Comparative Study of Ensemble Learning Models for Smart Meter Load

Load Forecasting plays a crucial role in the operation and management, such as demand response, energy management and resource optimization in the smart grid. Ensemble learning-based load forecasting techniques can significantly improve the accuracy and robustness of load prediction models, which combine the predictions from multiple individual models to create a more accurate and reliable prediction. In this paper, four ensemble learning-based load forecasting models are discussed. Experiments are performed on the Open Energy Data Initiative dataset, which shows that the Extended Gradient Boosting Regressor model has superiority in terms of mean square error.