Power grid outage maintenance plan arrangement method based on deep learning

Abstract

The invention discloses a power grid outage maintenance plan arrangement method based on deep learning, and relates to the technical field of electric power. According to the scheme, a power grid model data file is loaded, and power grid equipment model information is extracted and stored in the file as basic data; acquiring related information of a power failure maintenance plan as a key featureof the sample data; constructing an original maintenance application as original sample data of deep learning; performing feature augmentation and preprocessing on the original sample data to generatefeature data which can be directly input into a deep learning model; generating label data corresponding to the sample; determining the number of neurons of an input layer of the deep learning modelto construct the deep learning model for plan arrangement; verifying an arrangement result; and continuously training the deep learning model by taking the data meeting the verification requirements as sample data to realize continuous learning of the model. According to the invention, the deep learning technology is applied to the power failure maintenance plan arrangement, the power failure application is quickly and optimally arranged, and the arrangement accuracy and the arrangement efficiency are improved.

Description

technical field

[0001] The embodiment of the present invention relates to the field of electric power technology, and in particular to a deep learning-based method for planning power grid outage maintenance. Background technique

[0002] With the continuous expansion of the scale of the power grid, the demand for equipment outage maintenance has increased rapidly, and the risk prevention and control requirements of the power grid have also continued to increase. The traditional power outage plan management system is difficult to meet the actual work needs. The existing scheduling methods for power outage maintenance are mainly implemented from the perspectives of establishing optimization goals and constructing expert systems. The shortcomings are: first, the scheduling takes a long time, and repeated calculations and checks are required; second, it is dependent on the staff It is relatively large, and requires the editor to have strong professional knowledge and participate...

Images