On Prioritization Mechanisms for Large-Scale 3D Streaming in Distributed Virtual Environments

Abstract

Recently, peer-to-peer (P2P) networking has been proposed to deliver contents efficiently in Distributed Virtual Environments (DVEs) without overloading servers. Due to the nature of the real-time communications in DVEs, peers should carefully select neighbors and content pieces with prioritization in order to achieve the best streaming quality. In this paper, we proposed a prioritization framework for progressively transmitting multimedia contents in P2P-DVEs by taking advantages of the spatial relevance of the scalable multi-layer area-of-interests (SMLAOI). Considering various prioritization schemes at different granularity, we introduce the resource computation into the scene partition and the source selection in the AOI (area-of-interest) layer. Instead of querying objects for downloading randomly, these objects are transmitted progressively with prioritization from the nearest peer to the farthest peer in the AOI area. We have implemented this prioritization framework, called the Scheme of Progressive Transmission (SPT), in a simulated DVE platform for P2P-based 3D streaming applications. We have also conducted a comprehensive simulation study to evaluate the performance of the proposed prioritization algorithms. The experiment results demonstrate that the proposed prioritization algorithms outperform two other algorithms including FLoD and Enhanced-FLoD with smoother streaming performance and less server utilization.