Metrics for quantifying benefits and cost of session switchovers

Authors:
Mariusz A. Fecko;M. Ümit Uyar;Sunil Samtani;Jianliang Zheng
Affiliations:
Telcordia Technologies, Inc., Morristown, NJ;The City College of the City University of New York, New York, NY;Telcordia Technologies, Inc., Morristown, NJ;The City College of the City University of New York, New York, NY
Venue:
MILCOM'03 Proceedings of the 2003 IEEE conference on Military communications - Volume II
Year:
2003

Citing 6
Cited 0

Performance Study of Reliable Server Pooling

NCA '03 Proceedings of the Second IEEE International Symposium on Network Computing and Applications
Reliable Server Pooling in Highly Mobile Wireless Networks

ISCC '03 Proceedings of the Eighth IEEE International Symposium on Computers and Communications
On-Demand Multicasting in Ad-Hoc Networks: Comparing AODV and ODMRP

ICDCS '02 Proceedings of the 22 nd International Conference on Distributed Computing Systems (ICDCS'02)
Fine-grained failover using connection migration

USITS'01 Proceedings of the 3rd conference on USENIX Symposium on Internet Technologies and Systems - Volume 3
Reliable server pooling for future combat systems

MILCOM'03 Proceedings of the 2003 IEEE conference on Military communications - Volume II
Evaluation of architectures for reliable server pooling in wired and wireless environments

IEEE Journal on Selected Areas in Communications

Quantified Score

Hi-index	0.00

Visualization

Abstract

To persistently maintain client-server connections in mobile ad-hoc networks, we investigate the reliable server pooling (RSP), where servers that can provide equivalent functionality are pooled together. The RSP is meant to increase the availability and survivability of the battlefield infrastructure by allowing clients to access a pool of redundant information sources. As a result, some failed sessions are going to be prolonged through a series of transparent switchovers beyond the time of the first failure. However, both the prolonged sessions and the RSP infrastructure itself will put additional stress on the network and server resources. This paper introduces a classification of switchovers and sessions (sustained, lost, and inconclusive), and then defines several metrics that quantify the aggregate benefit and cost of RSP in a system: session sustainability throughput, gain, and cost, as well as switchover efficiency. A set of simulation experiments are run to better illustrate the meaning and practical application of the defined metrics.