Global solar irradiation prediction using a multi-gene genetic programming approach

Created by W.Langdon from gp-bibliography.bib Revision:1.8051

@Article{oai:arXiv.org:1403.0623,

• author = "Indranil Pan and Daya Shankar Pandey and Saptarshi Das",
• title = "Global solar irradiation prediction using a multi-gene genetic programming approach",
• journal = "Journal of Renewable and Sustainable Energy",
• year = "2013",
• volume = "5",
• number = "6",
• keywords = "genetic algorithms, genetic programming, computer science - neural and evolutionary computing, computer science - computational engineering, finance, and science, statistics - applications",
• eid = "063129",
• bibsource = "OAI-PMH server at export.arxiv.org",
• identifier = "Journal of Renewable and Sustainable Energy, vol. 5, no. 6, pp. 063129, 2013; doi:10.1063/1.4850495",
• oai = "oai:arXiv.org:1403.0623",
• URL = "http://arxiv.org/abs/1403.0623",
• URL = "http://scitation.aip.org/content/aip/journal/jrse/5/6/10.1063/1.4850495",
• DOI = "doi:10.1063/1.4850495",
• abstract = "In this paper, a nonlinear symbolic regression technique using an evolutionary algorithm known as multi-gene genetic programming (MGGP) is applied for a data-driven modelling between the dependent and the independent variables. The technique is applied for modelling the measured global solar irradiation and validated through numerical simulations. The proposed modelling technique shows improved results over the fuzzy logic and artificial neural network (ANN) based approaches as attempted by contemporary researchers. The method proposed here results in nonlinear analytical expressions, unlike those with neural networks which is essentially a black box modelling approach. This additional flexibility is an advantage from the modelling perspective and helps to discern the important variables which affect the prediction. Due to the evolutionary nature of the algorithm, it is able to get out of local minima and converge to a global optimum unlike the back-propagation (BP) algorithm used for training neural networks. This results in a better percentage fit than the ones obtained using neural networks by contemporary researchers. Also a hold-out cross validation is done on the obtained genetic programming (GP) results which show that the results generalise well to new data and do not over-fit the training samples. The multi-gene GP results are compared with those, obtained using its single-gene version and also the same with four classical regression models in order to show the effectiveness of the adopted approach.",

}

Genetic Programming entries for Indranil Pan Daya Shankar Pandey Saptarshi Das

Citations