ELECTRICAL CHARACTERISTIC CLASSIFICATION OF THE PV’S USING SUPPORT VECTOR MACHINES
Abstract
Photovoltaics have more attraction day by day due to increasing technologies and decreasing prices. However, in practice, the applicants encounter fundamental problems such as shadow effects and degradation. Due to these problems, the amount of produced annual electricity decreases considerably. Moreover, it is not easy to understand if the company's PV satisfies the requirements or is appropriate for the application. In order to solve such problems, it is instructed to examine the electrical characteristics of the modules. An initial task should be the classification of PV modules according to performance results. Here in this study, it is aimed to classify different PV modules, including different output characteristics. It is aimed to show whether it is possible to classify different PV modules including the same output power or not? To find the answer to this question, a test platform is built. 4 different panels are tested on the platform. While the test, the panels produced by different companies split into two groups, each has the same output power. Under a different insulation condition, the test is performed, and the cells' current-voltage curves are constructed. Different statistics are extracted by using this information. Different variations of these statistics are presented to multi-SVM. Finally, accurate classification results are obtained.
Keywords
Photovoltaic, IV Curve, Classification, Electrical Characteristics, Support Vector Machines
References
- [1] Fares MA, Atik L, Bachir G, Aillerie M. Photovoltaic panels characterization and experimental testing. Energy Procedia 2017;119:945–52.
- [2] Schill C, Brachmann S, Koehl M. Impact of soiling on IV-curves and efficiency of PV-modules. Sol Energy 2015;112:259–62.
- [3] Velilla E, Restrepo S, Jaramillo F. Cluster analysis of commercial photovoltaic modules based on the electrical performance at standard test conditions. Sol Energy 2017;144:335–41.
- [4] Ko SW, Ju YC, Hwang HM, So JH, Jung Y-S, Song H-J, et al. Electric and thermal characteristics of photovoltaic modules under partial shading and with a damaged by-pass diode. Energy 2017;128:232–43.
- [5] Chen Z, Wu L, Cheng S, Lin P, Wu Y, Lin W. Intelligent fault diagnosis of photovoltaic arrays based on optimized kernel extreme learning machine and I-V characteristics. Appl Energy 2017;204:912–31.
- [6] Dash PK, Gupta NC, Rawat R, Pant PC. A novel climate classification criterion based on the performance of solar photovoltaic technologies. Sol Energy 2017;144:392–8.
- [7] Dhimish M, Holmes V, Mehrdadi B, Dales M, Chong B, Zhang L. Seven indicators variations for multiple PV array configurations under partial shading and faulty PV conditions. Renew Energy 2017;113:438–60.
- [8] Wu Y, Chen Z, Wu L, Lin P, Cheng S, Lu P. An Intelligent Fault Diagnosis Approach for PV Array Based on SA-RBF Kernel Extreme Learning Machine. Energy Procedia 2017;105:1070–6.
- [9] Dhimish M, Holmes V, Mehrdadi B, Dales M, Mather P. Photovoltaic fault detection algorithm based on theoretical curves modelling and fuzzy classification system. Energy 2017;140:276–90.
- [10] Rus-Casas C, Aguilar JD, Rodrigo P, Almonacid F, Pérez-Higueras PJ. Classification of methods for annual energy harvesting calculations of photovoltaic generators. Energy Convers Manag 2014;78:527–36.