浅析ATM交换机呼叫处理体系结构

中结合ATM这一面向连接的网络技术，就ATM交换机呼叫体系结构作以浅析，重点阐述了集中呼叫，分布式信号呼叫，呼叫控制，路由呼叫处理体系结构。     

TCP over ATM的拥塞控制

研究了TCP层中的TCP拥塞控制算法和ATM层中的ATM拥塞算法,分析了TCPoverATM情况下两种不同拥塞算法的相互合作问题.     

ATM网络ABR业务流量控制算法的优化研究

文中介绍了ATM网络的基本概念、ABR服务类型。将有效的活动数VC引入到该算法中,使系统能快速达到稳定状态。通过提出一种快速减小反馈时延的算法对ATM网络ABR业务的流量控制进行了优化,实验表明：该算法可以使ATM网络减少拥塞,提高系统的性能,最终使网络达到最佳工作状态。     

ATM原理概论

介绍了ATM技术的框架，详细描述了ATM的协议栈；介绍了ATM的信元结构，描述了信元边界判定算法，指出了特殊信元的结构；叙述了常用的ATM适配层协议AAL1－AAL5；简单介绍了ATM的维护功能；最后指出了影响ATM性能的重要参数。     

ATM建模与仿真研究

文章主要描述了现代ATM仿真，及如何利用数学算法建立仿真模型。同时还建立了一个ATM交换机的模型。     

CLOS型大规模ATM交换网络结构

首先提出了大规模ATM交换网络应满足的基本特性,然后对CLOS型大规模ATM交换网络进行了研究。给出了CLOS型结构采用集中式路由选择算法时交换网络的连接级无阻塞条件,详细论述了两种分散式路由选择算法,并给出了它们对应的改进结构和改进算法。     

一个ATM局域网上的即时多媒体应用原型系统

本文概括说明了一个实验系统。该系统支持ATM网络上的即时多媒体(图像/视频/数据)应用。该系统是用来演示分布式多媒体文件处理和即时视频剧本的。这二者将来在ATM网络上将是非常重要的应用。实验原型在适当的信令、传输协议及应用软件之间使用了高速(2.4 Gbps)ATM转换开关(Switch),使得用户可以高速、可靠地访问存贮在一个或多个“多媒体服务器”上的视频/图像信息。目前系统是由如下关键模块构成的:(1)2.4 Gbps(16×16)ATM转换开关,(2)带有JPEG插板和ATM接口的UNIX工作站,(3)用于调用建立的Q.2931信令,(4)用于避免拥塞(Congestion)的ATM通信量控制,(5)多媒体传输协议,和(6)分布式多媒体文件要用到的应用软件等。本文对此系统实现的方法作了简要说明,并对上列的子系统进行了进一步地详细说明。     

RED分组丢弃算法性能研究

 本文研究了在ATM交换机上实现的RED算法的性能.在固定有效带宽、时变有效带宽情况下和同种、异种业务环境下,研究了RED算法的通过率、公平性和时延等性能.经研究表明:RED算法有必要与EPD算法相结合,构成RED+EPD算法.采用RED+EPD算法的ATM交换机通过控制平均排队长度,有效地减小了交换机的平均排队时延.通过与其他分组丢弃算法进行性能比较表明:采用RED+EPD算法的ATM交换机,可提供比EPD算法略高的通过率,更好的公平性和更低的排队时延,能较好地支持具有时延要求的业务.     

以太网流量监控方法研究

通过研究帧中继、IP、ATM等分组业务的流量监控算法,提出了可适用于光传输网络的以太网流量的2种监控算法:PIR/CIR和CIR/EIR。通过比较发现CIR/EIR算法的可控性和准确性比PIR/CIR高。最后通过计算机仿真和ATM平台移植对理论分析进行了验证。     

基于3DES加密算法的ATM加密密码键盘设计

主要介绍了3DES算法及其在ATM加密密码键盘中的应用,并对ATM加密密码键盘的原理以及系统的软、硬件设计作了较为详尽的阐述。     

N*DPT/D/1排队系统分析

多路离散周期串到达、单个服务台定长服务排队系统,是在研究CBR业务下ATM网络中间节点性能时所遇到的一种排队模型。在有线ATM网的CBR业务接进无线ATM网时也会遇到这种排队模型。本文分析了这一排队系统,得到了其队长剩余分布的计算公式。     

Real-time multimedia scheduling policies for end-to-end delayjitter and loss guarantees across ATM satellite systems

We propose a simple first-in first-out (FIFO)-based service protocol which is appropriate for a multimedia ATM satellite system. The main area of interest is to provide real-time traffic with upper bounds on the end-to-end delay, jitter, and loss experienced at various service queues within a satellite network. Various service protocols, each based on a common underlying strategy, are developed in light of the requirements and limitations imposed at each of the satellite's subsystems. These subsystems include the uplink (UL) earth station (ES) service queue, on-board processing (OBP) queues, and the downlink (DL) ES service queue feeding into a wireline ATM network or directly to an end-user application. Numerous network simulation results demonstrate the tractability, efficiency, and versatility of the underlying service discipline. Key features of our strategy are its algorithmic and architectural simplicity, its non-ad-hoc scheduling approach, and its unified treatment of all real-time streams at all service queues. In addition, the delay and jitter bounds are uncoupled. In this way, end-to-end jitter can be tightly controlled even if medium access requires long indeterminate waiting durations     

An ATM queue manager handling multiple delay and loss priorities

The asynchronous transfer mode (ATM) technique has been widely accepted as a flexible and effective scheme to transport various traffic over the future broadband network. To fully utilize network resources while still providing satisfactory quality of service (QOS) to all network users, prioritizing the user's traffic according to their service requirements becomes necessary. During call setup or service provisioning, each service can be assigned a service class determined by a delay priority and a loss priority. A queue manager in ATM network nodes will schedule ATM cells departing and discarding sequence based on their delay and loss priorities. Most queue management schemes proposed so far only consider either one of these two priority types. The queue manager handles multiple delay and loss priorities simultaneously. Moreover, a cell discarding strategy, called push-out, that allows the buffer to be completely shared by all service classes, has been adopted in the queue manager. We propose a practical architecture to implement the queue manager by using available VLSI sequencer chips     

ATM-based transport architecture for multiservices wirelesspersonal communication networks

This paper presents an ATM-based transport architecture for next-generation multiservices personal communication networks (PCN). Such “multimedia capable” integrated services wireless networks are motivated by an anticipated demand for wireless extensions to future broadband networks. An ATM compatible wireless network concept capable of supporting a mix of broadband ISDN services including constant bit-rate (CBR), variable bit-rate (VBR), and packet data transport is explored from an architectural viewpoint. The proposed system uses a hierarchical ATM switching network for interconnection of PCN microcells, each of which is serviced by high-speed, shared-access radio links based on ATM-compatible cell, relay principles. Design issues related to the physical (modulation), media access control (MAC), and data-link layers of the ATM-based radio link are discussed, and preliminary technical approaches are identified in each case. An example multiservice dynamic reservation (MDR) TDMA media access protocol is then considered in further detail, and simulation results are presented for an example voice/data scenario with a proportion of time-critical (i.e., multimedia) packet data. Time-of-expiry (TOE) based queue service disciplines are also investigated as a mechanism for improving the quality-of-service (QoS) in this scenario     

An experimental study for transmitting MPEG-2 streams over ATM networks

This paper presents a comparative study of different techniques aiming at transmitting MPEG-2 streams over ATM networks, with emphasis on the presentation of practical results achieved on an experimental platform available at LSI, a laboratory of the University of São Paulo, Brazil. This study has the purpose to determine some tuning parameters for optimizing the implementation of distributed multimedia applications on different network technologies. The focus of this experimental study has been on non-native ATM techniques like “Classical IP over ATM” and “LAN Emulation”, as well as native ATM techniques based on direct access service primitives to AAL5. The influence of different parameters, like packet length, buffer size, CPU speed, on the resulting throughput has been studied. Furthermore, a testing tool is being developed for assessing the transmission of MPEG-2 streams based on the practical experience achieved so far. These results will permit the evaluation of different network technologies and also help in the development of distributed multimedia applications like video-on-demand, videoconferencing and telemedicine.     

走近用户的ATM网

目前用户接入网广泛采用混合光纤／同轴网（ＨＦＣ）和非对称数字用户线（ＡＤＳＬ）技术,在此基础上建立ＡＴＭ网实现ＡＴＭ到家以适应未来宽带网的发展需要。基于ＨＦＣ网的ＡＴＭ网以ＡＴＭ节点交换、用户终端单元和头端单元设备来作支持。而在ＡＤＳＬ上完成ＡＴＭ交换业务时,则有两种方案可选：（１）通过在ＡＴＭ交换机与ＡＤＳＬ调制解调器之间加数字用户线接入复用器实现;（２）将离散多音频（ＤＭＴ）与ＡＴＭ相结合。     

Output-queue contents in a ‘minislot’ synchronized ATM switch

An N × N switching element with output queueing, as used in a large ATM switching network, is considered. All the inlets of the switching element are synchronized on ‘minislots’, where a minislot is the fixed-length time unit for the transmission of one ‘minicell’. When entering the switching network, an ATM cell is converted into a ‘minicell-train’, consisting of a fixed number of minicells. Using an active/silent model, it is assumed that on each inlet of the switching element, the number of minicelltrains in an active period and the length of a silent period are both geometrically distributed, and the arriving minicell-trains are uniformly distributed among all the outlets. The performance of the switching element can be obtained by analysing one single output queue, which is modeled as a discrete-time single-server queuing system with train arrivals. In this paper, an upper bound and an approximate expression for the mean queue length are derived. More importantly, an analytical method is developed to obtain a tight upper bound and a good approximation for the tail distribution of the queue length. This analytical method is very useful in buffer dimensioning of ATM switches.     

ATM via satellite: A framework and implementation

This paper describes an ATM‐based satellite network, focusing on the networking (ATM) aspects of the design. The ATM requirements and the basic design of the network are outlined. In particular, a simple MAC layer is proposed in which ATM service classes are mapped onto MF‐TDMA uplink access methods. The uplink access and resource allocation approaches based on this model are described in detail. Also, this paper shows how different qualities‐of‐service can be provided by using a combination of different access schemes. This paper also covers scheduling for the uplink portion of the satellite network. The use of Hierarchical Round Robin is argued on the grounds of performance, flexibility and implementability. This revised version was published online in June 2006 with corrections to the Cover Date.     

Worst-case performance of a buffer with independent shaped arrivalprocesses

In both asynchronous transfer mode (ATM) standards and evolving Internet guidelines, deterministic shaping has two principle objectives: (1) to facilitate the allocation of a suitable amount of resources (buffer memory, bandwidth) to a connection to achieve its required quality of service and (2) to easily police traffic and assure “fair” access to a shared resource. We take an ATM context and use fluid modeling, which is appropriate because ATM uses small fixed-length (53-byte) packets called cells. A buffer in a network access node with independent and identically distributed shaped arrival processes is considered. A worst-case performance bound is derived that relies only on the traffic shaping parameters