Bandwidth allocation and call admission control in ATM networks

2002

Asynchronous Transfer Mode (ATM) is one of the major enabling technologies of high-speed networking. It is the first technology that allows a corporation to use a common enterprise protocol and infrastructure for voice, data, and video communications. ATM excels when applications require specific quality of service (QoS) and reserved bandwidth. It offers economies of scale in network infrastructure by integrating different traffic types. ATM offers a tighter coupling between the user application and network protocol. It places intelligence into the Wide Area Network (WAN), making the network smarter and allowing the network to become more like a computer and less like a dump transport medium. ATM is the ideal technology when it is desirable for applications with different performance, QoS, and business requirements to be performed on the same computer multiplexer, router, switch, and/or network. It enables network managers to flexibly adapt to changing enterprise communications requirements, evolving business environment, and fluctuating traffic volumes and patterns. This special issue of SIMULATION: Transactions of The Society for Modeling and Simulation International aims at reporting on the state-of-the-art on research results in performance modeling and simulation of ATM systems and networks. The papers accepted in this special issue represent recent efforts by leading scientists and engineers from academia, industry, and government worldwide.

Section: Research Issues In Atmmentioning

confidence: 99%

Introduction to the Special Issue: ATM Systems and Networks: Basics, Issues, and Performance Modeling and Simulation

2002

“…Each service type is assigned based on the users' requirements and the nature of the application to be served. If the application is more stringent to loss and delay, the network will provide more guarantees about the quality that will be delivered, which means higher cost, in terms of bandwidth from the operator's point of view and in terms of expense from the customer's point of view [1][2][3][4].…”

Section: Introductionmentioning

confidence: 99%

Modeling and Simulation of Adaptive Available Bit Rate Voice over Asynchronous Transfer Mode Networks

Obeidat

2002

This article presents a modeling and simulation methodology to analyze the performance of voice quality when sent over the available bit rate service in asynchronous transfer mode networks. Sources can modify the rate at which they send traffic to the network based on the feedback carried in the resource management cells. This is achieved by changing the encoding level. As the contention increases to network resources-bandwidth in this case-sources start reducing the rate at which they generate and send traffic. The efficiency of the scheme under different scheduling/drop policies and other operating conditions and environments is evaluated using simulation modeling. Furthermore, sensitivity analysis is applied to different parameters, such as queue size and averaging interval length, to investigate their impact on the performance metrics. Results show that limiting the load to 41% of the link capacity results in an acceptable quality.

“…ATM switches are used to transfer cells at a very high rate, about 155.53 Mbps and higher. ATM combines the high speeds commonly associated with circuit switching and the flexibility of packet switching together in a single system [1][2][3][4][5][6][7][8][9][10].…”

Section: Introductionmentioning

confidence: 99%

“…Among the benefits that can be offered by ATM are [7][8]: (1) integration of multiple traffic types,…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Simulation Methodology to Study Input Buffering in ATM Switches

Riehl

1999

This paper presents a performance study of input buffering in Asynchronous Transfer Mode switches. The main performance metrics are average cell waiting time and output port contention under a variety of load conditions and operating environments. Results show that as the percent utilization increases, the average cell wait time increases. Analysis of output port contention shows that it increases with the increase in utilization, and the number of conflicts increases with both the utilization and the input queues. The results are presented in a series of curves that present the number of cells delivered during output conflicts versus percent utilization. The software developed offers several benefits: it provides a flexible approach to investigate performance of input queueing under a variety of conditions. The simulation duration, interarrival distribution, number of input queues and maximum queue size can all be varied simply by editing the initialization file; no recompiling of source code is required. It allows for modification and extensibility with only minor software changes. It does not contain operating-specific function calls; thus, it can be used without changes on standard DOS-based PCs or UNIX-based systems.