Original Research (Published On: 09-Jun-2026 )
DOI : https://doi.org/10.54364/AAIML.2026.63311Nathaniel Abidemi Akinrinade, Ayodele Onawumi, Abiola Ajayeoba, Emmanuel Sangotayo, Oludolapo Akanni Olanrewaju, Kazeem Bello, Rendani Maladzhi and Ilesanmi Daniyan
Adv. Artif. Intell. Mach. Learn., 6 (3):5630-5653
1. Nathaniel Abidemi Akinrinade: Department of Mechanical Engineering, College of Engineering, Bells University of Technology, Ota, Ogun State, Nigeria.
2. Ayodele Onawumi: Department of Mechanical Engineering, Faculty of Engineering and Technology, Ladoke Akintola University of Technology, Ogbomoso, Oyo State, Nigeria.
3. Abiola Ajayeoba: Department of Mechanical Engineering, Faculty of Engineering and Technology, Ladoke Akintola University of Technology, Ogbomoso, Oyo State, Nigeria
4. Emmanuel Sangotayo: Department of Mechanical Engineering, Faculty of Engineering and Technology, Ladoke Akintola University of Technology, Ogbomoso, Oyo State, Nigeria
5. Oludolapo Akanni Olanrewaju: Institute of Systems Science, Durban University of Technology, Durban South Africa
6. Kazeem Bello: Department of Mechanical Engineering, Durban University of Technology, Durban, South Africa.
7. Rendani Maladzhi: Department of Mechanical Engineering, Durban University of Technology, Durban, South Africa.
8. Ilesanmi Daniyan: Department of Mechatronics Engineering, Bells University of Technology P. M. B. 1015, Ota, Nigeria.
DOI: 10.54364/AAIML.2026.63311
Article History: Received on: 13-Nov-25, Accepted on: 02-Jun-26, Published on: 09-Jun-26
Corresponding Author: Nathaniel Abidemi Akinrinade
Email: naakinrinade@bellsuniversity.e
Citation: Nathaniel Abidemi Akinrinade, et al. Application of Machine Learning Models for the Prediction of Solar Panel Wattage for Rotating and Static Panel Systems. Advances in Artificial Intelligence and Machine Learning. 2026;6(3):311. https://dx.doi.org/10.54364/AAIML.2026.63311
Abstract
The
increasing energy demand, triggered by industrial
growth, technological advancements, and population increases necessitate the deployment of effective energy management systems capable of real time prediction.
This study applies six machine learning (ML) models for the prediction of solar
panel wattage for rotating and static panel systems. The ML employed include:
Adaboost, Neural Network (NN), Random Forest (RF), k-nearest neighbor (kNN),
Decision Tree (DT) and Gradient Boosting (GB). The implementation of ML was
done in the Orange software environment three phases namely data preparation and
pre-processing, application of ML models and performance evaluation. The
results obtained indicate that the Adaboost model outperform other models with a
Root Mean Square Error (RMSE) of 3.276 W, Mean Absolute Error (MAE) of 1.659,
Mean Absolute Percentage Error (MAPE) of 0.094 and coefficient of
determination (R2) of 0.888. The scatter plot also indicate a strong
correlation between the actual and predicted values of the solar panel wattage
for both the rotating and static systems. Hence, this study can assist in
effective solar energy prediction for improved energy management.
Statistics
Article Views: 1008
PDF Downloads: 3