{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,9]],"date-time":"2026-01-09T19:07:25Z","timestamp":1767985645445,"version":"3.49.0"},"reference-count":51,"publisher":"MDPI AG","issue":"17","license":[{"start":{"date-parts":[[2023,8,28]],"date-time":"2023-08-28T00:00:00Z","timestamp":1693180800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"National Natural Science Foundation of China","award":["82160347"],"award-info":[{"award-number":["82160347"]}]},{"name":"National Natural Science Foundation of China","award":["CSIEKJ230700104"],"award-info":[{"award-number":["CSIEKJ230700104"]}]},{"name":"National Energy Science and Technology Project","award":["82160347"],"award-info":[{"award-number":["82160347"]}]},{"name":"National Energy Science and Technology Project","award":["CSIEKJ230700104"],"award-info":[{"award-number":["CSIEKJ230700104"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Accurate prediction of solar irradiance holds significant value for renewable energy usage and power grid management. However, traditional forecasting methods often overlook the time dependence of solar irradiance sequences and the varying importance of different influencing factors. To address this issue, this study proposes a dual-path information fusion and twin attention-driven solar irradiance forecasting model. The proposed framework comprises three components: a residual attention temporal convolution block (RACB), a dual-path information fusion module (DIFM), and a twin self-attention module (TSAM). These components collectively enhance the performance of multi-step solar irradiance forecasting. First, the RACB is designed to enable the network to adaptively learn important features while suppressing irrelevant ones. Second, the DIFM is implemented to reinforce the model\u2019s robustness against input data variations and integrate multi-scale features. Lastly, the TSAM is introduced to extract long-term temporal dependencies from the sequence and facilitate multi-step prediction. In the solar irradiance forecasting experiments, the proposed model is compared with six benchmark models across four datasets. In the one-step predictions, the average performance metrics RMSE, MAE, and MAPE of the four datasets decreased within the ranges of 0.463\u20132.390 W\/m2, 0.439\u20132.005 W\/m2, and 1.3\u20139.2%, respectively. Additionally, the average R2 value across the four datasets increased by 0.008 to 0.059. The experimental results indicate that the model proposed in this study exhibits enhanced accuracy and robustness in predictive performance, making it a reliable alternative for solar irradiance forecasting.<\/jats:p>","DOI":"10.3390\/s23177469","type":"journal-article","created":{"date-parts":[[2023,8,28]],"date-time":"2023-08-28T06:10:22Z","timestamp":1693203022000},"page":"7469","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Dual-Path Information Fusion and Twin Attention-Driven Global Modeling for Solar Irradiance Prediction"],"prefix":"10.3390","volume":"23","author":[{"given":"Yushi","family":"Yang","sequence":"first","affiliation":[{"name":"Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming 650500, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-3959-5101","authenticated-orcid":false,"given":"Zhanjun","family":"Tang","sequence":"additional","affiliation":[{"name":"Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming 650500, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-2804-376X","authenticated-orcid":false,"given":"Zhiyuan","family":"Li","sequence":"additional","affiliation":[{"name":"Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming 650500, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianfeng","family":"He","sequence":"additional","affiliation":[{"name":"Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming 650500, China"},{"name":"Key Laboratory of Artificial Intelligence in Yunnan Province, Kunming 650500, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaobing","family":"Shi","sequence":"additional","affiliation":[{"name":"Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming 650500, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuting","family":"Zhu","sequence":"additional","affiliation":[{"name":"Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming 650500, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2023,8,28]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"96","DOI":"10.1016\/j.renene.2015.10.006","article-title":"The climatological relationships between wind and solar energy supply in Britain","volume":"87","author":"Bett","year":"2016","journal-title":"Renew. Energy"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"819","DOI":"10.1016\/j.renene.2015.09.011","article-title":"Benefits of solar forecasting for energy imbalance markets","volume":"86","author":"Kaur","year":"2016","journal-title":"Renew. Energy"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"83","DOI":"10.1016\/j.solener.2015.06.017","article-title":"Comparison of different physical models for PV power output prediction","volume":"119","author":"Dolara","year":"2015","journal-title":"Sol. Energy"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"100","DOI":"10.1016\/j.renene.2015.03.038","article-title":"Development of statistical time series models for solar power prediction","volume":"83","author":"Prema","year":"2015","journal-title":"Renew. Energy"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"128566","DOI":"10.1016\/j.jclepro.2021.128566","article-title":"Deep learning models for solar irradiance forecasting: A comprehensive review","volume":"318","author":"Kumari","year":"2021","journal-title":"J. Clean. Prod."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"65","DOI":"10.1016\/j.rser.2013.06.042","article-title":"Review of solar irradiance forecasting methods and a proposition for small-scale insular grids","volume":"27","author":"Diagne","year":"2013","journal-title":"Renew. Sustain. Energy Rev."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"116804","DOI":"10.1016\/j.enconman.2023.116804","article-title":"Hourly stepwise forecasting for solar irradiance using integrated hybrid models CNN-LSTM-MLP combined with error correction and VMD","volume":"280","author":"Liu","year":"2023","journal-title":"Energy Convers. Manag."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"121","DOI":"10.1002\/qj.49705021008","article-title":"Solar and terrestrial radiation","volume":"50","author":"Angstrom","year":"1924","journal-title":"Q. J. R. Meteorol. Soc."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"197","DOI":"10.1007\/BF02243322","article-title":"The determination of hourly values of total solar radiation from daily summations","volume":"7","author":"Whillier","year":"1956","journal-title":"Arch. F\u00fcr Meteorol. Geophys. Und Bioklimatol. Ser. B"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Atique, S., Noureen, S., Roy, V., Subburaj, V., Bayne, S., and Macfie, J. (2019, January 7\u20139). Forecasting of total daily solar energy generation using ARIMA: A case study. Proceedings of the 2019 IEEE 9th Annual Computing and Communication Workshop and Conference (CCWC), Las Vegas, NV, USA.","DOI":"10.1109\/CCWC.2019.8666481"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Yatiyana, E., Rajakaruna, S., and Ghosh, A. (2017, January 19\u201322). Wind speed and direction forecasting for wind power generation using ARIMA model. Proceedings of the 2017 Australasian Universities Power Engineering Conference (AUPEC), Melbourne, Australia.","DOI":"10.1109\/AUPEC.2017.8282494"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"1850004","DOI":"10.1142\/S2424786318500044","article-title":"Electricity price forecasting using multiple wavelet coherence method: Comparison of ARMA versus VARMA","volume":"5","year":"2018","journal-title":"Int. J. Financ. Eng."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"165207","DOI":"10.1016\/j.ijleo.2020.165207","article-title":"One month-ahead forecasting of mean daily global solar radiation using time series models","volume":"219","author":"Belmahdi","year":"2020","journal-title":"Optik"},{"key":"ref_14","first-page":"100427","article-title":"Spatial forecasting of solar radiation using ARIMA model","volume":"20","author":"Shadab","year":"2020","journal-title":"Remote Sens. Appl. Soc. Environ."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"118","DOI":"10.1016\/j.renene.2012.10.009","article-title":"Short-term solar power prediction using a support vector machine","volume":"52","author":"Zeng","year":"2013","journal-title":"Renew. Energy"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"105","DOI":"10.1016\/j.enconman.2016.03.082","article-title":"Prediction of daily and mean monthly global solar radiation using support vector machine in an arid climate","volume":"118","author":"Belaid","year":"2016","journal-title":"Energy Convers. Manag."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Ma, R., Boubrahimi, S.F., Hamdi, S.M., and Angryk, R.A. (2017, January 11\u201314). Solar flare prediction using multivariate time series decision trees. Proceedings of the 2017 IEEE International Conference on Big Data.","DOI":"10.1109\/BigData.2017.8258216"},{"key":"ref_18","unstructured":"Gupta, A., Bansal, A., and Roy, K. (2021, January 6\u20138). Solar Energy Prediction using Decision Tree Regressor. Proceedings of the 2021 5th International Conference on Intelligent Computing and Control Systems (ICICCS), Madurai, India."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"104","DOI":"10.1016\/j.solener.2018.10.018","article-title":"Performance prediction of PV module using electrical equivalent model and artificial neural network","volume":"176","author":"Mittal","year":"2015","journal-title":"Sol. Energy"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"587","DOI":"10.1016\/j.egypro.2016.11.227","article-title":"Development of ANN Based Model for Solar Potential Assessment Using Various Meteorological Parameters","volume":"90","author":"Kumar","year":"2016","journal-title":"Energy Procedia"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"012006","DOI":"10.1088\/1757-899X\/658\/1\/012006","article-title":"Solar radiation prediction based on random forest of feature-extraction","volume":"658","author":"Liu","year":"2019","journal-title":"IOP Conf. Ser. Mater. Sci. Eng."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"81","DOI":"10.1016\/j.solener.2020.01.034","article-title":"Random forest regression for improved mapping of solar irradiance at high latitudes","volume":"198","author":"Babar","year":"2020","journal-title":"Sol. Energy"},{"key":"ref_23","first-page":"935","article-title":"Hourly Solar Irradiance Prediction Based on Support Vector Machine and Its Error Analysis","volume":"32","author":"Bae","year":"2017","journal-title":"IEEE Trans. Power Syst."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"778","DOI":"10.1016\/j.apenergy.2018.12.034","article-title":"Designing a multi-stage multivariate empirical mode decomposition coupled with ant colony optimization and random forest model to forecast monthly solar radiation","volume":"236","author":"Prasad","year":"2019","journal-title":"Appl. Energy"},{"key":"ref_25","first-page":"100370","article-title":"Deakin microgrid digital twin and analysis of AI models for power generation prediction","volume":"18","author":"Natgunanathan","year":"2023","journal-title":"Energy Convers. Manag. X"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"e08803","DOI":"10.1016\/j.heliyon.2022.e08803","article-title":"Long-term power forecasting using FRNN and PCA models for calculating output parameters in solar photovoltaic generation","volume":"8","author":"Kazem","year":"2022","journal-title":"Heliyon"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"304","DOI":"10.1016\/j.procs.2017.09.045","article-title":"Solar Irradiance Forecasting Using Deep Neural Networks","volume":"114","author":"Alzahrani","year":"2017","journal-title":"Procedia Comput. Sci."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1016\/j.renene.2020.04.042","article-title":"Solar radiation prediction using recurrent neural network and artificial neural network: A case study with comparisons","volume":"156","author":"Pang","year":"2020","journal-title":"Renew. Energy"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Obiora, C.N., Ali, A., and Hasan, A.N. (2020, January 29\u201331). Forecasting Hourly Solar Irradiance Using Long Short-Term Memory (LSTM) Network. Proceedings of the 2020 11th International Renewable Energy Congress (IREC), Hammamet, Tunisia.","DOI":"10.1109\/IREC48820.2020.9310449"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"172524","DOI":"10.1109\/ACCESS.2020.3024901","article-title":"Short-Term Photovoltaic Power Forecasting Using an LSTM Neural Network and Synthetic Weather Forecast","volume":"8","author":"Hossain","year":"2020","journal-title":"IEEE Access"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"118952","DOI":"10.1016\/j.renene.2023.118952","article-title":"Advanced multimodal fusion method for very short-term solar irradiance forecasting using sky images and meteorological data: A gate and transformer mechanism approach","volume":"0960-1481","author":"Zhang","year":"2023","journal-title":"Renew. Energy"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Song, Z., and Brown, L.E. (2019, January 21\u201324). Multi-dimensional Evaluation of Temporal Neural Networks on Solar Irradiance Forecasting. Proceedings of the 2019 IEEE Innovative Smart Grid Technologies\u2014Asia (ISGT Asia), Chengdu, China.","DOI":"10.1109\/ISGT-Asia.2019.8881784"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Shekar, D.D., Hiremath, A.C., Keshava, A., and Vinatha, U. (2022, January 1\u20133). Solar Irradiance forecasting using Recurrent Neural Networks. Proceedings of the 2022 IEEE Region 10 Symposium (TENSYMP), Mumbai, India.","DOI":"10.1109\/TENSYMP54529.2022.9864498"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"4","DOI":"10.1063\/1.5110223","article-title":"Predicting day-ahead solar irradiance through gated recurrent unit using weather forecasting data","volume":"11","author":"Gao","year":"2019","journal-title":"J. Renew. Sustain. Energy"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"1041","DOI":"10.1016\/j.renene.2021.02.161","article-title":"Hybrid deep neural model for hourly solar irradiance forecasting","volume":"171","author":"Huang","year":"2021","journal-title":"Renew. Energy"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"120357","DOI":"10.1016\/j.jclepro.2020.120357","article-title":"A comprehensive review of hybrid models for solar radiation forecasting","volume":"258","author":"Guermoui","year":"2020","journal-title":"J. Clean. Prod."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"117061","DOI":"10.1016\/j.apenergy.2021.117061","article-title":"Long short term memory\u2013convolutional neural network based deep hybrid approach for solar irradiance forecasting","volume":"295","author":"Kumari","year":"2021","journal-title":"Appl. Energy"},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"26","DOI":"10.1016\/j.renene.2020.05.150","article-title":"Short-term global horizontal irradiance forecasting based on a hybrid CNN-LSTM model with spatiotemporal correlations","volume":"160","author":"Zang","year":"2020","journal-title":"Renew. Energy"},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"1665","DOI":"10.1016\/j.renene.2020.09.141","article-title":"Hourly forecasting of solar irradiance based on CEEMDAN and multi-strategy CNN-LSTM neural networks","volume":"162","author":"Gao","year":"2020","journal-title":"Renew. Energy"},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Qin, Y., Song, D., Chen, H., Cheng, W., Jiang, G., and Cottrell, G. (2017). A Dual-Stage Attention-Based Recurrent Neural Network for Time Series Prediction. arXiv.","DOI":"10.24963\/ijcai.2017\/366"},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Pan, C., Tan, J., Feng, D., and Li, Y. (2019, January 6\u20139). Very Short-Term Solar Generation Forecasting Based on LSTM with Temporal Attention Mechanism. Proceedings of the 2019 IEEE 5th International Conference on Computer and Communications (ICCC), Chengdu, China.","DOI":"10.1109\/ICCC47050.2019.9064298"},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"107387","DOI":"10.1109\/ACCESS.2021.3100105","article-title":"Two-Stage Attention Over LSTM With Bayesian Optimization for Day-Ahead Solar Power Forecasting","volume":"9","author":"Aslam","year":"2021","journal-title":"IEEE Access"},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"75237","DOI":"10.1109\/ACCESS.2020.2988909","article-title":"Novel Fault Location Method for Power Systems Based on Attention Mechanism and Double Structure GRU Neural Network","volume":"8","author":"Zhang","year":"2020","journal-title":"IEEE Access"},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"114979","DOI":"10.1016\/j.eswa.2021.114979","article-title":"A compound of feature selection techniques to improve solar radiation forecasting","volume":"178","author":"Castangia","year":"2021","journal-title":"Expert Syst. Appl."},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"533","DOI":"10.1109\/TIA.2022.3206731","article-title":"Dynamic Feature Selection for Solar Irradiance Forecasting Based on Deep Reinforcement Learning","volume":"59","author":"Lyu","year":"2023","journal-title":"IEEE Trans. Ind. Appl."},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"120109","DOI":"10.1016\/j.energy.2021.120109","article-title":"Prediction of solar energy guided by pearson correlation using machine learning","volume":"224","author":"Jebli","year":"2021","journal-title":"Energy"},{"key":"ref_47","unstructured":"Bai, S., Kolter, J.Z., and Koltun, V. (2018). An empirical evaluation of generic convolutional and recurrent networks for sequence modeling. arXiv."},{"key":"ref_48","doi-asserted-by":"crossref","unstructured":"Graves, A. (2012). Supervised Sequence Labelling with Recurrent Neural Networks, Springer.","DOI":"10.1007\/978-3-642-24797-2"},{"key":"ref_49","doi-asserted-by":"crossref","unstructured":"Liu, J., Gao, H., Yan, Q., Bai, B., and Wang, X. (2021, January 23\u201325). Short-term Load Forecasting Method Based on LSTM-Attention Mechanism. Proceedings of the 2021 IEEE Sustainable Power and Energy Conference (iSPEC), Nanjing, China.","DOI":"10.1109\/iSPEC53008.2021.9735593"},{"key":"ref_50","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":"ref_51","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, \u0141., and Polosukhin, I. (2017, January 4\u20139). Attention is all you need. Proceedings of the Neural Information Processing Systems 30 (NIPS 2017), Long Beach, CA, USA."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/17\/7469\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T20:40:48Z","timestamp":1760128848000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/17\/7469"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8,28]]},"references-count":51,"journal-issue":{"issue":"17","published-online":{"date-parts":[[2023,9]]}},"alternative-id":["s23177469"],"URL":"https:\/\/doi.org\/10.3390\/s23177469","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,8,28]]}}}