Search Results

In this work, a novel approach is introduced comprising a combination of unsupervised machine learning (ML) scheme and charging energy management of electric vehicles (EV). The main goal of this implementation is to reduce the load peak of charging EV’s, which are regular users of electric vehicle supply equipment (EVSE) of a certain building and, at the same time, to meet their electric and behavioral demands. The unsupervised ML considers certain features within the charging profiles in addition to the behavioral characteristics of the EV based on its intended use. Moreover, these features are extracted from large sets of history measurement data of the EVSE, which are stored in the data bank. The ML categorizes the EVs within certain clusters having defined specifications.

This paper addresses the performance and potential of using electric vehicles in the Gulf Arab states. Based on a survey executed in Salalah, Oman, a representative test driving cycle has been set up. This cycle is the first of its kind for this region, where it is driven with a vehicle provided with special measurement equipment to log important values, e.g. vehicle's speed and position, temperatures and solar irradiance. More than 40 test drives are performed to obtain a representative driver profile. The driving cycle and driver profile are used in a simulation model which is capable of simulating the energy consumption for internal combustion engine or electric motor propulsion systems. The simulation model which contains detailed models for the driver, driving cycle, vehicle components and its dynamics is validated and used to compare the consumed energy for the two different propulsion systems.