Randomized Decentralized Broadcasting Algorithms

Massoulié, Laurent; Twigg, Andrew; Gkantsidis, Christos; Rodríguez, P.

doi:10.1109/infcom.2007.129

Cited by 153 publications

(192 citation statements)

References 10 publications

Supporting

Mentioning

182

Contrasting

Unclassified

Order By: Relevance

“…Consider why we have non-empty C set, that is because there are less than I nodes left unexhausted and no initial tree could be further constructed. Suppose we can reallocate the remaining bandwidth of nodes in set C to all nodes from I + 1 to N, and suppose we relax the degree constraint to tree degree bound, then we can exhaust all nodes in set C. Suppose we have supported an extra rate r e in this extra step, then clearly, the total rate we have supported is r * b + r e , and we have Plugging (25), we have proved (11).…”

Section: Discussionmentioning

confidence: 93%

“…The inequality in (11) concludes that the ratio of the two critical rates is at least 1/2, and (12) comes from (11).…”

Section: B Throughput and Node Degree Analysismentioning

confidence: 99%

“…There are a few flavors of delay in P2P streaming, and there have been several works studying the bound of delay [11], [25], [26]. The delay we focus is the playback delay, which is defined as the time gap from a packet originating at source to it reaching the last receiver.…”

Section: Node Degree and Delay Boundmentioning

confidence: 99%

See 2 more Smart Citations

P2P Streaming Capacity under Node Degree Bound

Shao

Chen

Sengupta

et al. 2010

2010 IEEE 30th International Conference on Distributed Computing Systems

View full text Add to dashboard Cite

Abstract-Two of the fundamental problems in peer-to-peer (P2P) streaming are as follows: what is the maximum streaming rate that can be sustained for all receivers, and what peering algorithms can achieve close to this maximum? These problems of computing and approaching the P2P streaming capacity are often challenging because of the constraints imposed on overlay topology. In this paper, we focus on the limit of P2P streaming rate under node degree bound, i.e., the number of connections a node can maintain is upper bounded. We first show that the streaming capacity problem under node degree bound is NPComplete in general. Then, for the case of node out-degree bound, through the construction of a "Bubble algorithm", we show that the streaming capacity is at least half of that of a much less restrictive and previously studied case, where we bound the node degree in each streaming tree but not the degree across all trees. Then, for the case of node total-degree bound, we develop a "Cluster-Tree algorithm" that provides a probabilistic guarantee of achieving a rate close to the maximum rate achieved under no degree bound constraint, when the node degree bound is logarithmic in network size. The effectiveness of these algorithms in approaching the capacity limit is demonstrated in simulations using uplink bandwidth statistics of Internet hosts. Both analysis and numerical experiments show that peering in a locally dense and globally sparse manner achieves near-optimal streaming rate if the degree bound is at least logarithmic in network size.I. Introduction P2P systems have enabled scalable file sharing and video streaming for almost a decade, yet the following fundamental questions on its performance limits have only recently been answered partially: what is the streaming capacity, the maximum streaming rate that can be achieved by all receivers of a streaming session, under various overlay topology constraints? What kind of peering algorithms achieve near-capacity rates?As explained in Section II, P2P streaming can be modeled as multiple multicast trees superimposed on top of the overlay graph. The streaming capacity problem depends on the constraints on the graph and tree properties. The simplest case is the unconstrained tree construction on top of a full mesh (complete) graph, where the streaming capacity is derived in several papers [1], [8]- [12]. Various practical constraints on peering and overlay graph have since been considered. For example, [3], [4] solved the streaming capacity problem under the node per-tree degree bound on top of a complete graph. In contrast to node degree constraints in this paper, node per-tree degree constraints individually upper bound the number of peers a node can have in each of the multiple trees,

show abstract

Section: Discussionmentioning

confidence: 93%

“…The inequality in (11) concludes that the ratio of the two critical rates is at least 1/2, and (12) comes from (11).…”

Section: B Throughput and Node Degree Analysismentioning

confidence: 99%

See 1 more Smart Citation

P2P Streaming Capacity under Node Degree Bound

Shao

Chen

Sengupta

et al. 2010

2010 IEEE 30th International Conference on Distributed Computing Systems

View full text Add to dashboard Cite

show abstract

“…We assume a push mechanism, in which the transmitter selects both which chunk to transmit and to which peer. Several scheduling algorithms have been proposed in the literature (see for example [9,10,11,12]), among which we selected the simplest one since our focus is on the Overlay topology optimization rather than chunk scheduling algorithm. Therefore, we adopt a simple random chunk/random peer scheduling scheme: each peer selects at random one chunk among those it has received and still stores in the trading window ( [12] employs a sliding window mechanism to optimize chunk transmission); then it selects at random one of its neighbors among those that have not yet received the selected chunk.…”

Section: Chunk Scheduling Algorithmmentioning

confidence: 99%

Network Awareness in P2P-TV Applications

Traverso

Leonardi

Mellia

et al. 2009

The Internet of the Future

View full text Add to dashboard Cite

Abstract. The increasing popularity of applications for video-streaming based on P2P paradigm (P2P-TV) is raising the interest of both broadcasters and network operators. The former see a promising technology to reduce the cost of streaming content over the Internet, while offering a world-wide service. The latter instead fear that the traffic offered by these applications can grow without control, affecting other services, and possibly causing network congestion and collapse. The "Network-Aware P2P-TV Application over Wise Networks" FP7 project aims at studying and developing a novel P2P-TV application offering the chance to broadcast high definition video to broadcasters and to carefully manage the traffic offered by peers to the network, therefore avoiding worries to Internet providers about network overload. In such context, we design a simulator to evaluate performance of different P2P-TV solutions, to compare them both considering end-users' and network providers' perspectives, such as quality of service perceived by subscribers and link utilization. In this paper, we provide some results that show how effective can be a network aware P2P-TV system.

show abstract

“…Exceptions include systems described by their authors like Coolstreaming [16] or inferred by reverse engineering like PPlive [4] and TVAnts [12]. On the academic front, there have been several attempts to try to estimate theoretical limits in terms of optimality of bandwidth utilization [3] [7] or delay [15].…”

Section: Introductionmentioning

confidence: 99%

SmoothCache: HTTP-Live Streaming Goes Peer-to-Peer

Roverso

El-Ansary²,

Haridi

2012

Networking 2012

View full text Add to dashboard Cite

Abstract. In this paper, we present SmoothCache, a peer-to-peer live video streaming (P2PLS) system. The novelty of SmoothCache is threefold: i) It is the first P2PLS system that is built to support the relativelynew approach of using HTTP as the transport protocol for live content, ii) The system supports both single and multi-bitrate streaming modes of operation, and iii) In Smoothcache, we make use of recent advances in application-layer dynamic congestion control to manage priorities of transfers according to their urgency. We start by explaining why the HTTP live streaming semantics render many of the existing assumptions used in P2PLS protocols obsolete. Afterwards, we present our design starting with a baseline P2P caching model. We, then, show a number of optimizations related to aspects such as neighborhood management, uploader selection and proactive caching. Finally, we present our evaluation conducted on a real yet instrumented test network. Our results show that we can achieve substantial traffic savings on the source of the stream without major degradation in user experience.

show abstract

Randomized Decentralized Broadcasting Algorithms

Cited by 153 publications

References 10 publications

P2P Streaming Capacity under Node Degree Bound

P2P Streaming Capacity under Node Degree Bound

Network Awareness in P2P-TV Applications

SmoothCache: HTTP-Live Streaming Goes Peer-to-Peer

Contact Info

Product

Resources

About