Study on multi-depots vehicle scheduling problem and its two-phase particle swarm optimization

  • Authors:

  • Suxin Wang;Leizhen Wang;Huilin Yuan;Meng Ge;Ben Niu;Weihong Pang;Yuchuan Liu

  • Affiliations:

  • Northeastern University at Qinhuangdao, Qinhuangdao, Hebei, China;Northeastern University at Qinhuangdao, Qinhuangdao, Hebei, China;Northeastern University at Qinhuangdao, Qinhuangdao, Hebei, China;Northeastern University at Qinhuangdao, Qinhuangdao, Hebei, China;College of Management, Shenzhen University, Shenzhen, China;Northeastern University at Qinhuangdao, Qinhuangdao, Hebei, China;Northeastern University at Qinhuangdao, Qinhuangdao, Hebei, China

  • Venue:
  • ICIC'09 Proceedings of the Intelligent computing 5th international conference on Emerging intelligent computing technology and applications
  • Year:
  • 2009

Quantified Score

Hi-index 0.00

Visualization

Abstract

To get global solution in multi-depots vehicle scheduling problem (MDVSP), MDVSP models are established. Two-phase particle swarm optimization (TPPSO) is established to solve MDVSP. The optimization course are as follow: first phase, set up goods number dimension particle position vector, vector's every column corresponds to goods, vector elements are random vehicle serial number, thus we can assign goods to vehicles. Second phase, particle position matrix is set up, matrix's column number equal to vehicle freight goods number, every column corresponds to a goods, and matrix has two row, the first row correspond to goods start depot, second row correspond to end depot, matrix elements are random number between 0 and 1, matrix elements are sort ascending according to sort rules, we can get single vehicle route. Then evaluate and filtrate particles by optimization aim, circulate until meet terminate qualification. TPPSO can assign all freights to all vehicles and easy to get optimized solution.