一种基于QoS度量的Pareto并行路由寻优方法  

A Parallel QoS Routing Optimization Based on Pareto Subsets

作　　者：秦勇[1,2] 肖文俊[2] 黄翰[3] 梁本来[4] 赵成贵[2] 魏文红[2] 

机构地区：[1]茂名学院信息与网络中心,广东茂名525000 [2]华南理工大学计算机科学与工程学院,广州510641 [3]华南理工大学软件学院,广州510641 [4]太原理工大学计算机与软件学院,太原030024

出　　处：《计算机学报》2009年第3期463-472,共10页Chinese Journal of Computers

基　　金：国家自然科学基金(60433020;10471045;60673023);广东省自然科学基金(970472;000463;04020079;05011896);广东省教育厅自然科学研究项目(Z03080)资助~~

摘　　要：动态QoS路由是基于每个流计算的,为了优化动态QoSR请求中状态的时变性和控制滞后性,快速寻找满足多个约束的可行路径,提出一种基于QoS度量的Pareto子集并行路由预计算方法(QPAS).方法实现了并行状态收集和路由计算,求得满足路由请求约束可行路径的Pareto子集并综合选择合适的转发路由,仿真结果验证了QPAS的计算效率和有效性.QPAS可用于解决有限节点网络的复杂QoS路由等网络传输控制中的实际问题.The QoS routing is based on the computing of each flow. In order to optimize the volatile status messages and hysteresis quality of the dynamic routing request, a method （QPAS） for parallel routing optimization based on Pareto of QoS Metrics is proposed to find the feasible path quickly and inerrably. Parallel routing precomputing is used to obtain the Pareto subsets which satisfy the multiple routing request constraints, and a proper route is selected from these subsets synthetically. QPAS is proved to be valid and effective by simulated experiments, with its parallelized status collection and parallelized routing searching. QPAS can be used to solve the complex QoS routing problems and other actual information transmission cases in the finite-node networks.

关 键 词：并行路由算法 QOS度量 Pareto子集 多约束 复杂度 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]