Machine Learning Based Energy Forecasting for Photovoltaic Solar Plants

Yıl 2024, Cilt: 9 Sayı: 2, 128 - 146, 27.12.2024

Muhammed Tamay Gül Fatma Türker

Öz

As the global population continues to grow and technological advancements progress, energy demand is becoming increasingly noticeable worldwide. Solar energy, which is among the sustainable energy sources to reduce the environmental impact of fossil fuels, has a critical role in the global energy transition. Energy generation forecasts play a vital role in supply-demand balance, grid stability and cost optimization. Moreover, accurate and reliable generation forecasts are essential to facilitate the integration of renewable energy sources and improve the efficiency of energy systems. In this study, generation data from April 2022 to April 2024 for a solar power plant in Şanlıurfa province and weather data obtained from Solcast API service are used. The performance of machine learning algorithms such as XGBoost, Extra Trees, k-Nearest Neighbors (KNN), Gradient Boosting, Random Forest and Linear Regression are evaluated. The results show that the KNN model outperforms the other algorithms with a Mean Square Error (MSE) of 172.92, Root Mean Square Error (RMSE) of 13.14, Mean Absolute Error (MAE) of 5.37 and R² score of 0.95. This study contributes to a more reliable estimation of solar power generation, facilitating the integration of renewable energy sources and offering significant potential for the optimization of energy management systems.

Anahtar Kelimeler

Solar Power Generation Forecasting, Machine Learning, Renewable Energy

Fotovoltaik Güneş Santralleri için Makine Öğrenmesi Tabanlı Enerji Üretim Tahmini

Öz

Dünya nüfusu ve teknolojik gelişmelerin sürekli artmasıyla birlikte, enerji talebi tüm dünyada giderek daha fazla hissedilmektedir. Fosil yakıtların çevresel etkilerini azaltmak amacıyla sürdürülebilir enerji kaynakları arasında yer alan güneş enerjisi, küresel enerji dönüşümünde kritik bir öneme sahiptir. Enerji üretim tahminleri, arz-talep dengesi, şebeke stabilitesi ve maliyet optimizasyonu açısından hayati bir rol oynamaktadır. Ayrıca, doğru ve güvenilir üretim tahminleri, yenilenebilir enerji kaynaklarının entegrasyonunu kolaylaştırmak ve enerji sistemlerinin verimliliğini artırmak için gereklidir. Bu çalışmada, Şanlıurfa ilindeki bir güneş enerji santraline ait Nisan 2022 ile Nisan 2024 arasındaki üretim verileri ve Solcast API servisinden elde edilen hava durumu verileri kullanılmıştır. XGBoost, Extra Trees, k-Nearest Neighbors (KNN), Gradient Boosting, Random Forest ve Linear Regression gibi makine öğrenmesi algoritmalarının performansı değerlendirilmiştir. Elde edilen sonuçlar, KNN modelinin Ortalama Kare Hata (MSE) değeri 172,92, Kök Ortalama Kare Hata (RMSE) değeri 13,14, Ortalama Mutlak Hata (MAE) değeri 5,37 ve R² skoru 0,95 ile diğer algoritmalardan daha iyi performans gösterdiğini ortaya koymaktadır. Bu çalışma, güneş enerjisi üretiminin daha güvenilir bir şekilde tahmin edilmesine katkıda bulunarak yenilenebilir enerji kaynaklarının entegrasyonunu kolaylaştırmakta ve enerji yönetim sistemlerinin optimizasyonu için önemli bir potansiyel sunmaktadır.

Anahtar Kelimeler

Güneş Enerjisi Üretim Tahmini, Makine Öğrenmesi, Yenilenebilir Enerji

Kaynakça

• [1] Enerji Ajansı, "Türkiye’nin Kurulu Gücü (Ekim 2024)," 2024. [Online]. Available: https://enerjiajansi.com.tr/turkiyenin-kurulu-gucu/. [Accessed: Nov. 21, 2024].
• [2] T.C. Ministry of Energy and Natural Resources, Turkey National Energy Plan, Ankara, Turkey, 2022.
• [3] J. Antonanzas, N. Osorio, R. Escobar, R. Urraca, F. J. Martinez-de-Pison, and F. Antonanzas-Torres, "Review of photovoltaic power forecasting," Solar Energy, vol. 136, pp. 78-111, 2016.
• [4] W.-C. Tsai, C.-S. Tu, C.-M. Hong, and W.-M. Lin, "A review of state-of-the-art and short-term forecasting models for solar PV power generation," Energies, vol. 16, no. 14, p. 5436, 2023.
• [5] W. Khan, S. Walker, and W. Zeiler, "Improved solar photovoltaic energy generation forecast using deep learning-based ensemble stacking approach," Energy, vol. 240, p. 122812, 2022.
• [6] Y. Ledmaoui, A. E. Maghraoui, M. E. Aroussi, R. Saadane, A. Chebak, and A. Chehri, "Forecasting solar energy production: A comparative study of machine learning algorithms," Energy Reports, vol. 10, pp. 1004–1012, 2023.
• [7] S. Cantillo-Luna, R. Moreno-Chuquen, D. Celeita, and G. Anders, "Deep and machine learning models to forecast photovoltaic power generation," Energies, vol. 16, no. 10, p. 4097, 2023.
• [8] D. K. Dhaked, S. Dadhich, and D. Birla, "Power output forecasting of solar photovoltaic plant using LSTM," Green Energy and Intelligent Transportation, vol. 2, no. 5, p. 100113, 2023.
• [9] C. Scott, M. Ahsan, and A. Albarbar, "Machine learning for forecasting a photovoltaic (PV) generation system," Energy, vol. 278, p. 127807, 2023.
• [10] M. AlShafeey and C. Csáki, "Evaluating neural network and linear regression photovoltaic power forecasting models based on different input methods," Energy Reports, vol. 7, pp. 7601–7614, 2021.
• [11] T. AlSkaif, S. Dev, L. Visser, M. Hossari, and W. van Sark, "A systematic analysis of meteorological variables for PV output power estimation," Renewable Energy, vol. 153, pp. 12–22, 2020.
• [12] K. Mahmud, S. Azam, A. Karim, S. Zobaed, B. Shanmugam, and D. Mathur, "Machine learning-based PV power generation forecasting in Alice Springs," IEEE Access, vol. 9, pp. 46117–46128, 2021.
• [13] F. Nicoletti and P. Bevilacqua, "Hourly photovoltaic production prediction using numerical weather data," Energies, vol. 17, no. 2, p. 466, 2024.
• [14] A. Buonanno et al., "Machine learning and weather model combination for PV energy forecasting," Energies, vol. 17, no. 9, p. 2203, 2024.
• [15] A. Sedai et al., "Performance analysis of statistical, machine learning, and deep learning models in long-term forecasting of solar power production," Forecasting, vol. 5, no. 1, pp. 256–284, 2023.
• [16] S. Khadke et al., "Predicting active solar power with machine learning and weather data," Materials Circular Economy, vol. 5, no. 15, 2023.
• [17] A. A. H. Lateko, H.-T. Yang, and C.-M. Huang, "Short-term PV power forecasting using a regression-based ensemble method," Energies, vol. 15, p. 4171, 2022.
• [18] C. Voyant, G. Notton, S. Kalogirou, M. L. Nivet, C. Paoli, F. Motte, and A. Fouilloy, "Machine learning methods for solar radiation forecasting: A review," Renewable Energy, vol. 105, pp. 569–582, 2017.
• [19] D. Su, E. Batzelis, and B. Pal, "Machine learning algorithms in forecasting of photovoltaic power generation," in 2019 International Conference on Smart Energy Systems and Technologies (SEST), 2019, pp. 1-6.
• [20] T. Ahmad, S. Manzoor, and D. Zhang, "Forecasting high penetration of solar and wind power in the smart grid environment using a robust ensemble learning approach for large-dimensional data," Sustainable Cities and Society, vol. 75, p. 103269, 2021.
• [21] D. Markovics and M. J. Mayer, "Comparison of machine learning methods for photovoltaic power forecasting based on numerical weather prediction," Renewable and Sustainable Energy Reviews, vol. 161, p. 112364, 2022.
• [22] A. Abdellatif et al., "Forecasting photovoltaic power generation with a stacking ensemble model," Sustainability, vol. 14, no. 17, p. 11083, 2022.
• [23] U. Singh, M. Rizwan, M. Alaraj, and I. Alsaidan, "A machine learning-based gradient boosting regression approach for wind power production forecasting: A step towards smart grid environments," Energies, vol. 14, p. 5196, 2021.
• [24] H. M. I. and M. L. Sarper, "Prediction of daily photovoltaic energy production using weather data and regression," Journal of Solar Energy Engineering-Transactions of the ASME, 2021.
• [25] J. Wu, X. Chen, H. Zhang, L.-D. Xiong, H. Lei, and S. Deng, "Hyperparameter Optimization for Machine Learning Models Based on Bayesian Optimization," Journal of Electronic Science and Technology, vol. 17, pp. 26-40, 2019.
• [26] S. Uğuz, O. Oral, and N. Çağlayan, "PV Güç Santrallerinden Elde Edilecek Enerjinin Makine Öğrenmesi Metotları Kullanılarak Tahmin Edilmesi," International Journal of Engineering Research and Development, vol. 11, no. 3, pp. 769–779, 2019.