Fuzzy explicit marking for congestion control in differentiated services networks

Chrysostomou, Chrysostomos; Pitsillides, Andreas; Hadjipollas, G.; Şekercioğlu, Y. Ahmet; Polycarpou, Marios M.

doi:10.1109/iscc.2003.1214139

Cited by 22 publications

(12 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Chrysostomou et al [11] presented the effects of using fuzzy logic technique in the operation of RED-Fuzzy-RED. They believe that with fuzzy logic we are able to implement and better understand nonlinear systems, achieve better differentiation for dropping of packets in aggregated flows and provide better Q O S for various type of traffics.…”

Section: Review Of Related Workmentioning

confidence: 99%

An Intelligent Fuzzy Logic System for Network Congestion Control

Preye¹,

Nneka²

2017

CCS Archive

View full text Add to dashboard Cite

Network congestion is a major problem in all network environments as such it calls for ways to manage this problem. In this paper, we propose a Fuzzy Regulator Effective Random Early Detection (FRERED) system, which is an intelligent fuzzy logic based controller technique for early stage congestion detection, at the router buffer in the networks. The proposed technique extends the Fuzzy-Based system in the Fuzzy Hybrid ERED algorithm by considering the delay variable in its inference system to ease the problem of parameter initialization and parameter dependency. Unlike the Fuzzy-Based controller in the existing Fuzzy Hybrid ERED system which uses two parameter settings in its inference system that is, the queue size and average queue length in computing the dropping probability of packets. The proposed technique uses the queue size, average queue length and the delay approximation as input variables in computing the packet drop probability. The applied fuzzy logic system yields an output that denotes a packet dropping probability, which in turn controls and prevents congestion in early stage. This was achieved after simulating the proposed technique and the existing Fuzzy-Based controller using Matlab. The results obtained shows that this approach results in less packet drops for about the same link utilization as the existing Fuzzy-Based controller. Therefore, this technique, generally, controls network congestion and improves network performance. The methodology used to achieve this is the object oriented methodology and JAVA programming language was used to develop the system.

show abstract

Section: Review Of Related Workmentioning

confidence: 99%

An Intelligent Fuzzy Logic System for Network Congestion Control

Preye¹,

Nneka²

2017

CCS Archive

View full text Add to dashboard Cite

show abstract

“…Nevertheless, these early designs have various shortcomings including cell loss (even though cell loss is used as a congestion signal to compute the rate factor, e.g., [12]), queue size fluctuations, poor network latency, stability and low utilization. Later, FLC was used in Random Early Detection (RED) algorithm in TCP/IP networks, e.g., [13], [14], to reduce packet loss rate and improve utilization. However, they are still providing implicit or imprecise congestion signaling, and therefore cannot overcome the throughput fluctuations and conservative behavior of TCP sources.…”

Section: Related Workmentioning

confidence: 99%

A Fuzzy Controller for TCP Improvement over Mobile Networks

Qasim¹,

Alisa²

2014

IJCA

View full text Add to dashboard Cite

The Transmission Control Protocol (TCP) is used for reliable delivery of data over unreliable networks. Practically, most TCP mechanisms have been carefully designed for wired networks. Neglecting the characteristics of wireless environments can lead to TCP implementations with poor performance. In order to use TCP in mobile networks, improvements have been proposed in this paper to enhance TCP algorithm to distinguish between the different types of loss events. In mobile or static wireless environments, losses are not always due to network congestion, as in the case of wired networks. In this paper, a modified algorithm is presented using fuzzy controller to differentiate the loss events (error loss from congestion loss) that intend at adapting TCP to mobile and static wireless environments with better performance. Simulation results were performed using OMNET simulator and have showed that the new proposal has better throughput than other TCP schemes.

show abstract

“…Even though this mechanism succeeds in achieving relative differentiation among the several precedences within a queue, it is plagued by the parameter sensitivity problem 3 [13] [7]. Several schemes such as ARIO [14], DRED-MP [1], ARIO-D and ARIO-L [12] STAVQ [3], Fuzzy logic based AQM [4], have been proposed to overcome the shortcomings of RIO. Most of these schemes are in some way (directly or indirectly) a variant of RIO with support for adaptive parameter tuning.…”

Section: Related Workmentioning

confidence: 99%

“…This average is then used to forecast the average queue length over the next PI using Recursive Least Squares (RLS) algorithm -a popular algorithm from adaptive filter theory. The deviation of the predicted average queue size from the target queue size feeds into the computation of the packet drop probability (PDP) 4 . Whenever a packet arrives, the instantaneous queue length (qi) is compared against the target queue length (q0).…”

Section: Framework For Proactive Queue Managementmentioning

confidence: 99%

Building a controlled delay assured forwarding class in differentiated services networks

Kulkarni¹,

Mohammad²,

McClean³

2006

Proceedings of the 2006 SIGCOMM Workshop on Internet Network Management

View full text Add to dashboard Cite

Several Active Queue Management (AQM) based solutions have been proposed to enable service differentiation in the DiffServ Assured Forwarding (AF) class(es). Most of these solutions, however, provide throughput guarantees only. This paper proposes a new queue management approach called PAQMAN-DS which provides quantitative controlled delay guarantees to delay sensitive applications in the AF class. The proposed approach is based on predicting the future state of the queue and requires specification of only a single parameter (target delay) per hop. Performance evaluation of PAQMAN-DS through ns-2 simulations reveals that it regulates the delay around the target mark on a per-hop basis, discriminates in favour of IN contract traffic and simultaneously achieves high link utilization.

show abstract

Fuzzy explicit marking for congestion control in differentiated services networks

Cited by 22 publications

References 11 publications

An Intelligent Fuzzy Logic System for Network Congestion Control

An Intelligent Fuzzy Logic System for Network Congestion Control

A Fuzzy Controller for TCP Improvement over Mobile Networks

Building a controlled delay assured forwarding class in differentiated services networks

Contact Info

Product

Resources

About