Comprehensive Comparative Tables of Machine Learning, Deep Learning, and Metaheuristic Approaches for Energy Demand and Load Forecasting

This dataset contains three comprehensive supplementary tables that provide an in-depth comparison of computational approaches used in energy demand and load forecasting research.Table 1 presents a detailed comparison of machine learning and hybrid forecasting models, including information on authors, datasets, methodologies, performance metrics, and key findings.Table 2 focuses on deep learning architectures such as LSTM, CNN-LSTM hybrids, transformer-based models, bidirectional GRU networks, and temporal convolutional networks, highlighting their applications, strengths, limitations, and reported results.Table 3 provides an extended comparison of metaheuristic optimization algorithms applied to neural networks, including Particle Swarm Optimization (PSO), Genetic Algorithm (GA), Grey Wolf Optimizer (GWO), Whale Optimization Algorithm (WOA), and Artificial Bee Colony (ABC).These tables support transparency, reproducibility, and further analysis by offering a structured overview of existing literature. Summarized versions are included in the associated manuscript, while this dataset provides the complete extended versions.