Review of Forecasting Models for Solar Energy Applications Using Machine Learning
Keywords:
Solar irradiance forecasting, multi-horizon prediction, Machine learning, Deep learning, Renewable energy, Time series analysisAbstract
Efficiently incorporating solar energy into today's power system necessitates accurate solar radiation forecasting across multiple time horizons. The prediction of solar irradiance across short-term (minutes to hours), medium-term (day ahead), and long-term (weeks to months) involves its unique challenges due to the inherent variability and nonlinearity of atmospheric conditions. In recent years, machine learning (ML) approaches have emerged as effective tools for coping with these challenges, in many scenarios proving to be superior to traditional statistical and physical models. The main goal of this article is to investigate various state-of-the-art machine learning models to forecast solar irradiance for multiple time horizons. Particularly, it studies traditional machine learning models like Support Vector Machines (SVM), Random Forests (RF), Gradient Boosting, some new variants of deep learning architecture like Recurrent Neural Networks (RNNs), Long Short-Term Memory (LSTM), Gated Recurrent Units (GRUs), and Transformer models. The review also presents hybrid and ensemble models through a combination of a physical model and data-driven approaches. Moreover, the review highlighted essential input features such as meteorological variables, satellite imagery, and sky images, along with various preprocessing methods and evaluation metrics. It critically examines challenges such as data scarcity, generalization of models, interpretability, and computational complexity. Finally, future research strategies will focus on the roles of explainable AI, transfer learning, and real-time forecasting systems.
References
Ghiate, Saida. "Comparative analysis of machine learning and hybrid models for global horizontal irradiance prediction: a case study in Morocco." International Journal of Energy and Water Resources 10.1 (2026): 20.
Barhmi, K., et al. "Real-time solar irradiance forecasting for grid integration using all-sky imagery and multi-stage AI with Kalman filter optimization." Renewable Energy 259 (2026): 125117.
Albaqami, Hezam, et al. "A Hybrid Wavelet Transformer LightGBM Model Optimized by Optuna–TPE for Global Irradiance Forecasting in Solar Electric Vehicle Energy Management." Results in Engineering (2026): 109678.
Taganova, Guldana, et al. "Sub-Hourly Multi-Horizon Quantile Forecasting of Photovoltaic Power Using Meteorological Data and a HybridCNN–STTransformer." Algorithms 19.2 (2026): 123.
Mansoor, Majad, et al. "MHFTNet: Enhanced temporal feature extraction architecture for integrated solar & wind energy prediction in short, medium and long terms integrated energy trade." Energy Conversion and Management: X (2026): 101730.
Kim, Eun Ji, et al. "Evaluation of Photovoltaic Generation Forecasting Using Model Output Statistics and Machine Learning." Energies 19.2 (2026): 486.
Long, Jiancheng, Zihong Long, and Jiajie Yu. "Optics-guided and physics-guided multisource deep learning framework for short-term photovoltaic power forecasting." Third International Conference on Big Data, Computational Intelligence, and Applications (BDCIA 2025). Vol. 14128. SPIE, 2026.
CHOUDER, A., et al. "Adaptive LSR Fusion of Multi-Scale 3-Branch CNN-BiLSTM, LSTM and CNN-BiLSTM models for Robust Multi-Seasonal and Multi-Horizon Weather Forecasting in Renewable Energy Management."
Palandi, Reza Khodabakhshi, Loredana Cristaldi, and Luca Martiri. "Multi-Scale Photovoltaic Power Forecasting with WDT–CRMABIL–Fusion: A Two-Stage Hybrid Deep Learning Framework." Energies 19.2 (2026): 455.
Erdmann, Niklas, et al. "Multi-Horizon Time Series Forecasting of Non-Parametric CDFs with Deep Lattice Networks." Proceedings of the AAAI Conference on Artificial Intelligence. Vol. 40. No. 1. 2026.
Sharma, Girijapati, Subhash Chandra, and Arvind Kumar Yadav. "A Stacked GRU Approach to Enhance Predictive Accuracy of Global Horizontal Irradiance." MAPAN (2026): 1-31.
Moghadam Dost, Danial, et al. "Forecasting EV Charging Load with a Temporal Fusion Transformer: A Multi-Horizon and Interpretable Approach with Environmental Features." Mohsen and Eskandari, Aref and Peyravi, Mohammad Javad, Forecasting EV Charging Load with a Temporal Fusion Transformer: A Multi-Horizon and Interpretable Approach with Environmental Features.
Reina-Jiménez, P., et al. "A novel interpretable ozone forecasting approach based on deep learning with masked residual connections." Environmental Modelling & Software (2026): 106878.
Chou, Yen-Hsi, and Anderson Rodrigo de Queiroz. "Spatio-Temporal Solar Power Forecasting Using GAN-Enhanced Irradiance Maps and Deep Neural Networks." Available at SSRN 6314960.
Rong, Yi, et al. "Optics-guided stacking ensemble learning for short-term photovoltaic power forecasting using all-sky images." Third International Conference on Big Data, Computational Intelligence, and Applications (BDCIA 2025). Vol. 14128. SPIE, 2026.
Wang, Mingyang, et al. "Day-ahead power forecasting of self-cleaning nanocoated and conventional rooftop PV systems using SHAP-RFE-MCCV feature selection and deep learning." Energy and Buildings (2026): 117054.
Jazayeri, Pedram, et al. "Bridging prediction and optimization: A unified MINLP, traditional machine learning and deep learning framework for water distribution networks management." Ain Shams Engineering Journal 17.1 (2026): 103834.
Hassan, Amal A., et al. "Multi-label machine learning for power forecasting of a grid-connected photovoltaic solar plant over multiple time horizons." Scientific Reports 15.1 (2025): 32676.
Aboelkhair, Hassan, et al. "Ensemble Deep Learning for Global Solar Irradiance Forecasting in Egypt: A Multi-Model Approach." Earth Systems and Environment (2026): 1-17.
Cisse, Bilali Boureima, et al. "Optimized Hybrid Deep Learning Framework for Reliable Multi-Horizon Photovoltaic Power Forecasting in Smart Grids." Electricity 7.1 (2026): 4.
Benbrahim, Saad, et al. "Deep Learning Approach for Solar Irradiance Forecasting: A Moroccan Case." Advances in Electrical Systems and Innovative Renewable Energy Techniques: The Proceedings of the International Conference on Electrical Systems and Automation (Volume 1). Vol. 1. Springer Nature, 2024.
Singla, Pardeep, et al. "A solar irradiance forecasting model using iterative filtering and bidirectional long short-term memory." Energy Sources, Part A: Recovery, Utilization, and Environmental Effects 46.1 (2024): 8202-8222.
Hu, Xinyang. "Weather phenomena monitoring: Optimizing solar irradiance forecasting with temporal fusion transformer." IEEE Access 12 (2024): 194133-194149.
Jing, Tao, et al. "SolarFusionNet: Enhanced solar irradiance forecasting via automated multi-modal feature selection and cross-modal fusion." IEEE Transactions on Sustainable Energy 16.2 (2024): 761-773.
Erdmann, Niklas, et al. "Deep and Probabilistic Solar Irradiance Forecast at the Arctic Circle." 2024 IEEE 52nd Photovoltaic Specialist Conference (PVSC). IEEE, 2024.
Michael, Neethu Elizabeth, et al. "A cohesive structure of Bi-directional long-short-term memory (BiLSTM)-GRU for predicting hourly solar radiation." Renewable Energy 222 (2024): 119943.
Moradzadeh, Arash, et al. "Generalized global solar radiation forecasting model via cyber-secure deep federated learning." Environmental Science and Pollution Research 31.12 (2024): 18281-18295.
Ramsamooj, Neil, and Joshua Davis. "The application of deep learning methods in the forecasting and imputation of solar irradiance data." West Indian Journal of Engineering (2024): 64-78.
Ali, Hani Saed Faraj, and Nihan Kazak Çerçevik. "Optimizing Renewable Energy Utilization: A Study on Solar Radiation Forecasting with LSTM-Conv1D Models in Libya." 2024 8th International Symposium on Innovative Approaches in Smart Technologies (ISAS). IEEE, 2024.
Xu, Shaozhen, et al. "Minutely multi-step irradiance forecasting based on all-sky images using LSTM-InformerStack hybrid model with dual feature enhancement." Renewable Energy 224 (2024): 120135.
Colucci, Ray, and Imad Mahgoub. "Generalizable Solar Irradiance Prediction for Battery Operation Optimization in IoT-Based Microgrid Environments." Journal of Sensor and Actuator Networks 14.1 (2024): 3.
Saha, Sohag Kumar, and Satish M. Mahajan. "Multivariate Optimal Hybrid Deep Learning Model for Forecasting of Day-Ahead Solar Irradiance with Meteorological Constraints." 2024 56th North American Power Symposium (NAPS). IEEE, 2024.
Downloads
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
