ATM 网络预测拥塞控制器设计

网络传输中存在严重的不确定性，由此限制了常规反馈拥塞控制算法的应用．利用预测控制方法，设计出一种改进的拥塞控制算法，增强了闭环系统的鲁棒性和稳定性，实现了带宽分配的公平性．仿真结果证实了所提出方法是有效性的。     

A neural-fuzzy system for congestion control in ATM networks

We propose the use of a neural-fuzzy scheme for rate-based feedback congestion control in asynchronous transfer mode (ATM) networks. Available bit rate (ABR) traffic is not guaranteed quality of service (QoS) in the setup connection, and it can dynamically share the available bandwidth. Therefore, congestion can be controlled by regulating the source rate, to a certain degree, according to the current traffic flow. Traditional methods perform congestion control by monitoring the queue length. The source rate is decreased by a fixed rate when the queue length is greater than a prespecified threshold. However, it is difficult to get a suitable rate according to the degree of traffic congestion. We employ a neural-fuzzy mechanism to control the source rate. Through learning, membership values can be generated and cell loss can be predicted from the status of the queue length. Then, an explicit rate is calculated and the source rate is controlled appropriately. Simulation results have shown that our method is effective compared with traditional methods.     

A practical controller for explicit rate congestion control

This paper examines congestion control for explicit rate data networks. The available bit rate (ABR) service category of asynchronous transfer mode (ATM) networks serves as an example system, however, the results of this paper are applicable to other explicit rate systems as well. After a plant model is established, an adaptive control strategy is presented. Several algorithm enhancements are then introduced. These enhancements reduce convergence time, improve queue depth management, and reduce parameter bias. This work differentiates itself from the other contributions in the area of rate-based congestion control in its balanced approach of retaining enough complexity as to afford attractive performance properties, but not so much complexity as to make implementation prohibitively expensive     

ATM communications network control by neural networks

A learning method that uses neural networks for service quality control in the asynchronous transfer mode (ATM) communications network is described. Because the precise characteristics of the source traffic are not known and the service quality requirements change over time, building an efficient network controller which can control the network traffic is a difficult task. The proposed ATM network controller uses backpropagation neural networks for learning the relations between the offered traffic and service quality. The neural network is adaptive and easy to implement. A training data selection method called the leaky pattern table method is proposed to learn precise relations. The performance of the proposed controller is evaluated by simulation of basic call admission models.     

A cell spacing device for congestion control in ATM networks

In this paper, we study a cell spacing method of congestion control in ATM networks. The idea is to smooth the input flows at the access nodes in order to prevent cells from entering the network in a manner that could affect its performance. We consider a queueing system that prevents any two successive cells from being transmitted within a time shorter than a variable value. This device does not interfere with cells that find the queue empty and arrive a sufficiently long time after the last departure but spaces apart those which arrive too closely to each other. We analyze the statistical properties of the output traffic of such a cell spacer when the input process is modeled as a Compound-MMPP.     

A neural network controller for flexible-link robots

The object in this paper is to achieve tracking control of a partially unknown flexible-link robot arm. It is shown how to stabilize the internal dynamics by selecting a physically meaningful modified performance output for tracking; this output is the slow portion of the link-tip motions. That is, the tracking requirement is relaxed so that the internal dynamics are controllable through a boundary layer correction. The controller is composed of singular-perturbation based fast control and an outer-loop slow control. The slow subsystem is controlled by a neural network (NN) for feedback linearization, plus a PD outer-loop for tracking, and a robustifying term to assure the closed-loop stability. No off-line learning or training is needed for the NN. Tracking and stability are proven using Lyapunov techniques that yield a novel modified NN weight tuning algorithm.The research is supported by NSF grant IRI-9216545 and EPRI Grant RP8030-09.     

A novel fused neural network controller for lateral control of autonomous vehicles

We present a novel fused feed-forward neural network controller inspired by the notion of task decomposition principle. The controller is structurally simple and can be applied to a class of control systems that their control requires manipulation of two input variables. The benchmark problem of inverted pendulum is such example that its control requires availability of the angle as well as the displacement. We demonstrate that the lateral control of autonomous vehicles belongs to this class of systems and successfully apply the proposed controller to this problem. The parameters of the controller are encoded into real value chromosomes for genetic algorithm (GA) optimization. The neural network controller contains three neurons and six connection weights implying a small search space implying faster optimization time due to few controller parameters. The controller is also tested on two benchmark control problems of inverted pendulum and the ball-and-beam system. In particular, we apply the controller to lateral control of a prototype semi-autonomous vehicle. Simulation results suggest a good performance for all the tested systems. To demonstrate the robustness of the controller, we conduct Monte-Carlo evaluations when the system is subjected to random parameter uncertainty. Finally experimental studies on the lateral control of a prototype autonomous vehicle with different speed of operation are included. The simulation and experimental studies suggest the feasibility of this controller for numerous applications.     

Adaptive finite-time congestion controller design of TCP/AQM systems based on neural network and funnel control

This work investigates an adaptive finite-time congestion control problem of transmission control protocol/active queue management. By means of the funnel control, neural networks and sliding mode control, a new AQM algorithm is proposed to ensure that the tracking error \(e_{1}\left( t\right) \) converges to the prescribed boundary in finite time and the transient and steady-state performances of \(e_{1}\left( t\right) \) can be satisfied. The stability analysis is given to prove that all the signals of the closed-loop system are finite-time bounded. Finally, a comparison example is considered to demonstrate the feasibility and superiority of the presented scheme.

     

改进神经元PID无线拥塞研究

神经元PID算法能较好地控制瓶颈节点的队列长度,但当网络环境发生较大变化时,其控制效果往往难以保证。根据Ad Hoc网络环境参量时变的特点,推导了无线TCP/AQM离散模型,在神经元算法的加权系数中引入二次型性能指标。另外神经元增益K是系统敏感参数,而恒定的K值不易适应时变的无线自组织网络,据此设计了一种改进二次型性能指标神经元PID的AQM。仿真结果表明：在动态拓扑、突发流及链路容量变化的Ad Hoc网络中,该改进算法优于PI算法。     

基于神经网络监督控制的拥塞控制算法研究

提出了一个基于神经网络控制的主动队列管理（AQM）算法;研究了TCP/AQM拥塞控制系统的可逆性,并利用一种神经网络监督控制结构进行了AQM算法的设计。算法由一个三层前馈结构的神经网络控制器（neural network controller,NNC）和一个反馈控制器（feedback controller,FC）组成。NNC作为一个前馈控制器,通过FC产生的教师信号进行学习,以建立被控对象的逆动力学模型。仿真结果表明,提出的算法与PI（proportional-integral）算法相比,无论在瞬态性能     

多通道ATM 网络鲁棒拥塞控制

拥塞控制对ATM网络有效、稳定运行具有重要的作用，在单瓶颈多通道的网络模型下，基于Smith预估原理，提出一种新颖的鲁棒拥塞控制器设计方案，这种基于速率的拥塞控制可以保证ABR的服务质量(QoS)，理论分析和仿真结果表明，所提出方案收敛速度快，对网络的不确定因素具有较强的鲁棒性。     

A neural gain scheduling network controller for nonholonomicsystems

We propose a neural gain scheduling network controller (NGSNC) to improve the gain scheduling controller for nonholonomic systems. We derive the neural networks that can approximate the gain scheduling controller arbitrarily well when the sampling frequency satisfies the sampling theorem. We also show that the NGSNC is independent of the sampling time. The proposed NGSNC has the following important properties: 1) same performance as the continuous-parameter gain scheduling controller; 2) less computing time than the continuous-parameter gain scheduling controller; 3) good robustness against the sampling intervals; and 4) straightforward stability analysis. We then show that some of nonholonomic systems can be converted to equivalent linear parameter-varying systems. As a result, the NGSNC can stabilize nonholonomic systems     

A counter based congestion control (CBC) for ATM networks

This paper presents and analyzes a new congestion control strategy targeted toward integrated services in high speed ATM networks. The proposed control combines a new transmission control scheme with an existing access control to provide efficient, fair, and congestion-free network control. The transmission control scheme uses counters at each node to regulate the flow of packets from the output packet queues to the outgoing link. The transmission control is designed to be flexible in accomodating various existing and expected applications and to be simple in implementation. The resulting congestion control strategy supports different service rate for each service class according to its individual requirements and meets the GoS of each service class. The strategy is proven to provide bounded end-to-end queueing delay for each individual real-time application and at the same time give a best effort service to loss-sensitive and delay-tolerable data streams. An analytical model is presented to study the system state queueing behavior and the results how that the proposed strategy also has a good average performance.     

A novel congestion control in hybrid ATM/TDMA networks

A new congestion control scheme is analyzed for an ATM multiplexer node. This scheme is based on the leaky bucket and virtual leaky bucket techniques, and utilizes the interaction between the ATM and higher layers, in a hybrid asynchronous transfer mode/time division multiple access (ATM/TDMA) network. The transport users are assumed to be generic ATM sources, who modulate their end-to-end flow control parameters, i.e. protocol data unit size in case of video and voice users, and window size in case of data users, based on the congestion status. Simple analytical formulas are derived for congestion criteria, to represent the required bandwidth to support various classes of service, i.e. video, voice, data, etc. with their own performance requirements. An ATM multiplexer node buffer is analyzed using a modulated poisson process queuing model with bulk arrival and bulk service of cells. The ATM multiplexer node congestion performance criteria, i.e. the mean probabilities of ATM multiplexer node congestion, cell generation, cell discarding, buffer content and buffer overflow, are evaluated with and without the congestion control schemes.     

A neural network PI controller tuner

The development of a neural network system for tuning proportional and integral (PI) feedback controllers is presented. The tuning process includes an initial gain setting procedure and a fine tuning procedure. The initial gain settings are obtained by using the standard Ziegler-Nichols tuning rules based on the openloop step response of the process. The fine tuning procedure is performed iteratively by using a neural network. The neural network suggests adjustments to the proportional gain and integrator time based on the closed-loop controlled system response. Four parameters are defined to describe the response characteristics. They are the normalised peak rise time, normalised overshoot, normalised peak to peak height, and normalised final error. These four parameters are used as inputs to the neural network. The tuning knowledge of the neural network is extracted from the tuning of a representative process. Finally, examples covering a wide range of process dynamics are tested to demonstrate the excellent performance of the tuner.     

A neural network model predictive controller

A neural network controller is applied to the optimal model predictive control of constrained nonlinear systems. The control law is represented by a neural network function approximator, which is trained to minimize a control-relevant cost function. The proposed procedure can be applied to construct controllers with arbitrary structures, such as optimal reduced-order controllers and decentralized controllers.     

Dynamic pricing and congestion control for best-effort ATM services

Several researchers have recently advocated dynamic pricing mechanisms such as the smart market. This paper explores how dynamic state-dependent pricing and explicit congestion control can both be used to avoid and alleviate congestion. Dynamic pricing has significant advantages for heterogeneous traffic, although this paper demonstrates that this approach reduces raw throughput. It is shown that when propagation delay is non-trivial, as is the case in wide-area networks, a slow-reacting version of dynamic pricing is preferable. This paper also advocates the use of novel stream-oriented best-effort ATM services with which a stream's arrival process is declared to the network before transmission begins and then policed, although there are no performance guarantees and none of these best-effort streams are ever blocked. With this approach, it is possible to provide price incentives for applications to decrease traffic burstiness, and to reveal important information about their packet streams, making mechanisms like slow-reacting dynamic pricing more practical.     

基于Additive2multipl icative 模糊 神经网的ATM 网络拥塞控制

考虑了模糊神经网络的学习功能，提出利用Additive-multiplicative模糊神经网络(AMFNN)对ATM网络进行拥塞控制的方案．在拥塞控制过程中，利用AMFNN模糊神经网络预测下一个将要到达流的特征，结合当前缓冲区的队列信息预测网络是否发生拥塞．一旦预测出将有拥塞发生，控制器则向源端反馈拥塞控制信息，信源根据拥塞信息适当降低传输速率，从而避免了拥塞的发生．仿真结果表明，该方法可改善网络对拥塞的实时处理能力，提高网络资源的利用率．     

A neural network based adaptive robot controller

Neural network based adaptive controllers have been shown to achieve much improved accuracy compared with traditional adaptive controllers when applied to trajectory tracking in robot manipulators. This paper describes a new Recursive Prediction Error technique for estimating network parameters which is more computationally efficient. Results show that this neural controller suppresses disturbances accurately and achieves very small errors between commanded and actual trajectories.     

Fuzzy neural network based traffic prediction and congestion control in high-speed networks

Congestion control is one of the key problems in high-speed networks,such as ATM.In this paper,a kind of traffic prediction and preventive congestion control scheme is proposed using neural network approach.Traditional predictor using BP neural network has suffered from long convergence time and dissatisfying error.Fuzzy neural network developed in this paper can solve these problems satisfactorily.Simulations show the comparison among no-feedback control scheme,reactive control scheme and neural network based control scheme.