Short Term Power Demand Prediction Using Stochastic Gradient Boosting

摘要

Power prediction demand is vital in power system and delivery engineeringfields. By efficiently predicting the power demand, we can forecast the totalenergy to be consumed in a certain city or district. Thus, exact resourcesrequired to produce the demand power can be allocated. In this paper, aStochastic Gradient Boosting (aka Treeboost) model is used to predict the shortterm power demand for the Emirate of Sharjah in the United Arab Emirates (UAE).Results show that the proposed model gives promising results in comparison tothe model used by Sharjah Electricity and Water Authority (SEWA).