The parallelization of a highway traffic flow simulation

Abstract

This work implements and analyses a highway traffic flow simulation based on continuum modeling of traffic dynamics. A traffic-flow simulation was developed and mapped onto a parallel computer architecture. Two algorithms (the I-step and 2-step algorithms) to solve the simulation equations were developed and implemented. They were then tested on a Cray T3E, a 3-D toroidal mesh with very fast inter-processor communication (IPC) times. Tests with real traffic data collected from the freeway network in the metropolitan area of Minneapolis, MN were used to validate the accuracy and computation rate of the parallel simulation system. The execution time for a 24-hour traffic-flow simulation over a 15.5-mile freeway, which takes 65.7 minutes on a typical single processor computer, took only 2.39 seconds on the Cray T3E. The 2-step algorithm, whose goal is to trade off extra computation for fewer IPC's, was shown to save move than 5% on computation time. This parallel implementation has proven potential for real-time traffic engineering applications.

Original document

The different versions of the original document can be found in:

• http://www.cs.utsa.edu/faculty/atc/pub/C7.pdf

• http://www.cs.utsa.edu/faculty/atc/pub/C7.pdf,

https://dl.acm.org/citation.cfm?id=795668.796740,

https://ieeexplore.ieee.org/document/750600,

https://academic.microsoft.com/#/detail/2106675492

• http://xplorestaging.ieee.org/ielx4/6062/16195/00750600.pdf?arnumber=750600,

http://dx.doi.org/10.1109/fmpc.1999.750600