Title :
MOPS: Providing Content-Based Service in Disruption-Tolerant Networks
Author :
Li, Feng ; Wu, Jie
Author_Institution :
Dept. of Comput. Sci. & Eng., Florida Atlantic Univ., Boca Raton, FL, USA
Abstract :
Content-based service, which dynamically routes and delivers events from sources to interested users, is extremely important to network services. However, existing content-based protocols for static networks will incur unaffordable maintenance costs if they are applied directly to the highly mobile environment that is featured in disruption-tolerant networks (DTNs). In this paper, we propose a unique publish/subscribe scheme that utilizes the long-term social network properties, which are observed in many DTNs, to facilitate content-based services in DTNs. We distributively construct communities based on the neighboring relationships from nodes´ encounter histories. Brokers are deployed to bridge the communities, and they adopt a locally prioritized pub/sub scheme which combines the structural importance with subscription interests, to decide what events they should collect, store, and propagate. Different trade-offs for content-based service can be achieved by tuning the closeness threshold in community formation or by adjusting the broker-to-broker communication scheme. Extensive real-trace and synthetic-trace driven simulation results are presented to support the effectiveness of our scheme.
Keywords :
computer networks; middleware; mobile computing; MOPS; broker-to-broker communication scheme; content-based protocols; content-based service; disruption-tolerant networks; mobile environment; network services; publish/subscribe scheme; social network property; static networks; subscription interests; unaffordable maintenance costs; Bridges; Computer science; Costs; Delay; Disruption tolerant networking; Distributed computing; Network topology; Protocols; Social network services; Subscriptions; Disruption-tolerant networks (DTNs); localized algorithms; publish/subscribe; social network analysis;
Conference_Titel :
Distributed Computing Systems, 2009. ICDCS '09. 29th IEEE International Conference on
Conference_Location :
Montreal, QC
Print_ISBN :
978-0-7695-3659-0
Electronic_ISBN :
1063-6927
DOI :
10.1109/ICDCS.2009.28