Application level any-source multi-cast method satisfying capacity constraint and QoS constraint

Abstract

The invention relates to an application level any-source multi-cast method satisfying capacity constraint and QoS constraint, which is established on the basis of a random overlay network and a non-DHT (distributed hash table) ring, meets distributed application requirement such as capacity constraint, dynamic membership and the like, has the characteristic of complete distribution, and can be extended within the range of Internet. The method does not need extra maintenance, so that the method is suitable for multi-cast application with a plurality of potential data sources; the method has better hop complexity and communication complexity, and high multi-cast coverage rate of nodes; the method has node capacity constraint performance, and has the performance of satisfying dynamic QoS constraint; and the method has a simple structure and easy realization.

Description

technical field [0001] The invention relates to a computer network technology, in particular to an overlay network multicast method. Background technique [0002] Multicast technology is a group communication model for multipoint transmission and multiparty cooperative applications. Compared with unicast communication, it can save a lot of network communication resources, improve communication efficiency, and provide an effective way for multi-point concurrent transmission of data. In the early days, people devoted themselves to the research of IP multicast, but due to various reasons, IP multicast technology has not been widely used. Therefore, people put forward the concept of overlay multicast, hoping to provide multicast services directly at the application layer. [0003] Many literatures have studied overlay multicast from different angles. However, the existing systems cannot provide effective support for applications that require arbitrary source multicasting, nod...

AI Technical Summary

Problems solved by technology

The strategy of assigning the same number of sub-nodes to each intermediate node in the communication group is obviously not optimal: if the number of sub-nodes is set too large, the low-ability nodes will be overloaded, which will cause the overall session rate to drop; if the number of sub-nodes Too few, and high-capacity nodes will not be fully utilized

[0006] Most of the existing research on multicast applications satisfying QoS constraints is devoted to constructing an optimal multicast tree rooted at a single data source, which is not suitable for multicast applications satisfying any source of QoS constraints , and a single optimal tree that satisfies the constraints cannot adapt to the QoS requirements of different applications

[0007] To sum up, the current research on overlay multicast mainly focuses on how to build an efficient data forwarding structure that supports single-source multicast under the existing network conditions, and rarely discusses the application of multi-source multicast.

Images