Server fault automatic detection system and detection method based on decision tree

Abstract

The invention discloses a server fault automatic detection system and a detection method based on a decision tree, which combines an expert system and an IPMI management unit to generate a historicaldata set. The server running state data, i.e. Abnormal data stream, is obtained by IPMI management unit. According to the abnormal data stream, the new fault feature vector is extracted, and the new feature vector and the fault cause relation pair are formed into a fault data set, and the fault data set is trained into a self-diagnosing decision tree model. When the server fails while running, thecorresponding fault feature vectors are extracted, the fault types are automatically judged by the self-diagnostic decision tree model, After the fault is cleared, the fault feature vector and the fault cause relation are updated and the self-diagnosing fault tree model is updated. Therefore, the fault diagnosis system will be more accurate and reliable with the improvement of the history fault set.

Description

technical field [0001] The invention belongs to the technical field of server management, and in particular relates to a server fault automatic detection system and detection method based on a decision tree. Background technique [0002] As the complexity of the server system becomes higher and higher, the design of supporting software and hardware becomes more and more complex, and the corresponding hidden dangers of failure also increase. When the server system fails, if the fault diagnosis and targeted maintenance are not carried out in time, it will affect the normal operation of the server, and even cause serious consequences such as server downtime. [0003] Existing server fault diagnosis methods include: comparison diagnosis method, fault tree diagnosis method, simulation experiment diagnosis method, expert system diagnosis method, neural network diagnosis method and so on. The comparative diagnosis method collects and stores data of various information of various s...

AI Technical Summary

Problems solved by technology

Although the neural network has improved the efficiency and accuracy of server fault diagnosis, the neural network diagnosis method cannot be explained, and the fault phenomenon cannot be explained and analyzed from the root cause of the problem.

[0004] To sum up, first of all, the existing fault diagnosis methods have the problem of insufficient information sources. With the help of multimeters, oscilloscopes and other means, they rely too much on the experience and quality of diagnostic personnel, which has certain blindness and limitations; The diagnosis process does not make full use of the fault data flow, it is difficult to accumulate diagnosis experience, the diagnosis efficiency is low, and the efficient and reliable operation of the server cannot be guaranteed

In addition, the existing fault diagnosis results have problems such as uncertainty and poor interpretability, which cannot guarantee that the fault will be eliminated from the root cause, causing quality risks in server operation

Images