CNN-XGBoost Based Ensemble Model for Short-Term Load Forecasting

Precise short-term load forecasting is crucial in the electric power industry, which serves a vital purpose in maintaining a balance between demand and supply. Maintaining this equilibrium is essential for ensuring the stability and efficiency of power systems. This forecasting task, however, poses significant challenges due to its inherent complexity. This paper presents a new approach for short-term load forecasting through the combination of convolutional neural networks (CNN) and extreme gradient boosting (XGBoost) algorithms. The model incorporates the feature extraction skills of CNN with the sequential learning strength of XGBoost. Both the techniques are ensembled with gradient boosting, which functions as a meta-learner. Gradient boosting combines the individual predictions done by the CNN and XGBoost and enhances the accuracy. The research used the daily load consumption data of Queensland, Australia. This proposed ensemble method is evaluated on the dataset and compared with other forecasting techniques. The outcomes indicated that the suggested ensemble model surpasses the existing forecasting algorithms in terms of various evaluation metrics.