On a dynamic caching method for field segmented DVE by multi-server

Authors:
Syun-nosuke Yamakawa;Tatsuhiro Yonekura
Affiliations:
Ibaraki University, Hitachi-shi, Japan;Ibaraki University, Hitachi-shi, Japan
Venue:
NetGames '06 Proceedings of 5th ACM SIGCOMM workshop on Network and system support for games
Year:
2006

Citing 4
Cited 0

Effective remote modeling in large-scale distributed simulation and visualization environments

Effective remote modeling in large-scale distributed simulation and visualization environments
XCAST6: eXplicit Multicast on IPv6

SAINT-W '03 Proceedings of the 2003 Symposium on Applications and the Internet Workshops (SAINT'03 Workshops)
VELVET: an adaptive hybrid architecture for very large virtual environments

Presence: Teleoperators and Virtual Environments
A scalable dynamic load distribution scheme for multi-server distributed virtual environment systems with highly-skewed user distribution

Proceedings of the ACM symposium on Virtual reality software and technology

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, we propose a concrete strategy to decrease the divergence of the network traffic in a DVE (distributed virtual environment) and we propose an implementation scheme of a dispersed multi-server type of DVE. Recently, research of the large-scale DVE to support a large number of users is improving. There are many types of DVE model, for example. Server-Client model, multi-server model and P2P (Peer to Peer) model. However, there is a problem of the concentration of the traffic load around the server. And the efficient way against the increasing traffics and the method for effective use for constructing the DVE have been less studied. Our goal is to design a DVE model for the decline of the traffic without sacrificing the smoothness of the operation in the dispersed multi-server type DVE. The DVE is constructed by a large number of small-scale servers that is decentralized management using Xcast (eXplicit multicast) for the communication among the nodes. As an evaluation of the proposed model, we demonstrate the "Maze game" for experimentation effective.