Version 1
: Received: 11 June 2024 / Approved: 11 June 2024 / Online: 11 June 2024 (08:52:43 CEST)
How to cite:
Zaini, F. A.; Sulaima, M. F.; Razak, I. A. B. W. A.; Othman, M. L.; Mokhlis, H. A Hybrid Model Based on LSSVM and the Improved BFOA for Sustainability of Daily Electricity Load Forecasting in Malaysia. Preprints2024, 2024060693. https://doi.org/10.20944/preprints202406.0693.v1
Zaini, F. A.; Sulaima, M. F.; Razak, I. A. B. W. A.; Othman, M. L.; Mokhlis, H. A Hybrid Model Based on LSSVM and the Improved BFOA for Sustainability of Daily Electricity Load Forecasting in Malaysia. Preprints 2024, 2024060693. https://doi.org/10.20944/preprints202406.0693.v1
Zaini, F. A.; Sulaima, M. F.; Razak, I. A. B. W. A.; Othman, M. L.; Mokhlis, H. A Hybrid Model Based on LSSVM and the Improved BFOA for Sustainability of Daily Electricity Load Forecasting in Malaysia. Preprints2024, 2024060693. https://doi.org/10.20944/preprints202406.0693.v1
APA Style
Zaini, F. A., Sulaima, M. F., Razak, I. A. B. W. A., Othman, M. L., & Mokhlis, H. (2024). A Hybrid Model Based on LSSVM and the Improved BFOA for Sustainability of Daily Electricity Load Forecasting in Malaysia. Preprints. https://doi.org/10.20944/preprints202406.0693.v1
Chicago/Turabian Style
Zaini, F. A., Mohammad Lutfi Othman and Hazlie Mokhlis. 2024 "A Hybrid Model Based on LSSVM and the Improved BFOA for Sustainability of Daily Electricity Load Forecasting in Malaysia" Preprints. https://doi.org/10.20944/preprints202406.0693.v1
Abstract
: Leveraging the sustainability of the power system market, researchers have developed various ML models for forecasting electricity demand. The LSSVM is well suited to handle complex non-linear power load series. However, the less optimal regularization parameter and the Gaussian kernel function in the LSSVM model have contributed to flawed forecasting accuracy and random generalization ability. Thus, these parameters of LSSVM need to be chosen appropriately using intelligent optimization algorithms. This study proposes a hybrid model based on the LSSVM optimized by the IBFOA for forecasting the daily electricity load in Peninsular Malaysia. The IBFOA for parameter optimization of LSSVM is introduced. The IBFOA based on the sine cosine equation is proposed to adjust the constant step size in the BFOA, which creates an imbalance between the exploration and exploitation during optimization. Finally, the load forecasting model based on LSSVM-IBFOA is constructed using MAPE as the objective function. Comparative analysis demonstrates the model, achieving the highest R2 (0.9880) and significantly reducing error metrics (MAPE, MAE, RMSE, MSE, NRMSE) compared to the baseline LSSVM (average reduction of 27.72% to 47.72%). Additionally, IBFOA exhibits faster convergence and higher accuracy compared to BFOA, highlighting the accuracy of LSSVM-IBFOA for short-term load forecasting.
Keywords
Electricity load forecasting; Least square support vector machine (LSSVM); Improved Bacterial foraging optimization algorithm (IBFOA); hybrid model; machine learning (ML)
Subject
Engineering, Electrical and Electronic Engineering
Copyright:
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
,
*
