Failure mitigation in software defined networking employing load type prediction

Handle URI:
http://hdl.handle.net/10754/625712
Title:
Failure mitigation in software defined networking employing load type prediction
Authors:
Bouacida, Nader ( 0000-0002-4571-8484 ) ; Alghadhban, Amer Mohammad JarAlla; Alalmaei, Shiyam Mohammed Abdullah; Mohammed, Haneen ( 0000-0002-4535-1926 ) ; Shihada, Basem ( 0000-0003-4434-4334 )
Abstract:
The controller is a critical piece of the SDN architecture, where it is considered as the mastermind of SDN networks. Thus, its failure will cause a significant portion of the network to fail. Overload is one of the common causes of failure since the controller is frequently invoked by new flows. Even through SDN controllers are often replicated, the significant recovery time can be an overkill for the availability of the entire network. In order to overcome the problem of the overloaded controller failure in SDN, this paper proposes a novel controller offload solution for failure mitigation based on a prediction module that anticipates the presence of a harmful long-term load. In fact, the long-standing load would eventually overwhelm the controller leading to a possible failure. To predict whether the load in the controller is short-term or long-term load, we used three different classification algorithms: Support Vector Machine, k-Nearest Neighbors, and Naive Bayes. Our evaluation results demonstrate that Support Vector Machine algorithm is applicable for detecting the type of load with an accuracy of 97.93% in a real-time scenario. Besides, our scheme succeeded to offload the controller by switching between the reactive and proactive mode in response to the prediction module output.
KAUST Department:
Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
Citation:
Bouacida N, Alghadhban A, Alalmaei S, Mohammed H, Shihada B (2017) Failure mitigation in software defined networking employing load type prediction. 2017 IEEE International Conference on Communications (ICC). Available: http://dx.doi.org/10.1109/ICC.2017.7997295.
Publisher:
IEEE
Journal:
2017 IEEE International Conference on Communications (ICC)
Conference/Event name:
2017 IEEE International Conference on Communications, ICC 2017
Issue Date:
31-Jul-2017
DOI:
10.1109/ICC.2017.7997295
Type:
Conference Paper
Additional Links:
http://ieeexplore.ieee.org/document/7997295/
Appears in Collections:
Conference Papers; Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division

Full metadata record

DC FieldValue Language
dc.contributor.authorBouacida, Naderen
dc.contributor.authorAlghadhban, Amer Mohammad JarAllaen
dc.contributor.authorAlalmaei, Shiyam Mohammed Abdullahen
dc.contributor.authorMohammed, Haneenen
dc.contributor.authorShihada, Basemen
dc.date.accessioned2017-10-03T12:49:35Z-
dc.date.available2017-10-03T12:49:35Z-
dc.date.issued2017-07-31en
dc.identifier.citationBouacida N, Alghadhban A, Alalmaei S, Mohammed H, Shihada B (2017) Failure mitigation in software defined networking employing load type prediction. 2017 IEEE International Conference on Communications (ICC). Available: http://dx.doi.org/10.1109/ICC.2017.7997295.en
dc.identifier.doi10.1109/ICC.2017.7997295en
dc.identifier.urihttp://hdl.handle.net/10754/625712-
dc.description.abstractThe controller is a critical piece of the SDN architecture, where it is considered as the mastermind of SDN networks. Thus, its failure will cause a significant portion of the network to fail. Overload is one of the common causes of failure since the controller is frequently invoked by new flows. Even through SDN controllers are often replicated, the significant recovery time can be an overkill for the availability of the entire network. In order to overcome the problem of the overloaded controller failure in SDN, this paper proposes a novel controller offload solution for failure mitigation based on a prediction module that anticipates the presence of a harmful long-term load. In fact, the long-standing load would eventually overwhelm the controller leading to a possible failure. To predict whether the load in the controller is short-term or long-term load, we used three different classification algorithms: Support Vector Machine, k-Nearest Neighbors, and Naive Bayes. Our evaluation results demonstrate that Support Vector Machine algorithm is applicable for detecting the type of load with an accuracy of 97.93% in a real-time scenario. Besides, our scheme succeeded to offload the controller by switching between the reactive and proactive mode in response to the prediction module output.en
dc.publisherIEEEen
dc.relation.urlhttp://ieeexplore.ieee.org/document/7997295/en
dc.subjectControl systemsen
dc.subjectDelaysen
dc.subjectPrediction algorithmsen
dc.subjectReal-time systemsen
dc.subjectSoftwareen
dc.subjectSupport vector machinesen
dc.subjectSystem analysis and designen
dc.titleFailure mitigation in software defined networking employing load type predictionen
dc.typeConference Paperen
dc.contributor.departmentComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Divisionen
dc.identifier.journal2017 IEEE International Conference on Communications (ICC)en
dc.conference.date2017-05-21 to 2017-05-25en
dc.conference.name2017 IEEE International Conference on Communications, ICC 2017en
dc.conference.locationParis, FRAen
kaust.authorBouacida, Naderen
kaust.authorAlghadhban, Amer Mohammad JarAllaen
kaust.authorAlalmaei, Shiyam Mohammed Abdullahen
kaust.authorMohammed, Haneenen
kaust.authorShihada, Basemen
All Items in KAUST are protected by copyright, with all rights reserved, unless otherwise indicated.