Clustering of Usage Profiles for Electric Vehicle Behaviour Analysis

Abstract

Accurately predicting the behaviour of electric vehicles is going to be imperative for network operators. In order for vehicles to participate in either smart charging schemes or providing grid services, their availability and charge requirements must be forecasted. Their relative novelty means that data concerning electric vehicles is scarce and biased, however we have been collecting data on conventional vehicles for many years. This paper uses cluster analysis of travel survey data from the UK to identify typical conventional vehicle usage profiles. To this end, we determine the feature vector, introduce an appropriate distance metric, and choose a number of clusters. Five clusters are identified, and their suitability for electrification is discussed. A smaller data set of electric vehicles is then used to compare the current electric fleet behaviour with the conventional one.

A Stochastic Model for Uncontrolled Charging of Electric Vehicles Using Cluster Analysis

“…Clustering allows data to be grouped, thereby reducing the dimension to a single parameter. The clustering in this paper extends the method first presented by the authors in [23], by considering types of driving days instead of types of driver. Clustering of vehicle trajectories is a more mature research topic (e.g.…”

Capturing diversity in electric vehicle charging behaviour for network capacity estimation

“…Clustering allows data to be grouped, thereby reducing the dimension to a single parameter -the cluster to which the vehicle belongs. In Crozier et al (2018a) the authors proposed clustering travel survey data to identify different types of vehicle owner. Since the objectives are different, the clustering in this paper differs from this previous work in several respects.…”

Demonstration of Blockchain Based Peer to Peer Energy Trading System with Real-Life Used PHEV and HEMS Charge Control

“…In the context of energy disaggregation, prediction models of energy consumption behaviour is being proposed [34,35]. Also, studies to gain characteristics of EVs through behaviour data clustering have been conducted [36].…”