The project

A recent study by Cisco (2013) forecasts that the video will constitute more than 80% of the Internet traffic in 2016. As a matter of facts, all the multimedia offer will be digitalized and made available through video streaming platform over the Internet. However, the implementation of a service that is able to scale to millions of concurrent viewers is an ongoing challenge. Cloud computing allows implementing scalable services both from the point of view of required resources to deliver a high-quality service, and from the point of view of costs thanks to the pay-as-you-go billing model. However, to implement a seamless user experience while containing the distribution costs, it is necessary to build a control plane to efficiently manage the Cloud resources. This research project proposes to apply the theory of feedback control to design control systems for 1) the management of the cloud resources and 2) the adaptation of the video bitrate to the available bandwidth and the user device. The expected results are: 1) a mathematical framework that allows modeling the delivery system including the clients; 2) algorithms to minimize the distribution costs while maximizing the user's quality of experience. The results will be made available in the form of a demonstrator. The project results can be exploited through the integration of the proposed solutions in portals for the distribution of movies, short movies, independent productions, also through social platforms.

Results

Publications

  • Giuseppe Cofano, Luca De Cicco, Saverio Mascolo
    Modeling and Design of Adaptive Video Streaming Control Systems
    IEEE Transactions on Control of Network Systems, accepted, to appear, doi: 10.1109/TCNS.2016.2631452, Nov 2016
  • Giuseppe Cofano, Luca De Cicco, Saverio Mascolo
    A Hybrid Model of Adaptive Video Streaming Control Systems
    Proc. of IEEE Conference on Decision and Control (IEEE CDC 2016), Las Vegas, Nevada, USA, Dec 2016 (PDF) (Slides:PDF)

The project[edit]

A recent study by Cisco (2013) forecasts that the video will constitute more than 80% of the Internet traffic in 2016. As a matter of facts, all the multimedia offer will be digitalized and made available through video streaming platform over the Internet. However, the implementation of a service that is able to scale to millions of concurrent viewers is an ongoing challenge. Cloud computing allows implementing scalable services both from the point of view of required resources to deliver a high-quality service, and from the point of view of costs thanks to the pay-as-you-go billing model. However, to implement a seamless user experience while containing the distribution costs, it is necessary to build a control plane to efficiently manage the Cloud resources. This research project proposes to apply the theory of feedback control to design control systems for 1) the management of the cloud resources and 2) the adaptation of the video bitrate to the available bandwidth and the user device. The expected results are: 1) a mathematical framework that allows modeling the delivery system including the clients; 2) algorithms to minimize the distribution costs while maximizing the user's quality of experience. The results will be made available in the form of a demonstrator. The project results can be exploited through the integration of the proposed solutions in portals for the distribution of movies, short movies, independent productions, also through social platforms.

Results[edit]

Publications[edit]