Related Experiment Video
Updated: Jun 17, 2025
Integrating a Triplet-triplet Annihilation Up-conversion System to Enhance Dye-sensitized Solar Cell Response to Sub-bandgap Light
Published on: September 12, 2014
Enhancing solar photovoltaic energy production prediction using diverse machine learning models tuned with the chimp
Sameer Al-Dahidi1, Mohammad Alrbai2, Hussein Alahmer3
1Department of Mechanical and Maintenance Engineering, School of Applied Technical Sciences, German Jordanian University, Amman, 11180, Jordan. sameer.aldahidi@gju.edu.jo.
Accurate solar energy forecasting using machine learning models is crucial for sustainable power. The multi-layer perceptron (MLP) model, optimized with the Chimp Optimization Algorithm (ChOA), demonstrated superior performance in predicting photovoltaic energy production.
Area of Science:
- Renewable Energy Systems
- Artificial Intelligence in Energy
- Environmental Data Analysis
Background:
- Solar photovoltaic (PV) systems are key to sustainable energy but face forecasting challenges due to environmental variability.
- Accurate prediction of PV energy output is essential for grid integration and energy management.
Purpose of the Study:
- To compare five machine learning models for predicting solar PV energy production.
- To evaluate the impact of hyperparameter tuning using the Chimp Optimization Algorithm (ChOA) on model performance.
Main Methods:
- Developed and compared Multiple Linear Regression (MLR), Decision Tree Regression (DTR), Random Forest Regression (RFR), Support Vector Regression (SVR), and Multi-layer Perceptron (MLP) models.
- Utilized wind speed, relative humidity, ambient temperature, and solar irradiation as input variables.
- Applied the Chimp Optimization Algorithm (ChOA) for hyperparameter tuning and validated models on data from a 264 kWp PV system.
Main Results:
- The Multi-layer Perceptron (MLP) model achieved the best performance with a Root Mean Square Error (RMSE) of 0.503, Mean Absolute Error (MAE) of 0.397, and R-squared (R²) of 0.99.
- The Chimp Optimization Algorithm (ChOA) significantly enhanced the prediction accuracy of the machine learning models.
Conclusions:
- Optimized machine learning models, particularly MLP with ChOA, offer high accuracy for solar PV energy forecasting.
- Advanced optimization techniques are vital for improving prediction accuracy in renewable energy domains.
