DoS攻击下网络化控制系统基于观测器的记忆型事件触发预测控制

本文研究了DoS攻击下网络化控制系统记忆型事件触发预测补偿控制问题. 首先, 由于网络带宽资源有限 和系统状态不完全可观测性, 引入了记忆型事件触发函数, 为观测器提供离散事件触发传输方案. 然后, 分析了网络 传输通道上发生的DoS攻击. 结合上述记忆型事件触发方案, 在控制节点设计一类新颖的预测控制算法, 节省网络 带宽资源并主动补偿DoS攻击. 同时, 建立了基于观测器的记忆型事件触发预测控制的闭环系统, 并且分析稳定性. 通过线性矩阵不等式(LMI)和Lyapunov稳定性理论, 建立了控制器、观测器和记忆型事件触发矩阵的联合设计方案, 并验证了该方案的可行性. 仿真结果表明, 该方案结合记忆型事件触发机制可以有效补偿DoS攻击, 节约网络带宽 资源.     

媒体服务器中保证服务质量的技术研究

在分析VOD系统的构成和工作过程的基础上,考虑到不同客户对视频服务质量的要求不一样,提出了一种能提供不同级别服务的VOD系统的实现方案。服务器端通过为不同的客户分配不同的带宽来提供不同的视频服务质量。本文详细阐述了使用准入控制、速率控制和差错控制如何保证不同客户的服务质量。     

Congestion prevention in broadband wireless access systems: An economic approach

While the demand for mobile broadband wireless services continues to increase, radio resources remain scarce. Even with the substantial increase in the supported bandwidth in the next generation broadband wireless access systems (BWASs), it is expected that these systems will severely suffer from congestion, due to the rapid increase in demand of bandwidth-intensive multimedia services. Without efficient bandwidth management and congestion control schemes, network operators may not be able to meet the increasing demand of users for multimedia services, and hence they may suffer an immense revenue loss. In this paper, we propose an admission-level bandwidth management scheme consisting of call admission control (CAC) and dynamic pricing. The main aim of our proposed scheme is to provide monetary incentives to users to use the wireless resources efficiently and rationally, hence, allowing efficient bandwidth management at the admission level. By dynamically determining the prices of units of bandwidth, the proposed scheme can guarantee that the number of connection requests to the system are less than or equal to certain optimal values computed dynamically, hence, ensuring a congestion-free system. The proposed scheme is general and can accommodate different objective functions for the admission control as well as different pricing functions. Comprehensive simulation results with accurate and inaccurate demand modeling are provided to show the effectiveness and strengths of our proposed approach.     

一种基于度量的Web服务质量机制

提出了一种简单、准确和高效的带宽调节算法,该算法对每一个服务请求设置一个带宽标准,同时根据对服务请求的分类和Web服务器系统的有效带宽,来分配及调节每一个服务请求的实际带宽,构成一种基于度量的Web服务质量机制,使Web服务器系统能为不同类型的客户请求提供有区分的和有服务质量的Web服务。     

Performance evaluation for VBR Continuous Media File Server admission control

A file server for continuous media must provide resource guarantees and only admit requests that do not violate the resource availability. This paper addresses the admission performance of a server that explicitly considers the variable bit rate nature of the continuous media streams. A prototype version of the server has been implemented and evaluated in several heterogeneous environments. The two system resources for which admission control is evaluated are the disk bandwidth and the network bandwidth. Performance results from both measurement and simulation are shown with respect to different admission methods and varying scenarios of stream delivery patterns. We show that the vbrSim algorithm developed specifically for the server outperforms the other options for disk admission especially with request patterns that have staggered arrivals, while the network admission control algorithm is able to utilize a large percentage of the network bandwidth available. We also show the interactions between the limits of these two resources and how a system can be configured without wasted capacity on either one of the resources. Copyright © 2004 John Wiley & Sons, Ltd.     

基于4G-LTE的单中心无线通信扫雷车系统设计

目前常用的无线通信技术无法满足扫雷车需要的高带宽、低时延、大传输距离、可调度等技术指标的问题,研究无线通信技术、CAN-NET转换技术等内容,重点突破4G-LTE等关键技术,实现无人扫雷车的控制系统,同时也为其他无人控制平台使用4G-LTE技术提供技术储备。     

基于QoS的分布式接纳控制算法

随着人们对移动自组网(ad hoc网络)研究的深入,服务质量(QoS)已经成为了当前的研究热点之一.为了在ad hoc特殊的网络中提供对QoS的支持,必须设计一种针对流的高效的接纳控制算法.通过分析无线信道的特点,提出了估算本地可用带宽和流可用带宽的方法,同时对流的带宽耗费进行了推导,解决了实现接纳控制必须解决的关键问题,提出了一种基于QoS的分布式接纳控制算法.仿真实验证明,接纳控制算法应用到传统的路由协议(比如AODV)中,性能将会大大提高,并且更适合于实时业务的传输.     

Advanced multicast class-based bandwidth over-provisioning

Dynamic bandwidth aggregate over-provisioning has been proposed to provide differentiated services with scalable Quality of Service (QoS) control. Previous research showed that efficient over-reservation control allows minimizing QoS control overhead with reduced waste of bandwidth and blocking probability. However, existing over-reservation centric solutions are still inefficient in the face of network dynamics, as they are not able to accommodate the dynamic service demands, thus failing to optimize the bandwidth usage. This paper proposes a new Advanced Class-based resource Over-Reservation (ACOR) solution for multicast sessions, which seeks increased network resources utilization while minimizing QoS control overhead. More specifically, ACOR is able to dynamically update the share of bandwidth between different classes of service, providing improved results with less complexity than current solutions. Our analytical and simulation results prove the cost-effective and scalable QoS control capabilities of ACOR in decentralized networks with multiple distributed ingress routers coordinating the QoS control.     

基于流量控制的Docker容器网络带宽控制机制

针对Docker容器缺乏对网络带宽资源进行限制的能力的问题,提出了一种基于流量控制（TC）的Docker容器网络带宽控制机制。首先,基于CGroups文件系统的实时监测机制,利用Linux内核的虚拟文件系统（VFS）作为媒介,将Docker容器创建时设置的网络控制参数传递给Linux内核流量控制器TC;然后,通过引入IFB模块实现上下行带宽控制,并使用rate、ceil及prio参数进行空闲带宽共享及容器优先级控制;最后,控制TC执行具体的网络限制,以实现容器之间灵活的网络资源控制。实验结果表明,该机制在容器独占带宽场景下可有效地将实际容器带宽限制在2%的波动范围内,而在共享空闲带宽场景下可在平均误差0.5%的范围内精准限制容器带宽,同时该机制能够基于优先级弹性地管理资源。该机制具有提供更为原生的接口且无需额外工具配合的优势,可为基于Docker的云平台的细粒度弹性网络资源控制提供便捷有效的解决思路。     

一种基于TCPW的流媒体端到端拥塞控制方法

由于网络的时变性和异构性,流媒体系统往往不能很好地适应网络带宽的变化。为此,结合Darwin streaming server(DSS)的源代码对其拥塞控制方法进行分析,同时运用TCP Westwood(TCPW)的带宽估计算法来改进DSS的拥塞控制策略,并搭建了实际的视频流传输系统对该策略进行验证。实验结果表明,改进后的拥塞控制策略不仅能有效地提高接收端的视频质量,而且带宽利用率也有明显的提高。     

Integrated design of the feedback controller and topography estimator for atomic force microscopy

In atomic force microscopy (AFM) the force between the measurement tip and the sample is controlled in a feedback loop to prevent damage of the tip and sample during imaging, and to convert the measurement of the tip–sample force into an estimate of the sample topography. Dynamical uncertainties of the system limit the achievable control bandwidth and the accuracy of the topography estimation. This paper presents an integrated approach to design a feedback controller and topography estimator, taking into account the dynamical uncertainties of the system. The proposed methodology is experimentally demonstrated on a commercial AFM system, showing a direct trade-off between the control bandwidth and the accuracy of the topography estimation.     

宽带高精度鲁棒自适应位置跟踪系统研究

设计一宽带高精度鲁棒自适应位置跟踪系统，位置环采用二阶模型参考自适应控制，速度环采用一阶ＭＲＡＣ。采用可编程数字信号处理器ＴＭＳ３２０Ｃ２５作为控制器，实时实现了该系统。     

Adaptive explicit congestion control based on bandwidth estimation for high bandwidth-delay product networks

Existing congestion control protocols for high bandwidth-delay product (HBDP) networks either suffer from efficiency degradation caused by insufficient feedback of the network state, or are difficult to deploy in real networks because they require modification in IP header to provide enough feedback information. Based on VCP, this paper proposes the VCP-BE protocol that can provide more accurate network state information by estimating available bandwidth for sender with an adaptive bandwidth estimator. The estimator can dynamically adjust its parameters (e.g., observing interval) to achieve different accuracy and responsiveness to adapt to the network state indicated by two ECN bits, without no more modification in IP header than VCP. Furthermore, when the network load is high, VCP-BE calculates the ratio of current throughput to the available bandwidth to judge if network is close to the overload state. With these fine-grained network state estimation, VCP-BE can adjust the congestion window more precisely than VCP, thus greatly improves its convergence speed of achieving high bandwidth utilization and fairness. Simulation results show that VCP-BE also outperforms MLCP, which uses seven bits for explicit feedback while VCP-BE only uses two ECN bits.     

Dynamic Frame Dropping for Bandwidth Control in MPEG Streaming System

In a network environment where the available bandwidth changes dynamically, it is desirable for a streaming system to control the media quality in an adaptive way according to the dynamics of underlying network resource. This paper presents the implementation of a real-time MPEG filtering system which uses the concept of dynamic frame-drop. The filtering system drops video frames in a controlled way and reconstructs a valid MPEG system stream in real-time. The system consists of a sequence of filtering modules and each module is carefully designed to maintain the synchronization characteristics of real-time streaming. A special effort is given to the correct implementation of video and audio synchronization after frame-drop. The experiments show that the implemented system produces a valid MPEG system stream after filtering as well as the media bandwidth of a filtered stream is dynamically controlled by a given frame-drop policy.     

曙光超级服务器上DMPI和DPVM的设计

介绍了运行于曙光超级服务器上的DMPI和DPVM的设计与实现。DMPI支持RMA和动态进程管理的功能。DMPI和DPVM在对ADI层进行灵活有效的扩展(DADI-E)的基础上提供了一个高性能的通信层。该文对DADI-E的特点进行了阐述,包括RMA机制、动态进程管理和对PVM的支持。而且,DMPI还提供了一个特殊的数据通路———流水发送,它可以改善DMPI的带宽,使之接近于底层通信协议的带宽峰值。最后还给出了DMPI和DPVM在Myinet卡上的性能指标。     

输入饱和及带宽限制下高超飞行器的闭环稳定边界研究

针对于吸气式高超声速飞行器开环不稳定的动力学特性,研究了控制信号存在饱和约束及带宽限制条件下的闭环稳定边界.首先,简要介绍了吸气式高超声速飞行器的建模方法与动力学特性的主要问题.考虑到飞行器控制信号的幅值限制及带宽约束,综合高超声速飞行器的开环不稳定特性,定量地分析了系统的闭环稳定边界:与系统不稳定极点的位置,其对应的左特征向量及控制信号的幅值约束有关;执行器的带宽限制在此基础上进一步缩小了反馈控制系统的稳定边界.根据高超声速飞行器短周期不稳定特性,解析地给出了闭环稳定边界的计算公式.采用蒙特卡洛分析方法对闭环系统的稳定边界及滑模变结构控制器作用下的稳定区域进行验证.仿真结果与理论分析具有一致性,验证了系统开环特性对于闭环稳定性的限制及控制信号带宽约束对稳定性的影响.     

低带宽分布式虚拟环境中的预测技术

在分布式虚拟环境（DistributeVirtualEnvironment，DVE）中，带宽是影响系统性能和规模的一个重要因素。对系统动态场景中的运动物体使用现代控制论中的最优预测技术，使网络访问的次数可以减少，从而降低了整个分布式系统的网络带宽。还给出了场景中一个使用该预测算法的对象的定量测试数据，以此说明预测算法是有效的。     

Return difference bode diagram for optimal system design

This paper is concerned with a graphical method for the determination of bandwidth and optimal feedback gains for linear systems employing a quadratic form performing index. Using a fundamental frequency-domain condition of optimality developed by R. E. Kalman [1], the gain and bandwidth estimates are found from a logarithmic amplitude vs. frequency plot of the optimal system return difference. The method can be extended to systems with multiple outputs. An attempt is made to provide some insight into the connection between classical and optimal design, and into the price of optimality in terms of bandwidth.     

An end-to-end QoS framework with on-demand bandwidth reconfiguration

This paper proposes a new QoS framework, called the On-Demand QoS Path framework (ODP). It provides end-to-end QoS guarantees to individual flows with minimal overhead, while keeping the scalability characteristic of DiffServ. ODP exercises per-flow admission control and end-to-end bandwidth reservation at the edge of the network and only differentiates service types in the core of the network. In addition, to adapt to dynamically changing traffic load, ODP monitors the bandwidth utilization of the network and performs dynamic bandwidth reconfiguration in the network core based on the monitored bandwidth utilization. Through extensive simulations, the performance of ODP is investigated and compared with that of IntServ and DiffServ frameworks. The simulation results clearly showed that ODP provides end-to-end QoS guarantees to individual flows, which DiffServ can not provide, with much less overhead than IntServ.     

基于PSTN传输信道的视频编码器码率控制

码率控制是在低带宽信道上传输低延迟、高质量视频的关键技术之一．根据基于PSTN信道的远程视频监控应用需求，提出一种甚低码率控制策略，通过为视频编码器增加Ⅰ帧码率控制，改进P帧的位率控制算法，以及引入二阶率失真模型，较好地解决了甚低带宽下视频编码器的码率控制问题．实验结果表明，算法降低了编码缓冲区延迟同时提高了重建图像的质量。