Application of Artificial Neuron Networks as energy consumption forecasting tool in the building of Regulatory Authority of Energy, Athens, Greece

Abstract

The liberation of the Greek electricity market by the law 4426/2015 started a new area for the producers and the consumers of electricity, in order to improve energy efficiency and saving, promotes competitiveness and finally leads to the protection of the environment. The main objective of this work is the development of a forecasting tool with the use of Artificial Neural Networks (ANNs), in order to forecast the energy consumption in the building of Regulation Authority of Energy (RAE) in Athens city, Greece. More specifically, nine different scenarios and artificial neural networks respectively developed and trained in order give a sufficient prediction for the consumption of electricity, the consumption of natural gas during the cold period of the year and finally the chilling loads during the warm period of the year, 24hours ahead in hourly basis. For this purpose, hourly meteorological data from the nearest meteorological station belonging to the National Observatory of Athens as well as energy consumption data from the specific building in hourly bases were used. Results showed that ANNs present a remarkable forecasting ability to predict the energy consumption of the specific building 24hours ahead.