A Model of Evaluation of Adaptive Backpressure in Network of Queue

S. Lekcharoen, C. Chaochanchaikul, and C. Jittawiriyanukoon (Thailand)


Fuzzy control policing mechanisms, policing mechanisms, and backpressure


Congestion in network occurs when the demand exceeds the availability of network resources, leading to lower throughputs and higher delays. If congestion is not properly controlled, some sessions transported by the network may not meet their quality-of-service (QoS) requirements. When congestion builds up in a network, two general approaches are possible to cope with the shortage of buffer space. One approach is to drop incoming frames for which buffer is not available and to rely on the end-to-end protocols for the recovery of lost packets. However, as one way to solving this problem, we purpose a backpressure algorithm under which no frames will be dropped inside a network frame, even when congestion builds up, if congested nodes send backpressure feedback to neighboring nodes, informing them of unavailability of buffering capacity and stopping them from forwarding more frames until enough buffer becomes available. While there are potential advantages in backpressure networks that do not allow frames dropping, in this paper, we propose backpressure algorithm that aims at detecting violations in parameter negotiation. We evaluate and compare the performance of the backpressure with three fuzzy logic control policing mechanisms, namely: Fuzzy Leaky Bucket(FLB), Fuzzy Jumping Window(FJW) and Fuzzy Triggered Jumping Window(FTJW). Simulation results show that on VDSL frames, the backpressure helps improve high throughputs and non dropped frames compared to other fuzzy control policing mechanisms. In any case, backpressure meets its quality-of-service (QoS) requirements if source traffic is at low peak rate.

Important Links:

Go Back