Poster: While You Were Sleeping - Time-Shifted Prefetching of YouTube Videos to Reduce Peak-time Cellular Data Usage

Abstract

The load on wireless cellular networks is not uniformly distributed through the day, and is significantly higher during peak-times. In this context, we present a time-shifted prefetching solution that prefetches content during off-peak periods of network connectivity. We specifically focus on YouTube as it represents a significant portion of overall cellular data-usage. We make the following contributions: first, we establish that a significant portion of a user's YouTube watch behavior is indeed predictable by analyzing a real-life dataset of YouTube watch history spanning a 1-year period, from 206 users comprised of over 1.8 million videos; second, we develop an accurate prediction algorithm using a K-nearest neighbor classifier approach; and finally, we evaluate the prefetching algorithm on two different datasets and show that MANTIS is able to reduce the traffic during peak periods by 34% for a typical user.