Analysis and simulation of a fair queueing algorithm
SIGCOMM '89 Symposium proceedings on Communications architectures & protocols
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
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
IEEE Journal on Selected Areas in Communications
Optimization driven bandwidth provisioning in service overlay networks
Computer Communications
Hi-index | 0.24 |
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.