A comparison study of metaheuristic techniques for providing Qos to avatars in DVE systems

Abstract

Network-server architecture has become a de-facto standard for Distributed Virtual Environment (DVE) systems. In these systems, a large set of remote users share a 3D virtual scene. In order to design scalable DVE systems, different approaches have been proposed to maintain the DVE system working under its saturation point, maximizing system throughput. Also, in order to provide quality of service to avatars in a DVE systems, avatars should be assigned to servers taking into account, among other factors, system throughput and system latency. This highly complex problem is called quality of service (QoS) problem in DVE systems. This paper proposes two different approaches for solving the QoS problem, based on modern heuristics (simulated annealing and GRASP). Performance evaluation results show that the proposed strategies are able no only to provide quality of service to avatars in a DVE system, but also to keep the system away from the saturation point. © Springer-Verlag 2004.