Learning-based resource optimization in asynchronous transfer mode (ATM) networks

This paper tackles the issue of bandwidth allocation in asynchronous transfer mode (ATM) networks using recently developed tools of computational intelligence. The efficient bandwidth allocation technique implies effective resources utilization of the network. The fluid flow model has been used effectively among other conventional techniques to estimate the bandwidth for a set of connections. However, such methods have been proven to be inefficient at times in coping with varying and conflicting bandwidth requirements of the different services in ATM networks. This inefficiency is due to the computational complexity of the model. To overcome this difficulty, many approximation-based solutions, such as the fluid flow approximation technique, were introduced. Although such solutions are simple, in terms of computational complexity, they nevertheless suffer from potential inaccuracies in estimating the required bandwidth. Soft computing-based bandwidth controllers, such as neural networks- and neurofuzzy-based controllers, have been shown to effectively solve an indeterminate nonlinear input-output (I-O) relations by learning from examples. Applying these techniques to the bandwidth allocation problem in ATM network yields a flexible control mechanism that offers a fundamental tradeoff for the accuracy-simplicity dilemma.

I. Introduction

Asynchronous TRANSFER MODE (ATM) networks have become, in recent years, among the most promising technologies for supporting broad-band multimedia services [1]. It has been widely recognized that ATM technology has the necessary flexibility to handle the diversity of traffic that is foreseen for broad-band integrated services digital networks (B-ISDNs). For example, the packets in ATM networks have a fixed size of 53 B. In addition, a virtual path concept has been introduced in ATM networks [2]. This concept reduces the network operating control and the connection setup time, and simplifies the connection admission control (CAC). ATM has been designed to support a mixture of multimedia traffic (e.g., audio, video, data, images) with different traffic parameters, such as peak bit rate, burst time, cell delay transfer delay, and different Quality of Services (QoS) requirements [3]. The ATM layer supports several service classes, that impose different QoS, such as constant bit rate (CBR), real-time variable bit rate (rt VBR), nonreal-time variable bit rate (nrt VBR), available bit rate (ABR), and unspecified bit rate (UBR). However, ATM networks still represent some challenging problems in terms of properly utilizing the network resources (e.g., the bandwidth) and in properly guaranteeing QoS to all the different traffic classes without suffering from conflicts. Moreover, and as a technology that supports multimedia traffic, ATM networks suffer from unpredictable fluctuations and burstiness of traffic.