The project was undertaken essentially as a technical investigation of the utility of the minimal resource allocation network (MRAN) in the implementation of call admission control (CAC) on asynchronous transfer mode (ATM) networks. CAC is a fundamental mode of traffic management of ATM networks. The model development, simulation and testing were conducted with the aid of the simulation tool-Optimized Network Engineering Tools (OPNET) Version 6. In order to evaluate, the performance of the MRAN facilitated CAC scheme; a comparative study was done with existing conventional algorithms. This was an essential pre-requisite and an integral part of the technical study. The purpose of a call admission controller is to block incoming calls, thus reducing congestion in the network while maintaining quality of service (QoS). Conventional CAC controllers face certain drawbacks that are overcome with the use of neural networks. In this research initiative, the MRAN neural network algorithm has been used for predictive dynamic bandwidth allocation for the facilitation of a more efficient call admission controller. The MRAN is a minimal radial basis function (RBF) neural network which is a sequential learning algorithm.