In: Proc. IEEE Int. Conf. on Systems, Man, and Cybernetics (SMC'99), 12-15 October 1999, Tokyo, Japan, Vol. 1, pages 829-834. 1999.
Abstract: This paper proposes a method which uses a type of stochastic Petri nets for filtering problems and presents the application of this method to the estimation of traffic queues in urban networks. An extension of probabilistic transition Petri nets, which assigns to each place a distribution of timings, is developed. A firing algorithms is obtained by applying a composition operator on the densities of probability to the distribution of markings. The resulting distribution of markings is used as the initial distribution for the next sampling time. Because of real-time constraints, the net is split in several subnets. The experiments indicate that the proposed filtering is slightly better than the one based on Markov chains. The application of the filtering method to other fields of control in transportation systems is a promising prospect.
Keywords: filtering algorithms, p-timed Petri nets, traffic queue estimation.