TY - GEN
T1 - Content-aware caching and traffic management in content distribution networks
AU - Amble, Meghana M.
AU - Parag, Parimal
AU - Shakkottai, Srinivas
AU - Ying, Lei
PY - 2011
Y1 - 2011
N2 - The rapid increase of content delivery over the Internet has led to the proliferation of content distribution networks (CDNs). Management of CDNs requires algorithms for request routing, content placement, and eviction in such a way that user delays are small. 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. Our objective is to design policies for request routing, content placement and content eviction with the goal of small user delays. Stable policies ensure the finiteness of the request queues, while good polices also lead to short queue lengths. We first design a throughput-optimal algorithm that solves the routing-placement-eviction problem. The design yields insight into the impact of different cache refresh policies on queue length, and we construct throughput optimal algorithms that engender short queue lengths. We illustrate the potential of our approach through simulations on different CDN topologies.
AB - The rapid increase of content delivery over the Internet has led to the proliferation of content distribution networks (CDNs). Management of CDNs requires algorithms for request routing, content placement, and eviction in such a way that user delays are small. 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. Our objective is to design policies for request routing, content placement and content eviction with the goal of small user delays. Stable policies ensure the finiteness of the request queues, while good polices also lead to short queue lengths. We first design a throughput-optimal algorithm that solves the routing-placement-eviction problem. The design yields insight into the impact of different cache refresh policies on queue length, and we construct throughput optimal algorithms that engender short queue lengths. We illustrate the potential of our approach through simulations on different CDN topologies.
UR - http://www.scopus.com/inward/record.url?scp=79960863510&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=79960863510&partnerID=8YFLogxK
U2 - 10.1109/INFCOM.2011.5935123
DO - 10.1109/INFCOM.2011.5935123
M3 - Conference contribution
AN - SCOPUS:79960863510
SN - 9781424499212
T3 - Proceedings - IEEE INFOCOM
SP - 2858
EP - 2866
BT - 2011 Proceedings IEEE INFOCOM
T2 - IEEE INFOCOM 2011
Y2 - 10 April 2011 through 15 April 2011
ER -