Advances and Evaluation of Intelligent Techniques in Short-Term Load Forecasting
Asif Ahamed, Nur Ahmed, Jamshaid Iqbal Janjua, Zakir Hossain, Ekramul Hasan, Tahir Abbas
Abstract
In recent years, the stability of power grids has increasingly relied on the precision of short-term load forecasting (STLF). Numerous intelligent techniques have been proposed and refined to address the unique challenges posed by the varying characteristics of power load data, including the algorithm's generalization capabilities and model complexity. This paper provides a comprehensive overview of advancements in STLF over the past five years, focusing on key aspects such as data preprocessing, prediction algorithms, optimization models, and evaluation methodologies. The paper discusses the strengths and limitations of various forecasting models, particularly those based on machine learning and deep learning approaches. By highlighting the applicability and potential of these techniques, the paper aims to guide future research and model selection for effective power load forecasting in smart grid systems.