Please use this identifier to cite or link to this item:
|Title: ||A Fair and Efficient SOM-based Feedback Congestion Control Scheme for ATM ABR Services|
|Authors: ||Chang, Ing-Chau;Hsieh, Sheng-Wen|
|Issue Date: ||2012-05-25T07:47:37Z
|Publisher: ||Int. Inst. Inf. & Syst, Orlando, FL, USA|
|Abstract: ||ABR lite congestion control schemes, such as forward explicit congestion notification (FECN), backward explicit congestion notification (BECN), proportional rate control algorithm (PRCA), etc., have been proposed for congestion control of ATM available bit rate (ABR) services. However, unfair distributions of available ABR bandwidth among ABR VCs do occur. in this paper, combining the three-load-state buffering and linear time self-organizing map (SOM) neural network model, the SOM-based feedback congestion control (SFCC) scheme is proposed. With the SFCC scheme, current ABR VCs are adaptively classified into different classes when forthcoming congestion is predicted. ACR rates of different ABR VC classes are modified with different values to achieve low cell loss rate, high link utilization and fair share of ABR bandwidth in a dynamic ATM environment. Using statistical hypothesis testing, the achieved fairness of the SFCC scheme is significantly superior to previous schemes.|
|Relation: ||The 6th World Multi-Conference on SYSTEMICS, CYBERNETICS AND INFORMATICS (SCI 2002), Orlando, Florida U.S.A., July 2002: 88-93|
|Appears in Collections:||[資訊工程學系] 會議論文|
Files in This Item:
There are no files associated with this item.
All items in NCUEIR are protected by copyright, with all rights reserved.