Time Series Forecasting on Solar Energy Production Data Using LSTM

Abstract

The fact that countries have increased the use of renewable energy resources in order to meet the increasing energy demands has brought to light the fact that the components and energy production amounts of the solar energy systems to be installed must be estimated accurately. With the benefits of developing technology, the forecasting calculations of these variable nature energy resources have become much more economical by using machine learning methods. In this context, the article proposes a deep learning-based methodology that includes LSTM-based tuned models for PV power estimation, with univariate time series estimation of the amount of power obtained from a solar energy system integrated on a factory roof. When the created models are compared, the results show that the model approaches named LSTM13 provide the most accurate prediction performance with the lowest RMSE metric value of 0.1470 among other proposed models.

Keywords

• Deep Learning
• LSTM
• Machine Learning
• Renewable Energy
• Solar Power Systems.

References

1. Z. Şen, "Solar energy in progress and future research trends," Progress in Energy and Combustion Science 30, p. 367–416, 2004.
2. IRENA, "Renewable Energy Capacity Statistics 2023," International Renewable Energy Agency(IRENA), 2023.
3. H. Wang, Z. Lei, X. Zhang, B. Zhou and J. Peng, "A review of deep learning for renewable energy forecasting," Energy Conversion and Management, no. 198, p. 111799, 2019.
4. H. Bulut and O. Büyükalaca, "Simple model for the generation of daily global solar-radiation data in Turkey," Applied Energy 84, p. 477–491, 2007.
5. M. Çınaroğlu and M. Nalbantoğlu, "Şebekeye Bağlı Üç Adet Fotovoltaik Enerji Santralinin PVsyst Programı ile Analizi; Kilis Örneği," El-Cezerî Fen ve Mühendislik Dergisi, vol. 8, no. 2, pp. 675-687, 2021.
6. İ. T. Toğrul and H. Toğrul, "Global solar radiation over Turkey: comparison of predicted and measured data," Renewable Energy , no. 25, p. 55–67, 2002.
7. F. O. Hocaoğlu, Ö. N. Gerek and M. Kurban, "Hourly solar radiation forecasting using optimal coefficient 2-D linear filters and feed-forward neural networks," Solar Energy, vol. 82, pp. 714-726, 2008.
8. A. Chaouachi, R. M. Kamel and K. Nagasaka, "Neural Network Ensemble-Based Solar Power Generation Short-Term Forecasting," Journal of Advanced Computational Intelligence and Intelligent Informatics, pp. 69-75, 2010.

9. H. Demolli, Makine Öğrenmesi Teknikleri Kullanılarak Yenilenebilir Enerji Güç Tahmini ve Optimum Hibrit güç sistemi Tasarımı(Doktora tezi), Yükseköğretim Kurulu Ulusal Tez Merkezi veri tabanından erişildi (Tez No. 623617), 2020.
10. A. Tokgöz and G. Ünal, "Türkiye Elektrik Tüketimi Tahmini ˙Için RNN Tabanlı Zaman Serisi Yaklaşımı," IEEE, 2018.
11. K. Nam, S. Hwangbo and C. Yoo, "A deep learning-based forecasting model for renewable energy scenarios to guide sustainable energy policy: A case study of Korea," Renewable and Sustainable Energy Reviews, vol. 109725, no. 122, 2020.
12. B. Gao, . X. Huang, J. Shi, . Y. Tai and J. Zhang, "Hourly Forecasting of Solar Irradiance based on CEEMDAN and Multi-strategy CNN-LSTM neural networks," Renewable Energy, pp. 1665-1683, 2020.
13. O. T. Bişkin and A. Çifci, "Forecasting of Turkey’s Electrical Energy Consumption using LSTM and GRU Networks," BSEU Journal of Science, vol. 8, no. 2, pp. 656-667, 2021.
14. K. D. Ünlü, "A Data-Driven Model to Forecast Multi-Step Ahead Time Series of Turkish Daily Electricity Load," Electronics , vol. 11, no. 1524, 2022.
15. "Colaboratory," Google, [Online]. Available: https://colab.research.google.com/.
16. "TensorFlow v2.14.0," [Online]. Available: https://www.tensorflow.org/.
17. "Pandas 2.1.1," [Online]. Available: https://pandas.pydata.org/.
18. "Keras," [Online]. Available: https://keras.io/.
19. "Mathplotlib," [Online]. Available: https://matplotlib.org/.
20. S. Hochreiter and J. Schmidhuber, "Long short-term memory," Neural Comput. 9 (8) , p. 1735–1780, 1997.
21. 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.
22. 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. 4097, 2023.
23. A. Gensler, . J. Henze, . B. Sick and N. Raabe, "Deep Learning for Solar Power Forecasting – An Approach Using Autoencoder and LSTM Neural Networks," in IEEE International Conference on Systems, Man, and Cybernetics • SMC 2016 , Budapest, Hungary, 2016.
24. M. Neshat, M. M. Nezhad, S. Mirjalili, D. A. Garcia, E. Dahlquist and A. H. Gandomi, "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, no. 127701, 2023.