Adaptive statistical QoS: learning parameters to maximize end-to-end network good-put

Authors:
Scott C. Evans;Ping Liu;Asavari Rothe;Kai Goebel;Weizhong Yan;Ishan Weerakoon;Marty Egan
Affiliations:
GE Research, Niskayuna, NY;GE Research, Niskayuna, NY;GE Research, Niskayuna, NY;GE Research, Niskayuna, NY;GE Research, Niskayuna, NY;Lockheed Martin Integrated System Solutions, Clarksburg, MD;Lockheed Martin Integrated System Solutions, Clarksburg, MD
Venue:
MILCOM'06 Proceedings of the 2006 IEEE conference on Military communications
Year:
2006

Citing 4
Cited 0

An Adaptive Policy Based Management Framework for Differentiated Services Networks

POLICY '02 Proceedings of the 3rd International Workshop on Policies for Distributed Systems and Networks (POLICY'02)
Dynamic core provisioning for quantitative differentiated services

IEEE/ACM Transactions on Networking (TON)
Theory, Volume 1, Queueing Systems

Theory, Volume 1, Queueing Systems
Route Based QoS and the Biased Early Drop Algorithm (BED)

Proceedings of the Second International Conference on Quality of Service in Heterogeneous Wired/Wireless Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

We present an Adaptive QoS System that seeks to maximize end-to-end success through learning algorithms that take queue depths as input to control Weighted Fair Queue provision. Utilizing an analytical model we generate queue depth and E2E success data for various levels of load and WFQ provision and generate a WFQ provision surface for two classes of real time traffic using Neural Network techniques. We verify the nature of the surface through event driven simulation and discuss future opportunities for adaptive QoS policy management.