Operation risk early warning method and device based on power grid information system

Abstract

The invention discloses an operation risk early warning method based on a power grid information system. The method comprises the following steps: obtaining operation and maintenance data of the powergrid information system at a plurality of time nodes in preset time; carrying out linear regression analysis on the data under the same index and the same time node under the normal operation state of the power grid information system, setting a threshold value or a threshold value range of an operation and maintenance data index, and judging whether the operation and maintenance data exceeds a normal range or not according to the threshold value or the threshold value range; analyzing the abnormal reason, and judging an operation risk type; and if the detection index has a risk state, judging a fault level, and carrying out early warning. The invention further discloses an operation risk early warning device based on the power grid information system. By analyzing the operation data of the data center, the operation risk of the system is mined, and the operation and maintenance capability and efficiency of the edge data center are improved; and edge operation risks are reasonably identified, and graded progressive early warning of the operation risks is carried out to ensure accurate execution of the system during unattended operation.

Description

technical field [0001] The invention relates to the technical field of power systems, in particular to a method and device for early warning of operation risks based on power grid information systems. Background technique [0002] The power grid information system has an important impact on many industries, so it is very important for the operation and maintenance of the power grid information system. The scale of the equipment in the edge data center is relatively small, and some are even miniature. When clustered, the operation and maintenance of the power grid information system becomes very complicated, which is not conducive to the performance of the edge data center cluster. There are two main reasons for the complexity of the operation and maintenance. One: First, the configuration of operation and maintenance personnel has not reached the scale of a large data center, which makes the operation and maintenance efficiency low; second, it is difficult to grasp the actua...

AI Technical Summary

Problems solved by technology

[0003] Most of the risk warnings for the operation status of the power grid information system in the prior art are based on the sampling analysis and feature extraction of the power grid operation data, combined with big data information processing and information processing technology, extracting and reflecting the operating conditions of the power grid information system Feature parameters, using feature cluster analysis method to predict and judge risk, but this method ignores the connection between data at the same time node, as well as the connection between the fault state and non-fault state of the information system, reducing the prediction results. accuracy

Images