Community based forecasting for effective video content caching in mobile networks

Témavezető (TMIT): 
Doktori iskola: 
Informatikai Tudományok Doktori Iskola
Kiírás dátuma: 
2017. 01. 03
Érvényesség: 
inaktív
Téma leírása: 

Kutatási célkitűzések: Mobile client devices capable of caching are able to prefetch video content before the actual watching time, out of busy hour, to balance the network load. In one hand, there are video contents that are generally popular, they should be available with quick access everywhere and for everyone using central global caches, replicated in local caches as well. On the other hand, many of the videos are watched by a small number of viewers. Between the above two extremes, there is an open research field where the local popularity of the videos can be harmonized with the locality of the mobile users, thus local caches can be optimized. Based on the user preferences a forecasted video content can be prefetched not only in local caches, but also to the client devices directly.

Based on the user profiles and the available content a selective caching method should be developed. The performance of the local selective caches and the prefetching for the client devices can be enhanced by evaluating the behavior of the community of the video sharing sites deciding on what content, when, and to whom to preload. The goals for the selective caching method are effective service provisioning and user satisfaction.

Open problems:

  • Analysis and characterization of mobile video content related user profiles
  • Determining the harmonization between user locality and popularity groups
  • Development of a forecasting algorithm for selective video content caching and prefetching
  • Construction of an objective function which decides on whether the content have to be prefetched entirely or only partially

Requirements:

  • experience in user data collection methods
  • good knowledge in statistics

Előírt nyelvtudás: angol

Felvehető hallgatók száma: 1