A quantitative comparison of graph-based models for Internet topology
IEEE/ACM Transactions on Networking (TON)
Chord: A scalable peer-to-peer lookup service for internet applications
Proceedings of the 2001 conference on Applications, technologies, architectures, and protocols for computer communications
A scalable content-addressable network
Proceedings of the 2001 conference on Applications, technologies, architectures, and protocols for computer communications
Internet indirection infrastructure
Proceedings of the 2002 conference on Applications, technologies, architectures, and protocols for computer communications
The impact of DHT routing geometry on resilience and proximity
Proceedings of the 2003 conference on Applications, technologies, architectures, and protocols for computer communications
ATEC '04 Proceedings of the annual conference on USENIX Annual Technical Conference
Designing a DHT for low latency and high throughput
NSDI'04 Proceedings of the 1st conference on Symposium on Networked Systems Design and Implementation - Volume 1
Realization of the next-generation network
IEEE Communications Magazine
NGN architecture: generic principles, functional architecture, and implementation
IEEE Communications Magazine
Tapestry: a resilient global-scale overlay for service deployment
IEEE Journal on Selected Areas in Communications
Hi-index | 0.00 |
The authors are advocating the "Minimum Core" architecture toward New Generation Network (NWGN). In the architecture, network functionalities in the core network (e.g. mobility management, session control and application servers) are minimized by shifting them to access networks. This approach ensures high scalability essential for future networks. This paper proposes a session control method for the "Minimum Core", in which the call-setup time is guaranteed by cooperating core and overlay networks while minimizing processing and traffic load on the core network. In this method, latency on the overlay network is estimated prior to the session being established. If the estimated latency is desirable, the overlay network is utilized and otherwise the core system. This paper also proposes a blacklist scheme, which realizes on-the-fly decisions of the latency without increasing measurement traffic on the overlay network. Evaluation results on a developed test-bed system show the proposed methods drastically suppress the probability of call-setup time exceeding the desired time, and also mitigate the processing burden of the core compared to current centralized architecture.