Migrating big video data to cloud: a peer-assisted approach for VoD

Abstract

Since user demand for a Video-on-demand (VoD) service varies with time in one-day period, provisioning self-owned servers for the peak load it must sustain afew hours per day leads to bandwidth under-utilization at other times. Content clouds, e.g. Amazon CloudFront and Azure CDN, let VoD providers pay by bytes for bandwidth resources, potentially leading to cost savings even if the unit rate to rent a machine from a cloud provider is higher than the rate to own one. In addition, recent studies have presented fog computing as a new paradigm to extend the cloud-based platform for a cost-effective and highly scalable service. In this paper, based on long-term traces from two large-scale VoD systems and temporal development model of content clouds, we tackle challenges, design and potential benefits in migrating both Clients/Server-based and peer-assisted VoD services into the hybrid cloud and edge peers in fog computing environment. Our measurements show that the popularity of the most popular videos decays so quickly, for example, by 11% after one hour that it poses large challenges on updating videos in the cloud. However, the trace-driven evaluations show that our proposed migration strategies (active, reactive and smart strategies), although simply based on the current information, can make the hybrid cloud-assisted VoD deployment save up to 30% bandwidth expense compared with the Clients/Server mode. Moreover, they can also handle the flash crowd traffic with little cost. Leveraging the edge peers in fog computing, we propose a cloud-friendly peer replication strategy, which further reduces the migration cost by a factor of 4. Our simulation also shows that the cloud price and server bandwidth chosen play the most important roles in saving cost, while the cloud storage size and cloud content update strategy play the key roles in the user experience improvement.