Enhancing discrete-event simulation with big data analytics: a review

Abstract

This article presents a literature review of the use of the OR technique of discrete-event simulation (DES) in conjunction with the big data analytics (BDA) approaches of data mining, machine learning, data farming, visual analytics, and process mining. The two areas are quite distinct. DES represents a mature OR tool using a graphical interface to produce an industry strength process modelling capability. The review reflects this and covers commercial off-the-shelf DES software used in an organisational setting. On the contrary the analytics techniques considered are in the domain of the data scientist and usually involve coding of algorithms to provide outputs derived from big data. Despite this divergence the review identifies a small but emerging literature of use-cases and from this a framework is derived for a DES development methodology that incorporates the use of these analytics techniques. The review finds scope for two new categories of simulation and analytics use: an enhanced capability for DES from the use of BDA at the main stages of the DES methodology as well as the use of DES in a data farming role to drive BDA techniques.