A Novel Forecasting Algorithm for Electric Vehicle Charging Stations

In this paper, a recently proposed time series forecasting algorithm, Modified Pattern-based Sequence Forecasting (MPSF), is compared with three other algorithms. These algorithms have been applied to predict energy consumption at individual electric vehicle (EV) charging outlets using real world data from the University of California, Los Angeles (UCLA) campus. Two of these algorithms, namely MPSF and k-Nearest Neighbor (kNN), are relatively fast and structurally less complex. The other two, Support Vector Regression (SVR) and Random Forest (RF), are more complex and hence require more time to generate the forecast. Out of these four algorithms, kNN with k=1 turns out to be the fastest, MPSF and SVR were the most accurate with respect to different error measures, and radio frequency (RF) provides us with an importance computing scheme for our input variables. Selecting the appropriate algorithm for an application depends on the tradeoff between accuracy and computational time; however, considering all factors together (two different error measures and algorithm speed), MPSF gives reasonably accurate predictions with much less computations than NN, SVR and RF for the authors application.

• Record URL:
  https://doi.org/10.1109/ICCVE.2014.7297504
• Availability:
  • Find a library where document is available. Order URL: http://ieeexplore.ieee.org/xpl/mostRecentIssue.jsp?punumber=7284675&punumber%3D7284675%26filter%3DAND%28p_IS_Number%3A7297490%29%26pageNumber%3D2%26rowsPerPage%3D100&pageNumber=3&rowsPerPage=100
• Supplemental Notes:
  • Copyright © 2014, IEEE.
• Corporate Authors:

  Institute of Electrical and Electronics Engineers (IEEE)

  3 Park Avenue, 17th Floor
  New York, NY  United States  10016-5997
• Authors:
  • Majidpour, Mostafa
  • Qiu, Charlie
  • Chu, Peter
  • Gadh, Rajit
  • Pota, Hemanshu R
• Conference:
  • 2014 International Conference on Connected Vehicles and Expo (ICCVE)
  • Location: Vienna , Austria
  • Date: 2014-11-3 to 2014-11-7
• Publication Date: 2015

Language

• English

Media Info

• Media Type: Web
• Features: References;
• Pagination: pp 1035-1040
• Monograph Title: 2014 International Conference on Connected Vehicles and Expo (ICCVE)

Subject/Index Terms

• TRT Terms: Algorithms; Electric vehicle charging; Electric vehicles; Energy consumption; Forecasting; Radio frequency; Time series
• Identifier Terms: K-Nearest Neighbor Models
• Uncontrolled Terms: Support vector regression
• Subject Areas: Energy; Highways; Vehicles and Equipment;

Filing Info

• Accession Number: 01615670
• Record Type: Publication
• ISBN: 9781479967308
• Files: TRIS
• Created Date: Oct 31 2016 4:57PM