Evaluating the Predictability of Future Energy Consumption - Application of Statistical Classification Models to Data from EV Charging Points

Pietro Faes Belgrado, Luboš Buzna, Federica Foiadelli, Michela Longo

2018

Abstract

The overall purpose of our study has been to evaluate the predictability of future energy consumption analysing the electric mobility in the Netherlands. The climate and energy framework, the European energy production and main developments, as well as the European targets and policy objectives to reduce the current CO2 emissions were first assessed. Then, a deeper look was taken at electric mobility and at Electric Vehicles (EVs). The adoption and development of EVs in the European Union and charging infrastructure were taken into account. The Dutch energy production and emissions, as well as, the mobility in the country and its infrastructure were investigated. Previous studies about electric vehicles and charging points have addressed the predictability of future energy consumption in larger areas to only very limited extent, so our research work has concentrated on this gap. A large real-world dataset was used as a basis to create statistical models, in order to study the users’ behaviour within the charging points infrastructure and to evaluate the predictability of future energy consumption of the charging points in selected regions of the Netherlands. Results vary across different regions with the number of charging points, but suggest that statistical models could be useful in the management of energy production to optimize the dispatch of energy sources.

Download


Paper Citation


in Harvard Style

Faes Belgrado P., Buzna L., Foiadelli F. and Longo M. (2018). Evaluating the Predictability of Future Energy Consumption - Application of Statistical Classification Models to Data from EV Charging Points.In - RESIST, ISBN , pages 0-0. DOI: 10.5220/0006815206170625


in Bibtex Style

@conference{resist18,
author={Pietro Faes Belgrado and Luboš Buzna and Federica Foiadelli and Michela Longo},
title={Evaluating the Predictability of Future Energy Consumption - Application of Statistical Classification Models to Data from EV Charging Points},
booktitle={ - RESIST,},
year={2018},
pages={},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006815206170625},
isbn={},
}


in EndNote Style

TY - CONF

JO - - RESIST,
TI - Evaluating the Predictability of Future Energy Consumption - Application of Statistical Classification Models to Data from EV Charging Points
SN -
AU - Faes Belgrado P.
AU - Buzna L.
AU - Foiadelli F.
AU - Longo M.
PY - 2018
SP - 0
EP - 0
DO - 10.5220/0006815206170625