Photovoltaic module temperature prediction using various machine learning algorithms: Performance evaluation

被引:14
作者
Keddouda, Abdelhak [1 ,2 ]
Ihaddadene, Razika [1 ,3 ]
Boukhari, Ali [4 ,5 ]
Atia, Abdelmalek [6 ,7 ]
Arici, Muslum [8 ,9 ]
Lebbihiat, Nacer [4 ,6 ]
Ihaddadene, Nabila [1 ,3 ]
机构
[1] Univ Msila, Dept Mech Engn, POB 166, Msila 28000, Algeria
[2] Univ Msila, Lab Mat & Mech Struct LMMS, Msila, Algeria
[3] Univ Msila, Lab Water Environm & Renewable Energies, Msila, Algeria
[4] Univ El Oued, Fac Technol, Dept Mech Engn, El Oued 39000, Algeria
[5] Renewable Energy Res Unit Arid Zones, El Oued 39000, Algeria
[6] Univ El Oued, Fac Technol, LEVRES Lab, El Oued 39000, Algeria
[7] Univ El Oued, Technol Fac, UDERZA Unit, El Oued 39000, Algeria
[8] Kocaeli Univ, Fac Engn, Dept Mech Engn, TR-41001 Kocaeli, Turkiye
[9] Kocaeli Univ, Int Joint Lab Low Carbon & New Energy Nexus Res &, TR-41001 Kocaeli, Turkiye
关键词
PV module temperature; Machine learning; Prediction; Ambient conditions; PV power; OPERATING TEMPERATURE; RIDGE-REGRESSION; THERMAL-BEHAVIOR; DEPENDENCE; SELECTION; MODEL;
D O I
10.1016/j.apenergy.2024.123064
中图分类号
TE [石油、天然气工业]; TK [能源与动力工程];
学科分类号
0807 ; 0820 ;
摘要
This paper presents data-driven models for photovoltaic module temperature prediction and analyzes the relation and effects of ambient conditions to module temperature. A total of 12 different machine learning and regression algorithms are implemented, with a large experimental dataset of 345,600 x 7. Prior to implementing those algorithms, data preprocessing is performed to prepare the datasets and determine the informative attributes for the models. Using PCA with module temperature as target to predict, the selected features for models' inputs were determined to be ambient temperature, solar radiation, wind speed, and relative humidity, and each algorithm is cross-validated and tuned with optimal performance parameters. Results show that while relative humidity is more likely to introduce less information to the model, other aforementioned features are the important parameters to predict the module temperature. While for linear modeling, LASSO algorithm provided the best performance, the ANN model demonstrated the best overall results as it produced the most accurate predictions with lowest errors. A similar performance is attained by the proposed non-linear model, KRR and Gradient Boosting algorithm, with a slight advantage to the KRR model. Furthermore, in comparison to experimental data, the ANN model and the proposed non-linear model provided an R2 values of 0.986 and 0.981, with a MAE of 0.982 and 1.476, and MSE of 2.181and 3.464, respectively. Moreover, the proposed model supplied accurate results when compared to models from literature in an out-of-sample testing, it also proven to be robust and accurate when used to predict the PV power output.
引用
收藏
页数:21
相关论文
共 75 条
[41]   Calculation of the polycrystalline PV module temperature using a simple method of energy balance [J].
Mattei, M ;
Notton, G ;
Cristofari, C ;
Muselli, M ;
Poggi, P .
RENEWABLE ENERGY, 2006, 31 (04) :553-567
[42]   Development and experimental validation of a comprehensive thermoelectric dynamic model of photovoltaic modules [J].
Migliorini, Luca ;
Molinaroli, Luca ;
Simonetti, Riccardo ;
Manzolini, Giampaolo .
SOLAR ENERGY, 2017, 144 :489-501
[43]   Prediction of the output power of photovoltaic module using artificial neural networks model with optimizing the neurons number [J].
Mohammad, Abdulrahman Th. ;
Hussen, Hasanen M. ;
Akeiber, Hussein J. .
INTERNATIONAL JOURNAL OF RENEWABLE ENERGY DEVELOPMENT-IJRED, 2023, 12 (03) :478-487
[44]   Numerical and experimental investigation for analyzing the temperature influence on the performance of photovoltaic module [J].
Mohammad, Abdulrahman Th. ;
Al Shohani, Wisam A. M. .
AIMS ENERGY, 2022, 10 (05) :1026-1045
[45]   Comparison of measured and predicted long term performance of grid a connected photovoltaic system [J].
Mondol, Jayanta Deb ;
Yohanis, Yigzaw G. ;
Norton, Brian .
ENERGY CONVERSION AND MANAGEMENT, 2007, 48 (04) :1065-1080
[46]  
Murphy K. P., 2022, Probabilistic Machine Learning: An Introduction
[47]  
Muzathik A., 2014, INT J ENERGY ENG, V4, P151
[48]  
Nordmann T, 2003, WORL CON PHOTOVOLT E, P2243
[49]   Dynamic thermal modelling for the prediction of the operating temperature of a PV panel with an integrated cooling system [J].
Osma-Pinto, German ;
Ordonez-Plata, Gabriel .
RENEWABLE ENERGY, 2020, 152 :1041-1054
[50]  
Pawlowski A, 2010, PROC IEEE INT SYMP, P409, DOI 10.1109/ISIE.2010.5637867