PV Güç Santrallerinden Elde Edilecek Enerjinin Makine Öğrenmesi Metotları Kullanılarak Tahmin Edilmesi

Year 2019, Volume: 11 Issue: 3, 769 - 779, 31.12.2019

Sinan Uğuz , Okan Oral , Nuri Çağlayan

https://doi.org/10.29137/umagd.514933

Cited By: 5

Abstract

Elektrik enerjisi ihtiyacının artması, ülkeleri güvenilir, ucuz ve temiz enerji teminine yöneltmiştir. Son zamanlarda, bu enerji kaynakları arasından fotovoltaik güç sistemlerine dayalı olanlar öne çıkmıştır. Güneş enerjisi potansiyelinin yüksek olduğu Türkiye’de devlet teşvikleriyle birlikte fotovoltaik güç santrallerine olan yatırımların sayısı artmaktadır. Fotovoltaik santrallerin kuruluş yeri seçimi için fizibilite çalışmalarının yapılması ve buna bağlı olarak sistemlerin tasarlanması, yapılacak yatırımların ekonomikliliğinin belirlenmesi açısından önemli bir konu olarak görülmektedir. Santral kurulmadan önce ışınım enerjisine göre elde edilebilecek elektrik enerjisinin hesaplanması için eşitlikler ve yöntemler geliştirilmiştir. Bu yöntemlerden biri de makine öğrenme modellerinin geliştirilmesi ve simülasyon sonuçlarının elde edilmesidir. Bu çalışmada; Türkiye’de 125 farklı bölge için kurulması planlanan PV santrallerinin üreteceği elektrik gücünün, makine öğrenmesi modelleri ile tahmin edilmesi amaçlanmıştır. Bu amaç doğrultusunda PV sistemler için güneş ışınımı tahmin edilmesinde artificial neural networks (ANN), multiple linear regression (MLR) ve k-nearest neighbors regression (KNNR) makine öğrenimi metodolojileri kullanılmıştır. Bu metodolojilerin performansını analiz etmek amacıyla bir dizi deneysel değerlendirmeler yapılmıştır. Değerlendirmeler için veri seti, Numpy, Pandas, Scipy gibi temel python kütüphanelerinin yanı sıra makine öğrenmesi uygulamaları için geliştirilmiş olan scikit-learn kütüphanesinde test edilmiştir. Deneysel sonuçlar, girdi olarak kullanılmış yedi adet bağımsız değişkenin, makine öğrenimine dayalı tahmin algoritmalarının çalıştırılmasıyla PV tarafında üretilen elektrik gücünü tahmin edebildiğini göstermiştir.

Keywords

Yenilenebilir enerji, makine öğrenmesi, multiple lineae regression (MLR), k-nearest neighbors regression (KNNR)

Estimation of Energy to be Obtained from PV Power Plants Using Machine Learning Methods

Abstract

The increase in the need for electricity has led the countries to provide reliable, inexpensive and clean energy. Recently, among those energy sources, those based on photovoltaic power systems have come forward. Solar energy potential in Turkey is high, the number of investments in photovoltaic power plants with government incentives are increasing. The feasibility studies for the selection of the location of photovoltaic plants and the design of the systems are considered as an important issue in terms of determining the economic value of the investments to be made. Equations and methods have been developed to calculate the electrical energy that can be obtained according to the radiant energy before the plant is established. One of these methods is to develop machine learning models and to obtain simulation results. In this study; The establishment of the 125 planned for different areas of electric power to be generated by the PV power plant in Turkey, aimed to estimate with machine learning models. For this purpose, in the estimation of solar radiation for PV systems; artificial neural networks (ANN), multiple linear regression (MLR) and k-nearest neighbors regression (KNNR) machine learning methodologies were used. In order to analyze the performance of these methodologies, a series of experimental evaluations were made. The data set for evaluations has been tested in basic python libraries such as Numpy, Pandas, Scipy, as well as in the scikit-learn library developed for machine learning applications. Experimental results have shown that seven independent variables used as input can predict the electrical power produced by PV based on the study of prediction algorithms based on machine learning.

Keywords

Renewable energy, machine learning, multiple lineae regression (MLR), k-nearest neighbors regression (KNNR)

References

• [1] Volkan YURDADOĞ , Şebnem TOSUNOĞLU. Türkiye'de Yenilenebilir Enerji Destek Politikaları - Renewable Energy Support Policies in Turkey. Eurasian Academy of Sciences Eurasian Business & Economics Journal 2017 Volume:9 S: 1 – 21. Published Online April 2017 (http://busecon.eurasianacademy.org) (https://www.researchgate.net/publication/317233001_Turkiye%27de_Yenilenebilir_Enerji_Destek_Politikalari_-_RENEWABLE_ENERGY_SUPPORT_POLICIES_IN_TURKEY) Erişim: 19 June 2018
• [2] Koca A, Oztop HF, Varol Y, Koca GO. Estimation of solar radiation using artificial neural networks with different input parameters for Mediterranean region of Anatolia in Turkey. Expert Syst Appl 2011;38(7):8756–62. (https://www.researchgate.net/publication/220217239_Estimation_of_solar_radiation_using_artificial_neural_networks_with_different_input_parameters_for_Mediterranean_region_of_Anatolia_in_Turkey) Erişim: 19 June 2018
• [3]World Energy Council 2018. Energy Resources (Solar). https://www.worldenergy.org/data/resources/resource/solar/ Erişim: 19 June 2018
• [4] International Energy Agency (IEA), 2015. The Medium-Term Renewable Energy Market Report 2015. https://www.iea.org/publications/freepublications/publication/MTRMR2015.pdf Erişim: 19 June 2018
• [5] Ministry of Energy and Natural Resources. Turkey has high solar energy potential due to its geographical location. http://www.enerji.gov.tr/en-US/Pages/Solar Erişim: 21 June 2018
• [6] SETA. Dünyada ve Türkı̇ye’de Yenı̇lenebı̇lı̇r Enerjı̇. Yazarlar: Erdal Tanas Karagöl, İsmail Kavaz. Siyaset, Ekonomi ve Toplum Araştırmaları Vakfı (SETA) Analiz Yayını. Nisan 2017 SAYI: 197. https://setav.org/assets/uploads/2017/04/YenilenebilirEnerji.pdf Erişim: 19 June 2018
• [7] Photovoltaic Geographical Information System. Country and regional maps. European Commission, Joint Research Centre Energy Efficiency and Renewables Unit (PVGIS team) http://re.jrc.ec.europa.eu/pvg_download/map_index_c.html. Erişim: 19 June 2018
• [8] Enerji ve Tabii Kaynaklar Bakanlığı. 2018 Yılı Bütçe Sunumu”, Strateji Geliştirme Başkanlığı Kasım 2017http://www.enerji.gov.tr/File/?path=ROOT%2f1%2fDocuments%2fB%c3%bct%c3%a7e%20Konu%c5%9fmas%c4%b1%2f2018_Butce_Sunus_Kitabi.pdf. Erişim: 19 June 2018
• [9] 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, 105, 2017, pp. 569-582.
• [10] Li, Jiaming; Ward, John; Tong, Taffy; Collins, Lyle; Platt, Glenn. Machine Learning for Solar Irradiance Forecasting of Photovoltaic System. Renewable Energy. 2016; 90(1):542–553. https://doi.org/10.1016/j.renene.2015.12.069
• [11] D. Elizondo, G. Hoogenboom, and R. W. McClendon, “Development of a neural network model to predict daily solar radiation,” Agricultural and Forest Meteorology, vol. 71, no. 1-2, pp. 115–132, 1994. View at Google Scholar · View at Scopus
• [12] Tamer Khatib, Azah Mohamed, K. Sopian, and M. Mahmoud, “Solar Energy Prediction for Malaysia Using Artificial Neural Networks,” International Journal of Photoenergy, vol. 2012, Article ID 419504, 16 pages, 2012. https://doi.org/10.1155/2012/419504.
• [13] U. Das, K. Tey, M. Seyedmahmoudian, et al.SVR-based model to forecast PV power generation under different weather conditions. Energies, 10 (7) (2017), p. 876
• [14] S. Theocharides, G. Makrides, G. E. Georghiou and A. Kyprianou, "Machine learning algorithms for photovoltaic system power output prediction," 2018 IEEE International Energy Conference (ENERGYCON), Limassol, 2018, pp. 1-6.
• [15] Chen, C.; Duan, S.; Cai, T.; Liu, B. Online 24-h solar power forecasting based on weather type classification using artificial neural network. Sol. Energy 2011, 85, 2856–2870. [CrossRef]
• [16] Bacher, P.; Madsen, H.; Nielsen, H.A. Online short-Term solar power forecasting. Sol. Energy 2009, 83, 1772–1783.
• [17] Duffie, J.A.; Beckman,W.A. Solar Engineering of Thermal Processes; JohnWiley & Sons: Hoboken, NJ, USA, 2013.
• [18] Netsanet, S.; Zhang, J.; Zheng, D.; Hui, M. Input parameters selection and accuracy enhancement techniques in PV forecasting using Artificial Neural Network. In Proceedings of the 2016 IEEE International Conference on Power and Renewable Energy (ICPRE), Shanghai, China, 21–23 October 2016; pp. 565–569.
• [19] Panapakidis, I.P.; Christoforidis, G.C. A hybrid ANN/GA/ANFIS model for very short-term PV power forecasting. In Proceedings of the 2017 11th IEEE International Conference on Compatibility, Power Electronics and Power Engineering (CPE-POWERENG), Cadiz, Spain, 4–6 April 2017; pp. 412–417.
• [20] Ni, Q.; Zhuang, S.; Sheng, H.; Kang, G.; Xiao, J. An ensemble prediction intervals approach for short-term PV power forecasting. Sol. Energy 2017, 155, 1072–1083.
• [21] Y. Gala, _A. Fern_andez, J. Díaz, J.R. Dorronsoro, Hybrid machine learning forecasting of solar radiation values, Neurocomputing 176 (2016) 48e59, http://dx.doi.org/10.1016/j.neucom.2015.02.078.
• [22] Pedro, H. T. & Coimbra, C. F. (2012). Assessment of forecasting techniques for solar power production with no exogenous inputs. Solar Energy, 86, 2017--2028.
• [23] Gordon, R., 2009. Predicting solar radiation at high resolutions: a comparison of time series forecasts. Solar Energy 83, 342–349.
• [24] Picault, D., Raison, B., Bacha, S., de la Casa, J., Aguilera, J., 2010. Forecasting photovoltaic array power production subject to mismatch losses. Solar Energy 84, 1301–1309.
• [25] Karasu, S., Aytac Altan, Zehra Sarac, Rifat Hacioglu . 2017. "Prediction of Solar Radiatıon Based on Machine Learning Methods". The Journal of Cognitive Systems, vol. 2 (1): 16-20 http://dergipark.gov.tr/jcs/issue/33186/390233
• [26] Assouline, D., Mohajeri, N., Scartezzini, J.L. Quantifying Rooftop Photovoltaic Solar Energy Potential: A Machine Learning Approach, Solar Energy 141 (2017) 278–296.
• [27] T.T. Teo et al., Forecasting of photovoltaic power using extreme learning machine, in: IEEE Innovative Smart Grid Technologies - Asia (ISGT ASIA) (2015) 1–6.
• [28] RETScreen. Available on-line at: https://www.nrcan.gc.ca/energy/software-tools/7465; Nov 3, 2011.
• [29] Salata F., Andrea de Lieto Vollaro, Roberto de Lieto Vollaro A case study of technical and economic comparison among energy production systems in a complex of historic buildings in Rome. 68th Conference of the Italian Thermal Machines Engineering Association, ATI2013. Energy Procedia 45 (2014) 482-491
• [30] N. Caglayan, C. Ertekin, and F. Evrendilek, “Spatial viability analysis of grid-connected photovoltaic power systems for Turkey,” International Journal of Electrical Power & Energy Systems, vol. 56, pp. 270–278, 2014.
• [31] Stone, M. (1974). Cross-validatory choice and assessment of statistical predictions. Journal of the royal statistical society. Series B (Methodological), 111-147.
• [32] Bollegala, D. (2017). Dynamic feature scaling for online learning of binary classifiers. Knowledge-Based Systems, 129, 97-105.
• [33] Zheng,A. (2015). Evaluating Machine Learning Models, Farnham, U.K.:O’Reilly Media, Inc.
• [34] Al-Ghobari, H. M., El-Marazky, M. S., Dewidar, A. Z., & Mattar, M. A. (2018). Prediction of wind drift and evaporation losses from sprinkler irrigation using neural network and multiple regression techniques. Agricultural Water Management, 195, 211-221.
• [35] Grégoire, G. (2014). Multiple linear regression. European Astronomical Society Publications Series, 66, 45-72.
• [36] Patterson, J., & Gibson, A. (2017). Deep Learning: A Practitioner's Approach. " O'Reilly Media, Inc.".
• [37] Tiryaki, S., & Aydın, A. (2014). An artificial neural network model for predicting compression strength of heat treated woods and comparison with a multiple linear regression model. Construction and Building Materials, 62, 102-108.
• [38] John, G. H., Kohavi, R., & Pfleger, K. (1994). Irrelevant features and the subset selection problem. In Machine Learning Proceedings 1994 (pp. 121-129).
• [39] Narin, A., Isler, Y., & Ozer, M. (2014). Investigating the performance improvement of HRV Indices in CHF using feature selection methods based on backward elimination and statistical significance. Computers in biology and medicine, 45, 72-79.
• [40] Cover, T., & Hart, P. (1967). Nearest neighbor pattern classification. IEEE transactions on information theory, 13(1), 21-27.
• [41] Chemingui, H., & Ben lallouna, H. (2013). Resistance, motivations, trust and intention to use mobile financial services. International Journal of Bank Marketing, 31(7), 574-592.