Please use this identifier to cite or link to this item: https://doi.org/10.1145/2534142.2534143
Title: A cache miss equation for partitioning an NDN content Store
Authors: Rezazad, M.
Tay, Y.C. 
Keywords: Cache partitioning
Content networking
Fairness
Issue Date: 2013
Citation: Rezazad, M.,Tay, Y.C. (2013). A cache miss equation for partitioning an NDN content Store. Asian Internet Engineeering Conference, AINTEC 2013 : 1-8. ScholarBank@NUS Repository. https://doi.org/10.1145/2534142.2534143
Abstract: Named Data Networking (NDN) is becoming a prominent candidate for the next Internet architecture. One of the main features of the proposal lies in using in-network caching, which makes the performance of the storage in a router very crucial. As this storage capacity is very limited, to maintain its high functionality it is better to separate the contents of some applications (i.e., video, web, etc.) which can be reused by other clients and protect them from being replaced by non-cacheable content of other applications like emails, telephony app. etc., i.e. partitioning the content store. Partitioning might also provide means for ISPs to offer different level of quality for different applications based on service level agreements with the content producers. This paper considers dividing NDN traffi into classes, and examines how an NDN router's content store can be partitioned among these classes. It illustrates how this partitioning can be done dynamically by using the Buffer Miss Equation from previous work. This illustration considers two cases with different objectives: minimizing average (over all traffi classes) miss ratio and maintaining fairness (in miss ratios) among traffi classes. Copyright © 2013 ACM.
Source Title: Asian Internet Engineeering Conference, AINTEC 2013
URI: http://scholarbank.nus.edu.sg/handle/10635/104511
DOI: 10.1145/2534142.2534143
Appears in Collections:Staff Publications

Show full item record
Files in This Item:
There are no files associated with this item.

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.