","author":"Su","year":"2023","journal-title":"Ocean. Eng."},{"key":"ref_53","doi-asserted-by":"crossref","first-page":"24","DOI":"10.1186\/s42162-022-00212-9","article-title":"Load forecasting for energy communities: A novel lstm-xgboost hybrid model based on smart meter data","volume":"5","author":"Semmelmann","year":"2022","journal-title":"Energy Inform."},{"key":"ref_54","doi-asserted-by":"crossref","first-page":"109528","DOI":"10.1016\/j.patcog.2023.109528","article-title":"Continual spatio-temporal graph convolutional networks","volume":"140","author":"Hedegaard","year":"2023","journal-title":"Pattern Recognit."},{"key":"ref_55","first-page":"118","article-title":"Time series focused neural network for accurate wireless human gesture recognition","volume":"113","author":"Huang","year":"2025","journal-title":"IEEE Trans. Netw. Sci. Eng."},{"key":"ref_56","first-page":"440","article-title":"On the vortex theory of screw propeller","volume":"123","author":"Goldstein","year":"1929","journal-title":"Proc. R. Soc. A Math. Phys. Eng. Sci."},{"key":"ref_57","doi-asserted-by":"crossref","unstructured":"McKight, P.E., and Najab, J. (2010). Kruskal-wallis test. The Corsini Encyclopedia of Psychology, John Wiley & Sons.","DOI":"10.1002\/9780470479216.corpsy0491"},{"key":"ref_58","doi-asserted-by":"crossref","first-page":"130606","DOI":"10.1016\/j.energy.2024.130606","article-title":"Research and application of a Model selection forecasting system for wind speed and theoretical power generation in wind farms based on classification and wind conversion","volume":"293","author":"Xiaojia","year":"2024","journal-title":"Energy"},{"key":"ref_59","unstructured":"Tedeschi, P., Sciancalepore, S., and Pietro, R. (October, January 30). Modelling a communication channel under jamming: Experimental model and applications. Proceedings of the Parallel & Distributed Processing with Applications, Big Data & Cloud Computing, Sustainable Computing & Communications, Social Computing & Networking (ISPA\/BDCloud\/SocialCom\/SustainCom), New York, NY, USA."}],"container-title":["Future Internet"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1999-5903\/18\/1\/7\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,24]],"date-time":"2025-12-24T12:30:58Z","timestamp":1766579458000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1999-5903\/18\/1\/7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,22]]},"references-count":59,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,1]]}},"alternative-id":["fi18010007"],"URL":"https:\/\/doi.org\/10.3390\/fi18010007","relation":{},"ISSN":["1999-5903"],"issn-type":[{"value":"1999-5903","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,22]]}}}