Fraunhofer-Gesellschaft

Publica

Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Data-mining-based link failure detection for wireless mesh networks

 
: Lindhorst, Timo; Lukas, Georg; Nett, Edgar; Mock, Michael

:

IEEE Computer Society, Technical Committee on Distributed Computing:
29th IEEE Symposium on Reliable Distributed Systems, SRDS 2010 : New Delhi, India, 31 October - 3 November 2010; Including C-EMMs 2010: Workshop on Issues in Computing over Emerging Mobile Networks, RACOS 2010: Workshop on Resilience Assessment of Complex Systems, DNCMS 2010: Workshop on Dependable Network Computing and Mobile Systems
Los Alamitos, Calif.: IEEE Computer Society Press, 2010
ISBN: 978-1-4244-8706-6
ISBN: 978-0-7695-4250-8
pp.353-357
International Symposium on Reliable Distributed Systems (SRDS) <29, 2010, New Delhi>
Workshop on Issues in Computing over Emerging Mobile Networks (C-EMMs) <2010, New Delhi>
Workshop on Resilience Assessment of Complex Systems (RACOS) <2010, New Delhi>
Workshop on Dependable Network Computing and Mobile Systems (DNCMS) <2010, New Delhi>
English
Conference Paper
Fraunhofer IAIS ()
cross-layer; data mining; link failure detection; reliability; wireless mesh networks

Abstract
Mobile robot applications operating in wireless environments require fast detection of link failures in order to enable fast repair. In previous work, we have shown that cross-layer failure detection can reduce failure detection latency significantly. In particular, we monitor the behavior of the WLAN MAC layer to predict failures on the link layer. In this paper, we investigate data mining techniques to determine which parameters, i.e., the events, or combination and timing of events, occurring on the MAC layer most probably lead to link failures. Our results show, that the parameters revealed with the data mining approach produce similar or even more accurate failure predictions than achieved so far.

: http://publica.fraunhofer.de/documents/N-188415.html