Ant-based Integrated Traffic Control and Management in ATM Networks

Abstract

ABSTRACTAsynchronous transfer mode (ATM) is a cell-switching and multiplexing technology that combines the benefits of circuit switching with those of packet switching. Traffic management in ATM is concerned with ensuring that users get their desired quality of service (QoS). The problem of traffic management is especially difficult during the periods of heavy load particularly if the traffic demands cannot be predicted in advance. The issue of traffic control and bandwidth management in ATM-based networks is complex due to a mixture of different connection traffic types, QoS requirements, and time scales. In this paper, we provide an ant-based integrated technique to control the occurrence of congestion and allocate bandwidth for various traffic services in a prioritized manner. The forward ants collect the QoS information of the nodes regarding the available bandwidth and the buffer size. Then based on the QoS requirements of the various traffic classes, the optimum path is selected based on the observed QoS statistics collected by the ant agents. Therefore, the ant-based integrated technique provides the network to efficiently use the traffic, thus providing an efficient traffic management for the ATM network. By simulation results, we show that the proposed ant-based technique outperforms the existing architecture in terms of throughput and delay.