Machine learning-based performance prediction of photovoltaic cooling systems with porous mini-channels

Given the importance of increasing the efficiency of photovoltaic (PV) systems, the development of cooling systems is of particular importance. In this study, the effect of using a mini-channel integrated with a porous medium and fins on the performance of PV has been numerically investigated. The porous medium is partial and cross-flow. The findings indicate that the use of a mini-channel reduces the cell temperature and increases the electrical efficiency by about 10 to 17% with air and 25 to 27% with water, compared with the uncooled panel. At the same Reynolds number, changing the fluid from air to water increased the electrical efficiency by about 8 to 13%, the exergy efficiency by about 7 to 8% and the thermal efficiency by about 136 to 150%, but caused about a threefold increase in pressure drop. Adding a partial porous medium in the cross-flow path improved the efficiencies by about 0.2 to 7%, depending on the porosity, permeability and solid matrix conductivity (the largest effect, a 7.2% increase in thermal efficiency, came from the solid-to-fluid conductivity ratio), and increasing the number of porous regions from Case 3–1 to Case 3–3 raised the gain in electrical efficiency with increasing Re from 7.9% to 11.0%. In the mini-channel with fins of varying height (Cases 4–1 to 4–3), the thermal efficiency of the best case (Case 4–3) increases by 131% (from about 0.28 to 0.645) and its electrical efficiency by 8.7% as the Reynolds number rises from 40 to 1500. Using the random forest machine learning model and the data of the present study, electrical and thermal efficiency were simultaneously estimated with high accuracy. A strategy for selecting the appropriate configuration was presented by considering the criteria of electrical, thermal and pressure drop efficiency based on the TOPSIS multi-criteria decision-making method, which can help designers to optimize and increase efficiency and choose the most suitable configuration based on the desired criteria. The ranking was found to be stable when the criteria weights were varied.

Authors

Institutions

Publication Details

Journal
Discover Applied Sciences
Published
2026-11-19
DOI
https://doi.org/10.1007/s42452-026-09920-3
Primary Topic
Solar Thermal and Photovoltaic Systems
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Machine learning-based performance prediction of photovoltaic cooling systems with porous mini-channels

Samad Jafarmadar, Somayeh Davoodabadi Farahani, Ali Rabiee, As’ad Alizadeh
Discover Applied Sciences
Solar Thermal and Photovoltaic Systems
article

Machine learning-based performance prediction of photovoltaic cooling systems with porous mini-channels

Samad Jafarmadar, Somayeh Davoodabadi Farahani, Ali Rabiee, As’ad Alizadeh
article en

Abstract

Given the importance of increasing the efficiency of photovoltaic (PV) systems, the development of cooling systems is of particular importance. In this study, the effect of using a mini-channel integrated with a porous medium and fins on the performance of PV has been numerically investigated. The porous medium is partial and cross-flow. The findings indicate that the use of a mini-channel reduces the cell temperature and increases the electrical efficiency by about 10 to 17% with air and 25 to 27% with water, compared with the uncooled panel. At the same Reynolds number, changing the fluid from air to water increased the electrical efficiency by about 8 to 13%, the exergy efficiency by about 7 to 8% and the thermal efficiency by about 136 to 150%, but caused about a threefold increase in pressure drop. Adding a partial porous medium in the cross-flow path improved the efficiencies by about 0.2 to 7%, depending on the porosity, permeability and solid matrix conductivity (the largest effect, a 7.2% increase in thermal efficiency, came from the solid-to-fluid conductivity ratio), and increasing the number of porous regions from Case 3–1 to Case 3–3 raised the gain in electrical efficiency with increasing Re from 7.9% to 11.0%. In the mini-channel with fins of varying height (Cases 4–1 to 4–3), the thermal efficiency of the best case (Case 4–3) increases by 131% (from about 0.28 to 0.645) and its electrical efficiency by 8.7% as the Reynolds number rises from 40 to 1500. Using the random forest machine learning model and the data of the present study, electrical and thermal efficiency were simultaneously estimated with high accuracy. A strategy for selecting the appropriate configuration was presented by considering the criteria of electrical, thermal and pressure drop efficiency based on the TOPSIS multi-criteria decision-making method, which can help designers to optimize and increase efficiency and choose the most suitable configuration based on the desired criteria. The ranking was found to be stable when the criteria weights were varied.

Discover Applied Sciences
Urmia University (IR), Arak University of Technology (IR)
Solar Thermal and Photovoltaic Systems
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon