Machine Learning Based PV Power Prediction Using Different Environmental Parameters of Turkey
Abstract views: 47
/ 
PDF downloads: 33
Keywords:
PV power prediction, Machine learning, Environmental parameters, MLP, CNNAbstract
The prediction of photovoltaic power generation provides the basis for the generation,
transmission, and distribution systems of electrical energy, ensuring the establishment of uninterrupted and
reliable energy systems. In the present study, environmental parameters and power values produced from
photovoltaic panels were measured and recorded for 1 year with the measurement stations established in
three different regions (Adıyaman-Malatya-Şanlıurfa) in terms of environmental parameters. Modeling has
been developed for the power estimation to be produced using the MLP, CNN, LSTM, Stacked LSTM,
Bidirectional LSTM, and CNN-LSTM methods on the extensive dataset. Predictions were obtained from
the developed models with an accuracy rate of 98.9%, 98.6%, 95.1%, 95.0%, 95.0%, and 84.9%,
respectively. As a result of the study, it has been seen that all of the proposed methods are successful for
the problems of PV power prediction. In addition, it has been determined that the success rate of MLP and
CNN methods is superior to other methods. Thus, with the developed forecasting models, PV power
prediction for photovoltaic power systems desired to be installed by using environmental parameters
belonging to different regions in any part of the world can be estimated with a high degree of accuracy.
Downloads
References
Ayata, Deger, Murat Saraclar, and Arzucan Ozgur. 2017. “Political Opinion/Sentiment Prediction via Long Short Term Memory Recurrent Neural Networks on Twitter.” Pp. 1–4 in 25th Signal Processing and Communications Applications Conference (SIU). IEEE.
Çolak, Medine. 2020. Design and Analysis of Metaheuristic Optimization-Based Hybrid Model for Photovoltaic Power Estimation.
Das, Utpal Kumar, Kok Soon Tey, Mehdi Seyedmahmoudian, Saad Mekhilef, Moh Yamani Idna Idris, Willem Van Deventer, Bend Horan, and Alex Stojcevski. 2018. “Forecasting of Photovoltaic Power Generation and Model Optimization: A Review.” Renewable and Sustainable Energy Reviews 81:912–28.
Fischer, Thomas, and Christopher Krauss. 2018. “Deep Learning with Long Short-Term Memory Networks for Financial Market Predictions.” European Journal of Operational Research 270(2):654–69. doi: 10.1016/j.ejor.2017.11.054.
Gurney, Kevin. 1997. An Introduction to Neural Networks. UCL Press.
Hochreiter, Sepp, and Jürgen Schmidhuber. 1997. “Long Short-Term Memory.” Neural Computation 9(8):1735–80.
Kara, Ahmet. 2019. “Global Solar Irradiance Time Series Prediction Using Long Short-Term Memory Network.” GU J Sci, Part C 7(4):882–92. doi: 10.29109/gujsc.571831.
Kesici, Mert. 2019. “Wide Area Measurement Based Early Prediction of Power System Transient Instability and Its Evolution Using Deep Learning and Decision Tree Based Algorithms.” İstanbul Teknik Üniversity, İstanbul.
Khandakar, Amith, Muhammad E. H. Chowdhury, Monzure Khoda Kazi, Kamel Benhmed, Farid Touati, Mohammed Al-Hitmi, and Antonio S. P. Gonzales. 2019. “Machine Learning Based Photovoltaics (PV) Power Prediction Using Different Environmental Parameters of Qatar.” Energies 12(14):2782. doi: 10.3390/en12142782.
Luo, Xing, Dongxiao Zhang, and Xu Zhu. 2021. “Deep Learning Based Forecasting of Photovoltaic Power Generation by Incorporating Domain Knowledge.” Energy 225:120240. doi: 10.1016/j.energy.2021.120240.
Madsen, Henrik, Pierre Pinson, George Kariniotakis, Henrik Aa Nielsen, and Torben S. Nielsen. 2005. “Standardizing the Performance Evaluation of Short-Term Wind Power Prediction Models.” Wind Engineering 29(6):475–89. doi: 10.1260/030952405776234599.
Mohanty, Sthitapragyan, Prashanta K. Patra, Sudhansu S. Sahoo, and Asit Mohanty. 2017. “Forecasting of Solar Energy with Application for a Growing Economy like India: Survey and Implication.” Renewable and Sustainable Energy Reviews 78:539–53. doi: 10.1016/j.rser.2017.04.107.
O’Shea, Keiron, and Ryan Nash. 2015. “An Introduction to Convolutional Neural Networks.” Neural and Evolutionary Computing 1(1):1–11.
Pascanu, Razvan, Tomas Mikolov, and Yoshua Bengio. 2013. “On the Difficulty of Training Recurrent Neural Networks.” Proceedings of Machine Learning Research 28(3):1310–18.
Peng, Min, Chongyang Wang, Tong Chen, and Guangyuan Liu. 2016. “NIRFaceNet: A Convolutional Neural Network for Near-Infrared Face Identification.” Information 7(4):61. doi: 10.3390/info7040061.
Rajagukguk, Rial A., Raden A. A. Ramadhan, and Hyun-Jin Lee. 2020. “A Review on Deep Learning Models for Forecasting Time Series Data of Solar Irradiance and Photovoltaic Power.” Energies 13(24):6623. doi: 10.3390/en13246623.
Rumelhart, David E., Geoffrey E. Hinton, and Ronald J. Williams. 1986. “Learning Representations by Back-Propagating Errors.” Nature 323(9):533–36.
Sagheer, Alaa, and Mostafa Kotb. 2019. “Time Series Forecasting of Petroleum Production Using Deep LSTM Recurrent Networks.” Neurocomputing 323:203–13. doi: 10.1016/j.neucom.2018.09.082.
Suresh, Vishnu, Przemyslaw Janik, Jacek Rezmer, and Zbigniew Leonowicz. 2020. “Forecasting Solar PV Output Using Convolutional Neural Networks with a Sliding Window Algorithm.” Energies 13(3):723. doi: 10.3390/en13030723.
Wang, Huaizhi, Haiyan Yi, Jianchun Peng, Guibin Wang, Yitao Liu, Hui Jiang, and Wenxin Liu. 2017. “Deterministic and Probabilistic Forecasting of Photovoltaic Power Based on Deep Convolutional Neural Network.” Energy Conversion and Management 153:409–22. doi: 10.1016/j.enconman.2017.10.008.
Xiao, Yuelei, and Yang Yin. 2019. “Hybrid LSTM Neural Network for Short-Term Traffic Flow Prediction.” Information 10(3):105. doi: 10.3390/info10030105.
Yang, Dazhi, Jan Kleissl, Christian A. Gueymard, Hugo T. C. Pedro, and Carlos F. M. Coimbra. 2018. “History and Trends in Solar Irradiance and PV Power Forecasting: A Preliminary Assessment and Review Using Text Mining.” Solar Energy 168:60–101. doi: 10.1016/j.solener.2017.11.023.
