Nature inspired artificial intelligence based adaptive traffic flow distribution in computer network (1002.4004v1)

Abstract: Because of the stochastic nature of traffic requirement matrix, it is very difficult to get the optimal traffic distribution to minimize the delay even with adaptive routing protocol in a fixed connection network where capacity already defined for each link. Hence there is a requirement to define such a method, which could generate the optimal solution very quickly and efficiently. This paper presenting a new concept to provide the adaptive optimal traffic distribution for dynamic condition of traffic matrix using nature based intelligence methods. With the defined load and fixed capacity of links, average delay for packet has minimized with various variations of evolutionary programming and particle swarm optimization. Comparative study has given over their performance in terms of converging speed. Universal approximation capability, the key feature of feed forward neural network has applied to predict the flow distribution on each link to minimize the average delay for a total load available at present on the network. For any variation in the total load, the new flow distribution can be generated by neural network immediately, which could generate minimum delay in the network. With the inclusion of this information, performance of routing protocol will be improved very much.