Electric Vehicle Charging Sessions Generator Based on Clustered Driver Behaviors^{ †}
Abstract
:1. Introduction
1.1. Literature Review
1.2. Research Gap and Contributions
 The input dataset of the methodology originates from a standard communication protocol widely available in the interoperability of charging infrastructures. The standard communication protocol allows for applying the methodology on many different and specific use cases (office buildings, shops, houses, etc) and can help to investigate/design different use cases;
 The classification of EV driver’s profiles with similar charging behaviors in order to improve the modeling and simulation results. The classification is performed using a clustering technique. In addition, the Kernel Density Estimation process is used to better capture details of each cluster as well as particular charging behaviors;
 The modularity of the generator, its easeofuse and the standardized output data format are key attributes of its scalability and replicability.
1.3. Structure of Paper
2. Materials and Methods
2.1. Data PreProcessing
2.1.1. Dataset and Features
2.1.2. Data Cleaning
2.2. Clustering Technique
Data Normalization
2.3. Generator Principle
2.3.1. Statistical Distributions
 The probability of having a certain number of charging sessions per day. It has been decided to divide this probability into two probability distributions, mainly one for the working days and one for the weekend days, since the number of sessions are highly different;
 The probability of having an EV plugin and plugout at a certain time;
 The probability of having a certain amount of energy to charge.
2.3.2. Pseudo Algorithm
 Step (1) For each cluster, and for each day to simulate, a function (called f1) determines the number of charging sessions to generate;
 Step (2) For each charging session to generate, two functions (called f2 and f3) determine the plugin and plugout time, and the energy to charge.
Algorithm 1 EV charging session generator 

2.4. Validation Criteria
3. Results and Discussion
3.1. Use Case
3.2. Clustering Results
3.3. Generator Results
3.3.1. Validation
3.3.2. The Impact of Clustering and Kernel Density Distribution
3.3.3. The Evolution in Charging Behavior
3.4. Simulation Results
3.4.1. Scenario Construction
3.4.2. Uncoordinated vs. Smart Charging
4. Conclusions
Author Contributions
Funding
Data Availability Statement
Conflicts of Interest
Abbreviations
APS  Announced Pledges Scenario 
BEV  Battery Electric Vehicle 
CPO  Charge Point Operator 
CDR  Charge Detail Record 
DSO  Distribution System Operator 
EV  Electric Vehicle 
IEA  International Energy Agency 
LES  Local Energy System 
OCPP  Open Charge Point Protocol 
PHEV  Plugin Hybrid Electric Vehicle 
RAMP  RemoteAreas Multienergy systems load Profiles 
RFID  Radio Frequency Identification 
TSO  Transmission System Operator 
References
 European Parliament. 2021/0197(COD)CO2 Emission Standards for Cars and Vans. 2022. Available online: https://oeil.secure.europarl.europa.eu/oeil/popups/ficheprocedure.do?reference=2021/0197(COD)=en (accessed on 1 February 2023).
 International Energy Agency (IEA). Global EV Outlook 2022; IEA: Paris, France, 2022; pp. 98–100. [Google Scholar]
 Firouzjah, K.G. Profitbased electric vehicle charging scheduling: Comparison with different strategies and impact assessment on distribution networks. Int. J. Electr. Power Energy Syst. 2022, 138, 107977. [Google Scholar] [CrossRef]
 Mangipinto, A.; Lombardi, F.; Sanvito, F.D.; Pavičević, M.; Quoilin, S.; Colombo, E. Impact of massscale deployment of electric vehicles and benefits of smart charging across all European countries. Appl. Energy 2022, 312, 118676. [Google Scholar] [CrossRef]
 Dubey, A.; Santoso, S. Electric Vehicle Charging on Residential Distribution Systems: Impacts and Mitigations. IEEE Access 2015, 3, 1871–1893. [Google Scholar] [CrossRef]
 Van Kriekinge, G.; De Cauwer, C.; Sapountzoglou, N.; Coosemans, T.; Messagie, M. Peak shaving and cost minimization using model predictive control for uni and bidirectional charging of electric vehicles. Energy Rep. 2021, 7, 8760–8771. [Google Scholar] [CrossRef]
 Fischer, D.; Harbrecht, A.; Surmann, A.; McKenna, R. Electric vehicles’ impacts on residential electric local profiles – A stochastic modelling approach considering socioeconomic, behavioural and spatial factors. Appl. Energy 2019, 233–234, 644–658. [Google Scholar] [CrossRef]
 Muratori, M. Impact of uncoordinated plugin electric vehicle charging on residential power demand. Nat. Energy 2018, 3, 193–201. [Google Scholar] [CrossRef]
 Iversen, E.B.; Morales, J.M.; Madsen, H. Optimal charging of an electric vehicle using a Markov decision process. Appl. Energy 2014, 123, 1–12. [Google Scholar] [CrossRef]
 Gruosso, G.; Gaiani, G.S. A Model of Electric Vehicle Recharge Stations based on Cyclic Markov Chains. In Proceedings of the IECON 201945th Annual Conference of the IEEE Industrial Electronics Society, Lisbon, Portugal, 14–17 October 2019; Volume 1, pp. 2586–2591. [Google Scholar] [CrossRef]
 GaeteMorales, C.; Kramer, H.; Schill, W.P.; Zerrahn, A. An open tool for creating batteryelectric vehicle time series from empirical data, emobpy. Sci. Data 2021, 8, 1–18. [Google Scholar] [CrossRef] [PubMed]
 Lombardi, F.; Balderrama, S.; Quoilin, S.; Colombo, E. Generating highresolution multienergy load profiles for remote areas with an opensource stochastic model. Energy 2019, 177, 433–444. [Google Scholar] [CrossRef]
 Jiang, R.; Zhang, Z.; Li, J.; Zhang, Y.; Huang, Q. A coordinated charging strategy for electric vehicles based on multiobjective optimization. In Proceedings of the 2017 2nd International Conference on Power and Renewable Energy, ICPRE, Chengdu, China, 20–23 September 2017; pp. 823–827. [Google Scholar] [CrossRef]
 Schäuble, J.; Kaschub, T.; Ensslen, A.; Jochem, P.; Fichtner, W. Generating electric vehicle load profiles from empirical data of three EV fleets in Southwest Germany. J. Clean. Prod. 2017, 150, 253–266. [Google Scholar] [CrossRef]
 Brady, J.; O’Mahony, M. Modelling charging profiles of electric vehicles based on realworld electric vehicle charging data. Sustain. Cities Soc. 2016, 26, 203–216. [Google Scholar] [CrossRef]
 Lahariya, M.; Benoit, D.F.; Develder, C. Synthetic Data Generator for Electric Vehicle Charging Sessions: Modeling and Evaluation Using RealWorld Data. Energies 2020, 13, 4211. [Google Scholar] [CrossRef]
 Harris, C.B.; Webber, M.E. An empiricallyvalidated methodology to simulate electricity demand for electric vehicle charging. Appl. Energy 2014, 126, 172–181. [Google Scholar] [CrossRef]
 Open Charge AllainceOCPP2.0. 2022. Available online: https://www.openchargealliance.org/protocols/ocpp20/ (accessed on 1 February 2023).
 Aggarwal, C.C. Data Mining; Springer International Publishing: Cham, Switzerland, 2015; Volume 1, pp. 162–163. [Google Scholar] [CrossRef]
 Wang, Y.; Cai, S.; Shen, Y.; Shao, D.; Gong, X.; Zhou, C.; Chu, D. The analysis of electrical vehicles charging behavior based on charging big data. In Proceedings of the 2019 IEEE 4th International Conference on Cloud Computing and Big Data Analytics, ICCCBDA, Chengdu, China, 12–15 April 2019; Volume 1, pp. 63–67. [Google Scholar] [CrossRef]
 Crozier, C.; Apostolopoulou, D.; McCulloch, M. Clustering of Usage Profiles for Electric Vehicle Behaviour Analysis. In Proceedings of the Proceedings2018 IEEE PES Innovative Smart Grid Technologies Conference Europe, ISGTEurope, Sarajevo, Bosnia and Herzegovina, 21–25 October 2018; Volume 1, pp. 1–6. [Google Scholar] [CrossRef]
 Xydas, E.; Marmaras, C.; Cipcigan, L.M.; Jenkins, N.; Carroll, S.; Barker, M. A datadriven approach for characterising the charging demand of electric vehicles: A UK case study. Appl. Energy 2016, 162, 763–771. [Google Scholar] [CrossRef]
 Xiong, Y.; Wang, B.; Chu, C.C.; Gadh, R. Electric Vehicle Driver Clustering using Statistical Model and Machine Learning. In Proceedings of the IEEE Power and Energy Society General Meeting, Portland, OR, USA, 5–10 August 2018; Volume 2018. [Google Scholar] [CrossRef] [Green Version]
 Pedregosa, F.; Varoquaux, G.; Gramfort, A.; Michel, V.; Thirion, B.; Grisel, O.; Blondel, M.; Prettenhofer, P.; Weiss, R.; Dubourg, V.; et al. Scikitlearn: Machine learning in Python. J. Mach. Learn. Res. 2011, 12, 2825–2830. [Google Scholar]
 Pele, O.; Werman, M. The QuadraticChi Histogram Distance Family. In Lecture Notes in Computer Science, Proceedings of the Computer Vision—ECCV 2010, Crete, Greece, 5–11 September 2010; Daniilidis, K., Maragos, P., Paragios, N., Eds.; Springer: Berlin/Heidelberg, Germany, 2010; Volume 6312, pp. 749–762. [Google Scholar] [CrossRef]
 Virtanen, P.; Gommers, R.; Oliphant, T.E.; Haberland, M.; Reddy, T.; Cournapeau, D.; Burovski, E.; Peterson, P.; Weckesser, W.; Bright, J.; et al. SciPy 1.0: Fundamental Algorithms for Scientific Computing in Python. Nat. Methods 2020, 17, 261–272. [Google Scholar] [CrossRef] [Green Version]
Topic  Classification  Papers 

Survey  [4,7,17]  
Input data  Limited empirical data  [9,13,16] & [This paper] 
Abundant empirical data  [8,10,11,14,15]  
Residential  [7,8,9,15]  
Use cases  Local energy system (e.g., office building)  [10,14] & [This paper] 
Largescale use cases (e.g., country level)  [4,11,13,16,17]  
Consequential probabilities  [7,8,9,10,16]  
Method  Nonconsequential probabilities  [4,11,13,14,15,17] & [This paper] 
Cluster ID  # of Sessions  # of Drivers  PlugIn Time (Mean Value)  Parking Time (Mean Value)  Energy (Mean [kWh])  SubClusters 

Cluster 0  1088  104  Morning (09h26)  Mid (04h15)  Low (7.22)  2 
Cluster 1  826  139  Afternoon (15h51)  Mid (05h52)  Low (9.31)  2 
Cluster 2  521  39  Morning (09h42)  Long (07h03)  High (40.4)  2 
Cluster 3  2  1  Afternoon (16h45)  Very long (38h48)  Low (5.07)  N.A. 
Cluster 4  6618  69  Morning (08h15)  Long (08h58)  Mid (7.9)  3 
Scenario ID  Description  PlugIn Time  Parking Time  Energy Needs 

1  Gaussian distribution without clustering  491.8  135.7  261.3 
2  Gaussian distribution with clustering  379.1  167.7  136.7 
3  Kernel distribution without clustering  123.9  48.9  221.4 
4  Kernel distribution with clustering  103.7  37.9  181.5 
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. 
© 2023 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Van Kriekinge, G.; De Cauwer, C.; Sapountzoglou, N.; Coosemans, T.; Messagie, M. Electric Vehicle Charging Sessions Generator Based on Clustered Driver Behaviors. World Electr. Veh. J. 2023, 14, 37. https://doi.org/10.3390/wevj14020037
Van Kriekinge G, De Cauwer C, Sapountzoglou N, Coosemans T, Messagie M. Electric Vehicle Charging Sessions Generator Based on Clustered Driver Behaviors. World Electric Vehicle Journal. 2023; 14(2):37. https://doi.org/10.3390/wevj14020037
Chicago/Turabian StyleVan Kriekinge, Gilles, Cedric De Cauwer, Nikolaos Sapountzoglou, Thierry Coosemans, and Maarten Messagie. 2023. "Electric Vehicle Charging Sessions Generator Based on Clustered Driver Behaviors" World Electric Vehicle Journal 14, no. 2: 37. https://doi.org/10.3390/wevj14020037