Power-network-dispatching-oriented intelligent warning analysis method

Abstract

The invention discloses a power-network-dispatching-oriented intelligent warning analysis method. The method comprises the following steps that warning information of a power network is extracted and is preprocessed; denoising is carried out on the preprocessed warning information, and a denoising classification rule is obtained; the denoised warning information is subjected to induction and dupliction removal, warning combinations are generated, and the warning type to which each warning combination belongs is judged; each warning combination and the corresponding warning type are subjected to association rule mining, and a power network warning inference rule is obtained. After the intelligent warning analysis method is utilized, the filtering rate of noise data in the warning information and the comprehensiveness of the warning types are improved.

Description

Technical field [0001] The invention relates to an alarm analysis method, in particular to an intelligent alarm analysis method oriented to power grid dispatching, and belongs to the technical field of power system dispatching. Background technique [0002] With the continuous expansion of the scale of the power grid, the alarm information generated is also increasing, and thousands or even tens of thousands of alarm information flood into the control center every day. The abnormality of the measuring equipment during operation and the necessary equipment maintenance will generate noise data, resulting in insufficient accuracy of the alarm information. At the same time, the current alarm information is directly presented to dispatchers at an extremely fast speed, and no associated grid reasoning rules have been formed, which makes dispatchers unable to quickly determine the type of alarm. [0003] In order to ensure the accuracy of alarm information and quickly determine the type ...

AI Technical Summary

Problems solved by technology

[0012] 1) When denoising, only the history event table is used without combining other relevant information, resulting in long denoising time

[0013] 2) The decision tree algorithm was not improved during denoising, resulting in a decrease in classification accuracy

[0014] 3) When using the rough set algorithm for rule reasoning, the alarm type is only set to the common alarm type, resulting in insufficient comprehensive power grid alarm reasoning rules

[0015] When mining a large amount of alarm information, the noise filtering rate of the alarm information cannot be effectively improved, and comprehensive power grid alarm reasoning rules can not be excavated, which cannot effectively meet the needs of the power system.

Images