A Genetic Algorithm for the Design of a Fuzzy Controller for Active Queue Management (Articolo in rivista)

Type
Label
  • A Genetic Algorithm for the Design of a Fuzzy Controller for Active Queue Management (Articolo in rivista) (literal)
Anno
  • 2003-01-01T00:00:00+01:00 (literal)
Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#doi
  • 10.1109/TSMCC.2003.818946 (literal)
Alternative label
  • Di Fatta Giuseppe, Hoffmann Frank, Lo Re Giuseppe, Urso Alfonso (2003)
    A Genetic Algorithm for the Design of a Fuzzy Controller for Active Queue Management
    in IEEE transactions on systems, man and cybernetics. Part C, Applications and reviews
    (literal)
Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#autori
  • Di Fatta Giuseppe, Hoffmann Frank, Lo Re Giuseppe, Urso Alfonso (literal)
Pagina inizio
  • 313 (literal)
Pagina fine
  • 324 (literal)
Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#numeroVolume
  • 33-3 (literal)
Rivista
Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#descrizioneSinteticaDelProdotto
  • In this paper, a Fuzzy Proportional Integral controller for Active Queue Management is adopted in order to achieve both good queue regulation and high link utilization. A Genetic Algorithm is proposed and evaluated for the optimal tuning of the FPI controller parameters. Fast response to high load variations and disturbance rejection in steady-state behavior are the main objectives of the controller design method. These design goals are encoded in a performance index and the genetic algorithm is used as valid tool for the optimal tuning of the fuzzy system parameters, such as peak values of membership functions and system scaling factors. The Fuzzy PI controller is tested under different traffic conditions and compared to other AQM policies. The experiments show that the Fuzzy PI controller outperforms the other AQM policies in various operating conditions, especially in situations of functioning different from the design operating point. The improvement in terms of response time and link utilization is due to the non linear characteristics of the Fuzzy controller that is able to adapt its closed loop gain under different operating conditions and high variability of the traffic load. (literal)
Note
  • Google Scholar (literal)
  • Scopus (literal)
  • ISI Web of Science (WOS) (literal)
Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#affiliazioni
  • 1,3,4- ICAR-CNR; 2- University of Dortmund; (literal)
Titolo
  • A Genetic Algorithm for the Design of a Fuzzy Controller for Active Queue Management (literal)
Abstract
  • Active Queue Management (AQM) policies are those policies of router queue management that allow the detection of network congestion, the notification of such occurrences to the hosts on the network borders, and the adoption of a suitable control policy. This paper proposes the adoption of a Fuzzy Proportional Integral (FPI) controller as an active queue manager for Internet routers. The analytical design of the proposed FPI controller is carried out in analogy with a Proportional Integral (PI) controller, which recently has been proposed for AQM. A genetic algorithm is proposed for tuning of the FPI controller parameters with respect to optimal disturbance rejection. In the paper the FPI controller design metodology is described and the result of comparisons with Random Early Detection (RED), Tail Drop and PI controller is presented. (literal)
Prodotto di
Autore CNR
Insieme di parole chiave

Incoming links:


Prodotto
Autore CNR di
Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#rivistaDi
Insieme di parole chiave di
data.CNR.it