Summary: An Evaluation of Grouping Techniques for State Dissemination
in Networked Multi­User Games \Lambda
Li Zou , Mostafa H. Ammar Christophe Diot
Networking and Telecommunications Group Sprint ATL
College of Computing 1 Adrian Court
Georgia Institute of Technology Burlingame, CA 94010
Atlanta, GA 30332 cdiot@sprintlabs.com
fzou,ammarg@cc.gatech.edu
Abstract
In a distributed multi­user game, entities need to communicate their state information
to other entities. Usually only a subset of the game's entities are interested in information
being disseminated by any particular entity. In a large scale distributed game with many
machines interconnected by a wide­area network, broadcasting messages containing each
information to all participants and applying a relevance filter at the end host is wasteful
in both network resources and processing resources. We consider techniques that address
this problem by dividing the entities into groups and using multicast communication to
disseminate information to the groups which would be interested in such information. We
investigate two grouping strategies: cell­based grouping and entity­based grouping. Our goal
is to understand the tradeoffs between grouping overhead and communication overhead
and compare the cost of both strategies under various conditions. To achieve this, we first

Source: Ammar, Mostafa - College of Computing, Georgia Institute of Technology

Collections: Computer Technologies and Information Sciences