论文部分内容阅读
为了克服当前IP网络的带宽瓶颈问题,提出了一种基于网络编码的IP网络通信机制—IP编码网络。该文讨论了网络节点上包的代数运算与路由协议的结合方式,提出了IP编码网络中单、组播通信的实现方法。在此基础上,对应于现有最短路径、最小代价组播树的网络优化问题,提出了一种基于遗传算法的IP编码网络优化算法。该算法为单播和组播会话构造一个在最大流约束下通信代价优化的编码子网。算法的模拟实验结果表明对任意的单播和多源组播通信,都可以在有限的计算代价和计算时间内生成通信子网,有效减少了IP编码网络的编码开销和通信代价。该文的研究工作为网络编码的应用作了有益的实践探索。
In order to overcome the bandwidth bottleneck of the current IP network, this paper proposes a IP network communication mechanism based on network coding-IP coding network. This paper discusses the combination of algebraic operation and routing protocol on the network node, and proposes the realization of single and multicast communication in IP coding network. On this basis, corresponding to the existing shortest path and minimum cost multicast tree network optimization problem, this paper proposes a genetic algorithm based IP coding network optimization algorithm. The algorithm constructs a coding subnet optimized for communication costs under the maximum flow constraint for unicast and multicast sessions. The simulation results show that for any unicast and multi-source multicast communication, the communication subnet can be generated within a limited computational cost and computing time, which effectively reduces coding and communication costs of the IP coding network. The research work of this article makes useful practical exploration for the application of network coding.