Electric power communication network fault positioning method based on key alarm sets and supervised classification

Abstract

The invention provides an electric power communication network fault positioning method based on key alarm sets and supervised classification. The method is suitable for fault positioning of network devices or network links in a communication network, particularly for a positioning scene under large-scale network paralysis. The method first divides a network into an alarm area and a normal area through fault alarm information collection and topology analysis, extracts key alarm sets including a cut edge link set and an edge alarm set, then converts a network fault positioning problem into a series of binary classification problems, adopts a method based on supervised classification learning, uses alarm information as an input, and via a classifier using standardized fault source-fault alarm code records in a fault diagnosis database as training samples, obtains suspected fault sources. Finally, based on the key alarm sets in the first step and a preliminary fault positioning result in the second step, low-probability fault sources are removed and corresponding guessed fault sources are added to match with current fault alarm symptoms, and the fault positioning result is modified and perfected, thereby improving accuracy of fault positioning.

Description

technical field [0001] The invention relates to a fault location method of a power communication network based on key alarm sets and supervision classification, in particular to a fault location method and system of the power communication network. Background technique [0002] The power communication network has the characteristics of large scale and complex structure, which brings challenges to timely and accurately find out the source of the fault when a fault occurs. When an individual fault alarm occurs in the network, the source of the fault can be located relatively easily by using the existing network management and monitoring means. However, when a large amount of fault alarm information is monitored in the network, there are often serious network connectivity problems, and not every alarm information means that the corresponding network facilities have failed. Some network nodes in key positions Or a fault in a network link may cause a large area of ​​fault alarms...

AI Technical Summary

Problems solved by technology

The positioning effect based on the neural network method depends entirely on the number of hidden layers and the weights between layers. The disadvantage is that the inherent structural defects are difficult to be controlled, and the positioning effect cannot be guaranteed.

[0006] Existing fault location methods mainly rely on merging and correlating alarm information, and gradually narrowing down the range of fault sources to achieve the purpose of fault location, ignoring the location of fault sources in the topology and the relationship between fault alarms that may be caused by different fault combinations. Reduced accuracy of fault location

Images