超时策略动态阈值的阈值选择影响因素

为在能源有限的情况下增加系统运行时间,从动态电源管理的超时策略角度出发,探讨了超时策略中阈值选择的影响因素.在国内外动态电源管理策略的研究基础上,分析了超时策略中动态阈值策略与固定阈值策略的原理,完成了对现有的动态阈值策略的阈值选择影响因素的分析,得出了系统进入休眠与唤醒的能量消耗、电池放电电压大小、系统具体的应用环境三方面对阈值选择产生影响.证实了综合考虑阈值的三方面影响因素是找到最优阈值的捷径.     

基于动态混合超时的软件定义网络多目标优化

软件定义网络（SDN）中,流表项是由控制器创建并指导交换机处理数据包的转发规则。流表项保存在交换机的内存并有一定的超时时间,会影响SDN控制通道的带宽消耗、交换机的内存消耗以及系统资源和性能的管理。针对现有SDN性能优化方案大多为单一目标优化,未考虑流表项超时类型和时间对不同优化目标的影响,提出一种基于流表项动态混合超时的多目标优化方案,对大象流的侦测精度、流表项的交换机内存消耗和控制通道带宽占用进行三目标联合优化。动态混合超时将现有的两种流表项超时方式,即硬超时和空闲超时相结合,并对流表项的超时类型和时间进行双维度动态调节。通过NSGA-Ⅱ算法求解所提优化问题,评估不同超时方式和超时时间对三个优化目标的影响,并通过合并特定超时时间下的解集与贝叶斯多目标优化算法的解集对NSGA-Ⅱ算法的解集质量进行改进。结果表明,所提方案能提供更高的侦测精度、更低的带宽占用和更小的交换机内存消耗,明显提升了SDN的综合性能。     

柔性作业车间调度问题的多目标优化算法

柔性作业车间调度问题具有解集多样化与解空间复杂的特点,传统多目标优化算法求解时容易陷入局部最优且丢失解的多样性。在建立以最大完工时间、最大能耗、机器总负荷为优化目标的柔性作业车间调度模型的情况下,提出一种改进的非支配排序遗传算法（Improved Non-dominated Sorting Genetic Algorithm II, INSGA-II）求解该模型。INSGA-II算法先将随机式初始化与启发式初始化方法混合,提高种群多样性;然后对工序部分与机器部分采用针对性的交叉、变异策略,提高算法全局搜索能力;最后设计自适应的交叉、变异算子以兼顾算法的全局收敛与局部寻优能力。在mk01～mk07标准数据集上的实验结果显示INSGA-II算法有着更优的算法收敛性与解集多样性。     

TCP throughput and fairness performance in presence of delay spikes in wireless networks

Wireless networks are likely to experience delay spikes exceeding several times the typical round‐trip‐time figures, which can cause spurious timeouts that lead to unnecessary retransmissions and reduction of the TCP sender's transmission rate, and thus, the throughput of the TCP is degraded. This paper presents some research results on the effect of delay spikes caused by handover on TCP performance by using three different mobility models. It is shown that the throughput of TCP connection over a single bottleneck link is decreased in the presence of delay spikes significantly. Furthermore, it is shown that the fairness feature of TCP is also severely affected in the presence of delay spikes. Copyright © 2005 John Wiley & Sons, Ltd.     

基于包重传延时的主机操作系统探测技术的设计与实现

主机操作系统探测对于网络安全有重要的意义，它通过分析不同操作系统TCP／IP协议堆栈对数据包的不同响应来判断其性质．分析了现有的主机操作系统探测工具所面临的问题，并提出一种基于包重传延时的主机操作系统探测的思想及其实现。     

基于自动机的TCP流识别算法

为提升网络流识别性能,本文提出了一种TCP流识别算法.该算法基于传输控制协议(Transmission Control Protocol,TCP)下网络通信双方的交互过程构建双向流自动机,由该自动机根据TCP协议规则和网络流当前状态判断TCP流终止,同时以基于规则的过滤机制和超时策略为辅助措施,快速识别单包流和异常中断流.该算法内存开销、计算和内存总开销均低于经典算法固定超时策略(Fixed Timeout strategy,FT)和同类代表性算法两层自适应超时策略(Two-level Self-Adaptive Timeout,TSAT),同时该算法精度高于TSAT,且仅比默认精度标准略有下降.该算法基于协议规则识别TCP流,既保证了流的准确性,又节省了流的超时等待时间,而且算法尤其适合中流、小流和不规则TCP流比重较大的情况,使得识别系统在面临DDoS攻击、蠕虫爆发等网络异常时仍能正常运行.     

A multicriteria approach to timeout collaboration protocol

This paper presents a multicriteria approach to exploring the properties of timeout collaboration protocol with different timeout thresholds in general testing environments. This is formulated as a discrete multiple criteria optimisation problem by choosing five representative timeout thresholds as alternatives with five common performance measures of production systems. The PROMETHEE method is adopted to deal with this multicriteria problem. The divide-and-label algorithm is developed to rank all the alternatives with the overall intensity of their performance, by using multiple valued outranking graphs from the PROMETHEE with multiple replications. It is shown that two extreme timeout thresholds, T ₀ = 0 and ∞, are efficient over multiple criteria in almost all cases. The divide-and-label algorithm is a very efficient approach to overcome the limitations of the PROMETHEE algorithm and Belz and Mertens's procedure with multiple criteria and replications.     

Efficiency/Fairness Tradeoffs in Networks with Wireless Components and Transient Congestion

Our work explores the impact of aggressive/conservative congestion control strategies on the fairness and efficiency of reliable transport protocols, in a wired/wireless environment. Based on experiments, we study the behavior of congestion control mechanisms in response to wireless errors, and transient congestion caused by a small number of competing flows. We show that: (i) the traditional TCP algorithm proves to be inadequate in terms of efficiency and fairness when random wireless errors occur in the network and, (ii) an aggressive strategy does not necessarily yield better performance. On the contrary, in the combined presence of transmission errors and transient congestion a conservative strategy appears superior.     

大规模集群中一种自适应可扩展的RPC超时机制

在基于RPC(remote produce call)构建的分布式系统中,超时是一种通用的失效检测手段.在超大规模Lustre存储集群的压力测试中,发现传统的固定超时机制会导致很多不必要的超时而存在缺陷.提出了一种综合考虑了网络条件、服务器负载、扩展性和性能等因素的自适应可扩展的RPC超时机制(Adaptive Scalable RPC Timeout mechanism,简称AST).在其控制下,客户端超时值可以根据网络和服务器的拥塞情况动态地调整设置,而且服务器可以通过额外消息传递通知客户端修改原超时值.经过一系列的模拟和验证,其结果表明,AST是一种更适合的RPC失效检测模型,增强了系统的响应性、可靠性和稳定性,而且对系统的性能没有过大的负面影响.     

向家坝水电站励磁系统建压失败的原因分析

向家坝水电站机组出现起励建压失败现象是由于两个不同原因导致的起励建压失败缺陷。通过更换起励变压器解决了其二次电压偏低导致机组起励超时的缺陷;对由于程序缺陷导致机组在起励建压过程中定子电压跌落故障进行分析与试验,提出了切实可行的解决办法,为机组稳定运行及提高开机成功率提供了保障。