云环境中基于LVS集群的负载均衡算法

为了解决传统负载均衡技术应用到云计算环境中引发的新问题,提出一种云环境下基于LVS集群分组负载均衡算法。该算法首先根据硬件性能计算各节点的权值,将性能相同(或近似相同)的服务器分为一组,每组节点数量相等(或近似相等),负载均衡器定期地收集各节点CPU、内存、I/O、网络利用率以及响应时间,动态改变节点的权值,使用改进算法选择该组内最佳节点,并计算节点的综合负载和组负载。最后再次使用改进算法由组负载均衡器选择集群最佳节点,并进行任务请求的合理分配,从而解决因并发量过大而引起的时延等问题。实验结果表明,与加权轮询算法(WRR)和加权最少连接算法(WLC)相比,本算法能够在并发量较大的情况下维持较短的响应时间和较高的吞吐率,使集群负载更加均衡。     

虚拟环境下Web服务动态负载均衡策略改进

为了提高Web服务集群的伸缩性和自动化能力,从虚拟化和负载均衡两方面研究集群系统,对现有负载采集策略做了改进,设计并实现了一种可根据负载值自动控制集群规模的模型XCluster。新模型运行在Xen提供的虚拟化环境中,实时监视宿主机层和虚拟机层的负载状态,随着集群系统总负载的增长,逐渐引入新的虚拟机来扩大集群规模,同时将任务合理分配到各个虚拟机节点上;当总负载下降时,逐渐关闭虚拟机缩小集群规模,释放出来的硬件资源又可以提供给其他集群系统使用。理论分析和实验结果表明,XCluster只需占用很少的网络通信量完成信息收集和命令下达,能够充分利用虚拟机易于管理的优势完成后端节点的调度,并且在任务总量相同的情况下,使用尽可能少的集群节点来执行任务。     

Utilizing linguistically enhanced keystroke dynamics to predict typist cognition and demographics

Entering information on a computer keyboard is a ubiquitous mode of expression and communication. We investigate whether typing behavior is connected to two factors: the cognitive demands of a given task and the demographic features of the typist. We utilize features based on keystroke dynamics, stylometry, and “language production”, which are novel hybrid features that capture the dynamics of a typists linguistic choices. Our study takes advantage of a large data set (~350 subjects) made up of relatively short samples (~450 characters) of free text. Experiments show that these features can recognize the cognitive demands of task that an unseen typist is engaged in, and can classify his or her demographics with better than chance accuracy. We correctly distinguish High vs. Low cognitively demanding tasks with accuracy up to 72.39%. Detection of non-native speakers of English is achieved with F₁=0.462 over a baseline of 0.166, while detection of female typists reaches F₁=0.524 over a baseline of 0.442. Recognition of left-handed typists achieves F₁=0.223 over a baseline of 0.100. Further analyses reveal that novel relationships exist between language production as manifested through typing behavior, and both cognitive and demographic factors.     

基于磁耦合谐振的无线电能传输系统负载特性研究

为研究负载对无线电能传输系统传输性能的影响,建立了基于磁耦合谐振的无线电能传输系统的电路模型,利用电路耦合理论推导出在不同距离上为抑制频率分裂现象所需的最小负载以及当接收功率最大时的最佳匹配负载计算模型,且最佳匹配负载总是大于最小负载。仿真结果表明,对于不同的耦合系数,增大负载可以抑制频率分裂现象的出现;当接收功率达到最大值时,最佳匹配负载会因耦合系数的不同而改变,且总会有一个最佳匹配负载与之对应。这一结论为无线电能传输系统的负载选择提供了理论指导。     

基于改进粒子群优化算法的火电厂机组负荷分配

以坑口电厂厂级监控信息系统的机组负荷在线优化分配功能模块为应用背景,针对模块所运用的基本粒子群优化算法在优化过程中容易陷入局部收敛、收敛速度慢的缺点,提出一种基于惯性权重非线性减小策略的改进粒子群优化算法,使惯性权重呈对数减小;测试函数仿真结果表明,改进粒子群优化算法在收敛速度和寻优精度方面,优化性能均优于基本粒子群优化算法;通过MATLAB与Visual C++混合编程,开发了机组负荷在线优化分配功能模块,提高了算法的计算效率和工程应用价值。     

海量数据处理器MPC860T的DSP阵列设计

现代通信的数据量日益增加,数据处理的复杂度也日益加强,如何有效处理这些海量数据,是目前研究的难点,基于DSP阵列的数据处理系统是解决这些问题的有效方法。本文选用TI公司的TMS320C6713浮点型数字信号处理器以及Freescale公司的MPC860T通用通信处理器,设计了16颗浮点型DSP阵列来完成海量数据实时处理。详细介绍了该系统的DSP阵列的管理,包括复位、HPI数据管理通道设计。通过测试和实际应用验证,该系统不仅满足性能上的要求,还是一个通用的数据采集和处理平台。     

Distributed load-balancing algorithm for fast tag reading

The radio frequency identification (RFID) technology has gained a lot of recent interests because it has been widely recognised as a foundation technology for the ‘Internet of things’. In current multi-reader RFID systems, readers work with fairly less cooperation and are responsible to retrieve data from different number of tags individually, which results in large reading time of obtaining all tag data. In this paper, a fast tag reading problem in multi-reader RFID systems with the goal of obtaining all tag data by using minimum reading time is studied. A distributed load-balancing algorithm based on diffusion method is proposed to solve the problem by migrating tags from highly loaded reader to lightly loaded reader. The simulation results demonstrate the effectiveness and efficiency of proposed algorithm.     

Assessment of Numerical Models for Live Load Distribution in a Road Slab Bridge

This paper presents comparison of numerical models used in an analysis of a road bridge deck. The models were adapted for computing the live load distribution coefficients in composite concrete bridge deck. The load distribution method was chosen for assessment of the usability of different numerical model in slab bridge deck analysis. The goal of the study is to determine a simplest but still accurate numerical model to estimate live load effects on composite slab bridge. In the analysis, the well-established grillage approach was adapted for representation of the bridge deck as a basic model as well as more sophisticated three-dimensional models which was supposed to better represent the real behavior of the deck under concentrated wheel loads. The bridge deck was effectively modeled using beam and shell elements. The grillage method compares well with the finite-element method. This finding is allowed to establish simplification in numerical modeling of slab bridge decks for live load effect computations.     

电液负载模拟器的二次型最优控制算法

电液负载模拟器属于被动式加载系统,受载对象的自主运动和加载装置的运动相互耦合,所产生的位置扰动会引起多余力。为抑制多余力建立了电液负载模拟器的状态空间模型,利用线性二次型最优控制理论设计了最优控制算法,算法具有最优状态反馈、最优前馈补偿和外扰补偿,使得电液负载模拟器的性能有明显提高。电液负载模拟器的仿真计算结果表明,利用最优控制算法设计的电液负载模拟器较好地抑制了多余力,从而较好地跟踪力指令。