Determining Optimum Queue Length in Computer Networks by Using Memetic Algorithms

Making the choice of optimal queue length in manufacturing network equipments is one of the most significant fields of network researches. This study addresses the multi-objective problem of determining optimal queue length in computer networks which aims to trade off between cost and performance. In the proposed approach, first the parameter of the simulated queue model is estimated by a memetic algorithm, which makes the fitness function of a second memetic algorithm. In this phase optimum queue length is computed based on the trade off between cost and performance of system. To validate the proposed approach, several simulations are implemented. Simulation results show that by setting an appropriate limited length for network queue desired performance can be achieved. Employing the proposed method in designing and manufacturing of network equipments can be economically beneficial.