OUTPUT POWER ESTIMATION OF A PHOTOVOLTAIC PANEL BY EXTREME LEARNING MACHINE

Year 2024, , 37 - 42, 29.06.2024

Serhat Toprak , Resul Çöteli , Mehmet Ustundag , Hikmet Esen

https://doi.org/10.46460/ijiea.1421890

Abstract

In this study, the output power of a photovoltaic (PV) panel under different operating conditions was estimated with the help of an extreme learning algorithm (ELM). For this purpose, a PV panel with a power of 180W was installed, and the open circuit voltage, short circuit current, panel temperature, and solar radiation of this panel were measured and recorded at regular intervals. A total of 75 measurement data were obtained. The maximum power of the panel was calculated using the open circuit voltage and short circuit current information. While panel temperature and solar radiation were given as inputs to the regression model of the PV panel based on ELM, the output of the regression model was taken as the maximum power of the PV panel. To improve the prediction accuracy of ELM, the number of input neurons of ELM and the type of activation function used in the hidden layer were determined by trial and error method. The generated PV data set is separated into training and testing sets. The performance of the method was examined with the 5-fold cross-validation method. For this purpose, the dataset was divided into 5 equal parts. One of these parts was used for testing the ELM and the remaining four sets were used for training the ELM, and this was done by changing the test set each time. Thus, the network was trained and tested 5 times with different sets, and the test result of the network was obtained by averaging the sum of the performances of all test functions. Regression results obtained from ELM are given for different numbers of hidden layer neurons and different types of activation functions in the hidden layer. The best prediction result of ELM was obtained for the case where the hidden layer activation function was tangent sigmoid and the number of hidden layer neurons was 20. The R-values were found to be 1 when the number of hidden layer neurons was 20 and tangent and radial basis activation functions were used. From the results obtained, it has been seen that ELM predicts the output power of the PV panel with very high accuracy. It is concluded that ELM is a useful tool for estimating the PV panel output power.

Keywords

Extreme learning algorithm, regression, PV panel

ÇIKIŞ GÜCÜ UÇ ÖĞRENME ALGORİTMASI İLE BIR FOTOVOLTAİK PANELİN ÇIKIŞ GÜCÜ TAHMİNİ

Abstract

Bu çalışmada, farklı çalışma şartları altında bir PV panelin çıkış gücü uç öğrenme algoritması (UÖA) yardımı ile tahmin edilmiştir. Bu amaçla, 180 W gücünde bir PV panel kurulmuş, bu panelin açık devre gerilimi, kısa devre akımı, panel sıcaklığı ve güneş ışınımı belirli aralıklarla ölçülerek kaydedilmiştir. Toplam 75 adet ölçüm verisi elde edilmiştir. Açık devre gerilimi ve kısa devre akımı bilgileri kullanılarak panelin maksimum gücü hesaplanmıştır. UÖA kullanılarak oluşturulan PV panelin regresyon modeline giriş olarak panel sıcaklığı ve güneş ışınımı verilirken, regresyon modelinin çıkışı PV panelin maksimum gücü olarak alınmıştır. ÜOA’nın tahmin doğruluğunu iyileştirmek için UÖA’nın giriş nöron sayısı ve ara katmanda kullanılan aktivasyon fonksiyonu tipi deneme yanılma yöntemi belirlenmiştir. Oluşturulan veri kümesi eğitim ve test kümesi olarak ayrılmıştır. Yöntemin başarımı 5-katlamalı çapraz doğrulama yöntemi ile incelenmiştir. Bu amaçla, veri kümesi 5 eşit parçaya bölünmüştür. Bu parçalardan biri test için ayrılıp geri kalan dördü ağın eğitim için kullanılmış ve bu işlem her defasında test kümesi değiştirilerek gerçekleştirilmiştir. Böylece 5 defa ağ farklı kümelerle eğitilip test edilmiş ve ağın test sonucu bütün test fonksiyonlarının performanslarının toplamının ortalaması alınarak elde edilmiştir. UÖA’dan elde edilen regresyon sonuçları farklı ara katman nöron sayısı ve farklı tip aktivasyon fonksiyonları için verilmiştir. ÜOA’nın en iyi tahmin sonucu ara katman aktivasyon fonksiyonu tipinin tanjant sigmoid ve ara katman nöron sayısının 20 olduğu durum için elde edilmiştir. Elde edilen sonuçlardan UÖA’nın PV panelin çıkış gücünü çok yüksek doğrulukta tahmin ettiği görülmüş ve UÖA’nın PV panellerin çıkış gücünün tahmininde etkin bir araç olarak kullanılabileceğini göstermiştir.

Keywords

Uç öğrenme algoritması, regresyon, PV Panel

References

• Ela, E., Diakov, V., Ibanez, E., & Heaney, M. (2013). Impacts of variability and uncertainty in solar photovoltaic generation at multiple timescales (No. NREL/TP-5500-58274). National Renewable Energy Lab.(NREL), Golden, CO (United States).
• Tian, J., Zhu, Y. Q., & Tang, J. N. (2010, September). Photovoltaic array power forecasting model based on energy storage. In 2010 5th International Conference on Critical Infrastructure (CRIS) (pp. 1-4). IEEE.
• Gumar, A. K., & Demir, F. (2022). Solar photovoltaic power estimation using meta-optimized neural networks. Energies, 15(22), 8669.
• Tan, Y. T., & Kirschen, D. S. (2007, June). Impact on the power system of a large penetration of photovoltaic generation. In 2007 IEEE power engineering society general meeting (pp. 1-8). IEEE.
• Caputo, D., Grimaccia, F., Mussetta, M., & Zich, R. E. (2010, July). Photovoltaic plants predictive model by means of ANN trained by a hybrid evolutionary algorithm. In The 2010 international joint conference on neural networks (IJCNN) (pp. 1-6). IEEE.
• Grimaccia, F., Mussetta, M., & Zich, R. (2011, June). Neuro-fuzzy predictive model for PV energy production based on weather forecast. In 2011 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE 2011) (pp. 2454-2457). IEEE.
• Shi, J., Lee, W. J., Liu, Y., Yang, Y., & Wang, P. (2012). Forecasting power output of photovoltaic systems based on weather classification and support vector machines. IEEE Transactions on Industry Applications, 48(3), 1064-1069.
• Xu, R., Chen, H., & Sun, X. (2012, August). Short-term photovoltaic power forecasting with weighted support vector machine. In 2012 IEEE International Conference on Automation and Logistics (pp. 248-253). IEEE.
• O’Leary, D., & Kubby, J. (2017). Feature selection and ANN solar power prediction. Journal of Renewable Energy, 2017(1), 2437387.
• Alzahrani, A., Shamsi, P., Dagli, C., & Ferdowsi, M. (2017). Solar irradiance forecasting using deep neural networks. Procedia computer science, 114, 304-313.
• Geetha, A., Santhakumar, J., Sundaram, K. M., Usha, S., Thentral, T. T., Boopathi, C. S., ... & Sathyamurthy, R. (2022). Prediction of hourly solar radiation in Tamil Nadu using ANN model with different learning algorithms. Energy Reports, 8, 664-671.
• Lopes, S. M., Cari, E. P., & Hajimirza, S. (2022). A comparative analysis of artificial neural networks for photovoltaic power forecast using remotes and local measurements. Journal of Solar Energy Engineering, 144(2), 021007.
• Pang, Z., Niu, F., & O’Neill, Z. (2020). Solar radiation prediction using recurrent neural network and artificial neural network: A case study with comparisons. Renewable Energy, 156, 279-289.
• Halabi, L. M., Mekhilef, S., & Hossain, M. (2018). Performance evaluation of hybrid adaptive neuro-fuzzy inference system models for predicting monthly global solar radiation. Applied energy, 213, 247-261.
• Laarabi, B., Tzuc, O. M., Dahlioui, D., Bassam, A., Flota-Bañuelos, M., & Barhdadi, A. (2019). Artificial neural network modeling and sensitivity analysis for soiling effects on photovoltaic panels in Morocco. Superlattices and Microstructures, 127, 139-150.
• Kumar, K. R., & Kalavathi, M. S. (2018). Artificial intelligence based forecast models for predicting solar power generation. Materials today: proceedings, 5(1), 796-802.
• Huang, G. B., Zhu, Q. Y., & Siew, C. K. (2004, July). Extreme learning machine: a new learning scheme of feedforward neural networks. In 2004 IEEE international joint conference on neural networks (IEEE Cat. No. 04CH37541) (Vol. 2, pp. 985-990). Ieee.
• Ahila, R., & Sadasivam, V. (2013). S Transform based extreme learning machine for power system disturbances classification. Journal of The Institution of Engineers (India): Series B, 94, 179-191.
• Nguyen-Duc, T., Nguyen-Duc, H., Le-Viet, T., & Takano, H. (2020). Single-diode models of PV modules: A comparison of conventional approaches and proposal of a novel model. Energies, 13(6), 1296.
• Premkumar, M., Chandrasekaran, K., & Sowmya, R. (2020). Mathematical modelling of solar photovoltaic cell/panel/array based on the physical parameters from the manufacturer’s datasheet. International Journal of Renewable energy development, 9(1), 7.
• Senthilkumar, S., Mohan, V., Mangaiyarkarasi, S. P., & Karthikeyan, M. (2022). Analysis of Single‐Diode PV Model and Optimized MPPT Model for Different Environmental Conditions. International Transactions on Electrical Energy Systems, 2022(1), 4980843.
• Huang, G. B., Zhu, Q. Y., & Siew, C. K. (2006). Extreme learning machine: theory and applications. Neurocomputing, 70(1-3), 489-501.
• Chen, C., Li, K., Duan, M., & Li, K. (2017). Extreme learning machine and its applications in big data processing. In Big data analytics for sensor-network collected intelligence (pp. 117-150). Academic Press.