Data assimilation in discrete event simulations - A rollback based sequential Monte Carlo approach

Abstract

Data assimilation is an analysis technique which aims to incorporate measured observations into a dynamic system model in order to produce accurate estimates of the current state variables of the system. Although data assimilation is conventionally applied in continuous system models, it is also a desired ability for its discrete event counterpart. However, data assimilation has not been well studied in discrete event simulations yet. This paper researches data assimilation problems in discrete event simulations, and proposes a rollback based implementation of the Sequential Monte Carlo (SMC) method - the rollback based SMC method. To evaluate the accuracy of the proposed method, an identical-twin experiment in a discrete event traffic case is carried out and the results are presented and analyzed.