Future networks are expected to provide improved support for several different kinds of applications and services. All these services will have diverse characteristics and requirements to be satisfied. A potential technology to upgrade efficiently and effectively current generation networks is virtualization via network “softwarization.” This approach requires the combination of software-defined networking (SDN) and network function virtualization. Nevertheless, such a new complex network structure will raise further issues and challenges to be solved both reactively and proactively, without human intervention. In order to achieve that, academia and industry have identified the solution in the implementation and deployment of machine learning. Hence, very likely, 5G (and especially beyond 5G) networks will be cognitive virtualized networks. In that context, this paper proposes a cognitive SDN architecture based on fuzzy cognitive maps (FCMs). First, specific design modifications of FCMs are proposed to overcome some well-known issues of this learning paradigm. Second, the efficient integration with an SDN architecture is presented and analyzed. Finally, the emulation of a sample network scenario via Mininet is provided to validate the effectiveness and the potential of the new cognitive system and its capability to act and to adapt independently of human intervention.

Cognitive Software-Defined Networking Using Fuzzy Cognitive Maps / Baggio, Giovanni; Bassoli, Riccardo; Granelli, Fabrizio. - In: IEEE TRANSACTIONS ON COGNITIVE COMMUNICATIONS AND NETWORKING. - ISSN 2332-7731. - ELETTRONICO. - 5:3(2019), pp. 517-539. [10.1109/TCCN.2019.2920593]

Cognitive Software-Defined Networking Using Fuzzy Cognitive Maps

Bassoli, Riccardo;Granelli, Fabrizio
2019-01-01

Abstract

Future networks are expected to provide improved support for several different kinds of applications and services. All these services will have diverse characteristics and requirements to be satisfied. A potential technology to upgrade efficiently and effectively current generation networks is virtualization via network “softwarization.” This approach requires the combination of software-defined networking (SDN) and network function virtualization. Nevertheless, such a new complex network structure will raise further issues and challenges to be solved both reactively and proactively, without human intervention. In order to achieve that, academia and industry have identified the solution in the implementation and deployment of machine learning. Hence, very likely, 5G (and especially beyond 5G) networks will be cognitive virtualized networks. In that context, this paper proposes a cognitive SDN architecture based on fuzzy cognitive maps (FCMs). First, specific design modifications of FCMs are proposed to overcome some well-known issues of this learning paradigm. Second, the efficient integration with an SDN architecture is presented and analyzed. Finally, the emulation of a sample network scenario via Mininet is provided to validate the effectiveness and the potential of the new cognitive system and its capability to act and to adapt independently of human intervention.
2019
3
Baggio, Giovanni; Bassoli, Riccardo; Granelli, Fabrizio
Cognitive Software-Defined Networking Using Fuzzy Cognitive Maps / Baggio, Giovanni; Bassoli, Riccardo; Granelli, Fabrizio. - In: IEEE TRANSACTIONS ON COGNITIVE COMMUNICATIONS AND NETWORKING. - ISSN 2332-7731. - ELETTRONICO. - 5:3(2019), pp. 517-539. [10.1109/TCCN.2019.2920593]
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11572/251503
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 15
  • ???jsp.display-item.citation.isi??? 13
social impact