Conference Paper

Storage optimization for a peer-to-peer video-on-demand network.

DOI: 10.1145/1730836.1730844 In proceeding of: Proceedings of the First Annual ACM SIGMM Conference on Multimedia Systems, MMSys 2010, Phoenix, Arizona, USA, February 22-23, 2010
Source: DBLP

ABSTRACT This paper explores requirements for efficient pre-seeding of video-on-demand (VoD) movie data onto numerous customer set-top boxes in a cable ISP environment. The pre-seeded content will then be distributed to other set-top boxes in the same cable community using a peer-to-peer (P2P) network protocol such as BitTorrent. The challenges and solutions required for P2P VoD provided by a fixed provider such as a cable company are fundamentally different from those seen in traditional P2P networks or client-server VoD solutions. Our work pre-positions data into set-top boxes using a mathematical programming algorithm. The objective of the algorithm is to minimize uplink traffic, given a popularity model for various pieces of content and information about storage and bandwidth capacity constraints at the customer nodes. Given the complex non-linear nature of P2P interactions, these mathematical programs are solved using non-linear optimization approaches. Using a BitTorrent-like peer-to-peer data delivery system, we show through extensive simulations that our mathematical model for pre-seeding data based on object popularity and node bandwidth availability leads to noticeably greater reductions in uplink traffic and VoD server load than a weighted-random pre-seeding scheme that only considers object popularity.

  • [Show abstract] [Hide abstract]
    ABSTRACT: Recently, many video applications like video telephony, video conferencing, Video-on-Demand (VoD), and so forth have produced heterogeneous consumers in the Internet. In such a scenario, media servers play vital role when a large number of concurrent requests are sent by heterogeneous users. Moreover, the server and distributed client systems participating in the Internet communication have to provide suitable resources to heterogeneous users to meet their requirements satisfactorily. The challenges in providing suitable resources are to analyze the user service pattern, bandwidth and buffer availability, nature of applications used, and Quality of Service (QoS) requirements for the heterogeneous users. Therefore, it is necessary to provide suitable techniques to handle these challenges. In this paper, we propose a framework for peer-to-peer- (P2P-) based VoD service in order to provide effective video streaming. It consists of four functional modules, namely, Quality Preserving Multivariate Video Model (QPMVM) for efficient server management, tracker for efficient peer management, heuristic-based content distribution, and light weight incentivized sharing mechanism. The first two of these modules are confined to a single entity of the framework while the other two are distributed across entities. Experimental results show that the proposed framework avoids overloading the server, increases the number of clients served, and does not compromise on QoS, irrespective of the fact that the expected framework is slightly reduced.
    Advances in Multimedia 01/2012; 2012(2012):18.
  • [Show abstract] [Hide abstract]
    ABSTRACT: One of the key contributions of this work is that the model can substitute the long lasting simulations or the tedious measurements of the real systems in order to estimate the changes that would affect the system due to modifications of the system environment. The model can be also easily extended for planing the network environment for offering VoD service for High Definition (HD) videos. Although the network technologies permit higher upload rates, most of the users still do not have the sufficient capacity to stream entire videos, especially when the operator offers HD quality content. Therefore, our model could serve as a flexible tool for planning privately managed environments for VoD streaming.
    Computer Networks 06/2013; 57(9):2058-2074. · 1.23 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: With the rise of VOD (Video-on-Demand) services provisioning as a successful service on the Internet and managed networks, we are witnessing a drive towards cost-efficiency and economies of scale. Many broadband operators around the world are experimenting with P2P (Peer-to-Peer) systems centered on STBs (Set-Top-Boxes) to increase the competitiveness of their VOD services offering. By leveraging the storage and uplink bandwidth capacities available at a certain number of STBs operated by the broadband operator, the savings in terms of backend streaming capacities will represent sizable and decisive gains in cost. In these systems, video contents are usually fragmented into a number of complementary content fragments, called sub-streams, which are randomly injected in the network of STBs, and the VOD service is essentially provisioned through multisource streaming sessions from neighboring STBs to the requesting STB. One of the main challenges in such peer-assisted streaming systems remains the maximization of the utilization of STB resources utility for a given content popularity pattern. In this paper, we specifically focus on the content injection strategy and how the different content fragments should be dispatched in the network to achieve the highest performance in the VOD services provisioning epoch. We demonstrate that the random injection strategy is not appropriate for maximizing the number of simultaneous VOD streaming sessions in the network. Our objective is to first gain a better understanding of the factors driving P2P-based VOD streaming systems and provide guidelines to better operate such systems and ultimately give service operators the tools to achieve different performance objectives and/or fit specific network configurations. Further, we propose a new content dispatching strategy that maximizes the number of served VOD sessions by balancing the streaming load among the different STBs. Finally, we propose a complementary streaming resources reprovisioning mechanism that acts in real-time to reprovision the resources for serving VOD sessions to new STBs and to release trapped resources for new incoming VOD service requests.
    Multimedia Tools and Applications · 1.01 Impact Factor


Available from