Open data based electricity load forecasting

Abstract

[en] Electricity is one of the main engines of modern societies. The agents that are involved in the electricity system of a country need to have the best forecasts possible of electricity load in order to ensure that it is correctly supplied, and also to define their action strategies in the market. In this thesis we will focus on the electricity load forecasting for the daily market of the so called Mercado Ibérico de Electricidad (MIBEL), where most of the energy available is auctioned. We studied the State-of-the-Art of the electricity demand approaches, specially for short-term predictions, since we are making one day-ahead estimations. We extracted data from open sources that were later used for designing and testing different types of models. Based on the performance of the different approaches, we selected a model that efficiently combines both time series forecasting and machine learning, obtaining a precision close to the one provided by the system operator, Red Eléctrica. Finally, we analyzed the relevance of each of the variables involved by using the Shapley values and regularization techniques.