Minimizing Transmission Costs through Adaptive Marking in Differentiated Services Networks

Authors:
Chen-Khong Tham;Yong Liu
Affiliations:
-;-
Venue:
MMNS '02 Proceedings of the 5th IFIP/IEEE International Conference on Management of Multimedia Networks and Services: Management of Multimedia on the Internet
Year:
2002

Citing 9
Cited 2

Technical Note: \cal Q-Learning

Machine Learning
Adaptive packet marking for maintaining end-to-end throughput in a differentiated-services internet

IEEE/ACM Transactions on Networking (TON)
Neuro-Dynamic Programming

Neuro-Dynamic Programming
Learning to Predict by the Methods of Temporal Differences

Machine Learning
Qos measurement and management for internet real-time multimedia services

Qos measurement and management for internet real-time multimedia services
Call admission control and routing in integrated services networks using neuro-dynamic programming

IEEE Journal on Selected Areas in Communications
Adaptive call admission control under quality of service constraints: a reinforcement learning solution

IEEE Journal on Selected Areas in Communications
A random early demotion and promotion marker for assured services

IEEE Journal on Selected Areas in Communications
A dynamic channel assignment policy through Q-learning

IEEE Transactions on Neural Networks

Assured end-to-end QoS through adaptive marking in multi-domain differentiated services networks

Computer Communications
Reinforcement learning-based dynamic bandwidth provisioning for quality of service in differentiated services networks

Computer Communications

Quantified Score

Hi-index	0.00

Visualization

Abstract

The issue of resource management in multi-domain Differentiated Services (DiffServ) networks has attracted a lot of attention from researchers who have proposed various provisioning, adaptive marking and admission control schemes. In this paper, we propose a Reinforcement Learning-based Adaptive Marking (RLAM) approach for providing end-to-end delay and throughput assurances, while minimizing packet transmission costs since 'expensive' Per Hop Behaviors (PHBs) like Expedited Forwarding (EF) are used only when necessary. The proposed scheme tries to satisfy per flow end-to-end QoS through control actions which act on flow aggregates in the core of the network. Using an ns2 simulation of a multi-domain DiffServ network with multimedia traffic, the RLAM scheme is shown to be effective in significantly lowering packet transmission costs without sacrificing end-to-end QoS when compared to static and random marking schemes.