Cooperation of simulation and data model for performance analysis of complex systems

Abstract

Modelling and simulation (M&S) is one of the fundamental methods of performance analysis. In other words, how well a modeller builds a model is a key point of a successful performance analysis. Before such a performance analysis, a model for prediction should be constructed. There are two types of models: data model and simulation model. Data model represents correlational relationships between one set of data and another. Conversely, simulation model represents causal relationships between a set of controlled inputs and corresponding outputs. This paper identifies the characteristics of each modelling method and presents a cooperative model development process for performance analysis of complex systems. The cooperative method contains conceptual modelling, model classification, and model integration/implementation. The model classification method effectively reflects and maximizes the features compared earlier. Then, they are modelled respectively and integrated. This paper also applies the proposed modelling to develop a model of Hadoop using artificial neural network (ANN) and discrete event systems specification (DEVS). To demonstrate the validity of the case study, it presents experiments to show the possibility of a proposed approach.