Analysing risk orientation in a stochastic VRP

In this paper, the value of correctly addressing uncertainty and risk in operational planning is studied in the context of the Vehicle Routing Problem with Stochastic Demands (VRPSD). The main issues analysed in this paper concern (1) the evaluation of different risk attitudes in planning vehicle routes, (2) the value of considering the uncertainty for planning the vehicle routes (as opposed to dealing with the problem deterministically) in general and (3) the fit between the risk attitudes in performance measurement on the one hand and decision making on the other hand. Using an existing model of the VRPSD these issues are studied employing a heuristic solution approach based on Ant Colony Optimisation (ACO). [Received 20 July 2006; Revised 22 September; Accepted 17 October 2006].