Integrated support vector regression and an improved particle swarm optimization-based model for solar radiation prediction

Hamidreza Ghazvinian, Sayed Farhad Mousavi, Hojat Karami, Saeed Farzin, Mohammad Ehteram, Md Shabbir Hossain, Ming Fai Chow, Huzaifa Bin Hashim, Vijay P. Singh, Faizah Che Ros, Ali Najah Ahmed, Haitham Abdulmohsin Afan, Sai Hin Lai, Ahmed El-Shafie

Research output: Contribution to journalArticle

Abstract

Solar energy is a major type of renewable energy, and its estimation is important for decision- makers. This study introduces a new prediction model for solar radiation based on support vector regression (SVR) and the improved particle swarm optimization (IPSO) algorithm. The new version of algorithm attempts to enhance the global search ability for the PSO. In practice, the SVR method has a few parameters that should be determined through a trial-and-error procedure while developing the prediction model. This procedure usually leads to non-optimal choices for these parameters and, hence, poor prediction accuracy. Therefore, there is a need to integrate the SVR model with an optimization algorithm to achieve optimal choices for these parameters. Thus, the IPSO algorithm, as an optimizer is integrated with SVR to obtain optimal values for the SVR parameters. To examine the proposed model, two solar radiation stations, Adana, Antakya and Konya, in Turkey, are considered for this study. In addition, different models have been tested for this prediction, namely, the M5 tree model (M5T), genetic programming (GP), SVR integrated with four different optimization algorithms SVR-PSO, SVR-IPSO, Genetic Algorithm (SVR-GA), FireFly Algorithm (SVR-FFA) and the multivariate adaptive regression (MARS) model. The sensitivity analysis is performed to achieve the highest accuracy level of the prediction by choosing different input parameters. Several performance measuring indices have been considered to examine the efficiency of all the prediction methods. The results show that SVR-IPSO outperformed M5T and MARS.

Original languageEnglish
Article numbere0217634
JournalPLoS ONE
Volume14
Issue number5
DOIs
Publication statusPublished - 01 May 2019

Fingerprint

swarms
Solar radiation
Particle swarm optimization (PSO)
solar radiation
Radiation
prediction
Fireflies
Solar Energy
Renewable Energy
Lampyridae
Genetic Models
solar energy
Turkey
renewable energy sources
Genetic programming
Solar energy
Sensitivity analysis
Turkey (country)
Genetic algorithms
methodology

All Science Journal Classification (ASJC) codes

  • Biochemistry, Genetics and Molecular Biology(all)
  • Agricultural and Biological Sciences(all)

Cite this

Ghazvinian, Hamidreza ; Mousavi, Sayed Farhad ; Karami, Hojat ; Farzin, Saeed ; Ehteram, Mohammad ; Hossain, Md Shabbir ; Chow, Ming Fai ; Hashim, Huzaifa Bin ; Singh, Vijay P. ; Ros, Faizah Che ; Ahmed, Ali Najah ; Afan, Haitham Abdulmohsin ; Lai, Sai Hin ; El-Shafie, Ahmed. / Integrated support vector regression and an improved particle swarm optimization-based model for solar radiation prediction. In: PLoS ONE. 2019 ; Vol. 14, No. 5.
@article{d4d9cad76ea142e7ac1d9da9f5408e6c,
title = "Integrated support vector regression and an improved particle swarm optimization-based model for solar radiation prediction",
abstract = "Solar energy is a major type of renewable energy, and its estimation is important for decision- makers. This study introduces a new prediction model for solar radiation based on support vector regression (SVR) and the improved particle swarm optimization (IPSO) algorithm. The new version of algorithm attempts to enhance the global search ability for the PSO. In practice, the SVR method has a few parameters that should be determined through a trial-and-error procedure while developing the prediction model. This procedure usually leads to non-optimal choices for these parameters and, hence, poor prediction accuracy. Therefore, there is a need to integrate the SVR model with an optimization algorithm to achieve optimal choices for these parameters. Thus, the IPSO algorithm, as an optimizer is integrated with SVR to obtain optimal values for the SVR parameters. To examine the proposed model, two solar radiation stations, Adana, Antakya and Konya, in Turkey, are considered for this study. In addition, different models have been tested for this prediction, namely, the M5 tree model (M5T), genetic programming (GP), SVR integrated with four different optimization algorithms SVR-PSO, SVR-IPSO, Genetic Algorithm (SVR-GA), FireFly Algorithm (SVR-FFA) and the multivariate adaptive regression (MARS) model. The sensitivity analysis is performed to achieve the highest accuracy level of the prediction by choosing different input parameters. Several performance measuring indices have been considered to examine the efficiency of all the prediction methods. The results show that SVR-IPSO outperformed M5T and MARS.",
author = "Hamidreza Ghazvinian and Mousavi, {Sayed Farhad} and Hojat Karami and Saeed Farzin and Mohammad Ehteram and Hossain, {Md Shabbir} and Chow, {Ming Fai} and Hashim, {Huzaifa Bin} and Singh, {Vijay P.} and Ros, {Faizah Che} and Ahmed, {Ali Najah} and Afan, {Haitham Abdulmohsin} and Lai, {Sai Hin} and Ahmed El-Shafie",
year = "2019",
month = "5",
day = "1",
doi = "10.1371/journal.pone.0217634",
language = "English",
volume = "14",
journal = "PLoS One",
issn = "1932-6203",
publisher = "Public Library of Science",
number = "5",

}

Ghazvinian, H, Mousavi, SF, Karami, H, Farzin, S, Ehteram, M, Hossain, MS, Chow, MF, Hashim, HB, Singh, VP, Ros, FC, Ahmed, AN, Afan, HA, Lai, SH & El-Shafie, A 2019, 'Integrated support vector regression and an improved particle swarm optimization-based model for solar radiation prediction', PLoS ONE, vol. 14, no. 5, e0217634. https://doi.org/10.1371/journal.pone.0217634

Integrated support vector regression and an improved particle swarm optimization-based model for solar radiation prediction. / Ghazvinian, Hamidreza; Mousavi, Sayed Farhad; Karami, Hojat; Farzin, Saeed; Ehteram, Mohammad; Hossain, Md Shabbir; Chow, Ming Fai; Hashim, Huzaifa Bin; Singh, Vijay P.; Ros, Faizah Che; Ahmed, Ali Najah; Afan, Haitham Abdulmohsin; Lai, Sai Hin; El-Shafie, Ahmed.

In: PLoS ONE, Vol. 14, No. 5, e0217634, 01.05.2019.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Integrated support vector regression and an improved particle swarm optimization-based model for solar radiation prediction

AU - Ghazvinian, Hamidreza

AU - Mousavi, Sayed Farhad

AU - Karami, Hojat

AU - Farzin, Saeed

AU - Ehteram, Mohammad

AU - Hossain, Md Shabbir

AU - Chow, Ming Fai

AU - Hashim, Huzaifa Bin

AU - Singh, Vijay P.

AU - Ros, Faizah Che

AU - Ahmed, Ali Najah

AU - Afan, Haitham Abdulmohsin

AU - Lai, Sai Hin

AU - El-Shafie, Ahmed

PY - 2019/5/1

Y1 - 2019/5/1

N2 - Solar energy is a major type of renewable energy, and its estimation is important for decision- makers. This study introduces a new prediction model for solar radiation based on support vector regression (SVR) and the improved particle swarm optimization (IPSO) algorithm. The new version of algorithm attempts to enhance the global search ability for the PSO. In practice, the SVR method has a few parameters that should be determined through a trial-and-error procedure while developing the prediction model. This procedure usually leads to non-optimal choices for these parameters and, hence, poor prediction accuracy. Therefore, there is a need to integrate the SVR model with an optimization algorithm to achieve optimal choices for these parameters. Thus, the IPSO algorithm, as an optimizer is integrated with SVR to obtain optimal values for the SVR parameters. To examine the proposed model, two solar radiation stations, Adana, Antakya and Konya, in Turkey, are considered for this study. In addition, different models have been tested for this prediction, namely, the M5 tree model (M5T), genetic programming (GP), SVR integrated with four different optimization algorithms SVR-PSO, SVR-IPSO, Genetic Algorithm (SVR-GA), FireFly Algorithm (SVR-FFA) and the multivariate adaptive regression (MARS) model. The sensitivity analysis is performed to achieve the highest accuracy level of the prediction by choosing different input parameters. Several performance measuring indices have been considered to examine the efficiency of all the prediction methods. The results show that SVR-IPSO outperformed M5T and MARS.

AB - Solar energy is a major type of renewable energy, and its estimation is important for decision- makers. This study introduces a new prediction model for solar radiation based on support vector regression (SVR) and the improved particle swarm optimization (IPSO) algorithm. The new version of algorithm attempts to enhance the global search ability for the PSO. In practice, the SVR method has a few parameters that should be determined through a trial-and-error procedure while developing the prediction model. This procedure usually leads to non-optimal choices for these parameters and, hence, poor prediction accuracy. Therefore, there is a need to integrate the SVR model with an optimization algorithm to achieve optimal choices for these parameters. Thus, the IPSO algorithm, as an optimizer is integrated with SVR to obtain optimal values for the SVR parameters. To examine the proposed model, two solar radiation stations, Adana, Antakya and Konya, in Turkey, are considered for this study. In addition, different models have been tested for this prediction, namely, the M5 tree model (M5T), genetic programming (GP), SVR integrated with four different optimization algorithms SVR-PSO, SVR-IPSO, Genetic Algorithm (SVR-GA), FireFly Algorithm (SVR-FFA) and the multivariate adaptive regression (MARS) model. The sensitivity analysis is performed to achieve the highest accuracy level of the prediction by choosing different input parameters. Several performance measuring indices have been considered to examine the efficiency of all the prediction methods. The results show that SVR-IPSO outperformed M5T and MARS.

UR - http://www.scopus.com/inward/record.url?scp=85066505795&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85066505795&partnerID=8YFLogxK

U2 - 10.1371/journal.pone.0217634

DO - 10.1371/journal.pone.0217634

M3 - Article

VL - 14

JO - PLoS One

JF - PLoS One

SN - 1932-6203

IS - 5

M1 - e0217634

ER -