Deriving traffic demands for operational IP networks: methodology and experience
IEEE/ACM Transactions on Networking (TON)
A distributed approach to measure IP traffic matrices
Proceedings of the 4th ACM SIGCOMM conference on Internet measurement
Traffic matrices: balancing measurements, inference and modeling
SIGMETRICS '05 Proceedings of the 2005 ACM SIGMETRICS international conference on Measurement and modeling of computer systems
Class-Based OSPF Traffic Engineering Inspired on Evolutionary Computation
WWIC '07 Proceedings of the 5th international conference on Wired/Wireless Internet Communications
An approach to measurement based quality of service control for communications networks
IM'09 Proceedings of the 11th IFIP/IEEE international conference on Symposium on Integrated Network Management
On the use of accounting data for QoS-aware IP network planning
ITC20'07 Proceedings of the 20th international teletraffic conference on Managing traffic performance in converged networks
Quality of Service constrained routing optimization using Evolutionary Computation
Applied Soft Computing
Traffic engineering approaches using multicriteria optimization techniques
WWIC'11 Proceedings of the 9th IFIP TC 6 international conference on Wired/wireless internet communications
QoSPlan: A Measurement Based Quality of Service aware Network Planning Framework
Journal of Network and Systems Management
A framework for robust traffic engineering using evolutionary computation
AIMS'13 Proceedings of the 7th IFIP WG 6.6 international conference on Autonomous Infrastructure, Management, and Security: emerging management mechanisms for the future internet - Volume 7943
| Hi-index | 0.00 |
Estimations of network demand are an essential input to the IP network planning process. We present a technique for per traffic class IP network demand estimation based on harnessing information gathered for accounting and charging purposes. This technique represents an efficient use of pre-existing information, is easy to deploy, and, crucially, is highly cost-effective in comparison to traditional direct measurement systems employing dedicated traffic metering hardware. In order to facilitate QoS-aware network planning we also introduce a technique for estimation of QoS related effective bandwidth coefficients via analysis of a relatively small number of packet traces. The combination of the demand and effective bandwidth coefficient estimation techniques provide the basis for an effective, low-cost network planning solution. In this paper we present initial results that validate our contention that network accounting records can be reused to create a QoS aware demand matrix for IP networks.