Show/Hide Menu
Hide/Show Apps
anonymousUser
Logout
Türkçe
Türkçe
Search
Search
Login
Login
OpenMETU
OpenMETU
About
About
Açık Bilim Politikası
Açık Bilim Politikası
Frequently Asked Questions
Frequently Asked Questions
Browse
Browse
By Issue Date
By Issue Date
Authors
Authors
Titles
Titles
Subjects
Subjects
Communities & Collections
Communities & Collections
Statistical inference based load balanced routing in software defined networks
Download
12625795.pdf
Date
2020-10-14
Author
Kaya, Semih
Metadata
Show full item record
Item Usage Stats
10
views
2
downloads
Networks have been the main method of transferring data for more than forty years. The traffic volumes and sizes of networks have increased considerably in the last two decades. The traditional methods used in the networks to transfer data become inefficient due to this growth. Therefore, network planning and smart delivery methods have gained importance. Accordingly, traffic engineering methods are deployed to meet the faster and more efficient delivery requirements. These methods have been proven beneficial and they are still being used on every level of networking. Recently, software defined networking redefined the architecture of networks and network devices. This new architecture paved the way for more flexible network and traffic management techniques. In this thesis, we propose a new routing method, which minimizes the maximum link utilization in the software-defined networks. The proposed method defines a new cost metric based on statistical inference to distribute load evenly in the network. The method is demonstrated, and its performance is evaluated on virtual software defined network topologies under various artificial network loads. The experiments show that the proposed algorithm achieves the even distribution of traffic and minimizes the maximum link utilization in software defined networks.
Subject Keywords
Software defined networks
,
Routing
,
Traffic engineering
,
Minimization of maximum link utilization
,
Statistical inference
URI
https://hdl.handle.net/11511/69161
Collections
Graduate School of Informatics, Thesis