LSTM-CNN Tabanlı Derin Öğrenme Tekniği Kullanılarak Küresel Yatay Güneş Radyasyonu ile Hava Durumu Parametrelerinin Tahmini ve Analizi

Yıl 2022, Cilt: 9 Sayı: 1, 340 - 356, 30.06.2022

Sercan Yalçın , Münür Sacit Herdem

https://doi.org/10.35193/bseufbd.1037563

Öz

Önemli iklim parametrelerinin yanı sıra küresel yatay güneş ışınımının (GHSI) tahmin edilmesi, fotovoltaik panellerin enerji yönetimi ve kaynak planlamasında önemli bir rol oynamaktadır. Güneş enerjisinden daha fazla yararlanmak için, bu tür zaman serisi parametre verilerinin sıklıkla analiz edilmesi ve tahmin edilmesi yoluyla gelecek değerler hakkında bilgi elde edilmesi gerekmektedir. Bu nedenle, uzun vadeli güneş ışınımı verilerini tahmin etmek zorlu bir iştir. Bu amaçlarla, bu çalışmada, bu tür verilerin en doğru tahminini sağlamak için Uzun Kısa Süreli Bellek (LSTM) ve Evrişimsel Sinir Ağı (CNN) derin sinir ağlarının modellenmesi ile hibrit bir yöntem önerilmiştir. Ürdün vadisinde elde edilen GHSI ve sıcaklık, bağıl nem ve rüzgâr hızı verileri tahmin metodolojisinde kullanılır. Önerilen derin mimarinin CNN bloğunda, giriş parametreleri evrişim, havuzlama ve düzleştirme katmanlarından geçirilir ve çıkışlar LSTM veri girişine iletilir. Bu yöntemle daha etkin ve doğru tahminler yapılması hedeflenmektedir. Önerilen yöntem, diğer yöntemlerden farkını ortaya çıkarmak için RMSE, MADE ve MAPE hata performans kriterlerine göre karşılaştırılmıştır. Önerilen yöntem, özellikle GHSI tahmininde diğer algoritmalara göre daha üstün sonuçlar vermektedir.

Anahtar Kelimeler

Küresel Güneş Işınımı, Derin Sinir Ağları, Uzun Kısa Süreli Bellek, Evrişimli Sinir Ağı

Prediction and Analysis of Weather Parameters with Global Horizontal Solar Irradiance Using LSTM-CNN Based Deep Learning Technique

Öz

Predicting global horizontal solar irradiance (GHSI) as well as important climate parameters plays an important role in energy management and resource planning of photovoltaic panels. To further benefit from solar energy, it is necessary to obtain information regarding future values by frequently analyzing and predicting such time series parameter data. Hence, predicting long-term solar irradiance data is a challenging task. For these purposes, in this work, a hybrid method, with modeling of Long Short-Term Memory (LSTM) and Convolutional Neural Network (CNN) deep neural networks, is proposed to ensure the most accurate prediction of such data. The GHSI as well as temperature, relative humidity, and wind speed data obtained in the Jordan valley are used in the forecasting methodology. In the CNN block of the proposed deep architecture, the input parameters are passed through the convolution, pooling, and flattening layers, and the outputs are forwarded to the LSTM data input. With this method, it is aimed to make more effective and accurate estimations. The proposed method has been compared according to Root Mean Square Error (RMSE), Mean Absolute Deviation Error (MADE), and Mean Absolute Percentage Error (MAPE) error performance criteria in order to reveal the difference from other methods. The proposed method produces superior results compared to other algorithms, especially in GHSI estimation.

Anahtar Kelimeler

Global Solar Irradiance, Deep Neural Networks, Long Short Term Memory, Convolutional Neural Network

Kaynakça

• Arriaga, M., Cañizares, C. A., & Kazerani, M. (2014). Northern lights: Access to electricity in Canada's northern and remote communities. IEEE Power and Energy Magazine, 12(4), 50-59.
• Assouline, D., Mohajeri, N., & Scartezzini, J. L. (2018). Large-scale rooftop solar photovoltaic technical potential estimation using Random Forests. Applied energy, 217, 189-211.
• Cabrera, P., Carta, J. A., Lund, H., & Thellufsen, J. Z. (2021). Large-scale optimal integration of wind and solar photovoltaic power in water-energy systems on islands. Energy Conversion and Management, 235, 113982.
• Herdem, M. S., Mazzeo, D., Matera, N., Wen, J. Z., Nathwani, J., & Hong, Z. (2020). Simulation and modeling of a combined biomass gasification-solar photovoltaic hydrogen production system for methanol synthesis via carbon dioxide hydrogenation. Energy Conversion and Management, 219, 113045.
• Ahmad, T., Zhang, D., Huang, C., Zhang, H., Dai, N., Song, Y., & Chen, H. (2021). Artificial intelligence in sustainable energy industry: Status Quo, challenges and opportunities. Journal of Cleaner Production, 125834.
• Scher, S., & Messori, G. (2018). Predicting weather forecast uncertainty with machine learning. Quarterly Journal of the Royal Meteorological Society, 144(717), 2830-2841.
• Chantry, M., Christensen, H., Dueben, P., & Palmer, T. (2021). Opportunities and challenges for machine learning in weather and climate modelling: hard, medium and soft AI.
• Schultz, M. G., Betancourt, C., Gong, B., Kleinert, F., Langguth, M., Leufen, L. H., ... & Stadtler, S. (2021). Can deep learning beat numerical weather prediction?. Philosophical Transactions of the Royal Society A, 379(2194), 20200097.
• Moosavi, A., Rao, V., & Sandu, A. (2021). Machine learning based algorithms for uncertainty quantification in numerical weather prediction models. Journal of Computational Science, 50, 101295.
• Fouilloy, A., Voyant, C., Notton, G., Motte, F., Paoli, C., Nivet, M. L., ... & Duchaud, J. L. (2018). Solar irradiation prediction with machine learning: Forecasting models selection method depending on weather variability. Energy, 165, 620-629.
• Yagli, G. M., Yang, D., & Srinivasan, D. (2019). Automatic hourly solar forecasting using machine learning models. Renewable and Sustainable Energy Reviews, 105, 487-498.
• Feng, Y., Gong, D., Zhang, Q., Jiang, S., Zhao, L., & Cui, N. (2019). Evaluation of temperature-based machine learning and empirical models for predicting daily global solar radiation. Energy Conversion and Management, 198, 111780.
• Zhou, Y., Liu, Y., Wang, D., Liu, X., & Wang, Y. (2021). A review on global solar radiation prediction with machine learning models in a comprehensive perspective. Energy Conversion and Management, 235, 113960.
• Prieto, J.I., Martínez-García, J.C., & García, D. (2009). Correlation between global solar irradiation and air temperature in Asturias, Spain, Solar Energy, 83(7),1076-1085.
• Malakar, S., Goswami, S., Ganguli, B. et al. (2021). Designing a long short-term network for short-term forecasting of global horizontal irradiance. SN Applied Sciences, 3, 477.
• Jalali, S. M. J., Ahmadian, S., Kavousi-Fard, A., Khosravi, A. & Nahavandi, S. (2021). Automated Deep CNN-LSTM Architecture Design for Solar Irradiance Forecasting, IEEE Transactions on Systems, Man, and Cybernetics: Systems, 1-12, 10.1109/TSMC.2021.3093519.
• Zang, H., Liu, L., Sun, L., Cheng, L., Wei, Z., & Sun. G. (2020). Short-term global horizontal irradiance forecasting based on a hybrid CNN-LSTM model with spatiotemporal correlations, Renewable Energy, 160, 26-41.
• Cano, D. et al. (1987). A method for the determination of the global solar radiation from meteorological satellites data. Solar Energy, Elsevier, 37(1), 31-39.
• Rusen, S.E. (2018). Modeling and Analysis of Global and Diffuse Solar Irradiation Components Using the Satellite Estimation Method of HELIOSAT, CMES-Computer Modeling in Engineering & Sciences, 115 (3), 327-343.
• Rusen, S.E. (2018). Performance evaluation of a coupled method for the estimation of daily global solar radiation on a horizontal surface, Atmósfera, 31(4), 347-354.
• Rusen S.E. & Konuralp, A. (2020). Quality control of diffuse solar radiation component with satellite-based estimation methods, Renewable Energy, Elsevier, 145(C), 1772-1779.
• Rusen S.E., Hammer A. & Akinoglu B.G. (2013). Coupling satellite images with surface measurements of bright sunshine hours to estimate daily solar irradiation on horizontal surface, Renewable Energy, Elsevier, 55(C), 212-219.
• Rusen S.E., Hammer A. & Akinoglu B.G. (2013). Estimation of daily global solar irradiation by coupling ground measurements of bright sunshine hours to satellite imagery, Energy, Elsevier, 58(C), 417-425.
• Sarker, I.H. (2021). Deep Learning: A Comprehensive Overview on Techniques, Taxonomy, Applications and Research Directions. SN Computer Science, 2, 420.
• Greff, K., Srivastava, R. K., Koutnık, J., Steunebrink, B.R., & Schmidhuber, J. (2017). LSTM: A Search Space Odyssey, Transactions on Neural Networks and learning systems, 1-12.
• Kim, H., Ham, Y. G., Joo, Y. S. & Son, S. W. (2021). Deep learning for bias correction of MJO prediction. Nature Communications, 12, 3087.
• Hanab, J. M., Ang, Y. Q. Malkawi, A., & Samuelson, H. W. (2021). Using recurrent neural networks for localized weather prediction with combined use of public airport data and on-site measurements, Building and Environment, 192, 107601.
• Wang, K., Ma, C., Qiaoa, Y., Lua, X., Hao, W., & Dong, S. (2021). A hybrid deep learning model with 1DCNN-LSTM-Attention networks for short-term traffic flow prediction, Physica A: Statistical Mechanics and its Applications, 583, 126293.
• Bouktif, S., Fiaz, A., Ouni, A., & Serhani, M.A. (2020). Multi-Sequence LSTM-RNN Deep Learning and Metaheuristics for Electric Load Forecasting, Energies, 13, 391.
• Hoang, D. T., Yang, Pr. L., Cuong, L. D. P., Trung, P. D., Tu, N. H., Truong, L. V. , Hien, T. T., & Nha, V. T. (2020). Weather prediction based on LSTM model implemented AWS Machine Learning Platform. International Journal for Research in Applied Science & Engineering Technology (IJRASET), 8(5), 283-290.
• Pei, J., Deng, L., Song, S., et al. (2019). Towards artificial general intelligence with hybrid tianjic chip architecture, Nature, 572 (7767), 106-111.
• Gundu, V., & Simon, S. P. (2021). PSO–LSTM for short term forecast of heterogeneous time series electricity price signals, Journal of Ambient Intelligence and Humanized Computing, 12, 2375–2385.
• Liu, W., Wang, Z., Zeng, N., Alsaadi, F. E., & Liu, X. (2021). A PSO-based deep learning approach to classifying patients from emergency departments, International Journal of Machine Learning and Cybernetics,12, 1939–1948.
• Shao, B., Li, M., Zhao, Y. & Bian, G. (2019). Nickel Price Forecast Based on the LSTM Neural Network Optimized by the Improved PSO Algorithm, Mathematical Problems in Engineering, Article ID 1934796, 15 pages.
• Ju, Y. Sun, G.Y. Chen, Q.H. Zhang, M. Zhu, H.X. & Rehman, M.U. (2019). A model combining convolutional neural network and Light GBM algorithm for ultrashort-term wind power forecasting, IEEE Access 7 28309e28318.
• Lu, W., Li, J., Li, Y., Sun, A., & Wang, J. (2020). A CNN-LSTM-Based Model to Forecast Stock Prices. Complexity, vol. 2020, Article ID 6622927, 10 pages.
• Gensler, A., Henze, J., Sick, B. & Raabe, N. (2016). Deep learning for solar power forecasting—An approach using autoencoder and LSTM neural networks, in Proc. IEEE Int. Conf. Syst. Man Cybern. (SMC), Budapest, Hungary, 2016, 2858–2865.
• Dalalaa, Z., Al-Addous, M., Alawneha, F. & Class, C.B. (2020). Environmental data set for the design and analysis of the Photovoltaic system in the Jordan Valley, Data in Brief, 31, 105794.
• Richardson, C.W. (1985). Weather simulation for crop management models. Trans. ASAE, 28(5), 1602–1606.