DECISION SUPPORT FOR VEHICLE DISPATCHING USING GENETIC PROGRAMMING
Vehicle dispatching is aimed at allocating real-time service requests to a fleet of vehicles in movement. This paper models the problem as a multiattribute choice problem, in which different attribute values are associated with each vehicle in order to describe their situation with regard to the current service request. The study uses genetic programming to find a utility function, based on those attribute values, that approximates the decision process of a professional dispatcher. The paper reports the computational results of requests collected from a courier service company and compares the results to those of a backpropagation neural network model.
University of MontrealCenter for Research on Transportation (CRT)/CIRRELT
P.O. Box 6128, Station Centre-ville
Montreal, Quebec Canada H3C 3J7
- Benyahia, I
- Publication Date: 1995
- Pagination: 25 p.
- TRT Terms: Automatic vehicle location; Dispatching; Fleet management; Genetics; Real time control; Service stations
- Old TRIS Terms: Real time operations
- Subject Areas: Highways; Operations and Traffic Management;
- Accession Number: 00720335
- Record Type: Publication
- Files: TRIS
- Created Date: Apr 8 1996 12:00AM