Power grid information operation and maintenance monitoring method based on deep learning

Abstract

The invention discloses a power grid information operation and maintenance monitoring method based on deep learning. The method is based on time series data information in a power grid information operation and maintenance monitoring system. Cleaned time series data are obtained through a proper data preprocessing technology; a prediction function of to-be-detected time sequence data is realized by utilizing a long-short-term memory neural network, so that a normal behavior model of a to-be-detected time sequence is constructed, and whether the to-be-detected time sequence has an abnormal phenomenon is further judged through a control chart based on exponential weighted moving average. The method faces any abnormity influenced by time in the field of power grid information operation and maintenance monitoring, has certain universality, and has very important scientific significance and application value for instructive processing after abnormity discovery and prevention of serious faults possibly caused by the abnormity.

Description

technical field [0001] The invention relates to a data anomaly detection method based on deep learning combined with a control chart, in particular to a deep learning-based power grid information operation and maintenance monitoring method. Background technique [0002] In the power grid scenario, with the increase in the number of power enterprise business and related applications year by year, traditional operation and maintenance methods often seem stretched when dealing with GB, TB or even PB-level data in the data center, and the performance of hardware equipment in the infrastructure is uneven. The main contradictions in operation and maintenance, such as compatibility issues between devices and devices, make the problem of operation and maintenance difficulties in massive data scenarios more prominent. The existing operation and maintenance management system still has some deficiencies in data integration and in-depth analysis caused by the fusion of different systems...

AI Technical Summary

Problems solved by technology

[0002] In the power grid scenario, with the increase in the number of power enterprise business and related applications year by year, traditional operation and maintenance methods often seem stretched when dealing with GB, TB or even PB-level data in the data center, and the performance of hardware equipment in the infrastructure is uneven. The main contradictions in operation and maintenance, such as compatibility issues between devices and devices, make the problem of operation and maintenance difficulties in massive data scenarios more and more prominent.

The existing operation and maintenance management system still has some deficiencies in data integration and in-depth analysis caused by the fusion of different systems and different types of data. It is difficult to connect data between monitoring systems and conduct effective correlation analysis, which greatly hinders Improve operation and maintenance capabilities and effectively guarantee service quality

[0003] Furthermore, the work of the existing power grid in the operation and maintenance application scenario often only stops at designing a set of operation and maintenance data management system to integrate the massive operation and maintenance data with severe fragmentation, and lacks a follow-up system based on the integration. The full-link data consumption process specification of operation and maintenance monitoring data information

However, for the main problems of power grid operation and maintenance, such as frequent power grid failures and huge operation and maintenance costs, the effect of optimization for data integration is very limited. Expensive spending problem won't improve

Images