Data-Driven Charging Demand Prediction at Public Charging Stations Using Supervised Machine Learning Regression Methods

Plug-in Electric Vehicle (PEV) user charging behavior has a significant influence on a distribution network and its reliability. Generally, monitoring energy consumption has become one of the most important factors in green and micro grids; therefore, predicting the charging demand of PEVs (the energy consumed during the charging session) could help to efficiently manage the electric grid. Consequently, three machine learning methods are applied in this research to predict the charging demand for the PEV user after a charging session starts. This approach is validated using a dataset consisting of seven years of charging events collected from public charging stations in the state of Nebraska, USA. The results show that the regression method, XGBoost, slightly outperforms the other methods in predicting the charging demand, with an RMSE equal to 6.68 kWh and R 2 equal to 51.9%. The relative importance of input variables is also discussed, showing that the user’s historical average demand has the most predictive value. Accurate prediction of session charging demand, as opposed to the daily or hourly demand of multiple users, has many possible applications for utility companies and charging networks, including scheduling, grid stability, and smart grid integration.

[1]  Bo Chen,et al.  Electric Vehicle–Grid Integration with Voltage Regulation in Radial Distribution Networks , 2020 .

[2]  Jarod C. Kelly,et al.  Time-dependent plug-in hybrid electric vehicle charging based on national driving patterns and demographics , 2012 .

[3]  Mostafa Rafaie,et al.  An IoT Framework for Modeling and Controlling Thermal Comfort in Buildings , 2020, Frontiers in Built Environment.

[4]  Xueliang Huang,et al.  Urban Electric Vehicle Fast-Charging Demand Forecasting Model Based on Data-Driven Approach and Human Decision-Making Behavior , 2020, Energies.

[5]  Zofia Lukszo,et al.  Optimized Scheduling of EV Charging in Solar Parking Lots for Local Peak Reduction under EV Demand Uncertainty , 2020, Energies.

[6]  Hassan Fathabadi,et al.  Plug-In Hybrid Electric Vehicles: Replacing Internal Combustion Engine With Clean and Renewable Energy Based Auxiliary Power Sources , 2018, IEEE Transactions on Power Electronics.

[7]  J. Helmus,et al.  Estimating the Charging Profile of Individual Charge Sessions of Electric Vehicles in The Netherlands , 2018, World Electric Vehicle Journal.

[8]  Fares Al Juheshi,et al.  Analysis of Energy Consumption at Public Charging Stations, a Nebraska Case Study , 2020, 2020 IEEE Transportation Electrification Conference & Expo (ITEC).

[9]  Syed Muhammad Anwar,et al.  A survey on electric vehicle transportation within smart grid system , 2018 .

[10]  Wolf Fichtner,et al.  Generating electric vehicle load profiles from empirical data of three EV fleets in Southwest Germany , 2017 .

[11]  Chitchai Srithapon,et al.  Optimization of Electric Vehicle Charging Scheduling in Urban Village Networks Considering Energy Arbitrage and Distribution Cost , 2020, Energies.

[12]  Johan Jansson,et al.  Advances in consumer electric vehicle adoption research: A review and research agenda , 2015 .

[13]  Mahiraj Singh Rawat,et al.  A Comprehensive Review on Electric Vehicles Operation, Development and Grid Stability , 2018, 2018 International Conference on Power Energy, Environment and Intelligent Control (PEEIC).

[14]  M. Zima-Bočkarjova,et al.  Charging and Discharging Scheduling for Electrical Vehicles Using a Shapley-Value Approach , 2020 .

[15]  Rafael Cardoso,et al.  Electric Vehicles Energy Management with V2G/G2V Multifactor Optimization of Smart Grids , 2020, Energies.

[16]  Sung-Yul Kim,et al.  Selecting Locations of Electric Vehicle Charging Stations Based on the Traffic Load Eliminating Method , 2020, Energies.

[17]  Saifur Rahman,et al.  An investigation into the impact of electric vehicle load on the electric utility distribution system , 1993 .

[18]  Marc Ross,et al.  Evaluation of energy consumption, emissions and cost of plug-in hybrid vehicles , 2009 .

[19]  Bernhard Schölkopf,et al.  A tutorial on support vector regression , 2004, Stat. Comput..

[20]  Tom Molinski,et al.  PEV Charging Profile Prediction and Analysis Based on Vehicle Usage Data , 2012, IEEE Transactions on Smart Grid.

[21]  Daniela Proto,et al.  Predicting Popularity of Electric Vehicle Charging Infrastructure in Urban Context , 2020, IEEE Access.

[22]  Claire Weiller,et al.  Plug-in hybrid electric vehicle impacts on hourly electricity demand in the United States , 2011 .

[23]  Jing Qiu,et al.  Charging Station and Power Network Planning for Integrated Electric Vehicles (EVs) , 2019, Energies.

[24]  Sung Gu Lee,et al.  Assessment and Mitigation of Electric Vehicle Charging Demand Impact to Transformer Aging for an Apartment Complex , 2020 .

[25]  Ayaz Ahmad,et al.  A review of EVs charging: From the perspective of energy optimization, optimization approaches, and charging techniques , 2018, Transportation Research Part D: Transport and Environment.

[26]  Phil Blythe,et al.  A probabilistic approach to combining smart meter and electric vehicle charging data to investigate distribution network impacts , 2015 .

[27]  Xin Zhang,et al.  Intelligent Energy Management Algorithms for EV-charging Scheduling with Consideration of Multiple EV Charging Modes , 2019, Energies.

[28]  Golkar,et al.  Optimal Charging of Plug-In Electric Vehicle: Considering Travel Behavior Uncertainties and Battery Degradation , 2019, Applied Sciences.

[29]  Radoslav S Dimitrov.  The Paris Agreement on Climate Change: Behind Closed Doors , 2016, Global Environmental Politics.

[30]  Jinho Kim,et al.  Electric Vehicle Charging and Discharging Algorithm Based on Reinforcement Learning with Data-Driven Approach in Dynamic Pricing Scheme , 2020, Energies.

[31]  David P. Yuill,et al.  Data-driven fault detection and diagnosis for packaged rooftop units using statistical machine learning classification methods , 2020 .

[32]  Zhile Yang,et al.  A comprehensive study of economic unit commitment of power systems integrating various renewable generations and plug-in electric vehicles , 2017 .

[33]  Khaled Shuaib,et al.  Online scheduling scheme for smart electric vehicle charging infrastructure , 2017, 2017 13th International Wireless Communications and Mobile Computing Conference (IWCMC).

[34]  Jongsu Lee,et al.  Forecasting electricity demand of electric vehicles by analyzing consumers’ charging patterns , 2018 .

[36]  Hee-Sang Ko,et al.  Optimal Operation Strategy of ESS for EV Charging Infrastructure for Voltage Stabilization in a Secondary Feeder of a Distribution System , 2020 .

[37]  Yusheng XUE,et al.  A self-learning TLBO based dynamic economic/environmental dispatch considering multiple plug-in electric vehicle loads , 2014 .

[38]  Islam Safak Bayram,et al.  A General Model for EV Drivers’ Charging Behavior , 2019, IEEE Transactions on Vehicular Technology.

[39]  Jiankang Wang,et al.  An integrated algorithm for evaluating plug-in electric vehicle’s impact on the state of power grid assets , 2019 .

[40]  Marisca Zweistra,et al.  Large Scale Smart Charging of Electric Vehicles in Practice , 2020, Energies.

[41]  Barry G. Rabe,et al.  Beyond Kyoto: Climate Change Policy in Multilevel Governance Systems , 2007 .

[42]  Lixing Chen,et al.  Modeling the Charging Behaviors for Electric Vehicles Based on Ternary Symmetric Kernel Density Estimation , 2020, Energies.

[43]  F. Sprei,et al.  A review of consumer preferences of and interactions with electric vehicle charging infrastructure , 2018, Transportation Research Part D: Transport and Environment.

[44]  Makena Coffman,et al.  Electric vehicles revisited: a review of factors that affect adoption , 2017 .

[45]  Margaret O'Mahony,et al.  Modelling charging profiles of electric vehicles based on real-world electric vehicle charging data , 2016 .

[46]  Wolf Fichtner,et al.  Load shift potential of electric vehicles in Europe , 2014 .

[47]  Saifur Rahman,et al.  Challenges of PHEV penetration to the residential distribution network , 2009, 2009 IEEE Power & Energy Society General Meeting.

[48]  Sadrul Ula,et al.  Impacts of Plug-in Electric Vehicles on a Distribution Level Microgrid , 2019, 2019 North American Power Symposium (NAPS).

[49]  Mehmet Uzunoglu,et al.  A double-layer smart charging strategy of electric vehicles taking routing and charge scheduling into account , 2016 .

[50]  Aoife Foley,et al.  Impacts of Electric Vehicle charging under electricity market operations , 2013 .

[51]  Mohammed Abdel-Hafez,et al.  Secure Plug-in Electric Vehicle (PEV) Charging in a Smart Grid Network , 2017 .

[52]  Alexandre Lucas,et al.  EV Idle Time Estimation on Charging Infrastructure, Comparing Supervised Machine Learning Regressions , 2019, Energies.

[53]  M. Noussan,et al.  Cross-Country Comparison of Hourly Electricity Mixes for EV Charging Profiles , 2020, Energies.

[54]  Deok-Kee Choi,et al.  Data-Driven Materials Modeling with XGBoost Algorithm and Statistical Inference Analysis for Prediction of Fatigue Strength of Steels , 2019, International Journal of Precision Engineering and Manufacturing.

[55]  Caspar G. Chorus,et al.  Fully charged: An empirical study into the factors that influence connection times at EV-charging stations , 2018, Energy Policy.

[56]  Rajit Gadh,et al.  Ensemble machine learning-based algorithm for electric vehicle user behavior prediction , 2019, Applied Energy.

[57]  Zhile Yang,et al.  Computational scheduling methods for integrating plug-in electric vehicles with power systems: A review , 2015 .