基于免疫Agent的网格抗衰模型和决策方法

模拟生物免疫机理实现计算网格的性能抗衰是一个崭新的研究方向.分析和比较了免疫和抗衰之间的异同,构建了基于免疫Agent的系统抗衰逻辑模型,通过建立系统性能衰退的数学模型,给出了一种抗衰策略的决策方法.以一个分布式的音像资源事务处理系统为背景进行了应用研究,给出了一个两阶段超指数分布的数学模型来评估性能,结果表明方法是有效可行的.     

基于免疫原理的信号调理系统的故障自愈分析

在机电装备信号调理系统的故障自愈研究中,通过对信号调理系统的结构特点、参数特性及典型故障特征等进行分析,并建立健康因子群,对系统抗衰性能进行评估．在深入分析生物免疫机理的基础上,建立自愈系统与免疫系统映射关系,构建基于免疫原理的故障自愈系统结构模型,并给出模型中主要模块结构和实现算法．根据系统故障自愈模型建立的方法,建立信号调理系统的模型,分析系统的故障,并对此模型进行仿真实验,验证故障自愈系统模型的可行性和有效性．经仿真实验证明,基于免疫原理构建的信号调理故障自愈系统可以实现其主要故障的自愈．     

基于音圈电机的波动压力载荷控制研究

为开展波动载荷下滑动电接触摩擦动力学与电流传导机理研究,需在滑动电接触实验机上模拟弓网压力载荷波动,为此设计了基于音圈电机的动态压力伺服控制器.在建立波动载荷伺服系统数学模型基础上,设计了基于音圈电机的改进自抗扰控制方案,给出了改进自抗扰控制器的具体设计方法,并通过与模糊RBF网络相结合,实现参数自整定.针对传统自抗扰控制、PID控制与改进型自抗扰控制进行了仿真对比分析,并对改进型自抗扰控制进行了实验测试.仿真以及实验研究表明,该控制策略具有良好的控制性能以及鲁棒性能,满足实验系统要求.     

软件抗衰研究综述

软件衰退的现象存在于各类软件系统中且很难消除.文中分析了其成因和必然存在性,系统阐述了抗衰技术研究的动机、概念和发展,并对不同的模型和解决途径进行了分析和比较;接着探讨了软件抗衰研究领域的新的研究进展,设计了一个基于免疫机理的抗衰模型,同时给出了抗衰模型的免疫理论基础,为软件抗衰研究提供了一个崭新的研究方向;最后对软件抗衰未来的研究方向作出了一个简单的分析和预测.     

基于Copula函数的导弹多性能退化可靠性评估

针对导弹系统多性能退化中的各性能参数的关系问题,提出了一种评估导弹多性能退化可靠性的数学模型.根据多性能退化失效机理,建立了多性能退化可靠性模型,利用引入的Copula函数描述各性能之间的关系,建立了基于Copula函数的多性能退化可靠性评估模型,并通过实例仿真对导弹系统的可靠性进行了评估.结果表明:模型在保证准确可信的基础上,有效减小了计算量,为评估系统多性能退化可靠性模型研究提供了一种新方法,具有较好的推广性和实用性.     

基于特性方程的离心压气机的性能仿真

详细分析了空气在离心压气机中的流动机理,基于特性方程建立了一种能够达到设计精度要求的快速简单的离心压气机数学模型,模型中计及离心压气机内出现的各种损失。性能仿真模型具有速度快,适用于大量计算等优点。用Modelica语言和Dymola编译器实现了离心压气机的性能仿真。采用建立的数学模型对Chevis离心压气机的性能进行了模拟,并把仿真结果同实际性能曲线进行了比较。结果表明,采用建立的性能仿真数学模型能够模拟离心压气机性能,并能够实现非设计转速小流量工况下的性能仿真,为设计离心压气机提供了一个有力的工具,具有重要的参考价值。     

人—机工程系统CAD精度及计算机仿真置信度研究

提出了一个典型的人－机工程系统CAD精度及计算机仿真置信度实验研究模型,通过对同一数据的物理模型和计算机模型的测量数据和计算数据进行计算和分析,定量给出CAD精度和计算机仿真置信度,研究结果表明,对于由人控制、操作的机械系统,用CAD和计算机仿真代替实物模型的物理模型,既可以在制造之前进行工效预测,也可以对现有系统进行性能评估。     

基于标志点的InSAR系统仿真性能评估方法

系统仿真实验对于天基InSAR系统的总体设计和关键技术验证意义重大,性能评估是其中的关键环节之一。建立了由三大类共8项指标组成的InSAR系统性能指标体系,提出了基于标志点的InSAR系统仿真性能评估方法。该方法通过在仿真地面场景中合理布设标志点,并以标志点作为评估样本点来计算各项指标,可达到与理想干涉量评估方法相近的指标计算精度,同时避免了理想干涉量评估方法稳健性不足的问题,且计算效率更高。仿真实验结果验证了评估方法的有效性。     

使用混合模型预测Web服务器中的资源消耗

软件老化是一种在长期运行的软件系统中观察到的软件异常状态,如性能下降、暂停服务,甚至失效等现象。软件抗衰技术被用来处理软件老化带来的问题:停止软件应用、移除错误的因素、重新启动应用。对于软件老化和抗衰来说,如何准确地预测老化系统中的资源消耗并且找到一个合适的时机执行抗衰是一个关键的问题。针对该问题,提出一种混合模型方法用于资源消耗预测,并且提出 多门限值时间段抗衰算法用于抗衰时机的选择。实验结果表明,混合模型方法在资源消耗预测上要好于其他模型,并且提出的抗衰算法要好于单一的门限值算法。     

基于Dymola的航空发动机尾喷管建模与仿真

简要介绍了发动机尾喷管的数学模型,基于特性方程建立了一种能够达到设计精度要求的快速简单的尾喷管性能仿真模型。该模型具有速度快,适用于大量计算等优点。用Modelica语言和Dymola编译器实现了尾喷管的性能仿真。通过发动机系统级模型的仿真实验,验证了尾喷管模型的有效性。结果表明,采用建立的性能仿真数学模型能够模拟尾喷管性能,并能够实现非设计转速小流量工况下的性能仿真,为设计尾喷管提供了一个有力的工具。     

Rejuvenation effects on the grid environment performance with response time delays using Monte Carlo simulation

Grid computing is an evolutionary technological achievement that takes advantages of wide area communication and large scale resource sharing. Although there are several advantages, grid does not guaranty stableness of resources due to their resources’ nature, diverse failures and error conditions that may appear. Consequently, grid dependability issues arise. In this paper, a grid computing environment with star topology and direct access to resources is considered, which consists of a Resource Management System (RMS) and distributed Root Nodes (RNs). The distributed RNs are considered either as operational or as failed, though the RMS is susceptible to resource exhaustion, which can lead to software failures. The response waiting time from a distributed RN is also taken under consideration. A software rejuvenation to counteract RMS resource exhaustion is adopted, and its effect on grid environment performance is studied extensively. A non-Markovian approach is considered to model the system’s evolution in time and to evaluate the proposed performance measures. Due to the complicated structure of the system, analytic formulas for the proposed measures are not available, thus Monte Carlo simulation methods are employed.     

Autonomic resource contention‐aware scheduling

The complexity of computing systems introduces a few issues and challenges such as poor performance and high energy consumption. In this paper, we first define and model resource contention metric for high performance computing workloads as a performance metric in scheduling algorithms and systems at the highest level of resource management stack to address the main issues in computing systems. Second, we propose a novel autonomic resource contention‐aware scheduling approach architected on various layers of the resource management stack. We establish the relationship between distributed resource management layers in order to optimize resource contention metric. The simulation results confirm the novelty of our approach.Copyright © 2013 John Wiley & Sons, Ltd.     

Model of distributed computing system operation with time

A mathematical model of the operation dynamics of distributed computing systems is presented. This model covers operation of both hardware and software components. The model provides a theoretical basis for performance, reliability, and consistency analysis, checking the correctness of operation, designing computing system architecture.     

面向分布对象存储结构的高性能计算系统资源管理方法

当前的高性能计算系统的资源管理和调度关注的焦点是计算资源,然而随着高性能计算系统的规模增大和计算能力增强,其I/O瓶颈问题日益突出.由于高性能计算系统的存储结构多样性带来了存储资源管理分配的难题,在目前主流的资源管理系统中尚未有针对I/O存储资源的调度和管理.随着对象存储结构的发展和广泛使用,大多数主流高性能系统采用分布对象存储系统,研究对分布对象存储系统的管理并结合资源管理系统,实现面向存储的作业优化调度,对提升高性能计算系统的实际性能有重要意义.针对具有分布对象存储结构的高性能计算系统,研究面向分布存储的资源管理方法,在作业调度和资源分配时考虑不同应用的I/O需求,通过建立分布对象存储资源模型和应用程序I/O能力需求模型,并在资源调度和分配上根据不同的I/O应用级别,为作业分配合适的存储资源,设计并实现基于I/O能力分级的作业调度和资源分配算法.系统测试表明:该方法可以显著提高多作业环境下应用的性能,保证应用程序的性能稳定性,提高系统的吞吐率.     

Stochastic robustness metric and its use for static resource allocations

This research investigates the problem of robust static resource allocation for distributed computing systems operating under imposed Quality of Service (QoS) constraints. Often, such systems are expected to function in a physical environment replete with uncertainty, which causes the amount of processing required to fluctuate substantially over time. Determining a resource allocation that accounts for this uncertainty in a way that can provide a probabilistic guarantee that a given level of QoS is achieved is an important research problem. The stochastic robustness metric proposed in this research is based on a mathematical model where the relationship between uncertainty in system parameters and its impact on system performance are described stochastically.The utility of the established metric is then exploited in the design of optimization techniques based on greedy and iterative approaches that address the problem of resource allocation in a large class of distributed systems operating on periodically updated data sets. The performance results are presented for a simulated environment that replicates a heterogeneous cluster-based radar data processing center. A mathematical performance lower bound is presented for comparison analysis of the heuristic results. The lower bound is derived based on a relaxation of the Integer Linear Programming formulation for a given resource allocation problem.     

Hierarchical modeling of availability in distributed systems

Distributed computing systems are attractive due to the potential improvement in availability, fault-tolerance, performance, and resource sharing. Modeling and evaluation of such computing systems is an important step in the design process of distributed systems. We present a two-level hierarchical model to analyze the availability of distributed systems. At the higher level (user level), the availability of the tasks (processes) is analyzed using a graph-based approach. At the lower level (component level), detailed Markov models are developed to analyze the component availabilities. These models take into account the hardware/software failures, congestion and collisions in communication links, allocation of resources, and the redundancy level. A systematic approach is developed to apply the two-level hierarchical model to evaluate the availability of the processes and the services provided by a distributed computing environment. This approach is then applied to analyze some of the distributed processes of a real distributed system, Unified Workstation Environment (UWE), that is currently being implemented at AT&T Bell Laboratories     

Application of Relational Interval Arithmetic to Computer Performance Analysis: a Survey

This paper presents a survey of the existing work in the area of interval-based performance analysis of computing systems. Intervals in performance analysis is required when uncertainties or variabilities exist in the workload parameters for the performance model of the system. Intervals are also useful for computing upper and lower bounds on system performance. Most conventional analytic models accept a set of single valued parameters and produce a single valued model output. Adaptation of these existing models to handle interval parameters require new techniques that use interval arithmetic. Experiences with relational interval arithmetic provided by a constraint logic programming language in solving a number of performance analysis problems in conventional multiprogrammed computers as well as distributed processing systems are described.     

基于事件触发的网格资源监控研究

对于异构的高性能分布式计算环境——网格来说,监控其中每个计算节点获取资源的状态信息是至关重要的。然而传统的资源监控方式需要周期性地读取各个节点的信息,对网格系统资源浪费较大。本文提出一种基于事件触发的方法来降低监控服务开销,准确获取资源状态信息。然后采用该方法在Clobus Toolkit 4下实现网格资源监控系统,并对该系统做出客观评价。     

基于主动工作模式的分布式数据库服务器及其排队模型

由于单个服务器的分布计算环境在实用性和系统性能方面存在着明显的缺陷,所以通过高速网络连接的多服务器系统提供冗余服务已成为当今分布计算技术的研究热点。本文介绍了一种基于主动工作模式分布式数据库服务器的构成及运行模型,为其建立了排队模型,并与非主动模式的系统进行了比较,以性能价格比优略为依据对其冗余度进行了
了数学解析。     

“免疫软件人”概念及其协商控制模型

在研究生物免疫机理和软件人(SM)技术的基础上,将生物免疫特性融入SM技术中,提出了免疫软件人(ISM)的概念,设计了一种能够对动态网络环境进行实时监控和故障预警的多免疫软件人(MISM)联盟的协商控制模型;在对模型进行形式化描述的基础上,构造出一种新颖的ISM协商控制算法.以此构建的MISM联盟系统具有更强的灵活性、鲁棒性和局部更新能力,是一个适用于动态网络环境的自组织系统.