Computer network fault diagnosis method

Abstract

The invention discloses a computer network fault diagnosis method, which is based on an artificial immune algorithm, and comprises the following steps of: defining category information for describingantigens and antibodies, and dividing collected network fault samples into a training antigen set and a test antigen set; normalizing the proportion of the training antigen set to obtain a non-memoryantibody, selecting a certain number of antigens as memory antibodies, and purifying the memory antibodies; calculating the affinity between the training antigen set and the memory antibody and the affinity between the training antigen set and the non-memory antibody; selecting a plurality of antibodies with the highest affinity for cloning to obtain a selection set, and mutating the cloned antibodies to obtain an antibody set; obtaining a total memory antibody set according to the training antigen set and the mutated antibody set; circularly selecting a next antigen; inhibiting the memory antibody; and detecting the category of the antigen. The advantages of self-learning and self-memorizing of the artificial immune network are utilized, the fault sample antigen is trained, the obtained memory antibody set has fault category information, and the accuracy of the algorithm is improved.

Description

technical field [0001] The invention relates to the technical field of network diagnosis, in particular to a computer network fault diagnosis method. Background technique [0002] The rapid development of computer network technology has greatly promoted the development of human society, and has had a huge impact on people's daily life, study, work and other aspects. The application of computer networks has widely penetrated into every corner of the world. Users provide services such as resource sharing, communication, monitoring, communication and information dissemination. Due to the increasing dependence of human society on the network, if the network fails during operation, it may bring disastrous consequences. While the rapid development of the network is constantly exerting its advantages and potentials, its huge system and intricate structure have also brought great challenges to the effective management of the network. [0003] The current network fault diagnosis ca...

AI Technical Summary

Problems solved by technology

[0004] The invention provides a computer network fault diagnosis method to solve the problem that the current network fault diagnosis can only identify known faults, but cannot find unknown and emerging network faults, and cannot quickly and quickly diagnose computer network faults. It is unable to self-learn uncertain or unknown systems, and does not have the ability to adapt to various dynamic changes.

Images