The use of fuzzy sets for resource allocation in an advance request vehicle brokerage system – a case study

Community transport vehicle brokerage operators match the needs of groups without minibuses with the spare capacity of groups which own minibuses. They take bookings in advance, and allocate vehicles without knowing what the total demand will be for travel at a certain time. An approach has been developed which ranks vehicles according to a sequence number which indicates how ‘difficult to book’ they are, and presents the most difficult to book to the broker first, with the intention of maintaining the maximum flexibility in the system. The concept ‘difficult to book’ is not easy to define exactly. Fuzzy set theory provides a mechanism for dealing with imprecise concepts, and through fuzzy logic for reasoning about such concepts. Fuzzy inferencing systems consist of linguistic variables, fuzzy sets, rules, and methods to combine the sets and produce a final result. Fuzzy logic has been used to provide a means of automating the allocation of sequence numbers to vehicles. Three different approaches to developing the rules for this system have been tested, by simulating bookings, and the one which produced the best results was based on a knowledge acquisition process involving booking staff. This approach resulted in the allocation of the highest number of trips and in leaving the least hours of travel unallocated.