User Tools

Site Tools

Writing /home/users/ashutosn/public_html/CommNetS2016/dokuwiki/data/cache/c/cb4c653e33acbc7cebe1fdba82849362.i failed
Unable to save cache file. Hint: disk full; file permissions; safe_mode setting.
Writing /home/users/ashutosn/public_html/CommNetS2016/dokuwiki/data/cache/c/cb4c653e33acbc7cebe1fdba82849362.metadata failed
Writing /home/users/ashutosn/public_html/CommNetS2016/dokuwiki/data/cache/4/4c47e099ad93cfdd49da21f4cec5aad6.i failed
Unable to save cache file. Hint: disk full; file permissions; safe_mode setting.
Writing /home/users/ashutosn/public_html/CommNetS2016/dokuwiki/data/cache/4/4c47e099ad93cfdd49da21f4cec5aad6.xhtml failed


This shows you the differences between two versions of the page.

Link to this comparison view

content-aware_caching_and_traffic_management_in_content_distribution_networks [2016/09/01 19:15] (current)
Line 1: Line 1:
 +Content-Aware Caching and Traffic Management in Content Distribution Networks
 +Srinivas Shakkottai
 +Texas A&M University
 +Abstract: ​ The rapid increase of content delivery over the Internet
 +has led to the proliferation of content distribution networks (CDNs).
 +CDNs might consist of both managed infrastructure as well as
 +peer-to-peer (P2P) elements. ​  Our first focus in this talk is on CDN
 +management algorithms for request routing, content placement, and
 +eviction. ​  We abstract the system of frontend source nodes and
 +backend caches of the CDN in the likeness of the input and output
 +nodes of a switch. In this model, queues of requests for different
 +pieces of content build up at the source nodes, which route these
 +requests to a cache that contains the requested content. For each
 +request that is routed to a cache, a corresponding data file is
 +transmitted back to the requesting source across links of finite
 +capacity. Caches are of finite size, and the content of the caches can
 +be refreshed periodically. ​ Can we design distributed policies for
 +joint request routing, content placement and content eviction with the
 +goal of small user latencies?
 +In the second part of the talk, we attempt to utilize awareness of
 +demand for a piece of content in the interest of efficient resource
 +usage. ​ Suppose that we can use a managed CDN and/or a P2P network for
 +content distribution. ​  What would the latency experienced by users
 +look like? We use the Bass model of demand evolution to compare a
 +hybrid of P2P and a centralized client-server approach against each
 +method acting alone. ​ Can we determine how to combine managed
 +infrastructure and P2P methods so as to minimize the latency
 +experienced by users while maintaining low server utilization?​
 +Bio:  Srinivas Shakkottai received the M.S. (2003) and PhD (2007)
 +degrees, both in electrical engineering,​ from the University of
 +Illinois at Urbana-Champaign. ​ He was a post-doctoral associate at
 +Stanford University in 2007, and is currently an assistant professor
 +at the Dept. of ECE at Texas A&M University. ​ His research interests
 +include content distribution systems, wireless ad-hoc networks,
 +Internet economics and game theory, congestion control, and the
 +measurement and analysis of Internet data.
 +Srinivas is the recipient of the Defense Threat Reduction Agency Young
 +Investigator Award (US Dept. of Defense, 2009), as well as research
 +awards from Cisco (2008) and Google (2010). ​  He earlier received the
 +International Programs in Engineering Fellowship (University of
 +Illinois, 2005), and the National Science Fellowship (KVPY, Dept. of
 +Science and Technology, Govt. of India, 1999-2001).
content-aware_caching_and_traffic_management_in_content_distribution_networks.txt ยท Last modified: 2016/09/01 19:15 (external edit)