Topology aggregation for directed graphs
IEEE/ACM Transactions on Networking (TON)
Source-oriented topology aggregation with multiple QoS parameters in hierarchical networks
ACM Transactions on Modeling and Computer Simulation (TOMACS)
Crankback Prediction in Hierarchical ATM Networks
Journal of Network and Systems Management
A distributed cache architecture with snooping for QoS routing in large networks
Computer Networks: The International Journal of Computer and Telecommunications Networking
Big-bang simulation for embedding network distances in Euclidean space
IEEE/ACM Transactions on Networking (TON)
The effect of network hierarchy structure on performance of ATM PNNI hierarchical routing
Computer Communications
Towards an optimized abstracted topology design in cloud environment
Future Generation Computer Systems
| Hi-index | 0.00 |
In the future, global networks will consist of a hierarchy ofsubnetworks called domains. For reasons of both scalability andsecurity, domains will not reveal details of their internalstructure to outside nodes. Instead, these domains will advertiseonly a summary, or aggregated view, of their internal structure,e.g., as proposed by the ATM PNNI standard.This work compares, by simulation, the performance of severaldifferent aggregation schemes in terms of network throughput (thefraction of attempted connections that are realized), and networkcontrol load (the average number of crankbacks per realizedconnection). The simulation emulate a connection oriented networkwith a PNNI-like hierarchical source routing algorithm.Our main results are: (1) minimum spanning tree is a goodaggregation scheme; (2) exponential link cost functions performbetter than min-hop routing; (3) our suggested logarithmic updatescheme that determine when re-aggregation should be computed cansignificantly reduce the computational overhead due tore-aggregation with a negligible decrease in performance.