Yapay Sinir Ağları Kullanılarak Fotovoltaik Panel Güç Çıkışlarının Tahmini ve Sezgisel Algoritmalar ile Karşılaştırılması

Year 2019, Issue: 16, 146 - 158, 31.08.2019

Emre Dandıl Erol Gürgen

https://doi.org/10.31590/ejosat.540262

Cited By: 6

Abstract

Farklı zamanlarda fotovoltaik(FV) sistemlerden üretilen güç değerlerinin tahmini güneş panellerinin güvenilir bir enerji kaynağı olarak efektif kullanılması ve ekonomik kullanılması açısından gereklidir. Güneş panellerinden üretilen çıkış gücünün kestirimi aynı zamanda, güneş panellerinin kurulumu, elektrik şirketlerine rehberlik etmesi, enerjinin yönetimi ve dağıtılması ve bunun yanında en kısa sürede optimum enerjiyi elde edebilir hale gelmek ve maksimum üretim kapasitesi ulaşmaya yönelik gerekli panel adaptasyonlarının tespit edilmesi için gerekli zamandan kazanç; ek işçilik maliyetlerinin azaltılması anlamında büyük önem arz etmektedir Bu çalışmada, FV panellerinden elde edilen güç değerlerinin aylık olarak tahmini için farklı algoritmalar ile öğrenebilen Yapay Sinir Ağları(YSA) kullanılmıştır. Altı farklı açısal konuma yerleştirilen panellerden elde edilen güç değerlerinin tahmin edilmesinde Parçacık Sürü Optimizasyonu(PSO), Geriye Yayılım(GY) ve Klonal Seçim Algoritması(KSA) ile eğitilen YSA modellerinden yararlanılmıştır. Tahmin sonuçlarının doğrulanmasında üç popüler istatiksel değerlendirme kriteri olan Ortalama Mutlak Yüzde Hata (MAPE), Ortalama Karesel Hataların Karekökü (RMSE) ve Varyans (R2) eşitliklerinden yararlanılmıştır. Her üç kriterlerden elde edilen doğrulama sonuçları incelendiğinde, hemen hemen tüm aylar için PSO algoritması ile eğitilen YSA yapısının, KSA ve GY algoritmaları ile eğitilen YSA yapılarına göre daha başarılı olduğu görülmüştür. Bazı sonuçlarda ise GY ile eğitilen YSA yapısının, PSO ile eğitilen YSA yapısına göre, sonuçlar birbirine yakın olmakla birlikte daha başarılı olduğu anlaşılmıştır.

Keywords

Fotovoltaik Panel, Güç Tahmini, YSA, Geriye Yayılım, PSO, Klonal Seçim Algoritması

Prediction of Photovoltaic Panel Power Outputs using Artificial Neural Networks and Comparison with Heuristic Algorithms

Abstract

The prediction of power outputs generated from photovoltaic (PV) systems
at different times is necessary for reliable and economical for use of solar
panels. The prediction of the power output is also very important in terms of
factors such as installation of solar panels,
guidance of electricity companies, energy management and distribution.
Determination of optimum solar panel positions and angles, providing energy
productivity to maximize production capacity in a short time period is the most
time consuming job for regulations for a companies. Also, adaptation of panels
increases costs. Therefore, new and healthy prediction methods have a great
importance to minimize these work force costs. In this study, Artificial Neural
Network (ANN) model learned by heuristic algorithms are used for the prediction
of power outputs obtained from PV panels monthly. Particle Swarm Optimization
(PSO), Back-Propagation (BP), Clonal Selection Algorithm (CSA) are used to
train ANN to predict six different PV panel located in different angles from 10
to 60 degrees. Three different popular evaluation methods which are called mean
absolute percentage error (MAPE),  root
mean square error (RMSE), varyans (R2) used to do comparison.
According to examination of verification results, PSO is almost most successful
algorithm as a training method when it is compared with BP and CSA. It is seen
for the some of the results belong to a few months that BP is slightly better
than PSO.

Keywords

Photovoltaic Panel, Power Prediction, ANN, Back-propagation; PSO, Clonal Selection Algorithm

References

• Theodoropoulos, K., et al. (2017). Monthly Electricity Statistics. International Energy Agency, (https://www.iea.org/media/statistics/surveys/electricity/mes.pdf).
• Engin, S., Gülersoy, t. (2018). Hibrid Güç Sistemleri İçin Evirici Tasarımı, Avrupa Bilim ve Teknoloji Dergisi, 14, pp. 228-234.
• Parmaksiz, H., Karafil A., Özbay H., Kesler M. (2016). Farklı Eğim Açılarındaki Fotovoltaik Panellerin Elektriksel Ölçümlerinin Raspberry Pi ile İzlenmesi, Düzce Üniversitesi Bilim ve Teknoloji Dergisi, 4(2),pp. 711-718.
• Lorenz, E., Hurka, J., Heinemann, D., et al. (2009). Irradiance forecasting for the power prediction of grid-connected photovoltaic systems, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2(1),pp. 2-10.
• Kudo, M., Nozaki, Y., Endo, H. (2009). Forecasting electric power generation in a photovoltaic power system for an energy network. Electrical Engineering in Japan, 167(4), pp. 16-23.
• Junseok, S., Krishnamurthy, V., Kwasinski, A., et al. (2012). Development of a Markov-Chain-Based Energy Storage Model for Power Supply Availability Assessment of Photovoltaic Generation Plants, IEEE Transactions on Sustainable Energy, 4(2), pp. 491-500.
• Li, Y., Niu, J., (2009). Forecast of power generation for grid-connected photovoltaic system based on Markov chain, Power and Energy Engineering Conference, APPEEC 200, Asia-Pacific. 1-4.
• Ran, L., Guang-min, L. (2008). Photovoltaic power generation output forecasting based on support vector machine regression technique, CNKI Journal of Electric Power, 2, 031.
• Shi, J., Lee, W. J., Liu, Y., et al. (2012). Forecasting Power Output of Photovoltaic Systems Based on Weather Classification and Support Vector Machines, IEEE Transactions on Industry Applications, 48(3), pp. 1064-1069.
• Wang, F., Mi, Z., Su, S., Zhang, C. (2011). A practical model for single-step power prediction of grid-connected PV plant using artificial neural network, Innovative Smart Grid Technologies Asia (ISGT), pp. 1-4.
• Kou, J., et al. (2013). Photovoltaic power forecasting based on artificial neural network and meteorological data, TENCON 2013-2013 IEEE Region 10 Conference, Xian, China.
• Zhang, N. et al. (2013). Solar Radıation Prediction Based on Partıcle Swarm Optimization and Evolutıonary Algorithm Usıng Recurrent Neural Networks, IEEE Annual System Conference.
• Qasrawi, I., Awad, M. (2015). Prediction of the Power Output of Solar Cells Using Neural Networks: Solar Cells Energy Sector in Palestine, International Journal of Computer Science and Security (IJCSS), 9(6), pp. 280.
• Zhu, H., Li, X., (2016). A Power Prediction Method for Photovoltaic Power Plant Based on Wavelet Decomposition and Artificial Neural Networks”, Energies, 9(1), pp. 11.
• Prokop, L.,et al. (2012). Photovoltaic Power Plant Output Estimation by Neural Networks and Fuzzy Inference, IDEAL 2012, pp. 810–817.
• Paulin, B.J., Praynlin, E. (2016). Solar Photovoltaic Output Power Forecasting Using Back Propagation Neural Network, ICTACT Journal on Soft Computing, 6(2).
• Rana M., et. al. (2015). Forecasting Solar Power Generated by Grid Connected PV Systems Using Ensembles of Neural Networks, International Joint Conference on Neural Networks (IJCNN), Ireland.
• Kahramanli, H., Allahverdi, N. (2008). Design of a hybrid system for the diabetes and heart diseases, Expert Systems with Applications, 35 (1), pp. 82-89.
• Franklin, S.W., Rajan, S., Computerized screening of diabetic retinopathy employing blood vessel segmentation in retinal images, Biocybernetics and Biomedical Engineering, 34 (2), pp. 117-124.
• Haykin, S., (2004). A comprehensive foundation, Neural networks, 2, pp. 41.
• De Castro, L.N., Von Zuben, F.J. (2002). Learning and optimization using the clonal selection principle, Evolutionary Computation, 6(3), pp. 239-251.
• Gao, X.Z. (2009). Clonal optimization-based negative selection algorithm with applications in motor fault detection, Neural Computing and Applications, 18(7), pp. 719-729.