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

Authors:
Chen-Khong Tham;Timothy Chee-Kin Hui
Affiliations:
Department of Electrical and Computer Engineering, National University of Singapore, Singapore, Singapore;Department of Electrical and Computer Engineering, National University of Singapore, Singapore, Singapore
Venue:
Computer Communications
Year:
2005

Citing 12
Cited 1

Analysis and simulation of a fair queueing algorithm

SIGCOMM '89 Symposium proceedings on Communications architectures & protocols
Simple Statistical Gradient-Following Algorithms for Connectionist Reinforcement Learning

Machine Learning
Technical Note: \cal Q-Learning

Machine Learning
Random early detection gateways for congestion avoidance

IEEE/ACM Transactions on Networking (TON)
An engineering approach to computer networking: ATM networks, the Internet, and the telephone network

An engineering approach to computer networking: ATM networks, the Internet, and the telephone network
Proportional differentiated services: delay differentiation and packet scheduling

Proceedings of the conference on Applications, technologies, architectures, and protocols for computer communication
Minimizing Transmission Costs through Adaptive Marking in Differentiated Services Networks

MMNS '02 Proceedings of the 5th IFIP/IEEE International Conference on Management of Multimedia Networks and Services: Management of Multimedia on the Internet
Dynamic Core Provisioning for Quantitative Differentiated Service

IWQoS '01 Proceedings of the 9th International Workshop on Quality of Service
Forecasting network traffic using FARIMA models with heavy tailed innovations

ICASSP '00 Proceedings of the Acoustics, Speech, and Signal Processing, 2000. on IEEE International Conference - Volume 06
Dynamic resource management considering the real behavior ofaggregate traffic

IEEE Transactions on Multimedia
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

Optimization driven bandwidth provisioning in service overlay networks

Computer Communications

Quantified Score

Hi-index	0.24

Visualization

Abstract

The issue of bandwidth provisioning for Per Hop Behavior (PHB) aggregates in Differentiated Services (DiffServ) networks is imperative for differentiated QoS to be achieved. This paper proposes an adaptive provisioning scheme that determines at regular intervals the amount of bandwidth to provision for each PHB aggregate, based on traffic conditions and feedback received about the extent to which QoS is being met. The scheme adjusts parameters to minimize a penalty function that is based on the QoS requirements agreed upon in the service level agreement (SLA). The novel use of a continuous-space, gradient-descent reinforcement learning algorithm enables the scheme to work effectively without accurate traffic characterization or any assumption about the network model. Using ns-2 simulations, we show that the algorithm is able to converge to a policy that provisions bandwidth such that QoS requirements are satisfied.