Triggering cascades on undirected connected graphs

Consider the following cascading process on an undirected connected graph G(V,E). A set S of vertices, called the seeds, are active initially. Thereafter, an inactive vertex is activated when at least a ρ fraction of its neighbors is active, where ρ∈(0,1]. The cascading process proceeds asynchronously until no more vertices can be activated. This paper proves the existence of at most seeds that can activate all vertices at the end.     

基于输入排队的最大匹配调度算法仿真分析

针对路由器输入队列最大匹配调度算法中存在每个时隙内输入端口和输出端口匹配率低的问题,提出:在算法设计中,可通过改变更新轮询指针的方法提高端口匹配数目,解决输出端口同步问题,从而有效提高系统的吞吐率.仿真实验表明,采用轮询指针的调度算法可以有效地提高交换机的性能.     

Performance analysis of Markovian polling systems with single buffers

In this paper, we analyze the Markovian polling system with single buffers, asymmetric arrival rates, service times, and switchover times. A virtual buffer model is introduced to derive the relationship of the joint generating function for the queue length of each station at a polling instant. The Laplace-Stieltjes transforms of the cycle time and the intervisit time are obtained from the marginal generating function. We analyze the cyclic, load-oriented-priority, and symmetric random polling schemes which are classified by adjusting the transition probabilities, and compare the merits and demerits of each scheme for the performance measures. In particular, we prove that the mean queue lengths at the polling instants are the same for all stations in case of the load-oriented-priority polling scheme for the buffer relaxation system in which a new message is stored as soon as the transmission of the message currently in the buffer is initiated.     

一种改进的网络故障监测算法

为了减少网络监测开销，基于分层分布式网络管理体系结构．提出了一种改进的动态网络监测算法，算法根据SNMP网络管理方式中的轮询和事件通知获得的网络状态数据．预测发生告警的可能性．如果没有告警的可能性，则延时轮询．该方法既不满报告警．又有效地降低了网络管理的通信负担．仿真结果表明，提出的监测算法有效地减少了轮询次数，降低了管理信息占用的带宽．提高了网络管理的有效性．     

Linux系统中基于PF_RING套接字的高性能包捕获技术

介绍一种新型的数据包捕获方式--基于PF_RING套接字的数据包捕获技术.旨在提高高速复杂网络传输环境中的数据包捕获率.使用环形缓冲区,用来实现内核空间和用户空间的内存共享,用户空间可以直接对其进行读写操作,而且可以对该缓冲区的大小进行调整配置.经过实验,在100 M甚至Gbit网络环境中,结合设备轮询机制,在普通的PC机上便可以显示出其突出的数据包捕效率.     

基于队长参数的动态限定轮询多址协议分析

提出了基于队长参数的动态限定轮询多址协议（DPBQ）。该协议根据各节点内实时队列长度动态的控制轮询过程,每个轮询周期对具有最长队列的节点进行服务。通过采用嵌入马尔可夫链理论和休假排队模型,给出该协议的理论模型和性能分析,并且通过限定服务的基本轮询系统和DPBQ系统的对比分析,可以看出DPBQ系统缩短了分组的平均等待时间,能够更好的保证时延性能。     

无线局域网两级循环查询优先级控制系统的应用分析

在具体分析视频业务、语音业务等数据传输业务的基础上,通过两级循环查询多业务优先级控制传输系统的实际应用,并与文献[4]的周期查询限定服务（K=1）系统及周期查询限定服务（K=1）并行调度控制系统进行比较,进一步验证新系统对无线宽带视频等实时业务传输性能的改进。     

用于网络管理系统的智能轮询策略

为提高网络性能管理与故障管理的实时性和效率,研究信息收集轮询策略,提出一种基于马尔可夫链的智能轮询算法。该算法能根据被监视对象参数值的变化,动态调整轮询间隔时间。实验结果表明,与传统等时间轮询算法相比,该算法可以更准确地刻画数据变化特征,降低数据采集失真度并减小网络带宽,其效率和可靠性较高。     

Study of Asymmetric Polling System with Two Message Classes

A novel mixed polling system with multiple stations is considered. Each station produces two classes of messages served with different disciplines. The real time message served with exhaustive service discipline and the unreal time message served with gated service discipline. Using an iterative method, the exact mean waiting times for both message classes are derived. The influence of the gate location of the message class served by the gated service discipline on the mean waiting time is also analyzed. The analytical results are verified with simulation method and agree well with simulation results.     

嵌入式实时系统

随着计算机的发展和应用的普及，嵌入式实时计算机系统（以下简称嵌入式实时系统）已经在工业、交通、能源、科学研究和科学试验、国防等各个领域发挥极其重要的作用。本文介绍了嵌入式系统的特征，分析了嵌入式实时软件的结构及发展动向，并提出了嵌入式实时软件的开发步骤。