Estimation of Cell Loss Ratio and Cell Delay for ATM Networks using Novel Genetic Algorithm Approach

In this paper, an on line genetic algorithm (GA) is proposed for estimating the cell loss probability (CLP) and the cell delay in real time. They are key parameters to many vital functions in the network such as call admission (CAC), bandwidth allocation, etc. However, the CLR and delay depend usually on many unknown and unpredictable traffic parameters such as input traffic correlations. In this paper, a novel genetic algorithm to predict the CLR and delay in different sized systems based on both a small amount of information from these systems. This algorithm is used with real time traffic measurement to maintain and design the ATM network