Evaluating machine learning models comprehensively for predicting maximum power from photovoltaic systems
Abstract This paper presents a machine learning (ML) model designed to track the maximum power point of standalone Photovoltaic (PV) systems. Due to the nonlinear nature of power generation in PV systems, influenced by fluctuating weather conditions, managing this nonlinear data effectively remains...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-03-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-025-91044-6 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850207897612451840 |
|---|---|
| author | Samir A. Hamad Mohamed A. Ghalib Amr Munshi Majid Alotaibi Mostafa A. Ebied |
| author_facet | Samir A. Hamad Mohamed A. Ghalib Amr Munshi Majid Alotaibi Mostafa A. Ebied |
| author_sort | Samir A. Hamad |
| collection | DOAJ |
| description | Abstract This paper presents a machine learning (ML) model designed to track the maximum power point of standalone Photovoltaic (PV) systems. Due to the nonlinear nature of power generation in PV systems, influenced by fluctuating weather conditions, managing this nonlinear data effectively remains a challenge. As a result, the use of ML techniques to optimize PV systems at their MPP is highly beneficial. To achieve this, the research explores various ML algorithms, such as Linear Regression (LR), Ridge Regression (RR), Lasso Regression (Lasso R), Bayesian Regression (BR), Decision Tree Regression (DTR), Gradient Boosting Regression (GBR), and Artificial Neural Networks (ANN), to predict the MPP of PV systems. The model utilizes data from the PV unit’s technical specifications, allowing the algorithms to forecast maximum power, current, and voltage based on given irradiance and temperature inputs. Predicted data is also used to determine the boost converter’s duty cycle. The simulation was conducted on a 100 kW solar panel with an open-circuit voltage of 64.2 V and a short-circuit current of 5.96 A. Model performance was evaluated using metrics such as Root Mean Square Error (RMSE), Coefficient of Determination (R2), and Mean Absolute Error (MAE). Additionally, the study assessed the correlation and feature importance to evaluate model compatibility and the factors impacting the predictive accuracy of the ML models. Results showed that the DTR algorithm outperformed others like LR, RR, Lasso R, BR, GBR, and ANN in predicting the maximum current (Im), voltage (Vm), and power (Pm) of the PV system. The DTR model achieved RMSE, MAE, and R2 values of 0.006, 0.004, and 0.99999 for Im, 0.015, 0.0036, and 0.99999 for Vm, and 2.36, 0.871, and 0.99999 for Pm. Factors such as the size of the training dataset, operating conditions of the PV system, model type, and data preprocessing were found to significantly influence prediction accuracy. |
| format | Article |
| id | doaj-art-2c85624ec6e54e368af32903e5a0ebd9 |
| institution | OA Journals |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-03-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-2c85624ec6e54e368af32903e5a0ebd92025-08-20T02:10:21ZengNature PortfolioScientific Reports2045-23222025-03-0115112710.1038/s41598-025-91044-6Evaluating machine learning models comprehensively for predicting maximum power from photovoltaic systemsSamir A. Hamad0Mohamed A. Ghalib1Amr Munshi2Majid Alotaibi3Mostafa A. Ebied4Process Control Technology Department, Faculty of Technology and Education, Beni-Suef UniversityProcess Control Technology Department, Faculty of Technology and Education, Beni-Suef UniversityDepartment of Computer and Network Engineering, College of Computing, Umm Al-Qura UniversityDepartment of Computer and Network Engineering, College of Computing, Umm Al-Qura UniversityElectronics Technology Department, Faculty of Technology and Education, Beni-Suef UniversityAbstract This paper presents a machine learning (ML) model designed to track the maximum power point of standalone Photovoltaic (PV) systems. Due to the nonlinear nature of power generation in PV systems, influenced by fluctuating weather conditions, managing this nonlinear data effectively remains a challenge. As a result, the use of ML techniques to optimize PV systems at their MPP is highly beneficial. To achieve this, the research explores various ML algorithms, such as Linear Regression (LR), Ridge Regression (RR), Lasso Regression (Lasso R), Bayesian Regression (BR), Decision Tree Regression (DTR), Gradient Boosting Regression (GBR), and Artificial Neural Networks (ANN), to predict the MPP of PV systems. The model utilizes data from the PV unit’s technical specifications, allowing the algorithms to forecast maximum power, current, and voltage based on given irradiance and temperature inputs. Predicted data is also used to determine the boost converter’s duty cycle. The simulation was conducted on a 100 kW solar panel with an open-circuit voltage of 64.2 V and a short-circuit current of 5.96 A. Model performance was evaluated using metrics such as Root Mean Square Error (RMSE), Coefficient of Determination (R2), and Mean Absolute Error (MAE). Additionally, the study assessed the correlation and feature importance to evaluate model compatibility and the factors impacting the predictive accuracy of the ML models. Results showed that the DTR algorithm outperformed others like LR, RR, Lasso R, BR, GBR, and ANN in predicting the maximum current (Im), voltage (Vm), and power (Pm) of the PV system. The DTR model achieved RMSE, MAE, and R2 values of 0.006, 0.004, and 0.99999 for Im, 0.015, 0.0036, and 0.99999 for Vm, and 2.36, 0.871, and 0.99999 for Pm. Factors such as the size of the training dataset, operating conditions of the PV system, model type, and data preprocessing were found to significantly influence prediction accuracy.https://doi.org/10.1038/s41598-025-91044-6Maximum power extraction (MPE) techniqueMachine-learningDC–DC converterPrediction modelArtificial neural network |
| spellingShingle | Samir A. Hamad Mohamed A. Ghalib Amr Munshi Majid Alotaibi Mostafa A. Ebied Evaluating machine learning models comprehensively for predicting maximum power from photovoltaic systems Scientific Reports Maximum power extraction (MPE) technique Machine-learning DC–DC converter Prediction model Artificial neural network |
| title | Evaluating machine learning models comprehensively for predicting maximum power from photovoltaic systems |
| title_full | Evaluating machine learning models comprehensively for predicting maximum power from photovoltaic systems |
| title_fullStr | Evaluating machine learning models comprehensively for predicting maximum power from photovoltaic systems |
| title_full_unstemmed | Evaluating machine learning models comprehensively for predicting maximum power from photovoltaic systems |
| title_short | Evaluating machine learning models comprehensively for predicting maximum power from photovoltaic systems |
| title_sort | evaluating machine learning models comprehensively for predicting maximum power from photovoltaic systems |
| topic | Maximum power extraction (MPE) technique Machine-learning DC–DC converter Prediction model Artificial neural network |
| url | https://doi.org/10.1038/s41598-025-91044-6 |
| work_keys_str_mv | AT samirahamad evaluatingmachinelearningmodelscomprehensivelyforpredictingmaximumpowerfromphotovoltaicsystems AT mohamedaghalib evaluatingmachinelearningmodelscomprehensivelyforpredictingmaximumpowerfromphotovoltaicsystems AT amrmunshi evaluatingmachinelearningmodelscomprehensivelyforpredictingmaximumpowerfromphotovoltaicsystems AT majidalotaibi evaluatingmachinelearningmodelscomprehensivelyforpredictingmaximumpowerfromphotovoltaicsystems AT mostafaaebied evaluatingmachinelearningmodelscomprehensivelyforpredictingmaximumpowerfromphotovoltaicsystems |