Advanced automated machine learning framework for photovoltaic power output prediction using environmental parameters and SHAP interpretability
Accurate prediction of power output from a photovoltaic (PV) system is crucial for ensuring operational efficiency. This study addresses the challenge of predicting plant-scale PV power output by integrating automated machine learning (Auto-ML) with explainable modeling techniques. The integrated ap...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-03-01
|
| Series: | Results in Engineering |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2590123024020814 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841553813773746176 |
|---|---|
| author | Muhammad Paend Bakht Mohd Norzali Haji Mohd Babul Salam KSM Kader Ibrahim Nuzhat Khan Usman Ullah Sheikh Ab Al-Hadi Ab Rahman |
| author_facet | Muhammad Paend Bakht Mohd Norzali Haji Mohd Babul Salam KSM Kader Ibrahim Nuzhat Khan Usman Ullah Sheikh Ab Al-Hadi Ab Rahman |
| author_sort | Muhammad Paend Bakht |
| collection | DOAJ |
| description | Accurate prediction of power output from a photovoltaic (PV) system is crucial for ensuring operational efficiency. This study addresses the challenge of predicting plant-scale PV power output by integrating automated machine learning (Auto-ML) with explainable modeling techniques. The integrated approach enhances predictive accuracy, supporting well-informed decision-making in power systems through data-driven frameworks. Real PV power data from a plant at Universiti Tun Hussein Onn Malaysia (UTHM) and five key weather parameters were used in this experiment. Auto-ML was employed to automatically identify the best-performing models tailored to the dataset. The top four performing models, achieving the highest predictive accuracies, were identified as Extra Tree (91% accuracy), Random Forest (85%), XGBoost (75%), and Decision Tree (68%) for further analysis. Their performance was then validated against commonly used artificial neural networks (ANN) and support vector machines (SVM) using multiple evaluation metrics including prediction accuracy, error rates, and interpretability. The results clearly demonstrate the superiority of the proposed approach across all performance metrics. For practical applications, a novel data mining method is also proposed to identify primary environmental drivers of PV performance using bivariate data analysis. Additionally, the model-based role of each parameter in the machine learning (ML) context is assessed using additivity of feature importance to uncover the underlying predictive mechanism of each ML model. This study establishes an advanced and powerful framework combining Auto-ML and explainable AI for predictive modeling of PV power output. It sets new standards for significantly improved operational decisions and a broader integration of AI in renewable energy forecasting for data-driven optimization in power systems. |
| format | Article |
| id | doaj-art-56bf6ef0eb8a42da80bb9b73ac8d8a84 |
| institution | Kabale University |
| issn | 2590-1230 |
| language | English |
| publishDate | 2025-03-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Results in Engineering |
| spelling | doaj-art-56bf6ef0eb8a42da80bb9b73ac8d8a842025-01-09T06:14:29ZengElsevierResults in Engineering2590-12302025-03-0125103838Advanced automated machine learning framework for photovoltaic power output prediction using environmental parameters and SHAP interpretabilityMuhammad Paend Bakht0Mohd Norzali Haji Mohd1Babul Salam KSM Kader Ibrahim2Nuzhat Khan3Usman Ullah Sheikh4Ab Al-Hadi Ab Rahman5Faculty of Electrical and Electronic Engineering, Universiti Tun Hussein Onn Malaysia, Parit Raja, 86400, Malaysia; Department of Electrical Engineering, Balochistan University of Information Technology Engineering and Management Sciences, Quetta, 87300, PakistanFaculty of Electrical and Electronic Engineering, Universiti Tun Hussein Onn Malaysia, Parit Raja, 86400, MalaysiaGUST Engineering & Applied Innovation Research Centre (GEAR), Gulf University for Science & Technology, Hawally, 7207, Kuwait; Corresponding authors.Faculty of Electrical Engineering, Universiti Teknologi Malaysia, Johor Bahru, 81300, Johor, Malaysia; Corresponding authors.Faculty of Electrical Engineering, Universiti Teknologi Malaysia, Johor Bahru, 81300, Johor, Malaysia; Corresponding authors.Faculty of Electrical Engineering, Universiti Teknologi Malaysia, Johor Bahru, 81300, Johor, MalaysiaAccurate prediction of power output from a photovoltaic (PV) system is crucial for ensuring operational efficiency. This study addresses the challenge of predicting plant-scale PV power output by integrating automated machine learning (Auto-ML) with explainable modeling techniques. The integrated approach enhances predictive accuracy, supporting well-informed decision-making in power systems through data-driven frameworks. Real PV power data from a plant at Universiti Tun Hussein Onn Malaysia (UTHM) and five key weather parameters were used in this experiment. Auto-ML was employed to automatically identify the best-performing models tailored to the dataset. The top four performing models, achieving the highest predictive accuracies, were identified as Extra Tree (91% accuracy), Random Forest (85%), XGBoost (75%), and Decision Tree (68%) for further analysis. Their performance was then validated against commonly used artificial neural networks (ANN) and support vector machines (SVM) using multiple evaluation metrics including prediction accuracy, error rates, and interpretability. The results clearly demonstrate the superiority of the proposed approach across all performance metrics. For practical applications, a novel data mining method is also proposed to identify primary environmental drivers of PV performance using bivariate data analysis. Additionally, the model-based role of each parameter in the machine learning (ML) context is assessed using additivity of feature importance to uncover the underlying predictive mechanism of each ML model. This study establishes an advanced and powerful framework combining Auto-ML and explainable AI for predictive modeling of PV power output. It sets new standards for significantly improved operational decisions and a broader integration of AI in renewable energy forecasting for data-driven optimization in power systems.http://www.sciencedirect.com/science/article/pii/S2590123024020814Solar photovoltaicMachine learningArtificial intelligencePower predictionSustainable |
| spellingShingle | Muhammad Paend Bakht Mohd Norzali Haji Mohd Babul Salam KSM Kader Ibrahim Nuzhat Khan Usman Ullah Sheikh Ab Al-Hadi Ab Rahman Advanced automated machine learning framework for photovoltaic power output prediction using environmental parameters and SHAP interpretability Results in Engineering Solar photovoltaic Machine learning Artificial intelligence Power prediction Sustainable |
| title | Advanced automated machine learning framework for photovoltaic power output prediction using environmental parameters and SHAP interpretability |
| title_full | Advanced automated machine learning framework for photovoltaic power output prediction using environmental parameters and SHAP interpretability |
| title_fullStr | Advanced automated machine learning framework for photovoltaic power output prediction using environmental parameters and SHAP interpretability |
| title_full_unstemmed | Advanced automated machine learning framework for photovoltaic power output prediction using environmental parameters and SHAP interpretability |
| title_short | Advanced automated machine learning framework for photovoltaic power output prediction using environmental parameters and SHAP interpretability |
| title_sort | advanced automated machine learning framework for photovoltaic power output prediction using environmental parameters and shap interpretability |
| topic | Solar photovoltaic Machine learning Artificial intelligence Power prediction Sustainable |
| url | http://www.sciencedirect.com/science/article/pii/S2590123024020814 |
| work_keys_str_mv | AT muhammadpaendbakht advancedautomatedmachinelearningframeworkforphotovoltaicpoweroutputpredictionusingenvironmentalparametersandshapinterpretability AT mohdnorzalihajimohd advancedautomatedmachinelearningframeworkforphotovoltaicpoweroutputpredictionusingenvironmentalparametersandshapinterpretability AT babulsalamksmkaderibrahim advancedautomatedmachinelearningframeworkforphotovoltaicpoweroutputpredictionusingenvironmentalparametersandshapinterpretability AT nuzhatkhan advancedautomatedmachinelearningframeworkforphotovoltaicpoweroutputpredictionusingenvironmentalparametersandshapinterpretability AT usmanullahsheikh advancedautomatedmachinelearningframeworkforphotovoltaicpoweroutputpredictionusingenvironmentalparametersandshapinterpretability AT abalhadiabrahman advancedautomatedmachinelearningframeworkforphotovoltaicpoweroutputpredictionusingenvironmentalparametersandshapinterpretability |