Parameter optimisation for a discrete event simulator

Reactive thermostatistical search (RTS) is used within this paper to optimise parameter settings for discrete event simulation problems; the performance of its implementation within the Witness discrete event simulation package is benchmarked against that of the optimiser used within the ProModel package. RTS is a new technique, based upon simulated annealing, which incorporates elements of tabu search into the SA process, by learning from its experience of the problem domain and modifying its search strategy accordingly.