A Centralized Optimization Solution for Application Layer Multicast Tree
Xinchang Zhang, Lu Wang, Ye Li, Meng Sun · IEEE Transactions on Network and Service Management · 2017
Application layer multicast (ALM) is an effective group communication method. The ALM tree is usually built in a distributed manner because of its good scalability. However, the distributed ALM solution sometimes produces a low performance delivery tree. In this paper, we propose an ALM tree optimization solution, named ALMTO, for multicast applications, in particular, those with a large number of concurrent users. ALMTO manages and optimizes the ALM tree in the following four steps: 1) periodic collection of related structure information, based on a proposed structure report domain model and special tree structure; 2) construction and maintenance of a logical ALM tree, in terms of the collected structure information; 3) central computation of the ALM tree optimization scheme, according to the logical ALM tree and optimization objective corresponding to the specific multicast application; and 4) reshaping of the real ALM tree in terms of the optimization scheme. We analyze the problem of the centralized tree optimization scheme orchestration and present an effective solution that can adapt to the dynamics of group members. We also present two approaches: 1) degree-bounded connection-keeping tree transformation and 2) ring-based data compensation to ensure that the ALM tree can be reliably transformed.