Predicting Popularity and Adapting Replication of Internet Videos for High-Quality Delivery

Guthemberg da Silva Silvestre 1 Sébastien Monnet 1 David Buffoni 2 Pierre Sens 1
1 Regal - Large-Scale Distributed Systems and Applications
LIP6 - Laboratoire d'Informatique de Paris 6, Inria Paris-Rocquencourt
2 MLIA - Machine Learning and Information Access
LIP6 - Laboratoire d'Informatique de Paris 6
Abstract : Content availability has become increasingly important for the Internet video delivery chain. To deliver videos with an outstanding availability and meet the increasing user expectations, content delivery networks (CDNs) must enforce strict QoS metrics, like bitrate and latency, through SLA contracts. Adaptive content replication has been seen as a promising way to achieve this goal. However, it remains unclear how to avoid waste of resources when strict SLA contracts must be enforced. In this work, we introduce Hermes, an adaptive replication scheme based on accurate predictions about the popularity of Internet videos. Simulations using popularity growth curves from YouTube traces suggest that our approach meets user expectations efficiently. Compared to a non- collaborative caching, Hermes reduces storage usage for replication by two orders of magnitude, and under heavy load conditions, it increases the average bitrate provision by roughly 90%. Moreover, it prevents SLA violations through an application-level deadline-aware mechanism.
Complete list of metadatas

https://hal.inria.fr/hal-00930200
Contributor : Pierre Sens <>
Submitted on : Tuesday, January 14, 2014 - 2:28:46 PM
Last modification on : Thursday, March 21, 2019 - 1:00:00 PM

Identifiers

Citation

Guthemberg da Silva Silvestre, Sébastien Monnet, David Buffoni, Pierre Sens. Predicting Popularity and Adapting Replication of Internet Videos for High-Quality Delivery. ICPADS 2013 - 19th IEEE International Conference on Parallel and Distributed Systems, Dec 2013, Seoul, South Korea. pp.412-419, ⟨10.1109/ICPADS.2013.64⟩. ⟨hal-00930200⟩

Share

Metrics

Record views

241