Wykorzystanie logiki rozmytej w algorytmach AQM

• Autorzy: Płachecki K.

Warianty tytułu

EN

On a proposal of using fuzzy logic in AQM mechanism

• Języki publikacji: PL

Abstrakty

PL

W obecnych czasach wymagania stawiane sieciom TCP/IP zostały znacznie zróżnicowane poprzez aplikacje wymagające odmiennych poziomów usług sieciowych QoS (ang. Quality of Service). Dodatkowo, wzrastający udział transmisji czasu rzeczywistego RTP wymusza poszukiwanie nowych metod aktywnego zarządzania obsługą pakietów w węzłach sieci. Autor wskazuje możliwość wykorzystania logiki rozmytej w mechanizmach adaptacyjnych AQM (ang. Active Queueing Management), w celu poprawy wydajności układów zarządzania przepływem pakietów.

EN

Active Queue Management (AQM) is the name given to router mechanisms used in congestion control. AQM mechanisms manage queue lengths by dropping (or marking) packets during building up congestion, that is, before the queue is full. End-systems can then react to such losses by reducing their packet rate, hence avoiding severe congestion. AQM mechanisms are also relevant in the context of DiffServ. The DiffServ architecture has been defined to provide IP networks with scalable quality of service (QoS) processing of traffic aggregates, based on a special field in the IP header. This paper presents new active queue management mechanisms to provide congestion control in TCP/IP best-effort networks. The author propose how to use fuzzy logic to better solve the drop tail problem in the basic AQM mechanism (REM) with one buffer and a server. The objective of the fuzzy controller is to determine the optimal admission policies so as to maximise the average profit (reward minus cost). The proposed fuzzy logic approach for congestion control allows using linguistic knowledge to capture the dynamics of nonlinear probability marking functions. In the introduction the author defines a structure of Supervisory Expert Control System [10, 12, 14] and the project aims illustrated in Figs. 2 and 3 [15]. In Section 3 the author presents implementation of a new algorithm FREM that uses a Fuzzy Logic Controller. The model of FREM algorithm [8] is shown in Fig. 5. In Section 5 the author shows the plan on future works: a project of the FLC controller and verification of the FREM algorithm performance. The paper presents the FREM algorithm with nonlinear probability marking functions. There is shown a conception of applying Supervisory Expert Control System to congestion control in TCP/IP networks. The author proposes how to ensure the adaptation ability of the REM algorithm. The presented solution requires an additional FLC supervisory module. The objective of fuzzy controller is to determine the optimal admission policies so as to maximise the average profit (reward minus cost). The proposed fuzzy logic approach to congestion control allows using linguistic knowledge to capture the dynamics of nonlinear probability marking functions.

Słowa kluczowe

PL

logika rozmyta; aktywne zarządzanie kolejkami

EN

fuzzy logic; active queue management

• Wydawca: Wydawnictwo PAK
• Czasopismo: Pomiary Automatyka Kontrola
• Rocznik: 2009
• Tom: R. 55, nr 2
• Strony: 98--100
• Opis fizyczny: Bibliogr. 17 poz., rys., wzykr., wzory

Twórcy

autor

Płachecki K.

• Katedra Elektroniki, Politechnika Lubelska,

Bibliografia

• [1] Bertanzon C., Giacomazzi U., Gomiero F.: An export systems based diagnosis technique for industrial application, TOOLDIAG’93, Proc. Int. Conf. On Fault Diagnosis, Toulouse, France 1993, April 5-7, pp. 416-425.
• [2] Cholewa W., Pedrycz W.: Systemy doradcze, Skrypt uczelniany Pol. Śląskiej, Nr 1447, Gliwice 1987.
• [3] Chonggang W., Bo L., Kazem S., Yong P.: AFRED: An Adaptive Fuzzy-based Control Algorithm for Active Queue Management, 28th Annual IEEE International Conference on Local Computer Networks (LCN’03), p. 12.
• [4] Chrysostomou C., Pitsillides A., Rossides L., Sekercioglu A.: Fuzzy logic controlled RED: congestion control in TCP/IP differentiated services networks, Soft Computing 8, pp. 79-92, Springer-Verlag 2003.
• [5] Chrysostomou C., Pitsillides A., Hadjipollas G., Sekercioglu A., Polycarpu M.: Fuzzy Logic Congestion Control in TCP/IP Best-Effort Networks, Australian Telecommunications, Networks and Applications Conference, 8-10 December 2003, Sheraton Towers, Southbank, Melbourne.
• [6] Chwiałkowski E.: Sztuczna inteligencja w systemach eksperckich, MIKOM, Warszawa 1991.
• [7] Crookes D.: Architectures for high performance image processing: The future, Journal of Systems Architecture, nr 45, 1999.
• [8] Frank P. M.: Fuzzy supervision – Application of fuzzy logic to process supervision and fault diagnosis, Proc. Int. Workshop on Fuzzy Intelligent Systems, Duisburg, Germany, April 7-8, pp. 36-59.
• [9] Hipel K. W.: Fuzzy set techniques in decision making, Proc. IFAC Symp. On Theory and Application of Digital Control, January 5-7, New Delhi, India, Vol. 1, pp. 25-33.
• [10] Kulikowski R.: Wspomaganie decyzji. Systemy eksperckie, Instytut Badań Systemowych PAN, Warszawa 1995.
• [11] Lee C. C.: Fuzzy logic In control systems: Fuzzy logic controller – Part 1, IEEE Trans. On “Systems, Man and Cybernetics”, Vol. 20, No. 2, March/April 1990, pp. 404-435.
• [12] Möller N.: Window-based congestion control, Doctoral Thesis, Stockholm, Sweden 2008.
• [13] Pieczyński A.: Modelowanie rozmyte – struktury i parametry, Studia z Automatyki i Informatyki 2002, t. 27, pp. 99-122.
• [14] Płachecki K., Pawelski W.: Adaptacyjny algorytm przeciwdziałania przeciążeniom z logiką rozmytą, „Nowe Technologie Sieci Komputerowych”, WKŁ 2006.
• [15] Rutkowska D., Piliński M., Rutkowski L.: Sieci neuronowe, algorytmy genetyczne i systemy rozmyte, PWN, Warszawa Łódź 1999.
• [16] Sadiku M., Tofighi M.: A Tutorial on Simulation of Queueing Models, Int. J. Elect. Enging. Educ., Vol. 36, pp. 102-120, Manchester U. P., 1999.
• [17] Yang Y. R., Kim M. S., Lam S. S: Transient Behaviors of TCP-Friendly Congestion Control Protocols, IEEE INFOCOM, kwiecień 2001.