Software defined network-enabled multicast for multi-party video conferencing systems

Providing well-satisfactory multi-party video conferencing service is remarkably challenging, which demands not only high bandwidth but also low latency. Current commercial implementations typically use one or multiple multipoint control units (MCUs) as the central points for distributing video bit-streams to all participants in the conferencing session. Such MCU-based solution has limited control on quality of service (QoS), which may cause large delay, single-point malfunction and communication bottleneck for entire system. Recent years have witnessed the emergence of a new paradigm in networking, software defined networking (SDN), which advocates separating data plane and control plane, making network switches in the data plane simple packet forwarding devices and leaving a logically centralized controller to manipulate network behaviors. SDN provides the flexibility of changing underlying infrastructure and makes it possible to radically provide service/flow-aware QoS guarantee. In this paper, we propose a novel architecture for multi-party video conferencing by utilizing SDN-enabled multicasting, where SDN controller helps media controller to buildup multicast trees for video flows originated at video parties. To realize the architecture, we correspondingly propose a novel multicast construction and packing method, in which multiple source-based multicast trees are constructed and integrated to maximize system-wide utility while guaranteeing an end-to-end delay bound. Extensive simulations demonstrate that it could provide better video delivery compared to the conventional MCU-based solution in terms of video rate and delay in both sparsely and densely distributed networks.