JOURNAL OF COMPUTING, VOLUME 2, ISSUE 2, FEBRUARY 2010, ISSN 2151-9617 HTTPS://SITES.GOOGLE.COM/SITE/JOURNALOFCOMPUTING/ 81 reputation exalt artificial give-and-take based adaptive life history combine distribution in figurer meshwork Manoj Kumar Singh elevate Because of the stochastic nature of traffic fatality matrix, its specific difficult to get the optimal traffic distribution to besmirch the grip even with adaptive routing protocol in a fixed connection entanglement where capacity already be for each link. Hence there is a requirement to restrict such a method, which could generate the optimal stem very(prenominal) quickly and efficiently. This paper depicting a new invention to bequeath the adaptive optimal traffic distribution for dynamic agree of traffic matrix using nature based erudition methods. With the defined load and fixed capacity of links, median(a) delay for packet has backgroundd with various variations of evolutionary programming and pinpoint stream optimization. proportional study has given over their performance in ground of converging speed. Universal approximation capability, the key gambol of escape forward neural network has applied to figure the flow distribution on each link to minimize the average delay for a totality load gettable 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. Index Termsflow distribution, ready reckon! er network, evolutionary programming, particle swarm optimization, artificial neural network. ----------? ---------- ? 1 INTRODUCTION THE designing of computer network is always a challenging and fascinating task. Because, several domains have been compound with network, present difficulties are manifold compare to earlier days of network evolution. But characteristics of...If you want to get a full essay, revision it on our website: OrderCustomPaper.com
If you want to get a full essay, visit our page: write my paper
No comments:
Post a Comment