Short-term photovoltaic power forecasting in Çanakkale, Türkiye: A comparative study of machine learning, deep learning, and hybrid models

Abstract

This study investigates the short-term photovoltaic (PV) power forecasting problem using real field data and comparatively evaluates the performance of different forecasting approaches. The study utilizes active power and meteorological data from a 1 MW installed capacity PV plant located in Çanakkale province, northwest Turkey, with a 15-minute sampling interval. The dataset covers the period from August 2022 to August 2024, and only daytime data with solar irradiance above 20 W/m² were considered to minimize the negative impact of zero production on the model. Forecasting performance was analyzed for 15-minute (h = 1) and 60-minute (h = 4) forward forecasting horizons.In the comparative analysis, the persistence method was used as the basic reference model; Ridge regression, support vector regression (SVR), and LSBoost model were used as machine learning-based methods; Long-short-term memory (LSTM) and gated recurrent unit (GRU) networks were evaluated as deep learning-based methods. Additionally, a hybrid VMD+LSTM model combining Variational Mode Decomposition (VMD) with an LSTM network was investigated as a current signal decomposition-based approach. The models were evaluated using RMSE, MAE, normalized RMSE (nRMSE), and coefficient of determination (R²) metrics on a dataset separated by 70% training, 15% validation, and 15% testing ratios without time-order distortion.The results showed that the persistence model offered competitive performance at a very short prediction horizon (h = 1), but the accuracy of this approach decreased significantly as the prediction horizon increased. For 60-minute forward prediction, deep learning models produced more successful results; the optimized LSTM model achieved the best performance with 9.69% nRMSE and an R² value of 0.884. In contrast, while the VMD+LSTM hybrid model produced promising results during the validation phase, it exhibited poor generalization performance on the test set. This finding reveals that decomposition-based hybrid approaches are not superior in all conditions.

Keywords

• Photovoltaic power forecasting
• Short-term forecasting
• LSTM
• GRU
• Variational mode decomposition
• Machine learning

References

1. [1] Aydın A, Dindar T, Alp E. Investigating the performance impact of solar panels; a sample application in Izmir province with the PVsyst program. International Journal of Energy Studies, 2025; 10(3): 951-962.
2. [2] International Energy Agency (IEA). Renewables 2023: Analysis and Forecast to 2028. IEA Publications, Paris, France, 2023.
3. [3] Lauret P, David M, Pinson P. Verification of solar irradiance probabilistic forecasts. Solar Energy 2019; 194: 254–271.
4. [4] Mellit A, Kalogirou SA. Artificial intelligence techniques for photovoltaic applications: A review. Progress in Energy and Combustion Science 2008; 34: 574–632.
5. [5] Ahmed R, Sreeram V, Mishra Y, Arif MD. A review and evaluation of the state-of-the-art in PV solar power forecasting: Techniques and optimization. Renewable and Sustainable Energy Reviews 2020; 124: 109792.
6. [6] Reikard H. Predicting solar radiation at high resolutions: A comparison of time series forecasts. Solar Energy 2009; 83: 342–349.
7. [7] Chen C, Duan S, Cai T, Liu B. Online 24-h solar power forecasting based on weather type classification using artificial neural network. Solar Energy 2011; 85: 2856–2870.
8. [8] Shi J, Lee WJ, Liu Y, Yang Y, Wang P. Forecasting power output of photovoltaic systems based on weather classification and support vector machines. IEEE Transactions on Industry Applications 2012; 48: 1064–1069.

9. [9] Wang J, Li P, Ran R, Che Y, Zhou Y. A short-term photovoltaic power prediction model based on the gradient boost decision tree. Applied Sciences 2018; 8(5): 689.
10. [10] Hochreiter S, Schmidhuber J. Long short-term memory. Neural Computation 1997; 9: 1735–1780.
11. [11] Chung J, Gulcehre C, Cho K, Bengio Y. Empirical evaluation of gated recurrent neural networks on sequence modeling. Available from: https://arxiv.org/abs/1412.3555 Accessed: January 02, 2025. [Online].
12. [12] Zhang T, Zhang X, Choi SS, Chau TK, Chow Y, Fernando T, Iu HHC. Highly accurate peak and valley prediction short-term net load forecasting approach based on decomposition for power systems with high PV penetration. Applied Energy 2023; 333: 120641.
13. [13] Cao L, Yang H, Zhou C, Wang S, Shen Y, Yuan B. Photovoltaic short-term output power forecast model based on improved complete ensemble empirical mode decomposition with adaptive noise–kernel principal component analysis–long short-term memory. Energies 2024; 17(24): 6365.
14. [14] Liu Y, Liu Y, Cai H, Zhang J. An innovative short-term multihorizon photovoltaic power output forecasting method based on variational mode decomposition and a capsule convolutional neural network. Applied Energy 2023; 343: 121139.
15. [15] Xiang X, Li X, Zhang Y, Hu J. A short-term forecasting method for photovoltaic power generation based on the TCN–ECANet–GRU hybrid model. Scientific Reports 2024; 14(1): 6744.
16. [16] Wang J, Zhang Z, Xu W, Li Y, Niu G. Short-term photovoltaic power forecasting using a Bi-LSTM neural network optimized by hybrid algorithms. Sustainability 2025; 17(12): 5277.
17. [17] Piantadosi G, Dutto S, Galli A, De Vito S, Sansone C, Di Francia G. Photovoltaic power forecasting: A transformer-based framework. Energy and AI 2024; 18: 100444.
18. [18] Zhou N, Shang BW, Zhang JS, Xu MM. Research on prediction method of photovoltaic power generation based on transformer model. Frontiers in Energy Research 2024; 12: 1452173.
19. [19] Hou Z, Zhang Y, Liu Q, Ye X. A hybrid machine learning forecasting model for photovoltaic power. Energy Reports 2024; 11: 5125–5138.
20. [20] Zhai C, He X, Cao Z, Abdou-Tankari M, Wang Y, Zhang M. Photovoltaic power forecasting based on VMD–SSA–Transformer: Multidimensional analysis of dataset length, weather mutation and forecast accuracy. Energy 2025; 324: 135971.
21. [21] Hu F, Zhang L, Wang J. A hybrid Conv-LSTM-attention framework for short-term PV power forecasting incorporating data from neighboring stations. Available from: https://www.preprints.org/frontend/manuscript/2683edbca73066dac7026ea4e7a9d267/download_pub Accessed: December 25, 2024. [Online].
22. [22] El Robrini F, Amrouche B, Cali U, Ustun TS. Assessment of machine and deep learning models integrated with variational mode decomposition for photovoltaic power forecasting using real-world data from the semi-arid region of Djelfa, Algeria. Energy Conversion and Management: X 2025; 101108.
23. [23] Zhang L, et al. Photovoltaic power generation forecasting based on secondary data decomposition and hybrid deep learning model. Energies 2025; 18(12): 3136.
24. [24] Khelifi R, Guermoui M, Rabehi A, Taallah A, Zoukel A, Ghoneim SS, Zaitsev I. Short-term PV power forecasting using a hybrid TVF-EMD-ELM strategy. International Transactions on Electrical Energy Systems 2023; 2023(1): 6413716.
25. [25] Depoortere J, Driesen J, Suykens J, Kazmi HS. SolNet: Open-source deep learning models for photovoltaic power forecasting across the globe. International Journal of Forecasting 2025; 41(3): 1223-1236.
26. [26] Gao J, Cao Q, Chen Y, Zhang D. Cross-variable linear integrated enhanced transformer for photovoltaic power forecasting. Available from: https://arxiv.org/abs/2406.03808 Accessed: January 03, 2025. [Online].
27. [27] Lin H, Yu M. PV-VLM: A multimodal vision-language approach incorporating sky images for intra-hour photovoltaic power forecasting. Available from: https://arxiv.org/abs/2504.13624 Accessed: January 03, 2025. [Online].
28. [28] Esen V, Coban B, Kavus BY, Karaca TK, Dindar T, Sarkin AS. An interpretable statistical approach to photovoltaic power forecasting using factor analysis and ridge regression. Scientific Reports 2025; 15(1): 38947.
29. [29] Nematzadeh S, Esen V. Explainable machine learning and predictive statistics for sustainable photovoltaic power prediction on areal meteorological variables. Applied Sciences 2025; 15(14): 8005.