基于rLFA技术的性能优化及重路由选择算法研究  

Research of Performance Optimization and Re-routing Selection Algorithm Based on Improved rLFA

作　　者：王明鸣[1] 孟相如[1] 徐有[1] 崔文岩[1] 

机构地区：[1]空军工程大学信息与导航学院,西安710077

出　　处：《计算机科学》2015年第1期106-109,118,共5页Computer Science

基　　金：国家自然科学基金(61201209)资助

摘　　要：为进一步提高网络单故障快速恢复能力,基于改进的Remote Loop-Free Alternates(rLFA)重路由技术,提出一种采用混沌粒子群并考虑网络物理传输代价和拥塞代价的重路由选择算法。首先基于rLFA的隧道建立方法对其进行改进,结合引入隧道技术的链路增补方法来实现故障全覆盖,通过设置权重因子来保证在不同业务量下的重路由选择针对性。实验表明,改进的rLFA能进一步提高网络单故障覆盖率,同时结合链路增补方法在保证故障完全覆盖的情况下能够大幅度减少链路增补数量;路由选择算法能够动态选择不同业务量下的重路由路径,在提高网络单故障环境下的传输效率的同时也实现了负载均衡。Aiming at improving network single link （node） failure fast recovery capability further,a method based on improved rLFA was proposed by utilizing Chaos PSO and considering both transmission and congestion cost.Firstly,a method based on rLFA was proposed by improving the creation of tunnels,which was integrated with the supplement links in order to achieve full coverage for failures.The weight factor was set to keep the pertinence of re-routing selection under the different traffic demands.The experimental result shows that the improved rLFA can improve network single failure fast recovery capability further and reduce the numbers of supplement links sharply.The re-routing algorithm can achieve the dynamic selection of re-route to adapt the different traffic demands,meanwhile,it can improve the transmission efficiency and balance the load in single failure network.

关 键 词：单故障 rLFA 混沌粒子群 重路由选择算法 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]