Enhancing Short-Term Load Forecasting With a CNN-GRU Hybrid Model: A Comparative Analysis

Short-term load forecasting (STLF) is crucial in optimizing the economic efficiency and operational stability of power systems. Traditional energy forecasting models often exhibit limitations in capturing complex temporal dependencies and multi-scale features, restricting their effectiveness in identifying global and local patterns within time-series data. A more advanced forecasting method is required to leverage integrated multi-scale feature extraction and sophisticated temporal modeling techniques to improve scalability and predictive accuracy in energy load forecasting. This paper proposes a novel hybrid model of Convolutional Neural Networks and Gated Recurrent Units (CNN-GRU) model for improved electric energy forecasting, integrating multi-scale Conv1D layers to extract spatiotemporal features at different scales and GRU layers to model temporal dependencies. Therefore, this approach is useful in modeling both local and global patterns and can be considered a good solution to the problem of time series analysis in energy forecasting. APE and ISONE publicly available datasets are used to conduct a thorough analysis to evaluate the effectiveness of the proposed model. Proposed model findings show consistency across all key matrices in comparison with other models, achieving the lowest Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), and Mean Absolute Percentage Error (MAPE) values in both single-step and multi-step. With the AEP dataset, the model produced single-step forecasting results of MAE of 77.39, RMSE of 131.91, and MAPE of 0.67, and multi-step forecasting results of MAE of 486.17, RMSE of 686.32, and MAPE of 3.24. Using the ISONE dataset, the model achieved a single-step forecasting RMSE of 184.29, a multi-step forecasting RMSE of 588.03, a multi-step forecasting MAE of 297.94, and a MAPE of 0.52. This demonstrates the superior accuracy and robustness of the proposed model across different prediction horizons.