Traffic Analysis of Avatars in Second Life

James Kinicki and Mark Claypool

In Proceedings of the 18th ACM International Workshop on Network and Operating Systems Support for Digital Audio and Video (NOSSDAV)
Braunschweig, Germany
May 2008

New forms for interaction in virtual worlds, such as Second Life, bring dynamic network traffic because the number of online users can vary greatly from region to region and users can add their own content, such as dynamic objects and custom artwork. While there have been numerous studies on network traffic for multimedia applications and even online games, there has been little effort in understanding the traffic profile for virtual worlds. Earlier work suggests bandwidth used by Second Life varies with the avatar actions and amount of streaming content. Our paper complements this work, first by confirming some earlier results, then by strengthening the network analysis by extending the set of avatar actions studied and by varying the number of objects and avatars interacted with in the virtual world. Our results show that the population and number of objects near an avatar in the virtual world have a dramatic effect on the network characteristics, with dense, crowded areas demanding far more bandwidth than sparse, deserted areas. Similarly, avatar actions that require fast motion, such as walking and flying, use more bandwidth than standing, especially when the former is in a dense area and the latter is in a sparse area. The analysis in this paper can help network planning for access links and core networks as well as provide a base for building synthetic models for simulation.