Machine Learning Based Electricity Demand Forecasting

Abstract

In this empirical study we develop forecasting models for electricity demand using publicly available data and three models based on machine learning algorithms. It compares accuracy of these models using different evaluation metrics. The data consist of several measurements and observations related to the electricity market in Turkey from 2011 to 2016. It is available in different time granularities. Our results show that the electricity demand can be forecasted with high accuracy using machine learning algorithms such as linear regression and decision trees and publicly available data.