服务台可修的多水平优先权排队(二)

文献[1]讨论了服务台可修的多水平优先权排队的排队指标。本文讨论该系统的可靠性指标。利用文献[3]中的随机序,获得了这些可靠性指标的界值。     

动态车辆路径问题排队模型分析

分析了一类动态车辆路径问题,其中顾客需求以泊松流形式出现,现场服务时间服从一般分布.提出解决该问题的两种策略:顺序服务策略和中点改进策略,利用排队论、几何概率论等领域的知识分别求出了这两种策略的系统时间,并通过仿真数据实验验证了这两种策略的有效性.     

用ATM技术提高IP业务服务质量的研究

分析了在Ｉｎｔｅｒｎｅｔ网中无法提供ＩＰ业务服务质量的原因,阐述了其中涉及部分的关键问题。在保证ＩＰ网络服务质量的几种技术的基础上,提出了利用ＡＴＭ技术来提高ＩＰ业务服务质量的方法。通过研究和比较其他几种常用的分组排队技术,提出了一种能更好保证ＩＰ业业服务质量的分级排队方案,仿真实验证明了该方案的优越性。     

基于M/M/s/N/∞顾客排队的供应链系统可靠度研究

论文研究了带有M/M/s/N/∞排队系统的零售商一制造商混联供应链系统的可靠度,研究发现零售商一制造商混联供应链系统的可靠度随着零售商服务强度的增大而减小,随着制造商服务台数目和系统容量的增大而增大;可以通过提高服务台平均服务速率,增加制造商服务台数目和系统容量提高该混联供应链系统的可靠度;最后还考虑了该混联供应链系统的可靠度优化问题。该研究对于丰富供应链系统的可靠度理论和指导供应链系统可靠度控制实践有一定的参考意义和应用价值。     

飞机等待起飞时间实时信号控制模型与机场交通管理优化

在机场交通管理中,采用一种全新的动态智能管理策略——实时信号控制。在一个机场简化模型中,任何一架飞机等待起飞的时间与其他飞机等待降落的时间是依据一个预设的＂清空＂时限来实时决定,而不再以固定时间间隔交替进行。我们主要建立一个探讨在这种策略下飞机等待起飞和降落的时间延迟量的数学概率模型,重点探讨此实时控制策略下延迟时间的均值和方差,以便进一步探讨与传统的固定时间差交替变换起飞和降落策略相比的优劣。     

Ek／M／n排队模型及目标参量的确定

本文运用概率论和随机过程的基本知识，对排队论中的Ｅｋ／Ｍ／ｎ 排队模型进行研究，对其目标参量的计算公式进行推导，给出单路排队多通道服务系统Ｅｋ／Ｍ／ｎ 排队模型目标参量的计算公式，并探讨其在交通工程中的应用     

Performance-Related Reliability Analysis Methodology of Computer Networks

Based on the bottlenecks in current performance-related network reliability (PRNR) research, this article selects network time delay as PRNR evaluation foundation, and defines PRNR measure as the probability that the actual network delay is no bigger than the required value during network long-term operating under the specified conditions of resource allocation and network operating environment. To obtain PRNR, a novel threshold-optimization-based network traffic model is proposed to model real network traffic. In this model, the actual network traffic is divided into two different parts—a-traffic with burst characteristic, and b-traffic with steady characteristic—according to the optimized threshold value obtained with Particle Swarm Optimization (PSO). Analysis to PRNR is carried out in two different time levels—macro-time level and micro-time level—to avoid the difficulties resulting from the great difference in reliability and performance dimension. In the macro-time level, the number of the operational network workstations varying with random failures is obtained. In the micro-time level, the packet delay is analyzed with the number of the operational workstations as a parameter. Combing the analysis in these two time levels together, the integrated PRNR model is established, and influences of different parameters are analyzed.     

分组公平排队算法的仿真研究

对ＡＴＭ复接器和输出缓存ＡＴＭ交换机采用各种分组公平排队算法情况下的信元时延进行了仿真。仿真结果表明,ＳＣＦＱ对连接之间的隔离性比其他算法差;若一个ＣＢＲ速率组内没有流量超过其预约带宽的连接,则用 Ｐｅｒ＿Ｒａｔｅ＿Ｇｒｏｕｐｉｎｇ方式实现 ＷＦ２Ｑ＋和不用这种实现方式,从最大时延和平均时延来看,相差不大。提出了一个调度 ＣＢＲ、 ＶＢＲ、 ＡＢＲ和 ＵＢＲ的调度器结构,既能满足 ＣＢＲ对时延的严格要求,又能保证ＶＢＲ、ＡＢＲ和ＵＢＲ的吞吐率,同时还具有较低的实现复杂性。     

Self‐Selecting Priority Queues with Burr Distributed Waiting Costs

Service providers, in the presence of congestion and heterogeneity of customer waiting costs, often introduce a fee‐based premier option using which the customers self‐segment themselves. Examples of this practice are found in health care, amusement parks, government (consular services), and transportation. Using a single‐server queuing system with customer waiting costs modeled as a Burr Distribution, we perform a detailed analysis to (i) determine the conditions (fees, cost structure, etc.) under which this strategy is profitable for the service provider, (ii) quantify the benefits accrued by the premier customers; and (iii) evaluate the resulting impact on the other customers. We show that such self‐selecting priority systems can be pareto‐improving in the sense that they are beneficial to everyone. These benefits are larger when the variance in the customer waiting costs is high and the system utilization is high. We use income data from the poorest and richest areas (identified by zipcode) in the United States along with the countrywide income distribution to illustrate our results. Numerical results indicate that planning for a 20–40% enrollment in the high‐priority option is robust in ensuring that all the stakeholders benefit from the proposed strategy.