Evaluation Model of System Survivability

This paper puts forward a survivability evaluation model, SQEM （Survivability Quantitative Evaluation Model）, based on lucubrating the main method existed. Then it defines the measurement factors and parses the survivability mathematically, introduces state change probability and the idea of setting the weights of survivability factors dynamically into the evaluating process of SQEM, which improved the accuracy of evaluation. An example is presented to illustrate the way SQEM works, which demonstrated the validity and feasibility of the method.     

恢复时间敏感的光网络混合通路保护算法

针对波分复用(wavelength division multiplexing,WDM)光网络中双链路失效的抗毁需求,研究并提出一种恢复时间敏感的混合通路保护算法.该算法通过引入业务连接的恢复时间约束,利用专用保护业务切换时间快而共享保护资源利用率高的特点,采用专用通路保护(dedicated path protection,DPP)与共享通路保护(shared path protection,SPP)相结合的方式,解决业务切换时间与网络资源利用率之间的矛盾,根据服务等级协定(service level agreement,SLA),在网络资源较少的情况下,优先保证高等级业务的保护资源分配,从而为不同等级业务提供灵活的区分业务恢复度的资源配置方案.仿真结果表明,与传统的DPP和SPP相比,恢复时间敏感的混合通路保护算法在满足业务恢复时间门限的前提下,能够在平均恢复时间、网络资源利用率以及业务连接恢复度性能上获得较好地折中.     

生存体系结构模型

处于Internet中的重要信息系统面临的安全问题越来越多,如何增强系统生存能力,使系统在受到破坏后仍能继续提供用户需求的服务已引起人们普遍关注.笔者介绍了生存性定义,根据生存性具有的抵御、认识、恢复和演化4个功能属性设计了信息系统的生存体系结构模型,进而解释了模型中的系统生存需求、生存策略的含义.并依据生存策略的不同方面给出了为使系统达到生存性的技术措施.     

光网络中一种基于生存性的资源预留机制

在动态、复杂的光网络传输系统中,提前预留作为保证网络服务质量的重要手段而被广泛应用。通过分析光网络环境下现有提前预留机制对生存性的影响因素,结合光网络中存在的脆弱链路问题,提出了一种基于生存性的资源提前预留机制及其模型。仿真结果表明,该机制可在保证资源利用率的情况下降低网络阻塞率,提高网络生存性。     

New SRLG-diverse path selection algorithm in survivable GMPLS networks

In conventional shared risk link group (SRLG)-diverse path selection (CSPS) algorithm in survivable GMPLS networks, SRLG is taken into account when selecting the backup paths, while the primary path selection method is the same as the algorithms without SRLG constraint. A problem of CSPS algorithm is that, after a primary path is selected, the success probability to select an SRLG-diverse backup path for it is low. If SRLG is taken into account when computing the primary path, then the probability to successfully select an SRLG-diverse backup path will be much increased. Based on this idea, an active SRLG-diverse path selection (ASPS) algorithm is proposed. To actively avoid selecting those SRLG links, when computing the primary path, a link that share risk with more links is assigned a larger link cost. To improve the resource utilization ratio, it is permitted that the bandwidth resources are shared among backup paths. What is more, differentiated reliability (DiR) requirements of different customers are considered in ASPS algorithm. The simulation results show that, compared with CSPS algorithm, ASPS algorithm not only increases successful protection probability but also improves resource utilization ratio.     

一种基于概率滑动窗口的应用层DoS攻击防御模型

网络上种类繁多的服务面临着复杂且不安全的生存环境, 多种因素威胁着服务的生存, 应用层DoS攻击就是其中的重要因素之一。然而, 当前防御应用层DoS攻击的方法存在着对合法用户请求的误判, 需要额外的硬件设备支持和难以抵御某些低速率攻击等不足。为此,提出了一种全新的应用层DoS攻击防御模型——基于概率的滑动窗口模型PBSWM (ｐrobability-ｂased ｓliding ｗindow ｍodel)。该模型位于应用层, 利用滑动窗口机制控制客户端发送的请求速率和服务器端接收的负载总量, 利用概率发送控制在源端阻滞攻击者发送引发较大负载的请求, 利用概率接受控制防止来自少量客户的请求占用系统的大部分应用资源。实验结果表明,该模型能够达到降低攻击损害、保障服务生存的目的。     

不完全信息条件下的装备保障网络抗毁性模型

基于复杂网络理论,在对装备保障网络进行复杂网络描述的基础上,努力挖掘装备保障网络所面临威胁的特点,重点建立了不完全信息条件下的装备保障网络一般性攻击策略模型,同时给出了装备保障网络抗毁性测度的计算方法,并对基于流介数的网络节点重要度计算方法以及网络抗毁度进行了定义,由此构建了装备保障网络的抗毁性模型.研究结果表明:信息指数比攻击力度指数对装备保障网络抗毁性的影响程度要大,反映了信息化条件下获得制信息权的重要性;对装备保障网络的了解达到一定程度之后就能达到比较理想的攻击效果,而不需要对系统进行完全了解.     

无线自组网可生存性保证的拓扑控制

为了解决频繁发生的自然故障和恶意攻击引起的无线自组网可生存问题,根据无线自组网的特点,分析图的连通度大小对网络拓扑结构特性和应用服务质量的影响,在此基础上结合网络可生存概念,提出面向网络可生存的容错拓扑控制设计策略。通过理论和实验求得保证网络多连通的关键邻居数,并提出一种基于邻居数的拓扑控制算法k2TC,当节点失效时,及时维护其他节点度等于或略小于阈值k。该分布式算法能构建并维护容错拓扑结构,算法简单且开销小。仿真结果表明:在节点出现失效时,新算法能够保证网络的抗毁性和有效性,使得无线自组网具有可生存的能力。     

基于服务质量的链路不相交路由算法

针对网络可靠性问题,提出了一种基于链路保护机制的QoS路由算法,该算法首先在图论的基础上得到任意两点间的所有路由,再过滤链路条件使其满足QoS约束,由此求出结点对间的两条链路不相交的最短相似路由,对大数据流复用及高实时性网络都起到较好的优化作用.     

Survivability of components assembly in architecture

Based on the in-depth analysis of the interaction patterns between the components of software system in architecture, this paper illustrates that the association among them is complex and usually changeable during the running period. So we assume the interactions between two adjacency components are grouped into a single connector, which can be used to analyze the influence of components assembly on the survivability for software architecture. The survivability of the components assembly is mapped into the connectivity of graph model. We also bring forward a simplicity method to calculate and quantify the survivability of architecture that could provide a more usable model for designers to evaluate the architecture.