This paper presents a congestion control scheme for ATM traffic using a minimal radial basis function neural network referred to as Minimal Resource Allocation Network (MRAN). Earlier studies have shown that MRAN is well suited for online adaptive control of nonlinear time varying systems as it can adjust its size by adding and pruning the hidden neurons based on the input data. Since ATM traffic is nonlinear and time varying performance of MRAN as a congestion controller is investigated here. These studies are carried out using OPNET to model the ATM traffic. The ATM traffic model consists of bursty, Variable BitRate (VBR) and custom traffic in a multiplexed form so as to generate a heavily congested traffic situation. For this scenario, the controller has to minimize the congestion episodes and maintain the Quality of Service (QoS) requirements. This paper compares the performance of the MRAN congestion controller with that of a modified Explicit Rate Indication with Congestion Avoidance (ERICA) scheme and a Back-Propagation (BP) neural controller. Simulation results indicate that MRAN controller performs better than the modified ERICA and BP controller in reducing the congestion episodes and maintaining the desirable QoS.

This paper presents an adaptive control scheme using a newly developed Minimal Resource Allocation Network (MRAN) to solve the traffic congestion problem in ATM networks. MRAN generates a minimal radial basis function neural network by adding and pruning hidden neurons based on the input data and is ideal for on-line adaptive control for fast time varying nonlinear systems. The ATM traffic modeling is carried out using the well-known network simulation software OPNET for multiplexed traffic (combining both speech and video signals). Performance of MRAN controller is compared with conventional method and Back-Propagation (BP) neural network controller with the aim of minimizing the congestion episodes and maintaining the quality. Simulation results indicate that MRAN controller performs better than both conventional and BP controller in reducing the congestion and maintaining a better quality of the traffic.

No abstract