基于收发平衡判定的TCP流量回放方法

基于真实网络流量的互动式回放测试是当前针对防火墙、IPS等串接型安全设备进行测评的最新方法.文中在分析现有基于状态判定的TCP流量互动式回放方法基础之上,引入收发平衡机制,提出了一种基于收发平衡和状态判定相结合的新的TCP流量回放方法.通过在发送TCP数据包前优先进行收发平衡判定将数据包发送出去,提出的方法能够有效减少TCP流量在发送过程中的状态判定开销,提高回放性能.对引入收发平衡机制前后的TCP流量回放方法的差异进行了分析比较.从单个TCP会话特性、并发会话流量特性、网络传输延迟与丢包等角度分析验证了影响引入收发平衡机制后的算法有效性的因素.实际流量实验表明,文中所提方法在回放TCP流量时性能有显著提升,适用于在更大规模的流量环境下对防火墙、IPS等串接型网络安全设备进行测评.     

非线性系统的多神经网络自学习控制

本文提出了一种未知非线性动力学系统的多网络自学习控制方法。通过对系统的神经元网络辨识器和神经元网络控制器的有机结合，发展了基于逆动力学辨识器的控制网络广义Ｄｅｌｔａ学习规则，从而使得整个控制系统具有很强的自、自学习能力。文中最后通过对系统进行的仿真研究证实了这种控制结构的有效性，仿真例子说明经过１００个周期学习后，其系统的跟踪误差控制在１％以内。     

一种面向云计算的网络异常流量分组方法

针对云计算下大量用户环境下网络异常流量分组管理问题进行研究,提出一种面向云计算的网络流量分组方法.该方法采用BIRCH算法对云计算产生的大量网络数据进行初次聚类,然后根据初次分类的统计特征进行分组融合,从而得到对网络流量的最终分类结果.实验通过一个具有突发异常流量的仿真场景,从分组效果和基于该分组的流量管理两个角度进行验证.实验结果证明,基于该方法能有效对异常用户进行分组,并且在有效阻断异常流量的同时能极大地减少对正常流量的影响.     

基于数据ADP算法的一类带有执行器饱和的未知离散时间系统最优跟踪控制

针对一类带有执行器饱和的未知动态离散时间非线性系统, 提出了一种新的最优跟踪控制方案. 该方案基于迭代自适应动态规划算法, 为了实现最优控制, 首先建立了未知系统动态的数据辨识器. 通过引入M网络, 获得了稳态控制的精确表达式. 为了消除执行器饱和的影响, 提出了一个非二次的性能指标函数. 然后提出了一种迭代自适应动态规划算法获得最优跟踪控制的解, 并给出了收敛性分析. 为了实现最优控制方案, 神经网络被用来构建数据辨识器、计算性能指标函数、近似最优控制策略和求解稳态控制. 仿真结果验证了本文所提出的最优跟踪控制方法的有效性.     

基于流量约简的网络模拟方法

在大规模网络模拟中,由于网络流量较大导致网络模拟的性能大幅度降低。针对该问题,提出一种对网络端点流量进行缩减的网络模拟方法。该方法通过对原始网络模拟场景中的网络流量、路由器队列长度等网络模拟动态参数进行协同约简,降低模拟的计算开销,通过对约简后的网络模拟结果进行拓展,还原出原始网络模拟场景的真实结果。实验结果表明,流量约简后网络瞬时流量以及路由瞬时队列长度等网络参数有较高的可信度,而且模拟开销也大幅降低。     

采样非线性系统的神经网络稳定自适应控制

针对一类动力学未知或难以建模的采样非线性系统,提出了一种基于神经网络的跟随控 制器稳定自适应控制方法.控制器采用径向基函数神经网络近似对象的动力学非线性,神经 网络参数的自适应规律由稳定理论得到.文中给出了系统稳定性和跟随误差收敛性的证明, 并通过仿真实例揭示了所提方法的性能.     

基于SharpPcap的网络流量监控系统

为了在局域网中能够实时监视网络流量,并对流量进行分析和控制,提出了一个基于SharpPcap框架的局域网流量监控系统(SPCatcher).通过对网络流量监视、流量分析、流量控制等子模块进行需求分析,设计了流量监控系统的框架模型,并给出了根据数据传输方向和指令响应顺序进行划分和组合的功能实现图.通过SPCatcher系统捕获网络流量并进行分析,找出网络性能降低的源头,进而可对存在滥用网络带宽行为的特定客户端进行流量控制.实现了软件系统,测试结果验证了SPCatcher系统的流量监控功能的有效性.     

基于Netfilter的流量检测与控制系统

P2P流量已成为互联网流量的重要组成部分,由于其占用大量带宽,严重影响了其他网络业务的运行,因此如何有效地检测和控制网络流量已成为目前面临的一个重要难题。基于Linux的Netfilter防火墙和连接跟踪机制,结合应用层协议识别工具L7-filter和流量控制器TC设计并实现了一个简单而高效的流量控制系统。该系统首先对数据包进行应用层协议识别并分类,然后对有限的网络带宽进行合理分配,实现流量控制。实验证明此系统能有效地检测和控制网络流量。     

基于等价输入干扰补偿的改进型重复控制系统参数优化设计

针对一类同时具有周期性参考输入和非周期扰动的伺服系统,提出基于等价输入干扰补偿的改进型重复控制系统参数优化设计方法,实现对非周期扰动的有效抑制和周期性参考输入的高精度跟踪控制.首先,利用全维状态观测器的估计误差构造等价输入干扰估计器,通过将等价输入干扰估计值反馈到控制输入端,建立基于等价输入干扰补偿的复合重复控制规律.然后,基于小增益定理推导出系统的稳定性条件,引入一个对系统抗扰性能、跟踪性能和收敛速度进行整体评价的性能目标函数,建立系统参数优化模型,采用粒子群优化算法,实现对系统重复控制器参数、等价输入干扰估计器参数和状态反馈控制器参数的同时优化.最后,通过数值仿真分析对比说明所提方法的有效性和优越性.     

基于事件触发的离散 MIMO 系统自适应评判容错控制

本文针对具有执行器故障的一类离散非线性多输入多输出(Multi-input multi-output, MIMO)系统, 提出了一种基于事件触发的自适应评判容错控制方案. 该控制方案包括评价和执行网络. 在评价网络里, 为了缓解现有的非光滑二值效用函数可能引起的执行网络跳变问题, 利用高斯函数构建了一个光滑的效用函数, 并采用评价网络近似最优性能指标函数. 在执行网络里, 通过变量替换将系统状态的将来信息转化成关于系统当前状态的函数, 并结合事件触发机制设计了最优跟踪控制器. 该控制器引入了动态补偿项, 不仅能够抑制执行器故障对系统性能的影响, 而且能够改善系统的控制性能. 稳定性分析表明所有信号最终一致有界且跟踪误差收敛于原点的有界小邻域内. 数值系统和实际系统的仿真结果验证了该方案的有效性.     

Real-time volume control for interactive network traffic replay

Interactive network traffic replay is a new traffic generation tool very useful for testing in-line networking devices. It provides both a realism of traffic contents and a realism of traffic behaviors. But the lack of effective mechanisms to control important features of the generated traffic severely limits its capability of performing accurate, systematic and in-depth testing. This paper aims to improve controllability in interactive network traffic replay by studying the problem of controlling volume of the generated traffic. Due to complex traffic generation mechanism, controlling traffic volume in interactive network traffic replay is an interesting and challenging new problem.In this paper, we formulate the volume control task as a dynamic target tracking problem and analyze the influencing factors and basic control properties of the system. We propose two approaches, from both model-based and model-free perspectives, for solving the problem. The model-based approach relies on a probabilistic model that explores packets processing mechanism and converts the problem to a state prediction problem, while the adaptive optimal control approach uses process input/output information to regulate the system and converts the problem to a parameter estimation problem. Both of the two methods are validated via extensive experimental studies with real-world traces. Results indicate that our methods can track target output traffic volume effectively under a wide range of network conditions.     

MPC for tracking zone regions

This paper deals with the problem of tracking target sets using a model predictive control (MPC) law. Some MPC applications require a control strategy in which some system outputs are controlled within specified ranges or zones (zone control), while some other variables – possibly including input variables - are steered to fixed target or set-point. In real applications, this problem is often overcome by including and excluding an appropriate penalization for the output errors in the control cost function. In this way, throughout the continuous operation of the process, the control system keeps switching from one controller to another, and even if a stabilizing control law is developed for each of the control configurations, switching among stable controllers not necessarily produces a stable closed loop system. From a theoretical point of view, the control objective of this kind of problem can be seen as a target set (in the output space) instead of a target point, since inside the zones there are no preferences between one point or another. In this work, a stable MPC formulation for constrained linear systems, with several practical properties is developed for this scenario. The concept of distance from a point to a set is exploited to propose an additional cost term, which ensures both, recursive feasibility and local optimality. The performance of the proposed strategy is illustrated by simulation of an ill-conditioned distillation column.     

Adaptive Statistic Tracking Control Based on Two-Step Neural Networks With Time Delays

This paper presents a new type of control framework for dynamical stochastic systems, called statistic tracking control (STC). The system considered is general and non-Gaussian and the tracking objective is the statistical information of a given target probability density function (pdf), rather than a deterministic signal. The control aims at making the statistical information of the output pdfs to follow those of a target pdf. For such a control framework, a variable structure adaptive tracking control strategy is first established using two-step neural network models. Following the B-spline neural network approximation to the integrated performance function, the concerned problem is transferred into the tracking of given weights. The dynamic neural network (DNN) is employed to identify the unknown nonlinear dynamics between the control input and the weights related to the integrated function. To achieve the required control objective, an adaptive controller based on the proposed DNN is developed so as to track a reference trajectory. Stability analysis for both the identification and tracking errors is developed via the use of Lyapunov stability criterion. Simulations are given to demonstrate the efficiency of the proposed approach.      

基于信息融合估计的离散系统最优跟踪控制

针对期望输出和未来干扰无预见的离散线性系统最优跟踪问题,提出一种基于信息融合最优估计的控制方法.若将当前给定值和可测干扰值分别看作系统未来输出和干扰的预见值,则跟踪控制问题可转化为具有无限预见步数的预见控制问题,并将无限预见信息融合成一步等效预见信息,进而获得近似最优融合控制律.对线性直流电机系统和宏观经济系统的仿真结果均验证了该控制器在提高系统跟踪精度和抑制干扰等方面的有效性.     

Semi‐Global Output Feedback Tracking to Reference System with Input for a Benchmark Nonlinear System

In this paper, we solve the output feedback semi‐global tracking problem of the nonlinear benchmark RTAC system, in which the reference signals are output trajectories of a simple control systems subject to some input. The introduction of the input enlarges the class of the reference signals that can be tracked. And the proposed solution covers the previous results of output feedback global tracking, namely the solution is still global when the input is zero. Finally, a simulation illustrates the effectiveness of our approach.     

Optimal control on special Euclidean group via natural gradient algorithm欧几里德群的最优控制问题

Considering the optimal control problem about the control system of the special Euclidean group whose output only depends on its input is meaningful in practical applications. The optimal control considered here is described as the output matrix is as close as possible to the target matrix by adjusting the system input. The geodesic distance is adopted as the measure of the difference between the output matrix and the target matrix, and the trajectory of the control input obtained in the process is achieved. Furthermore, some numerical simulations are shown to illustrate our outcomes based on the natural gradient descent algorithm for optimizing the control system of the special Euclidean group.     

网络化系统周期信号的跟踪

研究线性时不变、单变量、离散网络化系统对周期信号的跟踪问题.与现有文献考虑的参考输入信号大都为常见的能量信号所不同的是,本文参考输入信号是离散时间周期方波功率信号.相应地,研究系统对基于功率谱的参考输入信号功率的响应,系统的跟踪性能通过输入信号与受控对象输出之差的功率来衡量,而最优跟踪性能采用跟踪误差的平均功率来度量.考虑的网络化控制系统仅上行通道存在丢包误差的影响,把丢包过程看作两个信号的合成,一是确定性信号,二是随机过程,进而丢包误差描述为源信号和白噪声之间乘积.根据被控对象和随机过程的性质,采用Parseval等式、维纳–辛钦定理和范数矩阵理论得到该系统跟踪性能极限的下界表达式.仿真结果表明,所设计的控制器能实现对周期信号的有效跟踪,进而验证了结论的正确性.     

Adaptive Fault‐Tolerant Control of Uncertain MIMO Systems with Reduced Requirement on Desired Trajectory Under Unknown Control Direction

This paper aims at investigating the tracking control problem for a class of multi‐input multi‐output (MIMO) nonlinear systems with non‐square control gain matrix subject to unknown control direction and uncertain desired trajectory. By using the artificial neural network (NN) reconstructs the target trajectory with actual disguised trajectory, we are able to design a practical and stable tracking control scheme without the need for the unavailable desired trajectory. Nussbaum‐type function is incorporated in the control law to handle the unknown control direction. The remarkable feature of the proposed scheme is that it is robust against modeling uncertainties and tolerant to actuation faults, yet guarantees that the closed‐loop system is stable in the sense of ultimately uniformly bounded (UUB). The effectiveness of the proposed control schemes are illustrated through simulation results.     

输入输出受限船舶的轨迹跟踪自适应递归滑模控制

针对输入输出受限, 模型部分不确定和受到未知海洋干扰的全驱动船舶的轨迹跟踪问题, 提出一种基于时 变非对称障碍李雅普诺夫函数的最小参数自适应递归滑模控制策略. 该策略首先设计障碍李雅普诺夫函数约束船 舶轨迹在有限区域内, 利用最小参数法神经网络逼近模型不确定项, 降低系统的计算复杂度, 然后采用指令滤波器 对输入信号进行幅值约束, 同时避免对因反步法导致的微分爆炸问题, 综合考虑船舶位置以及速度误差间的关系设 计递归滑模控制律, 提高系统的鲁棒性, 采用双曲正切函数和Nussbaum函数补偿由输入饱和引起的非线性项, 提高 系统稳定性. 最后通过Lyapunov理论分析证明了全驱动船舶闭环系统中所有信号是一致最终有界的. 仿真结果表 明, 本文所设计的船舶轨迹跟踪控制方案能有效处理船舶模型不确定部分以及未知外界干扰的问题, 能够实现船舶 在输入受限的情况下在有限区域内航行并准确的跟踪期望轨迹, 具有较强的鲁棒性.     

基于粗集理论和支持向量机的道路网短时交通流量预测*

为了解决城市交通流量预测问题,研究道路网中多断面同时作用的情况,先将各断面交通流时间序列在相空间中重构,以充分提取交通流中的相关信息,然后应用粗集理论的强定性分析能力对输入信息进行约简,消除了样本中的噪声和冗余。在此基础上,再利用支持向量机对约简信息进行预测。为了获得最优的预测精度,该方法还利用遗传算法对预测进行了优化。实例研究表明,该方法的预测效果令人满意,在交通控制领域具有较大的应用潜力。