非平稳网络链路延迟率估计过程仿真分析

Non-Stationary Network Link Delay Rate Estimation Process Simulation Analysis

研究非平稳网络链路延迟率准确估计问题。由于网络的规模越来越大,复杂性越来越高。传统方法通常通过网络内部节点协作获取网络内部性能参数,但是,节点的差异性会给算法的协作过程带来冲突,造成节点协作过程中的相互抵制,从而导致传统方法在非平稳网络链路延迟率估计中失效。提出了一种网络层析成像优化的网络延迟计算方法。在算法基础上根据源节点和目标节点的相关信息建立树结构,计算非平稳网络链路数据传输概率,克服不平稳造成的冲突。再利用网络层析成像优化方法,对链路的延迟率进行估计。实验结果表明,利用改进算法进行非平稳网络链路延迟率估计,能够提高网络链路延迟率估计的准确性,为网络性能评估提供准确的依据。

The paper put forward a network tomography method based on the optimization of the network delay calculation. According to the source node and destination node information, tree structure was established, non - stationary network link data transmission probability was calculated for network link delay rate estimation provide data base. Using network tomography optimization method, the link delay rates were estimated. The experimental results show that this algorithm using non - stationary network link delay rate estimation can improve the network link delay rate estimation accuracy, for the network performance evaluation to provide accurate basis.