What question did this study set out to answer?

The research aims to enhance solar irradiance forecasting using machine learning and wavelet techniques.

March 14, 2026Turkish Journal of Forecasting0 citationsOpen Access

Wavelet-Enhanced Machine Learning Models for Hourly Solar Irradiance Forecasting

GOGbadebo I. OlatonaOsun State University SAShuaib A. AdisaOsun State University MLMuyideen Olalekan LawalOsun State University

Key Points

The research aims to enhance solar irradiance forecasting using machine learning and wavelet techniques.
Applied continuous wavelet transform (CWT) for feature extraction on solar irradiance data.
Trained seven machine learning models using 70% of the dataset and assessed with 30%.
Evaluated model performance with statistical metrics including MAE, MSE, RMSE, MBE, and R2.
MLP achieved the best predictive accuracy with 12.9494 MAE, 339.81 MSE, and 0.9945 R2.
RF and GBR performed competitively in forecasting accuracy.
kNN exhibited the weakest performance with 32.71 MAE and 45.99 RMSE.

Abstract

Forecasting solar irradiance accurately is critical for optimizing renewable energy systems. In this study CWT was applied to solar irradiance for time frequency features. The CWT features, meteorological data and lag solar irradiance data were used to train seven ML models. The models were trained with 70% and assessed with 30% of the dataset with five statistical metrics. Results showed that MLP consistently achieved the best predictive accuracy with 12.9494 MAE, 339.81 MSE, 18.43 RMSE, -1.86 MBE and 0.9945 R2, while RF and GBR also performed competitively. Also, kNN with 32.71 MAE, 2115 MSE, 45.99 RMSE, -5.03 MBE and 0.97 R2 exhibited the weakest performance. These results show that CWT coefficient statistical features allow model like MLP, RF and GBR to capture irradiance variability more effectively.

AI से पूछें

Bookmark

View Full Paper