A centralized latency optimization solution for tree-based application layer multicast

Most application layer multicast (ALM) protocols build the delivery tree by the distributed way, which is necessary for large-scale group applications because of its good scalability. However, it is difficult for the distributed way to obtain high performance. To address the above problem, we study a VM-assisted ALM tree optimization solution (called ALMTO). The proposed solution uses cloud virtual machines (VMs) to collect the structure information on the ALM tree, and uses a centralized way to effectively reduce average latency of the ALM tree built by the distribute way.