Middleware fault early warning method and system based on machine learning

Abstract

The invention discloses a middleware fault early warning method and system based on machine learning. The method comprises the following steps: (1) collecting data of middleware of a power informationsystem in real time; (2) carrying out safety verification; (3) preprocessing the historical log data and the real-time log data of the middleware of the power information system; (4) training a classification algorithm based on machine learning by taking the preprocessed historical log data and real-time log data of the middleware as input to form a fault classifier; and (5) analyzing the relationship between the middleware index value and the middleware fault through a regression algorithm based on machine learning, fitting a fault feature function, and performing real-time judgment of faultearly warning based on the fault feature function and a fault classifier. According to the method, the problems of poor fault diagnosis timeliness, low accuracy, incapability of early warning and thelike of the power information system are effectively solved, real-time fault early warning based on the middleware of the power information system is realized, and safe and efficient operation of thesystem can be guaranteed.

Description

technical field [0001] The invention relates to the technical field of fault diagnosis signal processing, in particular to a machine learning-based fault early warning method and system. Background technique [0002] At present, the power information system architecture is based on application middleware to connect the underlying database and upper-level applications. The stability of the middleware is directly related to the stability of the entire information system. It is particularly important to build and monitor the key link of the information system middleware. . In response to this problem, at present, the manual method is mainly used to regularly check the working status of the above-mentioned environment, and strive to detect faults as early as possible and solve them as soon as possible. However, manual inspection is limited by factors such as time and experience. The timeliness of inspection is poor, the accuracy is low, and more importantly, the prediction of f...

AI Technical Summary

Problems solved by technology

[0003] (1) With the development of information operation and maintenance business, a large amount of data is continuously generated and accumulated. In terms of data types, in addition to repeated structured data, a large amount of semi-structured data such as logs and work orders are also generated; currently The information system has no analysis and processing of these data

[0004] (2) There is no unified early warning mechanism for the middleware of the power information system after a fault occurs, and the passive operation and maintenance mode of alarming and repairing after the fault occurs is mainly adopted. This mode causes the operation and maintenance personnel to spend most of their daily time and experience Spend on dealing with simple and repetitive problems, and the number of operation and maintenance personnel is limited. Generally, no matter what type of information system middleware fails, it will cause different degrees of economic losses and serious consequences.

[0005] (3) Lack of the ability to give early warning to the information operation and maintenance system before failures occur, and the ability to locate and analyze hidden dangers in operation and maintenance, so there is an urgent need for an active early warning method that focuses on prevention and prevents problems before they happen

Images