TY  - JOUR
A1  - Ahmadi, Mohammad Hossein
A1  - Baghban, Alireza
A1  - Sadeghzadeh, Milad
A1  - Zamen, Mohammad
A1  - Mosavi, Amir
A1  - Shamshirband, Shahaboddin
A1  - Kumar, Ravinder
A1  - Mohammadi-Khanaposhtani, Mohammad
T1  - Evaluation of electrical efficiency of photovoltaic thermal solar collector
JF  - Engineering Applications of Computational Fluid Mechanics
N2  - In this study, machine learning methods of artificial neural networks (ANNs), least squares support vector machines (LSSVM), and neuro-fuzzy are used for advancing prediction models for thermal performance of a photovoltaic-thermal solar collector (PV/T). In the proposed models, the inlet temperature, flow rate, heat, solar radiation, and the sun heat have been considered as the input variables. Data set has been extracted through experimental measurements from a novel solar collector system. Different analyses are performed to examine the credibility of the introduced models and evaluate their performances. The proposed LSSVM model outperformed the ANFIS and ANNs models. LSSVM model is reported suitable when the laboratory measurements are costly and time-consuming, or achieving such values requires sophisticated interpretations.
KW  - Fotovoltaik
KW  - Erneuerbare Energien
KW  - Solar
KW  - Deep learning
KW  - Machine learning
KW  - Renewable energy
KW  - neural networks (NNs)
KW  - adaptive neuro-fuzzy inference system (ANFIS)
KW  - least square support vector machine (LSSVM)
KW  - photovoltaic-thermal (PV/T)
KW  - hybrid machine learning model
KW  - OA-Publikationsfonds2020
Y1  - 2020
U6  - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:gbv:wim2-20200304-41049
UR  - https://www.tandfonline.com/doi/full/10.1080/19942060.2020.1734094
VL  - 2020
IS  - volume 14, issue 1
SP  - 545
EP  - 565
PB  - Taylor & Francis
ER  - 
TY  - INPR
A1  - Mosavi, Amir
A1  - Moeini, Iman
A1  - Ahmadpour, Mohammad
A1  - Alharbi, Naif
A1  - E. Gorji, Nima
T1  - Modeling the time-dependent characteristics of perovskite solar cells
N2  - We proposed two different time-dependent modeling approaches for variation of device characteristics of perovskite solar cells under stress conditions. The first approach follows Sah-Noyce-Shockley (SNS) model based on Shockley–Read–Hall recombination/generation across the depletion width of pn junction and the second approach is based on thermionic emission model for Schottky diodes. The connecting point of these approaches to time variation is the time-dependent defect generation in depletion width (W) of the junction. We have fitted the two models with experimental data reported in the literature to perovskite solar cell and found out that each model has a superior explanation for degradation of device metrics e.g. current density and efficiency by time under stress conditions. Nevertheless, the Sah-Noyce-Shockley model is more reliable than thermionic emission at least for solar cells.
KW  - Solarzelle
KW  - Solar
KW  - Solar cells
KW  - Modeling
KW  - Time-dependent
KW  - Defect generation
KW  - Perovskite
Y1  - 2018
U6  - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:gbv:wim2-20180907-37573
N1  - Published in final form at https://doi.org/10.1016/j.solener.2018.05.082.
ER  -