Comparison of Global Horizontal Irradiance Prediction Using LSTM and M-LSTM Across Seasonal Conditions

Rudi Kasianto; Totok Chamidy; Muhammad Faisal; M. Ainul Yaqin; M. Imamuddin

doi:10.47065/bits.v8i2.11094

Rudi Kasianto * Universitas Islam Negeri Maulana Malik Ibrahim, Malang, Indonesia
Totok Chamidy Universitas Islam Negeri Maulana Malik Ibrahim, Malang, Indonesia
Muhammad Faisal Universitas Islam Negeri Maulana Malik Ibrahim, Malang, Indonesia
M. Ainul Yaqin Universitas Islam Negeri Maulana Malik Ibrahim, Malang, Indonesia
M. Imamuddin Universitas Islam Negeri Maulana Malik Ibrahim, Malang, Indonesia

(*) Corresponding Author

DOI: https://doi.org/10.47065/bits.v8i2.11094

Keywords: Global Horizontal Irradiance; LSTM; Multivariate LSTM; Solar Irradiance Forecasting; Sliding Window

Abstract

Short-term prediction of Global Horizontal Irradiance (GHI) is challenging because solar radiation exhibits dynamic temporal patterns and rapidly responds to changing atmospheric conditions. This study compares univariate Long Short-Term Memory (LSTM) and multivariate LSTM models using four and six predictor variables (M-LSTM-4 and M-LSTM-6) for 30-minute-ahead GHI forecasting using Automatic Solar Radiation Station data from Malang, East Java. One-minute observations were aggregated into 30-minute intervals and evaluated using sliding windows of 12, 24, and 36 timesteps. Model performance was assessed using Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and the coefficient of determination (R²) for full-year, wet-season, and dry-season datasets. For the full-year dataset, M-LSTM-6 with a 12-timestep window achieved the best performance, with an MAE of 37.700 W/m², an RMSE of 79.340 W/m², and an R² of 0.9283. In contrast, M-LSTM-4 provided the best performance for both seasonal datasets using a 36-timestep window, achieving an MAE of 36.551 W/m² and an R² of 0.9378 during the wet season, and an MAE of 39.181 W/m² and an R² of 0.9454 during the dry season. M-LSTM-6 showed substantial performance degradation with longer historical windows, particularly during the dry season. This result suggests that combining a larger number of predictors with longer historical sequences increases the amount of input information processed by the model, which may be less effective when the additional historical information does not provide proportional predictive benefit under rapidly varying irradiance conditions. The results demonstrate that the effectiveness of multivariate information depends on predictor relevance, historical window length, and seasonal conditions. The main contribution of this study is the identification of different optimal combinations of predictor complexity and historical window length between full-year and seasonal GHI forecasting. Overall, the findings indicate that input-variable complexity and window length should be jointly optimized for local short-term GHI forecasting.

Downloads

Download data is not yet available.

References

S. Gbémou, J. Eynard, S. Thil, E. Guillot, and S. Grieu, “A Comparative Study of Machine Learning-Based Methods for Global Horizontal Irradiance Forecasting,” Energies (Basel)., vol. 14, no. 11, pp. 1–23, 2021, doi: 10.3390/en14113192.

N. E. Michael, S. Hasan, A. Al-Durra, and M. Mishra, “Short-Term Solar Irradiance Forecasting Based on A Novel Bayesian Optimized Deep Long Short-Term Memory Neural Network,” Appl. Energy, vol. 324, p. 119727, 2022, doi: 10.1016/j.apenergy.2022.119727.

M. Neshat, M. Majidi, S. Mirjalili, and D. Astiaso, “Short-Term Solar Radiation Forecasting Using Hybrid Deep Residual Learning and Gated LSTM Recurrent Network with Differential Covariance Matrix Adaptation Evolution Strategy,” Energy, vol. 278, p. 127701, 2023, doi: 10.1016/j.energy.2023.127701.

M. Ansong, G. Huang, T. N. Nyang’onda, R. J. Musembi, and B. S. Richards, “Very Short-Term Solar Irradiance Forecasting Based on Open-Source Low-Cost Sky Imager and Hybrid Deep-Learning Techniques,” Solar Energy, vol. 294, 2025, doi: 10.1016/j.solener.2025.113516.

G. Alkhayat, S. H. Hasan, and R. Mehmood, “SENERGY: A Novel Deep Learning-Based Auto-Selective Approach and Tool for Solar Energy Forecasting,” Energies (Basel)., vol. 15, no. 18, 2022, doi: 10.3390/en15186659.

A. Gupta, S. Sharma, and S. Saroha, “A New Hybrid Short Term Solar Irradiation Forecasting Method Based on CEEMDAN Decomposition Approach and BiLSTM Deep Learning Network with Grid Search Algorithm,” Distributed Generation and Alternative Energy Journal, vol. 38, no. 4, pp. 1073–1118, 2023, doi: 10.13052/dgaej2156-3306.3842.

D. Díaz-Bedoya, M. González-Rodríguez, X. Serrano-Guerrero, and J.-M. Clairand, “Solar Irradiance Forecasting With Deep Learning and Ensemble Models: LSTM, Random Forest and Extra Trees With Multivariate Meteorological Data,” IET Smart Grid, vol. 8, no. 1, 2025, doi: 10.1049/stg2.70019.

G. H. Park and J. C. Kim, “Multivariate Variable-Based LSTM-AE Model for Solar Power Prediction,” Int. J. Adv. Sci. Eng. Inf. Technol., vol. 15, no. 1, pp. 293–299, 2025, doi: 10.18517/ijaseit.15.1.20944.

M. Ajith and M. Martínez-Ramón, “Deep Learning Algorithms for Very Short Term Solar Irradiance Forecasting: A Survey,” Renewable and Sustainable Energy Reviews, vol. 182, p. 113362, 2023, doi: 10.1016/j.rser.2023.113362.

S. Hochreiter and J. Schmidhuber, “Long Short-Term Memory,” Neural Comput., vol. 9, no. 8, pp. 1735–1780, 1997, doi: 10.1162/neco.1997.9.8.1735.

N. Y. Hendrikx, K. Barhmi, L. R. Visser, T. A. de Bruin, M. Pó, A. A. Salah, and W. G. J. H. M. van Sark, “All Sky Imaging-Based Short-Term Solar Irradiance Forecasting with Long Short-Term Memory Networks,” Solar Energy, vol. 272, 2024, doi: 10.1016/j.solener.2024.112463.

F. R. Alharbi and D. Csala, “Wind Speed and Solar Irradiance Prediction Using A Bidirectional Long Short-Term Memory Model Based on Neural Networks,” Energies (Basel)., vol. 14, no. 20, 2021, doi: 10.3390/en14206501.

M. Alkhatib, F. Y. Alsadi, J. Ramadan, M. Nasser, R. Awdallah, A. Chrysikopoulos, and C. V. Maalouf, “Comparative Analysis of Deep Learning Techniques for Global Horizontal Irradiance Forecasting in US Cities,” Clean Energy, vol. 9, pp. 66–83, 2025, doi: 10.1093/ce/zkae097.

K. Kaysal, F. O. Hocaoglu, A. H. Yurttakal, and H. Erbay, “M/LSTM-GRU Hybrid Model for Solar Radiation Estimation,” Comptes rendus de l’Académie bulgare des Sciences, vol. 78, no. 6, pp. 894–903, 2025, doi: 10.7546/CRABS.2025.06.12.

S. C. Bektas and I. H. Altas, “DWT-Bilstm-Based Models for Day-Ahead Hourly Global Horizontal Solar Irradiance Forecasting,” Neural Comput. Appl., vol. 36, pp. 13243–13253, 2024, doi: 10.1007/s00521-024-09701-2.

V. Nourani, E. Sharghi, N. Behfar, and Y. Zhang, “Multi-Step-Ahead Solar Irradiance Modeling Employing Multi-Frequency Deep Learning Models and Climatic Data,” Appl. Energy, vol. 315, p. 119069, 2022, doi: 10.1016/j.apenergy.2022.119069.

B.-K. Jeon and E.-J. Kim, “Solar Irradiance Prediction Using Reinforcement Learning Pre-Trained with Limited Historical Data,” Energy Reports, vol. 10, pp. 2513–2524, 2023, doi: 10.1016/j.egyr.2023.09.042.

A. K. Chaaban and N. Alfadl, “A Comparative Study of Machine Learning Approaches for An Accurate Predictive Modeling Of Solar Energy Generation,” Energy Reports, vol. 12, pp. 1293–1302, 2024, doi: 10.1016/j.egyr.2024.07.010.

C. I. Otuka, D. Cai, C. C. Ukwuoma, S. Luo, Z. Yang, O. Bamisile, C. D. Ukwuoma, C. U. Otuka, N. O. Otuka, and Q. Huang, “Experimental Review and Recent Advances in Deep Learning Techniques for Solar Irradiance Forecasting and Prediction,” Solar Energy, vol. 304, p. 114175, 2026, doi: 10.1016/j.solener.2025.114175.

H.-M. Zuo, J. Qiu, Y.-H. Jia, Q. Wang, and F.-F. Li, “Ten-Minute Prediction Of Solar Irradiance Based on Cloud Detection and A Long Short-Term Memory (LSTM) Model,” Energy Reports, vol. 8, pp. 5146–5157, 2022, doi: 10.1016/j.egyr.2022.03.182.

Z. Bounoua and A. Mechaqrane, “Hourly And Sub-Hourly Ahead Global Horizontal Solar Irradiation Forecasting Via a Novel Deep Learning Approach: A Case Study,” Sustainable Materials and Technologies, vol. 36, p. e00599, 2023, doi: 10.1016/j.susmat.2023.e00599.

M. T. Tsai and I. C. Lo, “Application of Long Short-Term Memory Networks and SHAP Evaluation in the Solar Radiation Forecast,” Energies (Basel)., vol. 18, p. 6099, 2025, doi: 10.3390/en18236099.

L. S. Hoyos-Gómez, J. F. Ruiz-Muñoz, and B. J. Ruiz-Mendoza, “Short-term forecasting of global solar irradiance in tropical environments with incomplete data,” Appl. Energy, vol. 307, p. 118192, 2022, doi: 10.1016/j.apenergy.2021.118192.

Bila bermanfaat silahkan share artikel ini

Berikan Komentar Anda terhadap artikel Comparison of Global Horizontal Irradiance Prediction Using LSTM and M-LSTM Across Seasonal Conditions