An Advanced Short-Term Load Forecasting Framework Based on LSTM and GRU Neural Networks

This dataset supports the research article titled “An Advanced Short-Term Load Forecasting Framework Based on LSTM and GRU Neural Networks”.

The dataset contains processed electrical load time-series data used to develop and evaluate deep learning models, specifically Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) networks, for short-term load forecasting.

The original data were obtained from publicly available sources and have been preprocessed by the authors. Preprocessing steps include data cleaning, normalization, and transformation into a supervised learning format suitable for training neural network models.

The dataset includes input features and corresponding load values used in model training and testing. Additionally, figures illustrating the model structure, forecasting performance, and error comparisons are provided.

This dataset is intended to ensure the reproducibility of the study and to support further research in short-term load forecasting and intelligent energy systems.