Guidelines and techniques for comparing system observations with multiple sets of simulation results

Using simulation to support reaching conclusions for real-time processes imposes that models are thoroughly validated. This paper discusses widely adopted techniques for testing the validity of simulation results against real observations and proposes a more effective comparison technique for the case where a single system data set and multiple model data sets are available. To apply this technique, we consider the system data set as a discrete signal and use M-fold decimation, fulfilling the essential requirements Imposed according to signal processing theory. Experimental results are also presented to exhibit the applicability and effectiveness of the proposed technique.