DocumentCode :
278918
Title :
Categorization for network fault diagnosis
Author :
Maeda, Christopher
Author_Institution :
Sch. of Comut. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA
Volume :
i
fYear :
1992
fDate :
7-10 Jan 1992
Firstpage :
486
Abstract :
A new method of LAN fault diagnosis is described based on host behavior categorization. Monitored network traffic is used to represent a host´s behavior as a point in a high-dimensional parameter space. A number of these points (one for each host) is categorized by an inductive Bayesian classifier and the resulting categorization is used to predict future network host behavior. If a host´s subsequent behavior is not consistent with its expected class, the host is flagged anomalous and becomes a focus of further diagnosis. The system has been tested on approximately a network-year of data and has successfully diagnosed all known faults in this data due to programmer error and has even pointed out several that had previously gone undetected. Ways to improve the system´s performance with complementary diagnostic techniques are introduced
Keywords :
fault tolerant computing; local area networks; telecommunication network management; LAN fault diagnosis; diagnostic techniques; future network host behavior; host behavior categorization; inductive Bayesian classifier; network fault diagnosis; network traffic; Aggregates; Bayesian methods; Circuit faults; Computer network management; Computer science; Ethernet networks; Fault diagnosis; File servers; Local area networks; Spine;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
System Sciences, 1992. Proceedings of the Twenty-Fifth Hawaii International Conference on
Conference_Location :
Kauai, HI
Print_ISBN :
0-8186-2420-5
Type :
conf
DOI :
10.1109/HICSS.1992.183198
Filename :
183198
Link To Document :
بازگشت