Probabilistic probe selection method, system, apparatus and application for fault diagnosis

Abstract

The invention belongs to the technical field of network communication, and discloses a probability probe selection method, system, equipment and application for fault diagnosis. In the fault detection stage, the probability greedy probe selection method is used to select from the available probe set, which can cover all networks. The minimum probes of nodes; and these probes are sent by the detection station to detect whether there are faulty nodes in the network. Once there are faulty probes, it means that there may be faulty nodes in the network; the fault location process is triggered, and the probe selection method with the smallest probability is used. Accurately locate the faulty node. The present invention establishes a large number of simulation experiments to evaluate the performance of the proposed algorithm, and the results show that the algorithm has high fault location accuracy, low detection cost and strong adaptability; in an uncertain environment, the probability of using the algorithm for fault location is the smallest. The search probe selection method can reduce the influence of uncertain factors and improve the accuracy of fault location.

Description

technical field [0001] The invention belongs to the technical field of network communication, and in particular relates to a method, system, device and application for selecting a probability probe for fault diagnosis. Background technique [0002] At present: In recent years, with the increase of global Internet users, mobile smart devices, and network user service demands, the scale and complexity of communication networks have shown a rapid growth trend, which has brought huge challenges to the operation of the network management system. for fault management. Due to environmental factors or equipment aging, network components are prone to failure, which is unavoidable in large-scale communication networks. Therefore, it is very important to perform real-time fault diagnosis on communication networks. For communication networks, the fault diagnosis process consists of two parts: fault detection and fault location. Fault detection is the process of identifying if there is...

AI Technical Summary

Problems solved by technology

[0011] 1. Considering the influence of noise and other environmental factors in an uncertain environment, there may be cases where the probe detection results of all normal nodes may be invalid, which will cause a certain degree of identification to the results of fault detection and fault location errors and uncertainties;

[0012] 2. The fault location process needs to accurately locate the fault node. Compared with the fault detection process that only needs to find the minimum probes that can cover all network nodes to detect whether there is a fault node, the complexity of the fault detection process is greatly increased. How to accurately locate the fault in an uncertain environment Node is also one of the difficult problems to be solved

[0016] 3. Existing fault detection and location methods in a deterministic environment are used in an uncertain environment to obtain large errors, which are not suitable for the fault diagnosis process in an uncertain environment. Real-time and effective fault diagnosis for communication networks is also a Critical and urgent issues

Images