TRANSPORTATION SCHEDULING SYSTEM BASED ON EVOLUTION ALGORITHM AND SUPER PARALLEL COMPUTER

The authors have developed a system that creates a well-balanced schedule to minimize traveling time and transportation cost in many industrial fields. In recent years, it has become essential not only to reduce working hours to make a transportation schedule but also to establish efficient logistics. Moreover, it is important to improve a traffic jam that becomes more serious in Japan. To solve these problems, the authors searched for a long time and found such a system called NEUPLANET. This system is based on evolution algorithm, which includes genetic algorithms. Since NEUPLANET has a parallel processing structure, the authors can get a well-balanced schedule quickly by using a super parallel computer. To verify the effects of the system, the authors performed a simulation with actual traffic data. As a result, the following effects could be verified: 1) 14 percent reduction of working hours; 2) 96.6 percent reduction of waiting hours; and 3) 13.7 percent improvement of carrying capacity ratio.

• 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:
  • Hamaguchi, Y
  • Inoue, H
  • Jinguji, T
  • YOSHIDA, H
  • SHIOZAWA, M
• Conference:
  • Steps Forward. Intelligent Transport Systems World Congress
  • Location: Yokohama, Japan
  • Date: 1995-11-9 to 1995-11-11
• Publication Date: 1995-11

Language

• English

Media Info

• Pagination: p. 2027

Subject/Index Terms

• TRT Terms: Algorithms; Costs; Economic efficiency; Intelligent transportation systems; Logistics; Production; Scheduling; Traffic simulation; Transportation; Travel time
• Uncontrolled Terms: Efficiency
• Geographic Terms: Japan
• Old TRIS Terms: Industrial production
• Subject Areas: Operations and Traffic Management; Transportation (General); I71: Traffic Theory;

Filing Info

• Accession Number: 00724447
• Record Type: Publication
• Report/Paper Numbers: Volume 4
• Files: TRIS
• Created Date: Aug 20 1996 12:00AM