M/G/1排队网络系统性能研究

本论文以单一路由器(服务器)为例,从最原始的队列理论出发,探讨具有容量C的M/G/1队列模型的系统平均时延、系统稳态下的报文(用户)平均值、以及时延等问题。并对报文(用户)的服务质量需求作了详尽的数学推导。     

Loss behavior in space priority queue with batch Markovian arrival process — discrete-time case

This paper applies matrix-analytic approach to the examination of the loss behavior of a space priority queue. In addition to the evaluation of the long-term high-priority and low-priority packet loss probabilities, we examine the bursty nature of packet losses by means of conditional statistics with respect to critical and non-critical periods that occur in an alternating manner. The critical period corresponds to having more than a certain number of packets in the buffer; non-critical corresponds to the opposite. Hence there is a threshold buffer level that splits the state space into two. By such a state-space decomposition, two hypothesized Markov chains are devised to describe the alternating renewal process. The distributions of various absorbing times in the two hypothesized Markov chains are derived to compute the average durations of the two periods and the conditional high-priority packet loss probability encountered during a critical period. These performance measures greatly assist the space priority mechanism for determining a proper threshold. The overall complexity of computing these performance measures is of the order O(K²m₁³m₂³), where K is the buffer capacity, and m₁ and m₂ are the numbers of phases of the underlying Markovian structures for the high-priority and low-priority packet arrival processes, respectively. Thus the results obtained are computationally tractable and numerical results show that, by choosing a proper threshold, a space priority queue not only can maintain the quality of service for the high-priority traffic but also can provide the near-optimum utilization of the capacity for the low-priority traffic.     

Windows消息子类化及应用

Win32消息处理机制是Win32应用编程的核心内容之一。Windows窗口消息的子类化,是根据消息处理的基本原理,把发送或投递到一个窗口的消息交给自己定义的函数处理,而不是交给默认的窗口过程处理。利用窗口子类化,开发者可以实现对应用程序的窗口消息进行独特的处理。     

Lot release times and dispatching rule for a TFT-LCD cell process

In this paper, the simulation analysis of the cell process in a thin film transistor-liquid crystal display (TFT-LCD) manufacturing was analyzed, and the effects of the lot release times and dispatching rule were considered. Discrete-event simulation models were developed in an e-M Plant to study this system. The lot release times and dispatching rule based on minimum setup times was used in this system. In order to improve the system performance, a heuristic algorithm for lot release times and a queue time maximum un-matches (QTMU) dispatching rule for rubbing machines are proposed. The simulation results revealed a substantial improvement of the cell process performance and reduced the setup times for the rubbing machine and the cycle time of TFT-array substrate and color filter (CF) substrate processing.     

流量管理中队列调度算法研究

介绍了包交换芯片流量管理中队列调度的算法,分析DWRR(Deficit Weighted Round-Robin)算法的优缺点,并提出了一种基于DWRR改进的调度算法.该算法能够根据网络中实时的数据包帧长,来调节每次轮询中向各个队列添加的信用度,能够减少各个队列的时延,同时又增强带宽分配的相对公平性,改善了DWRR算法不能很好满足业务的时延特性.使用NS-2仿真器来对改进的算法进行网络仿真,最终的仿真结果表明改进后的DWRR算法能够有效地降低时延,可以在一定程度上提高QoS.     

北京电话号码查询系统

本文介绍了新建的北京电话号码查询系统，内容包括系统配置、工作流程以及排队机、查询数据库、管理系统和系统连接功能等特点，并介绍了系统可拓展的业务。     

缩短机械加工中零件等待时间的方法讨论

在机械制造系统中，零件在各工序间加工及流转，一般情况下许多工序难免存在零件等待加工的现象。为了提高系统的加工性能，本文利用现代仿真技术及排队论，通过优化工件在各相关工序的加工时间，从而消除工序中存在的工件等待加工现象。文章提出的方法还可用来预测机械制造系统的运行性能、比较各种可供选择的方案以及实现制造系统决策的优化。     

基于动静态频谱相结合的接纳控制机制

在不同频段频谱共存的情况下,针对动静态频谱资源相结合的接入策略和接纳控制机制进行了研究.提出了一种支持动静态频谱资源相结合的非随机接入机制,利用排队论建立了相应的马尔可夫转移模型,定义了联合接纳控制因子,根据用户的需求不同设定了不同的控制因子门限值.启动接纳控制算法,以相应的概率来接纳新的呼叫请求.仿真结果表明,启动接纳控制算法后,用户的阻塞率、强制中断概率、联合接纳控制因子都得到了一定的改善.     

Performance comparison of some discrete service time systems

This paper analyzes and compares the slotted time operation and the non-slotted time operation of a singleserver system with deterministic service time. These two operations are commonly used to model discrete service time systems in computer or digital communications. But due to the similarity in their operations and performance, the two models may be mixed up with each other. This paper examines by means of queueing analysis the performance of a few classes of systems that differ in the service order of their customers. The means and variances of the queue lengths, waiting times and interdeparture times of FCFS systems using the slotted time operations are first obtained from their respective LST and generating function equations. These are then used for comparison with those in non-slotted time systems. The results show that although the slotted time operation in the FCFS systems can be approximated by the non-slotted time operations under heavy traffic condition, the performances under other regions and service disciplines (e.g., the LCFS and the priority systems) may deviate significantly. They must be properly adjusted if one wishes to use the simpler equations of the non-slotted time operations to approximate the slotted time operations. The comparison graphs provided in this paper supply adjustments guidelines for the careful designers.