Fig 4 - uploaded by Roberto Bruschi
Content may be subject to copyright.
ECDF of the query success rate for different overlay network topologies. The number of ultrapeers and their number of neighbors are reported for each curve
Source publication
Nowadays P2P applications dominate many networks. However, despite of their diffusion, the analysis of tele- traffic generated by these applications in real-time environment remains an open issue. In this paper we look at analytical and simulation models, which can be used for quantifying volumes of P2P teletraffic at the network layer, to ease sti...
Contexts in source publication
Context 1
... the section concerning the network layer, we report results about the query success rate of the system, showing that it can be strongly biased by modifications in the topology of the overlay network. In Fig. 4 we report the ECDF of the query success rate in case of 4 different ...
Context 2
... does not rise anymore, reporting a constant behavior. Initially files are available just in the EN, but as soon as they are downloaded, they become available in the whole network, causing a decline in the peak profile. The differences in Figures 7 and 8 are caused by the different query success rates of two overlay network topologies, reported in Fig. 4. In case of a low number of ultrapeers, the query success rate is so high that the presence of a honey-pot has an immediate impact on the network. In a more realistic case, like the one in Fig. 7, the strong sharing activity of one peer does not change significantly the traffic profiles. In this Section we look at our findings related ...
Context 3
... first show the case of 2,700 ultrapeers and 16 neighbors in Fig. 12. We would expect a reduction in the traffic with respect to the reference traffic profiles in Fig. 5, due to the lower query success rate reported in Fig. 4. The figure evidences that the system needs some days to reach the same values of offered load. The effect of the reduction in the query success rate is a slower trend in reaching the same traffic volume. We can then claim that the traffic generated in a network with a high number of ultrapeers (2,700) does not report differences, the ...
Similar publications
We have previously proposed a P2P video broadcast method called MTcast for simultaneously delivering video to user peers with different quality requirements. In this paper, we design and implement a prototype system of MT-cast and report the results of its performance evaluation in the real Internet environment. MTcast relies on each peer to transc...
In this paper, we investigate the limitation caused by reception bandwidth in current overlay streaming, and propose a novel overlay network architecture for high-quality, real-time streaming. The proposed architecture consists of two components: 1) join and retransmission control (JRC), and 2) redundant node selection (RNS). The JRC dy-namically a...
We propose and clarify the manner in which a distributed information retrieval (IR) is con-ducted using a Peer-to-Peer (P2P) technology that has approximately the same accuracy as a current index-integrated search engine with the statistical information calculated from the contents. We need to solve the following three problems to develop distribut...
Dynamic distributed system (DDS) is a continually running system with a large number of entities as processes or nodes that are connected with each other and each of them has only a partial view of the system as Peer-to-peer (P2P) system which can be decentralized, centralized or hybrid of both to make the system operations faster as possible. In P...
Multimedia contents are distributed to peers in various ways like downloading in peer-to-peer (P2P) overlay networks. A peer which holds a content, even a part of a content can provide other peers with the content. Multimedia streaming is more significant in multimedia applications than downloading way. We discuss how to support the multimedia stre...
Citations
This chapter discusses the efficiency aspects of caching systems. It explains the applications and performance aspects of caching. This is followed by a discussion on user request pattern for Internet content that can be characterized by Zipf laws with positive effect on cache hit rates. Traditionally, there are two main application areas for caching: Caching by operation systems of computers in fast storage in order to shorten delays in data access, and Web caching in order to shorten transport paths. The chapter evaluates the influence of caching strategies on the hit rate and reveals large differences between simple approaches and more elaborate methods, which combine statistics on requests in the past with adaption capability to changing popularity of objects. It concludes with a discussion on traffic management and optimization via content delivery (CDN) and peer-to-peer (P2P) overlays on the network infrastructure.
Many measurement studies are showing that peer-to-peer (P2P) file sharing applications have evolved to become a major traffic source in the Internet. The ability to quantify their impact on the network is fundamental for network managers, who have to guarantee a satisfactory service level to their customers. We present here a scalable simulation model, which aims at providing useful criteria in the capacity planning of Internet access links for enterprise networks, by considering the important effects of P2P file sharing traffic. Results are reported, along with a measurement study of real traffic traces, which confirms the validity of the model and its findings.
