Short Term Power Demand Prediction Using Stochastic Gradient Boosting

TL;DR

This paper presents a stochastic gradient boosting model for short-term power demand prediction in Sharjah, UAE, demonstrating improved accuracy over existing models used by local authorities.

Contribution

The paper introduces a novel application of stochastic gradient boosting for short-term power demand forecasting in a specific regional context.

Findings

Model outperforms existing SEWA model

Provides accurate short-term demand forecasts

Supports efficient resource allocation

Abstract

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