TRAFFIC SIGNAL CONTROL SYSTEM BASED ON GENETIC ALGORITHM

The authors introduce a system to optimize traffic signal parameters (cycle, split, offset) with wide area distribution. Traffic signals are generally controlled with fixed-time schedules. It is difficult to determine optimal parameter value of signals, though, because of traffic condition change uncertainty and a limited ability of current computer by conventional theories. To solve these problems, a new traffic signal control method based on genetic algorithm and super parallel computer is developed. The new system: 1) solves an explosion of traffic signals control plan combination by genetic algorithm and 2) makes the algorithm run on a super parallel computer, realizing an on-line, real-time traffic control system. To verify quantitative effects of the system, a simulation with virtual data was performed. Results indicate a 10 percent or more reduction in traffic congestion as compared to convvetional methods. Details of the simulation are provided.

  • Supplemental Notes:
    • Five volumes of papers and one volume of abstracts comprise the published set of conference materials.
  • Corporate Authors:

    VERTIS

    TORANOMOM 34 MORI BUILDING 1-25-5
    TORANOMON, MINATOKU, TOKYO 105  Japan 
  • Authors:
    • Sano, Y
    • SHIOZAWA, M
    • Nakamura, K
    • Inoue, H
    • Yokota, T
    • Inoue, T
  • Conference:
  • Publication Date: 1995-11

Language

  • English

Media Info

  • Pagination: p. 36

Subject/Index Terms

Filing Info

  • Accession Number: 00716536
  • Record Type: Publication
  • Report/Paper Numbers: Volume 1
  • Files: TRIS
  • Created Date: Feb 27 1996 12:00AM