Distributed simulation framework based on load balanced implementation of standard clock algorithm with web based extensions

Abstract

Standard Clock approach is used to simulate a number of parametric variants of a single system. In this thesis, a simulation engine based on the distributed implementation of the Standard Clock approach on networks of heterogeneous UNIX workstations is developed. The objective is to examine the scalability of the implementation and study the effect of load balancing. Two different heuristic load balancing techniques are proposed: (1) a static load balancing that is based on estimated cost of each variant and (2) a dynamic load balancing that migrates variants between workstations, based on their estimated performance during the simulation process. Simple queueing models are used to study the performance. Numerical results obtained from real-time simulations on a network of up to 7 workstations are used to investigate the speedup and the efficiency of both the implementation and the load balancing techniques. As more workstations are added to the simulation environment, a sublinear speedup is obtained. In addition, the load balanced distribution has produced an improvement up to 8 per cent compared to random distribution. Secondly, a web based user interface is integrated to this engine to provide an easy to use and practical experimentation platform. The complete system mainly consists of a web based graphical user interface that communicates with a powerful server that runs the engine. The user interface allows creating simulation models of queueing network, performing simulation experiments using the simulation engine, and performing simple output analysis in a platform independent manner. Finally, a prototype for a web based simulation optimization tool is developed by extending the system with the power of experimental design methodology and response surface method. Hence, this tool provides a way of planning which variants to simulate in order to quickly reach the neighbor of the optimal solution. The applicability of this simulation optimization approach and the features of the interface are illustrated using a two-node Jackson network and a manufacturing system as examples.