Solution to weight-adaptive fair queuing

The weighted fair queuing (WFQ) suffers from the transmission disorder problem while applying adaptive weight adjustment since its virtual time implementation does not yield the correct approximation of the generalised processor sharing scheme under weight adjustments. This is because the backlogged packets' timestamps are not updated properly with the change of weights. A new algorithm, timestamp-update WFQ (T-WFQ), is proposed to avoid the above problem by updating the timestamps of all the backlogged packets as soon as the weight adjustment takes place.

[1]  T. Hamalainen,et al.  Revenue and delay control in 3G service network , 2004, IEEE 60th Vehicular Technology Conference, 2004. VTC2004-Fall. 2004.

[2]  Yau-Hwang Kuo,et al.  An adaptive approach to weighted fair queue with QoS enhanced on IP network , 2001, Proceedings of IEEE Region 10 International Conference on Electrical and Electronic Technology. TENCON 2001 (Cat. No.01CH37239).

[3]  Abhay Parekh,et al.  A generalized processor sharing approach to flow control in integrated services networks: the single-node case , 1993, TNET.

[4]  James Zijun Wang,et al.  Self-Configuration Protocols for Small-Scale P2P Networks , 2006, 2006 IEEE/IFIP Network Operations and Management Symposium NOMS 2006.