{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T06:47:20Z","timestamp":1781246840147,"version":"3.54.1"},"reference-count":58,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Expert Systems with Applications"],"published-print":{"date-parts":[[2026,9]]},"DOI":"10.1016\/j.eswa.2026.132637","type":"journal-article","created":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T17:52:48Z","timestamp":1777571568000},"page":"132637","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":5,"special_numbering":"C","title":["DMoE-LLM: A dual-branch mixture-of-experts framework with large language models for wind power forecasting"],"prefix":"10.1016","volume":"325","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5340-4592","authenticated-orcid":false,"given":"Xingyu","family":"Feng","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-0389-6014","authenticated-orcid":false,"given":"Dekang","family":"Guo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-1022-1807","authenticated-orcid":false,"given":"Mingshun","family":"Ye","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.eswa.2026.132637_bib0001","article-title":"Chronos: Learning the language of time series","author":"Ansari","year":"2024","journal-title":"Transactions on Machine Learning Research"},{"issue":"1","key":"10.1016\/j.eswa.2026.132637_bib0002","doi-asserted-by":"crossref","first-page":"577","DOI":"10.1038\/s41597-022-01696-6","article-title":"Solar and wind power data from the Chinese state grid renewable energy generation forecasting competition","volume":"9","author":"Chen","year":"2022","journal-title":"Scientific Data"},{"key":"10.1016\/j.eswa.2026.132637_bib0003","series-title":"2017\u202fIEEE 60th international midwest symposium on circuits and systems (MWSCAS)","first-page":"1597","article-title":"Gate-variants of gated recurrent unit (GRU) neural networks","author":"Dey","year":"2017"},{"key":"10.1016\/j.eswa.2026.132637_bib0004","doi-asserted-by":"crossref","DOI":"10.1016\/j.renene.2025.124808","article-title":"Zero-shot forecasting of volatile wind power against data missing with large language model through attentive residual prompt tuning","volume":"257","author":"Duan","year":"2026","journal-title":"Renewable Energy"},{"key":"10.1016\/j.eswa.2026.132637_bib0005","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2025.127436","article-title":"Prompting large language model for multi-location multi-step zero-shot wind power forecasting","volume":"280","author":"Duan","year":"2025","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.eswa.2026.132637_sbref0006","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2026.131620","article-title":"Ev-STLLM: Electric vehicle charging forecasting based on spatio-temporal large language models with multi-frequency and multi-scale information fusion","volume":"313","author":"Fan","year":"2026","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.eswa.2026.132637_bib0007","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2025.103541","article-title":"M2WLLM: Multi-modal multi-task ultra-short-term wind power prediction algorithm based on large language model","volume":"126","author":"Fan","year":"2026","journal-title":"Information Fusion"},{"issue":"21","key":"10.1016\/j.eswa.2026.132637_bib0008","doi-asserted-by":"crossref","first-page":"7915","DOI":"10.3390\/app10217915","article-title":"M2gsNet: Multi-modal multi-task graph spatiotemporal network for ultra-short-term wind farm cluster power prediction","volume":"10","author":"Fan","year":"2020","journal-title":"Applied Sciences"},{"key":"10.1016\/j.eswa.2026.132637_bib0009","doi-asserted-by":"crossref","DOI":"10.1016\/j.apenergy.2025.126535","article-title":"Wind power prediction using foundation large time series models enhanced by time series prompt in exogenous and tuning forms","volume":"400","author":"Fan","year":"2025","journal-title":"Applied Energy"},{"key":"10.1016\/j.eswa.2026.132637_bib0010","doi-asserted-by":"crossref","DOI":"10.1016\/j.renene.2024.122123","article-title":"Middle-term wind power forecasting method based on long-span NWP and microscale terrain fusion correction","volume":"240","author":"Ge","year":"2025","journal-title":"Renewable Energy"},{"key":"10.1016\/j.eswa.2026.132637_bib0011","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2025.103247","article-title":"Transfer learning with foundational models for time series forecasting using low-rank adaptations","author":"Germ\u00e1n-Morales","year":"2025","journal-title":"Information Fusion"},{"issue":"10","key":"10.1016\/j.eswa.2026.132637_bib0012","doi-asserted-by":"crossref","first-page":"2222","DOI":"10.1109\/TNNLS.2016.2582924","article-title":"LSTM: A search space odyssey","volume":"28","author":"Greff","year":"2016","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"issue":"8","key":"10.1016\/j.eswa.2026.132637_bib0013","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long short-term memory","volume":"9","author":"Hochreiter","year":"1997","journal-title":"Neural Computation"},{"key":"10.1016\/j.eswa.2026.132637_bib0014","series-title":"The Tenth International Conference on Learning Representations, ICLR 2022, Virtual Event, April 25-29, 2022","article-title":"LoRA: Low-rank adaptation of large language models","author":"Hu","year":"2022"},{"key":"10.1016\/j.eswa.2026.132637_bib0015","doi-asserted-by":"crossref","DOI":"10.1016\/j.renene.2025.123465","article-title":"A novel attention-enhanced LLM approach for accurate power demand and generation forecasting","volume":"252","author":"Hu","year":"2025","journal-title":"Renewable Energy"},{"key":"10.1016\/j.eswa.2026.132637_bib0016","doi-asserted-by":"crossref","DOI":"10.1016\/j.renene.2025.123200","article-title":"Development of a hybrid model for medium-term wind farm power output forecasting","author":"Ignatev","year":"2025","journal-title":"Renewable Energy"},{"key":"10.1016\/j.eswa.2026.132637_bib0017","series-title":"The twelfth international conference on learning representations","article-title":"Time-LLM: Time series forecasting by reprogramming large language models","author":"Jin","year":"2024"},{"key":"10.1016\/j.eswa.2026.132637_bib0018","series-title":"International conference on learning representations","article-title":"Reversible instance normalization for accurate time-series forecasting against distribution shift","author":"Kim","year":"2021"},{"key":"10.1016\/j.eswa.2026.132637_bib0019","series-title":"The 41st international ACM SIGIR conference on research & development in information retrieval","first-page":"95","article-title":"Modeling long-and short-term temporal patterns with deep neural networks","author":"Lai","year":"2018"},{"key":"10.1016\/j.eswa.2026.132637_bib0020","series-title":"ICASSP 2022-2022 IEEE international conference on acoustics, speech and signal processing (ICASSP)","first-page":"4138","article-title":"Deep spatio-temporal wind power forecasting","author":"Li","year":"2022"},{"issue":"5","key":"10.1016\/j.eswa.2026.132637_bib0021","doi-asserted-by":"crossref","first-page":"4073","DOI":"10.1109\/TSG.2023.3236992","article-title":"A TCN-based hybrid forecasting framework for hours-ahead utility-scale PV forecasting","volume":"14","author":"Li","year":"2023","journal-title":"IEEE Transactions on Smart Grid"},{"issue":"3","key":"10.1016\/j.eswa.2026.132637_bib0022","doi-asserted-by":"crossref","first-page":"1491","DOI":"10.1109\/TSTE.2024.3477288","article-title":"WpFormer: A spatial-temporal graph transformer with auto-correlation for wind power forecasting","volume":"16","author":"Liang","year":"2025","journal-title":"IEEE Transactions on Sustainable Energy"},{"key":"10.1016\/j.eswa.2026.132637_bib0023","doi-asserted-by":"crossref","DOI":"10.1016\/j.renene.2025.122775","article-title":"Developing a robust wind power forecasting method: Integrating data repair, feature screening, and economic impact analysis for practical applications","volume":"247","author":"Liang","year":"2025","journal-title":"Renewable Energy"},{"key":"10.1016\/j.eswa.2026.132637_bib0024","unstructured":"Liu, A., Feng, B., Xue, B., Wang, B., Wu, B., Lu, C., Zhao, C., Deng, C., Zhang, C., Ruan, C. et al. (2024a). Deepseek-v3 technical report. arXiv: 2412.19437."},{"key":"10.1016\/j.eswa.2026.132637_bib0025","series-title":"Proceedings of the 39th AAAI Conference on Artificial Intelligence","first-page":"18780","article-title":"TimeCMA: Towards LLM-Empowered Multivariate Time Series Forecasting via Cross-Modality Alignment","volume":"39","author":"Liu","year":"2025"},{"key":"10.1016\/j.eswa.2026.132637_bib0026","doi-asserted-by":"crossref","DOI":"10.1016\/j.asoc.2023.111050","article-title":"Short-term wind power forecasting based on multivariate\/multi-step LSTM with temporal feature attention mechanism","volume":"150","author":"Liu","year":"2024","journal-title":"Applied Soft Computing"},{"key":"10.1016\/j.eswa.2026.132637_bib0027","unstructured":"Liu, Y., Hu, T., Zhang, H., Wu, H., Wang, S., Ma, L., & Long, M. (2023). iTransFormer: Inverted transformers are effective for time series forecasting."},{"key":"10.1016\/j.eswa.2026.132637_bib0028","doi-asserted-by":"crossref","DOI":"10.1016\/j.apenergy.2025.126912","article-title":"CPLLM-WPF: A multi-scale prompting framework for generalizable wind power forecasting with LLMs","volume":"402","author":"Liu","year":"2025","journal-title":"Applied Energy"},{"key":"10.1016\/j.eswa.2026.132637_bib0029","doi-asserted-by":"crossref","DOI":"10.1016\/j.apenergy.2022.119608","article-title":"A hybrid attention-based deep learning approach for wind power prediction","volume":"323","author":"Ma","year":"2022","journal-title":"Applied Energy"},{"key":"10.1016\/j.eswa.2026.132637_bib0030","doi-asserted-by":"crossref","DOI":"10.1016\/j.enconman.2020.112824","article-title":"A new short-term wind speed forecasting method based on fine-tuned LSTM neural network and optimal input sets","volume":"213","author":"Memarzadeh","year":"2020","journal-title":"Energy Conversion and Management"},{"key":"10.1016\/j.eswa.2026.132637_bib0031","unstructured":"Nie, Y. (2022). A time series is worth 64words: Long-term forecasting with transformers."},{"key":"10.1016\/j.eswa.2026.132637_bib0032","doi-asserted-by":"crossref","DOI":"10.1016\/j.apenergy.2023.121905","article-title":"A novel ultra-short-term wind power prediction method based on XA mechanism","volume":"351","author":"Peng","year":"2023","journal-title":"Applied Energy"},{"key":"10.1016\/j.eswa.2026.132637_sbref0033","doi-asserted-by":"crossref","DOI":"10.1016\/j.renene.2025.124132","article-title":"A HO-biGRU-transformer based PEMFC degradation prediction method under different current conditions","volume":"256","author":"Quan","year":"2026","journal-title":"Renewable Energy"},{"key":"10.1016\/j.eswa.2026.132637_sbref0034","doi-asserted-by":"crossref","DOI":"10.1080\/15435075.2026.2622422","article-title":"Interpretable degradation forecasting of fuel cells under steady, quasi-dynamic and dynamic conditions: An ALA optimized timesnet model based on ICEEMDAN decomposition","author":"Quan","year":"2026","journal-title":"International Journal of Green Energy"},{"key":"10.1016\/j.eswa.2026.132637_sbref0035","doi-asserted-by":"crossref","DOI":"10.1016\/j.est.2025.116788","article-title":"A hybrid data-driven approach for SOH estimation of lithium-ion batteries based on health index extraction and QHDBO-biTCN-biGRU","volume":"125","author":"Quan","year":"2025","journal-title":"Journal of Energy Storage"},{"key":"10.1016\/j.eswa.2026.132637_sbref0036","doi-asserted-by":"crossref","DOI":"10.1016\/j.applthermaleng.2025.125946","article-title":"Improving the performance of a polygonal automobile exhaust thermoelectric generator with a crested porcupine optimizer","volume":"268","author":"Quan","year":"2025","journal-title":"Applied Thermal Engineering"},{"key":"10.1016\/j.eswa.2026.132637_bib0037","series-title":"R0-Fomo: Robustness of few-shot and zero-shot learning in large foundation models","article-title":"Lag-LLama: Towards foundation models for time series forecasting","author":"Rasul","year":"2023"},{"key":"10.1016\/j.eswa.2026.132637_bib0038","doi-asserted-by":"crossref","DOI":"10.1016\/j.energy.2023.127799","article-title":"An imputation and decomposition algorithms based integrated approach with bidirectional LSTM neural network for wind speed prediction","volume":"278","author":"Sareen","year":"2023","journal-title":"Energy"},{"key":"10.1016\/j.eswa.2026.132637_bib0039","series-title":"2019\u202fIEEE International conference on big data (big data)","first-page":"3285","article-title":"The performance of LSTM and biLSTM in forecasting time series","author":"Siami-Namini","year":"2019"},{"key":"10.1016\/j.eswa.2026.132637_bib0040","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2024.127284","article-title":"An optimized CNN-biLSTM network for bearing fault diagnosis under multiple working conditions with limited training samples","volume":"574","author":"Song","year":"2024","journal-title":"Neurocomputing"},{"key":"10.1016\/j.eswa.2026.132637_bib0041","series-title":"Advances in neural information processing systems","article-title":"Attention is all you need","volume":"vol. 30","author":"Vaswani","year":"2017"},{"key":"10.1016\/j.eswa.2026.132637_bib0042","article-title":"A method for ultra-short-term wind power forecasting of large-scale wind farms based on adaptive spatiotemporal graph convolution","author":"Wang","year":"2025","journal-title":"Renewable Energy"},{"key":"10.1016\/j.eswa.2026.132637_bib0043","first-page":"469","article-title":"Timexer: Empowering transformers for time series forecasting with exogenous variables","volume":"37","author":"Wang","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.eswa.2026.132637_bib0044","unstructured":"Wu, H., Hu, T., Liu, Y., Zhou, H., Wang, J., & Long, M. (2022a). TimesNet: Temporal 2D-variation modeling for general time series analysis."},{"key":"10.1016\/j.eswa.2026.132637_bib0045","doi-asserted-by":"crossref","DOI":"10.1016\/j.energy.2022.125231","article-title":"Multistep short-term wind speed forecasting using transformer","volume":"261","author":"Wu","year":"2022","journal-title":"Energy"},{"key":"10.1016\/j.eswa.2026.132637_bib0046","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2025.113739","article-title":"GLALLM: Adapting LLMs for spatio-temporal wind speed forecasting via global-local aware modeling","volume":"323","author":"Wu","year":"2025","journal-title":"Knowledge-Based Systems"},{"key":"10.1016\/j.eswa.2026.132637_bib0047","doi-asserted-by":"crossref","DOI":"10.1016\/j.renene.2025.123217","article-title":"Short-term wind power forecast with turning weather based on DBSCAN-RFE-lightGBM","author":"Wu","year":"2025","journal-title":"Renewable Energy"},{"key":"10.1016\/j.eswa.2026.132637_bib0048","series-title":"ICLR 2025: The thirteenth international conference on learning representations","article-title":"Time-Moe: Billion-scale time series foundation models with mixture of experts","author":"Xiaoming","year":"2025"},{"key":"10.1016\/j.eswa.2026.132637_bib0049","doi-asserted-by":"crossref","DOI":"10.1016\/j.energy.2024.133210","article-title":"A centralized power prediction method for large-scale wind power clusters based on dynamic graph neural network","volume":"310","author":"Yang","year":"2024","journal-title":"Energy"},{"key":"10.1016\/j.eswa.2026.132637_bib0050","doi-asserted-by":"crossref","DOI":"10.1016\/j.energy.2022.125556","article-title":"A novel time-frequency recurrent network and its advanced version for short-term wind speed predictions","volume":"262","author":"Yu","year":"2023","journal-title":"Energy"},{"key":"10.1016\/j.eswa.2026.132637_bib0051","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"11121","article-title":"Are transformers effective for time series forecasting?","volume":"vol. 37","author":"Zeng","year":"2023"},{"issue":"4","key":"10.1016\/j.eswa.2026.132637_bib0052","doi-asserted-by":"crossref","first-page":"2205","DOI":"10.1109\/TSTE.2021.3086851","article-title":"Multi-source and temporal attention network for probabilistic wind power prediction","volume":"12","author":"Zhang","year":"2021","journal-title":"IEEE Transactions on Sustainable Energy"},{"key":"10.1016\/j.eswa.2026.132637_bib0053","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2024.124766","article-title":"Interpretable multi-graph convolution network integrating spatio-temporal attention and dynamic combination for wind power forecasting","volume":"255","author":"Zhao","year":"2024","journal-title":"Expert Systems with Applications"},{"issue":"21","key":"10.1016\/j.eswa.2026.132637_bib0054","first-page":"45411","article-title":"STCA-LLM: Spatial\u2013temporal cross-attention large language model for wind speed forecasting","volume":"12","author":"Zhou","year":"2025","journal-title":"IEEE Internet of Things Journal"},{"key":"10.1016\/j.eswa.2026.132637_bib0055","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"11106","article-title":"Informer: Beyond efficient transformer for long sequence time-series forecasting","volume":"vol. 35","author":"Zhou","year":"2021"},{"key":"10.1016\/j.eswa.2026.132637_bib0056","unstructured":"Zhou, J., Lu, X., Xiao, Y., Su, J., Lyu, J., Ma, Y., & Dou, D. (2022). SDWPF: A dataset for spatial dynamic wind power forecasting challenge at kdd cup 2022."},{"key":"10.1016\/j.eswa.2026.132637_bib0057","first-page":"43322","article-title":"One fits all: Power general time series analysis by pretrained lm","volume":"36","author":"Zhou","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.eswa.2026.132637_bib0058","doi-asserted-by":"crossref","DOI":"10.1016\/j.enconman.2025.119673","article-title":"CMLLM: A novel cross-modal large language model for wind power forecasting","volume":"330","author":"Zhu","year":"2025","journal-title":"Energy Conversion and Management"}],"container-title":["Expert Systems with Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0957417426015502?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0957417426015502?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T23:03:32Z","timestamp":1777935812000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0957417426015502"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":58,"alternative-id":["S0957417426015502"],"URL":"https:\/\/doi.org\/10.1016\/j.eswa.2026.132637","relation":{},"ISSN":["0957-4174"],"issn-type":[{"value":"0957-4174","type":"print"}],"subject":[],"published":{"date-parts":[[2026,9]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"DMoE-LLM: A dual-branch mixture-of-experts framework with large language models for wind power forecasting","name":"articletitle","label":"Article Title"},{"value":"Expert Systems with Applications","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.eswa.2026.132637","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"132637"}}