An Adaptive Load Balancing Technique for Distributed Virtual Environment Systems

One of the key issues in the design of scalable and costeffective Distributed Virtual Environment (DVE) systems is the partitioning problem. This problem consists of efficiently assigning clients (3-D avatars) to the servers in the system, and some methods have been already proposed for solving it. However, only one of these methods takes into account the non-linear behavior of DVE servers with the number of avatars they support, and this method uses a load balancing technique of local scope. As a result, it only provides good performance if the movement pattern of avatars is uniform. In this paper, we propose an adaptive load balancing technique of global scope for solving the partitioning problem in DVE systems. The global scope of the proposed technique allows to avoid DVE saturation as long as possible. Evaluation results show that the proposed strategy can improve DVE system performance, regardless of both the movement patterns of avatars and also the initial distribution of avatars in the virtual world.

[1]  Maja Matijasevic,et al.  Application of a multi-user distributed virtual environment framework to mobile robot teleoperation over the Internet , 2002 .

[2]  Randy Chow,et al.  Distributed Operating Systems & Algorithms , 1997 .

[3]  Douglas C. Schmidt,et al.  Measuring the impact of event dispatching and concurrency models on Web server performance over high-speed networks , 1997, GLOBECOM 97. IEEE Global Telecommunications Conference. Conference Record.

[4]  K. Fujita,et al.  An application of distributed virtual environment to foreign language education , 2000, 30th Annual Frontiers in Education Conference. Building on A Century of Progress in Engineering Education. Conference Proceedings (IEEE Cat. No.00CH37135).

[5]  Chris Greenhalgh.  Analysing movement and world transitions in virtual reality tele-conferencing , 1997, ECSCW.

[6]  Rynson W. H. Lau,et al.  A multi-server architecture for distributed virtual walkthrough , 2002, VRST '02.

[7]  Richard C. Waters,et al.  Building Multiuser Interactive Multimedia Environments at MERL , 1995, IEEE Multim..

[8]  José Duato,et al.  On the Characterization of Distributed Virtual Environment Systems , 2003, Euro-Par.

[9]  John C. S. Lui,et al.  An Efficient Partitioning Algorithm for Distributed Virtual Environment Systems , 2002, IEEE Trans. Parallel Distributed Syst..

[10]  Juan M. Orduña,et al.  On the characterization of avatars in Distributed Virtual Worlds , 2003, Eurographics.

[11]  G. G. Stokes.  "J." , 1890, The New Yale Book of Quotations.

[12]  Michael Lewis,et al.  GAME ENGINES IN SCIENTIFIC RESEARCH , 2002 .

[13]  José Manuel Rebordão,et al.  mWorld: A Multiuser 3D Virtual Environment , 1997, IEEE Computer Graphics and Applications.

[14]  Juan M. Orduña,et al.  An ACS-based partitioning method for distributed virtual environment systems , 2003, Proceedings International Parallel and Distributed Processing Symposium.

[15]  D. C. Miller,et al.  SIMNET: the advent of simulator networking , 1995, Proc. IEEE.