Alarm processing analysis system and method of broadcasting and TV access network

Abstract

The invention provides an alarm processing analysis system and method of a broadcasting and TV access network. The system comprises a collecting module used for collecting various warning messages sent by network equipment, an analysis module used for analyzing the relevance of various received equipment warning messages according to a correlation model established through data mining in advance between different devices and different warning types, and a judging model used for further judging the relevance types of the warning devices according to an expert knowledge base which is established in advance to obtain the specific relevance type between different devices and different warning types and to find out a root alarm. By means of the alarm processing analysis system and method of the broadcasting and TV access network, the dependency of original warning relevance analysis on TOPO is removed, meanwhile, the expert knowledge base is used for overcoming the defects of data mining analysis warning relevance, the warning real-time performance processing demand can be met, and the analysis accuracy requirement can be met as well.

Description

technical field [0001] The invention relates to a radio and television access network alarm processing and analysis system and its analysis method, in particular to a radio and television access network monitoring and alarm processing and analysis system and its analysis method. Background technique [0002] Data mining is a technique of data statistics. From a large amount of factual data, it finds out the internal relationship of these data through clustering, correlation analysis, fitting and other statistical means. Among them, correlation analysis is commonly used and used in data mining. An important method is to find out the connection between different data through correlation analysis. At present, the commonly used correlation algorithm is APRIORI and some optimization algorithms based on APRIORI. [0003] The knowledge base is the formalization and symbolization of people's understanding of a certain field. The expert knowledge base is the symbolization of the know...

AI Technical Summary

Problems solved by technology

[0005] In addition to traditional switches, there are a large number of EPON, EOC, and ONU devices in the access network of radio and television. Compared with traditional IP networks, the number and types of devices that need to be managed are much larger. When network devices fail, often A large number of derivative alarms are generated to cause an alarm storm. How to quickly and efficiently locate the problem and shield minor alarms is a problem faced by the network management of the radio and television access network. At present, the common method in the industry is to analyze the root alarm, which is adopted in the analysis technology. The way of data mining and the way of the rule base, the way of data mining can effectively avoid the network TOPO problem, but it is impossible to determine the business relationship between the alarms. The correlation analysis through the rule base has better accuracy but often needs to rely on the network. TOPO relationship or alarm dependency graph relationship. When the network scale is large, the search for TOPO will often become a performance bottleneck. This TOPO-dependent rule base is difficult to apply to real-time alarm processing. Therefore, it is necessary to find a method that can satisfy alarm requirements. The real-time processing requirements can also take into account the requirements of analysis accuracy

Images