Failure-Tolerant Overlay Trees for Large-Scale Dynamic Networks

Frey, Davide; Murphy, Amy L.

doi:10.1109/p2p.2008.30

Cited by 12 publications

(16 citation statements)

References 28 publications

(28 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…If changes of the weights are asynchronous and infrequent, the a ected parent-child connections may be simply dropped and the coordination level of AETOS must guarantee that the new connections are coordinated based on the up-to-date weights. If dropping connections is not a desirable approach, alternative reactive mechanisms such as the one of Frey and Murphy [2008] may be applicable. Another solution is to use the 'healer' peer selection policy of the peer sampling service in the discovery level [Jelasity et al, 2007].…”

Section: Discussion and Future Workmentioning

confidence: 99%

“…Disconnected overlay networks do not perform well as network resources remain unexploited in multiple disconnected clusters or components as referred in graph theory. For example, a multimedia multicasting application is disrupted [Frey and Murphy, 2008] if a tree is disconnected and, therefore, content cannot be forwarded further. Similarly, aggregation queries over a disconnected tree result in inaccurate estimations of aggregates [Li et al, 2006, Ogston andJarvis, 2010].…”

Section: Graph Properties and Applicationsmentioning

confidence: 99%

“…Frey and Murphy [2008] propose a number of transformation and rewiring strategies for reconnecting disconnected branches. The configuration of tree connections is similar to the configuration which the coordination level of AETOS performs.…”

Section: Comparison With Related Workmentioning

confidence: 99%

“…The configuration of tree connections is similar to the configuration which the coordination level of AETOS performs. However, the adaptations of Frey and Murphy [2008] do not sort a tree or control its graph properties required for an application.…”

Section: Comparison With Related Workmentioning

confidence: 99%

See 3 more Smart Citations

Multi-level reconfigurable self-organization in overlay services

Pournaras¹

View full text Add to dashboard Cite

Section: Discussion and Future Workmentioning

confidence: 99%

Section: Graph Properties and Applicationsmentioning

confidence: 99%

Section: Comparison With Related Workmentioning

confidence: 99%

Section: Comparison With Related Workmentioning

confidence: 99%

See 2 more Smart Citations

Multi-level reconfigurable self-organization in overlay services

Pournaras¹

View full text Add to dashboard Cite

“…Typical structures used in constructing reliable overlay networks for data dissemination include forest [12], [13], [14], [15], [16], [17] and mesh [11], [18], [19] structures. In these overlay networks, each node has multiple neighbors and hence there exist multiple data paths via which information may reach their final destinations; unless all paths are unavailable simultaneously, data dissemination works without any retransmission or reconfiguration.…”

Section: Introductionmentioning

confidence: 99%

Assessing the Impact of Geographically Correlated Failures on Overlay-Based Data Dissemination

Kim

Venkatasubramanian

2010

2010 IEEE Global Telecommunications Conference GLOBECOM 2010

View full text Add to dashboard Cite

Abstract-This paper addresses reliability of data dissemination applications when there are severe disruptions to the underlying physical infrastructure. Such massive simultaneous physical failures can happen during the geographical events such as natural disasters (earthquakes, floods, tornados) or sudden power outages -infrastructure failures in these cases are geographically correlated. In particular, we focus on overlay based data dissemination mechanisms and explore their ability to tolerate such large geographically correlated failures. Due to the tight correlation between multiple overlay links and a single physical link, a few physical failures may affect lots of overlay links. To enable reliable dissemination under such conditions, we propose overlay network construction methods that incorporate proximity-aware neighbor selection methods to improve the performance of the overlay data dissemination, to the extent possible, in terms of reliability and latency. In this approach, the overlay nodes select neighbors which are most likely distinct in presence of a geographical failure; we show how an overlay structure constructed using our proximity-aware neighbor selection techniques can disseminate data to over 80% of reachable end clients without any significant additional latency under various geographical failure conditions.

show abstract

Self-Optimised Tree Overlays Using Proximity-Driven Self-Organised Agents

Pournaras

Warnier

Brazier

2010

Complex Intelligent Systems and Their Applications

View full text Add to dashboard Cite

Hierarchical structures are often deployed in large scale distributed systems to structure communication. Building and maintaining such structures in dynamic environments is challenging. Self-organisation is the approach taken in this chapter. AETOS, the Adaptive Epidemic Tree Overlay Service, provides tree overlays on demand. AETOS uses three local agents to this purpose (i) to translate application requirements to self-organisation requirements, (ii) to self-organise nodes into optimised tree topologies based on these requirements, (iii) to control bootstrapping and termination of self-organisation. The evaluation of AETOS in different simulation settings shows that it provides high connectivity in tree overlays optimised according to application requirements.

show abstract

Failure-Tolerant Overlay Trees for Large-Scale Dynamic Networks

Abstract: Abstract

Cited by 12 publications

References 28 publications

Multi-level reconfigurable self-organization in overlay services

Multi-level reconfigurable self-organization in overlay services

Assessing the Impact of Geographically Correlated Failures on Overlay-Based Data Dissemination

Self-Optimised Tree Overlays Using Proximity-Driven Self-Organised Agents

Contact Info

Product

Resources

About