PreFeed: Cloud-Based Content Prefetching of Feed Subscriptions for Mobile Users

While the user demands on mobile multimedia services (e.g., video streaming, web surfing, and news reading) have been souring, the wireless link capacity cannot keep up with the traffic demand. The gap between the traffic demand and the link capacity, along with time-varying link conditions, results in limited quality of mobile services over current 3G/4G cellular networks, such as long loading/buffering time and intermittent disruptions. By utilizing the cloud computing technology, we propose a new framework to improve the quality of Really Simple Syndication (RSS) reading service for mobile users called PreFeed. PreFeed consists of two parts, i.e., cloud-assisted prefetching, which will proactively fetch the multimedia content of the RSS feeds for all subscribed mobile users, and cognitive pushing, which will push the content to mobile users at an appropriate time by evaluating the link quality. Furthermore, the social impact among users in many RSS services is considered. We implement a prototype of the PreFeed framework to evaluate its performance. It is shown that cloud computing can effectively facilitate feed prefetching and cognitive pushing for mobile users; a large portion of traffic load (around 43%-74%) due to redundant downloads can be reduced.