A Deterministic Multivariate Clustering Method for Drive Cycle Generation from In-Use Vehicle Data

Eric Miller, Adam Duran

Research output: Contribution to conferencePaperpeer-review

1 Scopus Citations


Accurately characterizing vehicle drive cycles plays a fundamental role in assessing the performance of new vehicle technologies. Repeatable, short duration representative drive cycles facilitate more informed decision making, resulting in improved test procedures and more successful vehicle designs. With continued growth in the deployment of onboard telematics systems employing global positioning systems (GPS), large scale, low cost collection of real-world vehicle drive cycle data has become a reality. As a result of these technological advances, researchers, designers, and engineers are no longer constrained by lack of operating data when developing and optimizing technology, but rather by resources available for testing and simulation. Experimental testing is expensive and time consuming, therefore the need exists for a fast and accurate means of generating representative cycles from large volumes of real-world driving data. This paper explores the development and initial validation of a method of generating representative drive cycles from large collections of real-world vehicle data using a deterministic multivariate clustering approach. Starting with theory and diving into the methodology behind representative cycle generation, the paper aims to also present graphical and tabular results of initial validation via vehicle simulation and chassis dynamometer testing. Additional topics for further research and areas for ongoing development will also be presented.

Original languageAmerican English
Number of pages7
StatePublished - 2021
EventSAE 2021 WCX Digital Summit - Virtual, Online, United States
Duration: 13 Apr 202115 Apr 2021


ConferenceSAE 2021 WCX Digital Summit
Country/TerritoryUnited States
CityVirtual, Online

Bibliographical note

Publisher Copyright:
© 2021 SAE International. All rights reserved.

NREL Publication Number

  • NREL/CP-5400-78647

Other Report Number

  • SAE Technical Paper No. 2021-01-0395


  • drive cycle
  • duty cycle
  • dynamometer testing


Dive into the research topics of 'A Deterministic Multivariate Clustering Method for Drive Cycle Generation from In-Use Vehicle Data'. Together they form a unique fingerprint.

Cite this