Performance Optimization of Commercial Photovoltaic Technologies Under Local Spectral Irradiances Using Machine Learning

The irradiance from the sun or solar spectral can have significant variance in different locations due to the latitude, humidity, cosine effect of incident sunlight. Performance of the outdoor photovoltaic (PV) modules is greatly influenced by the spectrum. In this study, the effects of the local spectral irradiance on outdoor PV modules is of interest. With similar irradiance and operating temperature, the performance of the PV modules at different locations differ as compared with the benchmark AM1.5G results. In order to predict the actual PV module performance under local climate conditions, a total of five locations in Peninsular Malaysia are considered. Twelve solar PV modules from different manufacturers and materials are analysed. Two sets of experiments were conducted using variants of Genetic Algorithms, where the PCE at different irradiance levels is first taken into account. Then, a multi-objective problem involving several parameters of the solar module is considered. Results from the study show that there is a gap from the AM1.5G results with the results from the five locations being analysed.

[1]  Mohammad Ali Abido,et al.  Parameter estimation for five- and seven-parameter photovoltaic electrical models using evolutionary algorithms , 2013, Appl. Soft Comput..

[2]  John H. Holland,et al.  Adaptation in Natural and Artificial Systems: An Introductory Analysis with Applications to Biology, Control, and Artificial Intelligence , 1992 .

[3]  Carlos Andrés Ramos-Paja,et al.  A genetic algorithm for identifying the single diode model parameters of a photovoltaic panel , 2017, Math. Comput. Simul..

[4]  Kian Jon Chua,et al.  Sunlight to hydrogen conversion: Design optimization and energy management of concentrated photovoltaic (CPV-Hydrogen) system using micro genetic algorithm , 2016 .

[5]  William A. Beckman,et al.  Improvement and validation of a model for photovoltaic array performance , 2006 .

[6]  D. Petreus,et al.  A novel MPPT (maximum power point tracking) algorithm based on a modified genetic algorithm specialized on tracking the global maximum power point in photovoltaic systems affected by partial shading , 2014 .

[7]  Christian Reise,et al.  On the impact of solar spectral irradiance on the yield of different PV technologies , 2015 .

[8]  Tamer Khatib,et al.  A comparative study of evolutionary algorithms and adapting control parameters for estimating the parameters of a single-diode photovoltaic module's model , 2016 .

[9]  Nipon Ketjoy,et al.  Impact of spectral irradiance distribution on the outdoor performance of photovoltaic system under Thai climatic conditions , 2012 .

[10]  Robert Tibshirani,et al.  An Introduction to the Bootstrap , 1994 .

[11]  Ricardo Mejía-Gutiérrez,et al.  Optimization of V-Trough photovoltaic concentrators through genetic algorithms with heuristics based on Weibull distributions , 2018 .

[12]  Dhiaa Halboot Muhsen,et al.  Parameters extraction of double diode photovoltaic module’s model based on hybrid evolutionary algorithm , 2015 .

[13]  Rabee M. Reffat,et al.  Genetic algorithm based optimization for photovoltaics integrated building envelope , 2016 .

[14]  Sancho Salcedo-Sanz,et al.  Sizing and maintenance visits optimization of a hybrid photovoltaic-hydrogen stand-alone facility using evolutionary algorithms , 2014 .

[15]  Terence C. Fogarty,et al.  Comparison of steady state and generational genetic algorithms for use in nonstationary environments , 1996, Proceedings of IEEE International Conference on Evolutionary Computation.

[16]  Hashim Hizam,et al.  Mismatch losses minimization in photovoltaic arrays by arranging modules applying a genetic algorithm , 2014 .

[17]  Tao Ma,et al.  Long term performance analysis of a standalone photovoltaic system under real conditions , 2017 .

[18]  F. Almonacid,et al.  Effects of spectral coupling on perovskite solar cells under diverse climatic conditions , 2015 .

[19]  Sanjay Agrawal,et al.  Efficiency maximization and performance evaluation of hybrid dual channel semitransparent photovoltaic thermal module using fuzzyfied genetic algorithm , 2016 .

[20]  M. Norton,et al.  Comparison of solar spectral irradiance measurements using the average photon energy parameter , 2015 .

[21]  C. A. Coello Coello,et al.  Multiobjective structural optimization using a microgenetic algorithm , 2005 .

[22]  Takashi Minemoto,et al.  Difference in the outdoor performance of bulk and thin-film silicon-based photovoltaic modules , 2009 .

[23]  Deepika Chauhan,et al.  Application of genetic algorithm with multi-objective function to improve the efficiency of glazed photovoltaic thermal system for New Delhi (India) climatic condition , 2015 .

[24]  M. D. Pérez-Godoy,et al.  Is the average photon energy a unique characteristic of the spectral distribution of global irradiance , 2017 .

[25]  P. Ashwini Kumari,et al.  Adaptive Genetic Algorithm Based Multi-Objective Optimization for Photovoltaic Cell Design Parameter Extraction , 2017 .

[26]  Pablo Cortés,et al.  Genetic algorithms to optimize the operating costs of electricity and heating networks in buildings considering distributed energy generation and storage , 2018, Comput. Oper. Res..

[27]  Arvind Tiwari,et al.  Modeling and parameter optimization of hybrid single channel photovoltaic thermal module using genetic algorithms , 2015 .

[28]  Kok-Keong Chong,et al.  Comprehensive method for analyzing the power conversion efficiency of organic solar cells under different spectral irradiances considering both photonic and electrical characteristics , 2016 .

[29]  Y. Hishikawa,et al.  Impact of average photon-energy coefficient of solar spectrum on the short circuit current of photovoltaic modules , 2017 .

[30]  Scott Bucking,et al.  Distributed evolutionary algorithm for co-optimization of building and district systems for early community energy masterplanning , 2018, Appl. Soft Comput..

[31]  Kalyanmoy Deb,et al.  A fast and elitist multiobjective genetic algorithm: NSGA-II , 2002, IEEE Trans. Evol. Comput..

[32]  Sanjay Agrawal,et al.  Parameter identification of the glazed photovoltaic thermal system using Genetic Algorithm–Fuzzy System (GA–FS) approach and its comparative study , 2015 .

[33]  P. L. Carotenuto,et al.  An evolutionary approach to the dynamical reconfiguration of photovoltaic fields , 2015, Neurocomputing.

[34]  T. Muneer.  Solar radiation and daylight models , 2004 .

[35]  David E. Goldberg,et al.  Sizing Populations for Serial and Parallel Genetic Algorithms , 1989, ICGA.

[36]  Rajit Gadh,et al.  Optimization of single channel glazed photovoltaic thermal (PVT) array using Evolutionary Algorithm (EA) and carbon credit earned by the optimized array , 2015 .

[37]  T. Minemoto,et al.  Impact estimation of average photon energy from two spectrum bands on short circuit current of photovoltaic modules , 2017 .

[38]  Ilhami Colak,et al.  An enhanced dynamic model of battery using genetic algorithm suitable for photovoltaic applications , 2016 .

[39]  Kenji Otani,et al.  Effects of solar spectrum and module temperature on outdoor performance of photovoltaic modules in round‐robin measurements in Japan , 2011 .

[40]  Chee Peng Lim,et al.  A multi-objective evolutionary algorithm-based decision support system: A case study on job-shop scheduling in manufacturing , 2015, 2015 Annual IEEE Systems Conference (SysCon) Proceedings.

[41]  Michael Böttiger,et al.  Comparison of particle swarm and genetic algorithm based design algorithms for PV-hybrid systems with battery and hydrogen storage path , 2017 .

[42]  Carlos A. Coello Coello,et al.  A Micro-Genetic Algorithm for Multiobjective Optimization , 2001, EMO.

[43]  Chee Peng Lim,et al.  A Modified micro Genetic Algorithm for undertaking Multi-Objective Optimization Problems , 2013, J. Intell. Fuzzy Syst..

[44]  A. Wright,et al.  Theoretical analysis of steady state genetic algorithms , 2014 .