*Long short-term memory, *Grey Wolf Optimizer algorithm, *Load forecasting (Electric power systems), *Search algorithms, *Energy consumption, *Renewable energy sources

With the increasing proportion of renewable energy in the power system, short-term electricity load forecasting is crucial for optimizing grid operation and improving energy efficiency. In this paper, we propose a comprehensive model that integrates the Grey Wolf Optimizer (GWO), Variational Mode Decomposition (VMD), Improved Sparrow Search Algorithm (ISSA), and Long Short-Term Memory networks (LSTM) to enhance the precision of short-term electricity load forecasting. Firstly, the raw power load data are preprocessed using the VMD optimized by the GWO algorithm to adaptively decompose them into a collection of different frequency components in order to eliminate the limitations of the traditional methods in dealing with non-smooth signals. Secondly, the ISSA is used to optimize the LSTM parameters to further enhance the generalization ability and prediction accuracy of LSTM. Finally, the optimized LSTM is utilized to forecast each frequency component, resulting in the final forecasted value. The final experimental results indicate that the model outperforms the traditional LSTM and other benchmark models on the actual electricity dataset, indicating that the proposed GWO-VMDISSA-LSTM model has high practical value and potential for generalization. [ABSTRACT FROM AUTHOR]

Copyright of IAENG International Journal of Applied Mathematics is the property of Newswood Limited and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)