A computational intelligence based approach for computer network traffic shaping

The classification and treatment of different kinds of traffic in computer networks have become essential on the implementation of Quality of Service (QoS) policies. However, the correct setup of the traffic shaping mechanism is a challenge in terms of performance and robustness. This paper proposes a methodology for optimizing operational parameters of traffic shaping in network environments, using evolutionary algorithms and artificial neural networks. The real data captured from a large network infrastructure has been used for validation.