
The rise of popularity of video streaming services has resulted in increased volumes of network traffic, which in turn have created Internet bottlenecks leading to perceived quality degradations. In this paper, we argue that a good way to tackle this type of congestion is to make the contents available inside ISPs' networks. We thus propose a network friendly content delivery architecture that considers the complex video distribution chain and its associated business models. This comprehensive architecture allows a network operator to fully engineer video traffic distribution in order to both alleviate peering links' workload and improve delivered QoS. This proposal is fully compatible with Adaptive Bitrate Streaming (ABS) architectures, which are currently used to distribute video in the Internet. Extensive simulations show that the proposed architecture optimizes resources' use while clearly improving the quality of experience by reducing peering links' load and by shortening significantly the waiting time of clients. From an ISP's point of view, such an architecture promises dramatic savings on the costs associated with video delivery. The feasibility of the architecture is proved by a prototype implementation based on DASH ("Dynamic Adaptative Streaming over HTTP"), which is the MPEG version of ABS. This architecture actually presents an evolutionary and pragmatic method to efficiently deploy an Information Centric Networking (ICN) architecture based on the collaboration between service providers or traditional CDNs and peer-assisted CDNs operated by ISPs.
[MATH.MATH-PR] Mathematics [math]/Probability [math.PR], [SPI.OPTI] Engineering Sciences [physics]/Optics / Photonic, [INFO.INFO-NI] Computer Science [cs]/Networking and Internet Architecture [cs.NI], [INFO] Computer Science [cs]
[MATH.MATH-PR] Mathematics [math]/Probability [math.PR], [SPI.OPTI] Engineering Sciences [physics]/Optics / Photonic, [INFO.INFO-NI] Computer Science [cs]/Networking and Internet Architecture [cs.NI], [INFO] Computer Science [cs]
| selected citations These citations are derived from selected sources. This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | 14 | |
| popularity This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network. | Average | |
| influence This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | Top 10% | |
| impulse This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network. | Top 10% |
