Prediction-based Active Queue Management in the Internet

• Autorzy: Jamali S. , Nosrati M. , Hashemi S. N.

Warianty tytułu

PL

Aktywne zarządzanie kolejką w Internecie bazujące na przewidywaniu

• Języki publikacji: EN

Abstrakty

EN

Random early detection (RED) is the most popular active queue management algorithm that is used by the Internet routers. This paper proposes a neuro-fuzzy controller which enhances the network performance by dynamically tuning of RED's maxp parameter. The controller first learns the network behavior against maxp variations and then adjusts maxp. Simulation results in ns-2 environment show that, the proposed learning RED, called LRED, keeps queue length and queuing delay in a pre-determined level and outperforms RED in terms of queue length and stability.

PL

W artykule zaprezentowano sterownik neuro-fuzzy który poprawia dynamiczne strojenie system RED stosowanego do kolejkowania w Internecie. Proponowany uczący się algorytm nazwany LRED pozwala na utrzymanie długości kolejki i opóźnienia w założonych granicach.

Słowa kluczowe

EN

active queue management; neuro-fuzzy; RED

PL

Internet; kolejkowanie; RED

• Wydawca: Wydawnictwo SIGMA-NOT
• Czasopismo: Przegląd Elektrotechniczny
• Rocznik: 2013
• Tom: R. 89, nr 1a
• Strony: 296--299
• Opis fizyczny: Bibliogr. 12 poz., schem., wykr.

Twórcy

autor

Jamali S.

• University of Mohaghegh Ardabili

autor

Nosrati M.

• Payame Noor University

autor

Hashemi S. N.

• Islamic Azad University

Bibliografia

• [1] Arani E., Lucas C., Araabi B. N., “WLoLiMoT: A Wavelete and LoLiMoT Based Algorithm for Time Series Prediction”, Integrated Systems, Design and Technology, 2010.
• [2] Cisco Systems, Congestion Avoidance Overview, Available from: http://www.cisco.com/univercd/cc/td/doc/product/software/ios12 0/12cgcr/qos_c/qcpart3.
• [3] Floyd, V. Jacobson, “Random early detection gateways for congestion avoidance”, IEEE/ACM Transactions Networking, 1993.
• [4] Gholipour A., Araabi B. N., Lucas C., “Predicting Chaotic Time Series Using Neural and Neurofuzzy Models: A Comparative Study”, neural processing letters, volume 24, number 3, 2009.
• [5] Gholipour A., Lucas C., Araabi B. N., Mirmomeni M., and Shafiee M., “Extracting the main patterns of natural time series for longterm neuro fuzzy prediction,” Neural Computing and Applications, 2006.
• [6] May M., Bolot J., Diot C., Lyles B., “Reasons Not to Deploy RED”, 7th. International Workshop on Quality of Service, 1999.
• [7] Mirmomeni M., Lucas C., Moshiri B., Araabi B. N., “Introducing adaptive neurofuzzy modeling with online learning method for prediction of time-varying solar and geomagnetic activity indices”, Expert systems with applications, Volume 37, Issue 12, 2010.
• [8] Misra V., Gong W. Bo, Towsley D. F., “Fluid-based Analysis of a Network of AQM Routers Supporting TCP Flows with an Application to RED”, SIGCOMM, 2000.
• [9] Nelles O., Nonlinear system identification, Springer Verlag press, 2001.
• [10] Network Simulator-ns2, http://-mash.cs.berkelay.edu/ns.
• [11] Ott T., Lakshman T., Wong L., SRED: Stabilized RED, Infocom, 1999.
• [12] Pedram A., Jamali M. R., Pedram T., Fakhraie S. M., Lucas C., “Local Linear Model Tree (LOLIMOT) Reconfigurable Parallel Hardware”, World Academy of Science, Engineering and Technology, 2006.