Design of a Novel Fractional Whale Optimization-Enhanced Support Vector Regression (FWOA-SVR) Model for Accurate Solar Energy Forecasting DOI Creative Commons
Abdul Wadood, Hani Albalawi, Aadel M. Alatwi

et al.

Fractal and Fractional, Journal Year: 2025, Volume and Issue: 9(1), P. 35 - 35

Published: Jan. 11, 2025

This study presents a novel Fractional Whale Optimization Algorithm-Enhanced Support Vector Regression (FWOA-SVR) framework for solar energy forecasting, addressing the limitations of traditional SVR in modeling complex relationships within data. The proposed incorporates fractional calculus Algorithm (WOA) to improve balance between exploration and exploitation during hyperparameter tuning. FWOA-SVR model is comprehensively evaluated against SVR, Long Short-Term Memory (LSTM), Backpropagation Neural Network (BPNN) models using training, validation, testing datasets. Experimental results show that achieves superior performance with lowest MSE values (0.036311, 0.03942, 0.03825), RMSE (0.19213, 0.19856, 0.19577), highest R2 (0.96392, 0.96104, 0.96192) testing, respectively. These highlight significant improvements prediction accuracy efficiency, surpassing benchmark capturing patterns findings effectiveness integrating optimization techniques into machine learning frameworks advancing forecasting solutions.

Language: Английский

Design of a Novel Fractional Whale Optimization-Enhanced Support Vector Regression (FWOA-SVR) Model for Accurate Solar Energy Forecasting DOI Creative Commons
Abdul Wadood, Hani Albalawi, Aadel M. Alatwi

et al.

Fractal and Fractional, Journal Year: 2025, Volume and Issue: 9(1), P. 35 - 35

Published: Jan. 11, 2025

This study presents a novel Fractional Whale Optimization Algorithm-Enhanced Support Vector Regression (FWOA-SVR) framework for solar energy forecasting, addressing the limitations of traditional SVR in modeling complex relationships within data. The proposed incorporates fractional calculus Algorithm (WOA) to improve balance between exploration and exploitation during hyperparameter tuning. FWOA-SVR model is comprehensively evaluated against SVR, Long Short-Term Memory (LSTM), Backpropagation Neural Network (BPNN) models using training, validation, testing datasets. Experimental results show that achieves superior performance with lowest MSE values (0.036311, 0.03942, 0.03825), RMSE (0.19213, 0.19856, 0.19577), highest R2 (0.96392, 0.96104, 0.96192) testing, respectively. These highlight significant improvements prediction accuracy efficiency, surpassing benchmark capturing patterns findings effectiveness integrating optimization techniques into machine learning frameworks advancing forecasting solutions.

Language: Английский

Citations

0