树突状细胞算法在检测任务超时异常中的应用

描述树突状细胞算法(DCA)的生物学机理及其主要步骤和适用环境。通过分析实时任务的特征,抽象出应用DCA所需要的参数。以传统检测任务超时方法为基准,验证DCA检测实时任务超时的准确性。实验结果表明,DCA能够节省更多的系统资源,较准确地发现超时异常。     

分布式系统中失败结点的判定与优先列表的重构新方法

实时分布式系统中，如果结点n自从上一次收到结点i的广播信息后经过超时值时没有再收到结点i的广播信息，就认为结点i失败。这时需要调整各正常结点的优先列表，以保证每个结点被一个也只能是一个结点选择为自己的第后个优先结点，以减少任务的失败率。本文提出了一种确定最佳超时值以及检测结点失败并且调整结点的优先列表以处理结点失败的新方法。     

一种新的过滤SYN洪水攻击的方法

本文提出了一种新的过滤SYN洪水攻击的方法。这种方法(故意丢弃过滤)通过观察客户的协议一致性行为判定客户的请求是否正常。它的主要思想是故意丢弃每个连接请求上的第一个SYN数据包,后续的SYN只有遵守TCP超时与重传机制才能通过。分析表明,我们的方法能有效地降低攻击的成功率,同时连接建立的延迟也是可以接受的。     

基于单向并行多链表的流管理

高速条件下数据访存是流管理的瓶颈,传统表项操作“读-处理-写”模式效率仅为36％,读写转换和读写延时是制约效率的重要因素.针对这个问题,提出了连续读写法处理表项,通过合并读写时延和复用读写转换的方式使表项操作效率超过90％;并在此基础上提出了单向并行多链表法.通过多个链表的交替操作,使连续读写法应用于处理不活动超时流.理论分析和实验表明,单向并行多链表法能够适用于OC-768(40Gbps)链路下管理千万条表项明显优于辅助存储法和双向链表法的OC-192 (10Gbps)下百万条表项的管理能力.     

A simplification of a real‐time verification problem

We revisit the problem of real‐time verification with dense‐time dynamics using timeout and calendar‐based models and simplify this to a finite state verification problem. We introduce a specification formalism for these models and capture their behaviour in terms of semantics of timed transition systems. We discuss a technique, which reduces the problem of verification of qualitative temporal properties on infinite state space of a large fragment of these timeout and calender‐based transition systems into that on clock‐less finite state models through a two‐step process comprising of digitization and finitary reduction. This technique enables us to verify safety invariants for real‐time systems using finite state model checking avoiding the complexity of infinite state (bounded) model checking and scale up models without applying techniques from induction‐based proof methodology. In the same manner, we verify timeliness properties. Moreover, we can verify liveness for real‐time systems, which are not possible by using induction with infinite state model checkers. Copyright © 2016 John Wiley & Sons, Ltd.     

Combined ICA and FCA Schemes for a Hierarchical Network

A combined idle channel assignment (ICA) and fixed channel assignment (FCA) scheme is proposed to improve the traffic performance in a hierarchical network. This dual-mode network integrates the Frequency Division Duplex (FDD) and Time Division Duplex (TDD) modes of the Universal Mobile Telecommunication System (UMTS) and Terrestrial Radio Access (UTRA) in a given cell. This approach includes a high traffic load area and a blocked area as an example to evaluate the traffic performance. The ICA threshold and network timeout period effects on the traffic performance of this integrated dual-mode network are also investigated. The analytical results show that the handoff failure probabilities of the integrated dual-mode network can be reduced significantly with a minimal increase in the new call blocking probability when the combined ICA and FCA scheme replaces the FCA scheme. The integrated dual-mode network using the combined ICA and FCA scheme also increases the carried traffic. The traffic performance improvements for non-uniformly generated new calls are more significant than those for uniformly generated new calls when the combined ICA and FCA scheme is used. An increase in the high ICA threshold will result in an increase in the total carried traffic and an increase in the new call blocking and handoff failure probabilities for higher-tiered and low-tiered systems located in the high traffic load area. The traffic performance was evaluated using the discrete time simulation method to validate the analysis results.     

Improving TCP performance for vertical handover in heterogeneous wireless networks

The incorporation of wireless local area networks (WLANs) into existing cellular networks as supplementary access technologies has become an issue of great interest. However, vertical handover (VHO), which allows users to roam between a WLAN and a cellular network, causes an abrupt change in certain link characteristics such as the round trip time and data rate. Owing to such changes, reordering problem and premature timeout occur and trigger unnecessarily fast retransmission during VHO, causing throughput degradation. Thus, we propose a new transmission control protocol (TCP) mechanism, which resolves the reordering problem by suppressing unnecessary retransmission caused by spurious duplicate acknowledgments (dupacks) incurred because of the reordering problem, and prevents premature timeout by employing an adaptive retransmission timer. We analytically investigate the throughput of our proposed TCP scheme. The numerical and simulation results show that our proposed TCP performs better in terms of throughput than other schemes appearing in the literature. Copyright © 2009 John Wiley & Sons, Ltd.     

Performance enhancement of mSCTP for vertical handover across heterogeneous wireless networks

In the mobile Stream Control Transmission Protocol (mSCTP) for vertical handover, a mobile user may suffer from performance degradation due to the problems of packet reordering and retransmission timeout and due to the packet loss during handover. To solve these problems, we propose a new scheme of handover retransmission for mSCTP handover, in which the correspondent node retransmits the outstanding data packets to the mobile node over the new primary path. From simulation results, it is shown that the proposed scheme can avoid the packet reordering and retransmission timeout problems during handover. Moreover, we can see that the proposed scheme can significantly improve throughput of mSCTP handover, compared with the existing schemes. Copyright © 2009 John Wiley & Sons, Ltd.     

一种基于预测与动态调整负载因子的SDN流表优化算法

通过对SDN流表更新的研究,发现了网络流量高峰期流表更新不及时的问题。提出了一种基于预测与动态调整负载因子的SDN流表优化算法。算法首先收集每个单位时间内的新增流条目,然后用二次移动平均算法对收集的历史数据进行分析,并估计下一个单位时间内新增的流条目,最终根据负载因子动态调整交换机流表中流条目的停滞超时时间。实验结果表明,该算法提高了流表匹配率和数据成功转发率,增加了活动流表项的数量。     

一种基于动态阈值的TCP慢启动策略

针对目前TCP拥塞控制机制的慢启动算法中存在的实际问题,提出了一种基于动态阈值的新慢启动策略COS-Slow-Start。最后NS2仿真实验表明,该策略能有效地减少分组丢失、平缓突发流量冲击,并可增加带宽的有效利用率。