Skip to Main Content
This paper extends our recent work on computing the total average end-to-end packet delay in IEEE 802.11 wireless network based on normalized measure of dispersion and offered load dependency study. From this study we find that the coefficient of variation for service times does not follow exponential distribution rather it follows Gamma distribution. Using a reverse engineering approach with average service time Gamma distributed, patterns for the shape parameter α are established in order to gain insight into computing the total average end-to-end packet delay. Using the patterns and computing the average end-to-end packet delay at different data rates, we have shown significant improvement in results of. Our results have been extensively verified through simulations.