journal article
Open Access
Mar 27, 2026
Advanced Multivariate Deep Learning Methodology for Forecasting Wind Speed and Solar Irradiation
Abstract
The transition to smart cities is accelerating distributed wind and solar deployment. However, their intermittency challenges grid operation, thereby making accurate machine-learning-based prediction of wind speed and global horizontal irradiance (GHI) crucial. This study presents a cost-effective approach that enhances prediction accuracy by extracting additional features from timestamp records for deep learning models used to forecast GHI and wind speed. Unlike conventional methods that require onsite meteorological measurements, the proposed approach uses only date and time information as inputs to multivariate deep neural networks, including recurrent neural networks, gated recurrent units, long short-term memory (LSTM), bidirectional LSTM, and convolutional neural networks. For wind speed prediction, the proposed configuration achieves R2 up to 0.9987, with RMSE as low as 0.067 m/s for 3 d ahead forecasting, outperforming univariate baselines and matching models. For GHI forecasting, the time-based configuration attains R2 values above 0.9994 in 12 h ahead predictions, with the RMSE reduced to approximately 4.47 W/m2, representing a substantial improvement over univariate models. The proposed framework maintains strong performance, particularly under clear and sunny conditions. These results demonstrate that timestamp-engineered features can deliver forecasting accuracy comparable to conventional multivariate meteorological models while significantly reducing infrastructure requirements, making the approach well-suited for scalable smart city energy management.
Topics
No keywords indexed for this article. Browse by subject →
References
70
[1]
Bisegna, F., Vespasiano, F., Pompei, L., Burattini, C., Belli, E., Bellucci, A.M., Di Vittorio, F., and Blaso, L. (2026). Towards the Decarbonization of Urban Communities: Evaluation of Smart and Green Strategies to Reduce Gas Carbon Emissions. Smart Cities, 9.
10.3390/smartcities9020026
[2]
Elmousalami, H., Alnaser, A.A., and Kin Peng Hui, F. (2024). Advancing Smart Zero-Carbon Cities: High-Resolution Wind Energy Forecasting to 36 Hours Ahead. Appl. Sci., 14.
10.3390/app142411918
[3]
Restrepo "Fossil or bioenergy? Global fuel market trends" Renew. Sustain. Energy Rev. (2021) 10.1016/j.rser.2021.110905
[4]
Ritchie, H., Roser, M., and Rosado, P. (2026, February 18). Renewable Energy. Our World in Data. Available online: https://ourworldindata.org/renewable-energy.
[5]
International Energy Agency (IEA) (2022). Renewable Power Generation by Technology in the Net Zero Scenario, 2010–2030, IEA. Available online: https://www.iea.org/data-and-statistics/charts/renewable-power-generation-by-technology-in-the-net-zero-scenario-2010-2030.
[6]
Ahmed "Grid integration challenges of wind energy: A review" IEEE Access (2020) 10.1109/access.2020.2964896
[7]
Shafiullah "Grid integration challenges and solution strategies for solar PV systems: A review" IEEE Access (2022) 10.1109/access.2022.3174555
[8]
Ruhnau "Economic implications of forecasting electricity generation from variable renewable energy sources" Renew. Energy (2020) 10.1016/j.renene.2020.06.110
[9]
Amir "Assessment of renewable energy: Status, challenges, COVID-19 impacts, opportunities, and sustainable energy solutions in Africa" Energy Built Environ. (2022) 10.1016/j.enbenv.2021.03.002
[10]
Mastoi "Large-scale wind power grid integration challenges and their solutions: A detailed review" Environ. Sci. Pollut. Res. (2023) 10.1007/s11356-023-29653-9
[11]
Tang "Flexibility categorization, sources, capabilities and technologies for energy-flexible and grid-responsive buildings: State-of-the-art and future perspective" Energy (2021) 10.1016/j.energy.2020.119598
[12]
Li "A review on the integration of probabilistic solar forecasting in power systems" Sol. Energy (2020) 10.1016/j.solener.2020.07.066
[13]
Lv, Q., Zhang, J., Zhang, J., Zhang, Z., Zhou, Q., Gao, P., and Zhang, H. (2025). Short-Term Wind Power Prediction Model Based on PSO-CNN-LSTM. Energies, 18.
10.3390/en18133346
[14]
Zhong, Q., Wang, L., and Huang, C. (2026). T-LSTM: A Novel Model for High-Precision Wind Power Prediction by Integrating Transformer and Improved LSTM. Appl. Sci., 16.
10.3390/app16031609
[15]
Cisse, B.B., Rashed, G.I., Badjan, A., Haider, H., Gony, H.A.I., and Ershad, A.M. (2026). Optimized Hybrid Deep Learning Framework for Reliable Multi-Horizon Photovoltaic Power Forecasting in Smart Grids. Electricity, 7.
10.3390/electricity7010004
[16]
Alguhi, A.A., and Al-Shaalan, A.M. (2025). LSTM-Based Prediction of Solar Irradiance and Wind Speed for Renewable Energy Systems. Energies, 18.
10.3390/en18174594
[17]
Li, B., Ding, B., Pang, W., and Ni, H. (2025). Triple-Flow Dynamic Graph Convolutional Network for Wind Power Forecasting. Symmetry, 17.
10.3390/sym17122026
[18]
Yaghi, M.A., and Al-Omari, H. (2026). Physics-Aware Deep Learning Framework for Solar Irradiance Forecasting Using Fourier-Based Signal Decomposition. Algorithms, 19.
10.3390/a19010081
[19]
Sweeney "The future of forecasting for renewable energy" WIREs Energy Environ. (2020) 10.1002/wene.365
[20]
A hybrid framework for forecasting power generation of multiple renewable energy sources
Jianqin Zheng, Jian Du, Bohong Wang et al.
Renewable and Sustainable Energy Reviews
2023
10.1016/j.rser.2022.113046
[21]
Su "An intra-hour photovoltaic power generation prediction method for flexible building energy systems and its application in operation scheduling strategy" Sol. Energy (2024) 10.1016/j.solener.2024.113031
[22]
"A short-term solar radiation forecasting system for the Iberian Peninsula. Part 1: Models description and performance assessment" Sol. Energy (2020) 10.1016/j.solener.2019.11.028
[23]
Apeh "Machine learning approach for short- and long-term global solar irradiance prediction" J. Energy Environ. Sustain. (2024)
[24]
Almaghrabi "Multivariate solar power time series forecasting using multilevel data fusion and deep neural networks" Inf. Fusion (2024) 10.1016/j.inffus.2023.102180
[25]
Mfetoum "A multilayer perceptron neural network approach for optimizing solar irradiance forecasting in Central Africa with meteorological insights" Sci. Rep. (2024) 10.1038/s41598-024-54181-y
[26]
Ribeiro "Identifying representative days of solar irradiance and wind speed in Brazil using machine learning techniques" Energy AI (2024) 10.1016/j.egyai.2023.100320
[27]
Monteiro, C., Bessa, R., Miranda, V., Botterud, A., Wang, J., and Conzelmann, G. (2009). Wind Power Forecasting: State-of-the-Art 2009, Argonne National Laboratory.
10.2172/968212
[28]
Patel "Machine intelligent hybrid methods based on Kalman filter and wavelet transform for short-term wind speed prediction" Wind (2022) 10.3390/wind2010003
[29]
Ding "Copula-based JPDF of wind speed, wind direction, wind angle, and temperature with SHM data" Probab. Eng. Mech. (2023) 10.1016/j.probengmech.2023.103483
[30]
He "A short-time wind speed forecasting method based on feature selection and KF-CNN-LSTM hybrid model" J. Supercomput. (2025) 10.1007/s11227-025-07887-3
[31]
Liu "Short-term offshore wind speed forecast by seasonal ARIMA—A comparison against GRU and LSTM" Energy (2021) 10.1016/j.energy.2021.120492
[32]
Freire "Optimizing wind power forecasting with hybrid neural networks: Insights from Brazil" Neural Comput. Appl. (2025) 10.1007/s00521-025-11464-3
[33]
Wang "A deep-learning wind speed interval forecasting architecture based on modified scaling approach with feature ranking and two-output gated recurrent unit" Expert Syst. Appl. (2023) 10.1016/j.eswa.2022.118419
[34]
Joseph "Near real-time wind speed forecast model with bidirectional LSTM networks" Renew. Energy (2023) 10.1016/j.renene.2022.12.123
[35]
Wang "Wind speed interval prediction based on multidimensional time series of convolutional neural networks" Eng. Appl. Artif. Intell. (2023) 10.1016/j.engappai.2023.105987
[36]
Liu "A unified multi-step wind speed forecasting framework based on numerical weather prediction grids and wind farm monitoring data" Renew. Energy (2023) 10.1016/j.renene.2023.05.006
[37]
Zhang "Developing a hybrid probabilistic model for short-term wind speed forecasting" Appl. Intell. (2023) 10.1007/s10489-022-03644-8
[38]
Lv "Multivariate wind speed forecasting based on multi-objective feature selection approach and hybrid deep learning model" Energy (2023) 10.1016/j.energy.2022.126100
[39]
Comparison of three machine learning models for the prediction of hourly PV output power in Saudi Arabia
Abdullahi Abubakar Mas'ud
Ain Shams Engineering Journal
2022
10.1016/j.asej.2021.11.017
[40]
Samadianfard "Innovative strategies for hourly global horizontal irradiance forecasting using a hybrid gated recurrent unit and long short-term memory architecture with spatio-temporal attention mechanism" Earth Sci. Inform. (2025) 10.1007/s12145-025-01947-1
[41]
Alkhatib "Comparative analysis of deep learning techniques for global horizontal irradiance forecasting in US cities" Clean Energy (2025) 10.1093/ce/zkae097
[42]
Liu "Development and trending of deep learning methods for wind power predictions" Artif. Intell. Rev. (2024) 10.1007/s10462-024-10728-z
[43]
Azimi "A hybrid wind power forecasting model based on data mining and wavelet analysis" Energy Convers. Manag. (2016) 10.1016/j.enconman.2016.09.002
[44]
Mastoi "AI-driven control and optimization for renewable energy integration in smart grids: Challenges, applications, and future research directions" Energy Strat. Rev. (2026) 10.1016/j.esr.2026.102049
[45]
Elmousaid "Ultra-short-term global horizontal irradiance forecasting based on a novel hybrid GRU–TCN model" Results Eng. (2024) 10.1016/j.rineng.2024.102817
[46]
Kumar "Forecasting wind speed over multiple horizons: Superiority of deep learning and decomposition-driven hybrid models" Unconv. Resour. (2026)
[47]
Pang "Shape-aware Seq2Seq model for accurate multistep wind speed forecasting" J. Ocean Univ. China (2026) 10.1007/s11802-026-6145-7
[48]
Otuka "Experimental review and recent advances in deep learning techniques for solar irradiance forecasting and prediction" Sol. Energy (2026) 10.1016/j.solener.2025.114175
[49]
Kumari "Long short-term memory–convolutional neural network based deep hybrid approach for solar irradiance forecasting" Appl. Energy (2021) 10.1016/j.apenergy.2021.117061
[50]
Kiziloklu, I.D., and Cifci, U. (2024, February 23). Solar Radiation and Meteorological Dataset. Kaggle. Available online: https://www.kaggle.com/datasets/ibrahimkiziloklu/solar-radiation-dataset/data.
Showing 50 of 70 references
Metrics
0
Citations
70
References
Details
- Published
- Mar 27, 2026
- Vol/Issue
- 9(4)
- Pages
- 59
- License
- View
Authors
Cite This Article
Md Shafiullah, Abdul Rahman Katranji, Mannan Hassan, et al. (2026). Advanced Multivariate Deep Learning Methodology for Forecasting Wind Speed and Solar Irradiation. Smart Cities, 9(4), 59. https://doi.org/10.3390/smartcities9040059
Related
You May Also Like
Introducing the “15-Minute City”: Sustainability, Resilience and Place Identity in Future Post-Pandemic Cities
Carlos Moreno, Zaheer Allam · 2021
1,459 citations
IoT-Enabled Smart Sustainable Cities: Challenges and Approaches
Laura Belli, Antonio Cilfone · 2020
195 citations
Artificial Intelligence in Smart Cities—Applications, Barriers, and Future Directions: A Review
Radosław Wolniak, Kinga Stecuła · 2024
187 citations
Barcelona under the 15-Minute City Lens: Mapping the Accessibility and Proximity Potential Based on Pedestrian Travel Times
Carles Ferrer-Ortiz, Oriol Marquet · 2022
184 citations
Advanced Adaptive Street Lighting Systems for Smart Cities
Gianfranco Gagliardi, Marco Lupia · 2020
100 citations