A hybrid CFD and machine learning study of energy performance of photovoltaic systems with a porous collector: Model development and validation

This study investigates the predictive modeling of temperature (T(K)) using a dataset of over 128,000 data points characterized by x, y, and z coordinates as inputs. The case study considered here is a photovoltaic system with porous collector for enhancing the efficiency of solar system. Computatio...

Full description

Saved in:
Bibliographic Details
Main Authors: Yinling Wang, Lei Yu, Mazhar Ali, Imran Ali Khan, Tahir Maqsood, Haining Gao, Qi Wang, Xiaolei Guo
Format: Article
Language:English
Published: Elsevier 2025-05-01
Series:Case Studies in Thermal Engineering
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2214157X25002588
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850183043418947584
author Yinling Wang
Lei Yu
Mazhar Ali
Imran Ali Khan
Tahir Maqsood
Haining Gao
Qi Wang
Xiaolei Guo
author_facet Yinling Wang
Lei Yu
Mazhar Ali
Imran Ali Khan
Tahir Maqsood
Haining Gao
Qi Wang
Xiaolei Guo
author_sort Yinling Wang
collection DOAJ
description This study investigates the predictive modeling of temperature (T(K)) using a dataset of over 128,000 data points characterized by x, y, and z coordinates as inputs. The case study considered here is a photovoltaic system with porous collector for enhancing the efficiency of solar system. Computational modeling was carried out via CFD (Computational Fluid Dynamics), and the temperature distribution was determined which was later used in machine learning (ML) evaluation. Indeed, a hybrid model was developed combining CFD and ML for the first time to predict temperature distribution versus special coordinates in a photovoltaic thermal system. Three advanced machine learning models, i.e., Gradient Boosting (GB), Extreme Gradient Boosting (XGB), and Histogram-based Gradient Boosting (HGB) were applied to analyze and predict T in system. A systematic preprocessing pipeline was developed to enhance model performance, including outlier detection and feature normalization. Hyperparameter optimization process in this study uses the Water Cycle Algorithm (WCA), a metaheuristic method inspired by natural processes. Among the models, XGB emerged as the best performer, revealing a total R2 of 0.99823, a Root Mean Square Error (RMSE) of 0.06596, and a Mean Absolute Error (MAE) of 0.04442. These results demonstrated the capability of machine learning to accurately capture complex relationships within structured datasets.
format Article
id doaj-art-ba36060517bf45648095daf4e092894f
institution OA Journals
issn 2214-157X
language English
publishDate 2025-05-01
publisher Elsevier
record_format Article
series Case Studies in Thermal Engineering
spelling doaj-art-ba36060517bf45648095daf4e092894f2025-08-20T02:17:28ZengElsevierCase Studies in Thermal Engineering2214-157X2025-05-016910599810.1016/j.csite.2025.105998A hybrid CFD and machine learning study of energy performance of photovoltaic systems with a porous collector: Model development and validationYinling Wang0Lei Yu1Mazhar Ali2Imran Ali Khan3Tahir Maqsood4Haining Gao5Qi Wang6Xiaolei Guo7International Joint Laboratory of New Energy Digitalization Technology in Henan Province, Huanghuai University, Zhumadian, Henan, 463000, China; Corresponding author.International Joint Laboratory of New Energy Digitalization Technology in Henan Province, Huanghuai University, Zhumadian, Henan, 463000, China; Department of Computer Science, COMSATS University Islamabad, Abbottabad, 22060, PakistanDepartment of Computer Science, COMSATS University Islamabad, Abbottabad, 22060, Pakistan; Corresponding author.Department of Computer Science, COMSATS University Islamabad, Abbottabad, 22060, PakistanDepartment of Computer Science, COMSATS University Islamabad, Abbottabad, 22060, PakistanInternational Joint Laboratory of New Energy Digitalization Technology in Henan Province, Huanghuai University, Zhumadian, Henan, 463000, ChinaInternational Joint Laboratory of New Energy Digitalization Technology in Henan Province, Huanghuai University, Zhumadian, Henan, 463000, ChinaInternational Joint Laboratory of New Energy Digitalization Technology in Henan Province, Huanghuai University, Zhumadian, Henan, 463000, ChinaThis study investigates the predictive modeling of temperature (T(K)) using a dataset of over 128,000 data points characterized by x, y, and z coordinates as inputs. The case study considered here is a photovoltaic system with porous collector for enhancing the efficiency of solar system. Computational modeling was carried out via CFD (Computational Fluid Dynamics), and the temperature distribution was determined which was later used in machine learning (ML) evaluation. Indeed, a hybrid model was developed combining CFD and ML for the first time to predict temperature distribution versus special coordinates in a photovoltaic thermal system. Three advanced machine learning models, i.e., Gradient Boosting (GB), Extreme Gradient Boosting (XGB), and Histogram-based Gradient Boosting (HGB) were applied to analyze and predict T in system. A systematic preprocessing pipeline was developed to enhance model performance, including outlier detection and feature normalization. Hyperparameter optimization process in this study uses the Water Cycle Algorithm (WCA), a metaheuristic method inspired by natural processes. Among the models, XGB emerged as the best performer, revealing a total R2 of 0.99823, a Root Mean Square Error (RMSE) of 0.06596, and a Mean Absolute Error (MAE) of 0.04442. These results demonstrated the capability of machine learning to accurately capture complex relationships within structured datasets.http://www.sciencedirect.com/science/article/pii/S2214157X25002588CFDHybrid modelingSolar energyExtreme gradient boostingHistogram-based gradient boostingWater cycle algorithm
spellingShingle Yinling Wang
Lei Yu
Mazhar Ali
Imran Ali Khan
Tahir Maqsood
Haining Gao
Qi Wang
Xiaolei Guo
A hybrid CFD and machine learning study of energy performance of photovoltaic systems with a porous collector: Model development and validation
Case Studies in Thermal Engineering
CFD
Hybrid modeling
Solar energy
Extreme gradient boosting
Histogram-based gradient boosting
Water cycle algorithm
title A hybrid CFD and machine learning study of energy performance of photovoltaic systems with a porous collector: Model development and validation
title_full A hybrid CFD and machine learning study of energy performance of photovoltaic systems with a porous collector: Model development and validation
title_fullStr A hybrid CFD and machine learning study of energy performance of photovoltaic systems with a porous collector: Model development and validation
title_full_unstemmed A hybrid CFD and machine learning study of energy performance of photovoltaic systems with a porous collector: Model development and validation
title_short A hybrid CFD and machine learning study of energy performance of photovoltaic systems with a porous collector: Model development and validation
title_sort hybrid cfd and machine learning study of energy performance of photovoltaic systems with a porous collector model development and validation
topic CFD
Hybrid modeling
Solar energy
Extreme gradient boosting
Histogram-based gradient boosting
Water cycle algorithm
url http://www.sciencedirect.com/science/article/pii/S2214157X25002588
work_keys_str_mv AT yinlingwang ahybridcfdandmachinelearningstudyofenergyperformanceofphotovoltaicsystemswithaporouscollectormodeldevelopmentandvalidation
AT leiyu ahybridcfdandmachinelearningstudyofenergyperformanceofphotovoltaicsystemswithaporouscollectormodeldevelopmentandvalidation
AT mazharali ahybridcfdandmachinelearningstudyofenergyperformanceofphotovoltaicsystemswithaporouscollectormodeldevelopmentandvalidation
AT imranalikhan ahybridcfdandmachinelearningstudyofenergyperformanceofphotovoltaicsystemswithaporouscollectormodeldevelopmentandvalidation
AT tahirmaqsood ahybridcfdandmachinelearningstudyofenergyperformanceofphotovoltaicsystemswithaporouscollectormodeldevelopmentandvalidation
AT haininggao ahybridcfdandmachinelearningstudyofenergyperformanceofphotovoltaicsystemswithaporouscollectormodeldevelopmentandvalidation
AT qiwang ahybridcfdandmachinelearningstudyofenergyperformanceofphotovoltaicsystemswithaporouscollectormodeldevelopmentandvalidation
AT xiaoleiguo ahybridcfdandmachinelearningstudyofenergyperformanceofphotovoltaicsystemswithaporouscollectormodeldevelopmentandvalidation
AT yinlingwang hybridcfdandmachinelearningstudyofenergyperformanceofphotovoltaicsystemswithaporouscollectormodeldevelopmentandvalidation
AT leiyu hybridcfdandmachinelearningstudyofenergyperformanceofphotovoltaicsystemswithaporouscollectormodeldevelopmentandvalidation
AT mazharali hybridcfdandmachinelearningstudyofenergyperformanceofphotovoltaicsystemswithaporouscollectormodeldevelopmentandvalidation
AT imranalikhan hybridcfdandmachinelearningstudyofenergyperformanceofphotovoltaicsystemswithaporouscollectormodeldevelopmentandvalidation
AT tahirmaqsood hybridcfdandmachinelearningstudyofenergyperformanceofphotovoltaicsystemswithaporouscollectormodeldevelopmentandvalidation
AT haininggao hybridcfdandmachinelearningstudyofenergyperformanceofphotovoltaicsystemswithaporouscollectormodeldevelopmentandvalidation
AT qiwang hybridcfdandmachinelearningstudyofenergyperformanceofphotovoltaicsystemswithaporouscollectormodeldevelopmentandvalidation
AT xiaoleiguo hybridcfdandmachinelearningstudyofenergyperformanceofphotovoltaicsystemswithaporouscollectormodeldevelopmentandvalidation