A hybrid method using Exponential Smoothing and Gradient Boosting for electrical short-term load forecasting

摘要

Accurate load forecasts are required in most tasks of energy planning. In this paper we present a hybrid method for short-term load forecasting. We combined Exponential Smoothing, a classical method for time series forecasting, with Gradient Boosting, a powerful machine learning algorithm. The proposed model was tested with real data and the results showed a considerable improvement in forecasting accuracy.