Login| Sign Up| Help| Contact|

Patent Searching and Data


Title:
DATA DUAL-DRIVE METHOD, APPARATUS, AND DEVICE FOR PREDICTING POWER GRID FAILURE DURING TYPHOON
Document Type and Number:
WIPO Patent Application WO/2023/045278
Kind Code:
A1
Abstract:
Disclosed in the present invention are a data dual-drive method, apparatus, and device for predicting power grid failure during a typhoon. The method comprises: constructing a disaster cause data set, equalizing the disaster cause data set, constructing a dual-channel prediction model, and performing prediction by using the dual-channel prediction model; classifying multiple influencing factors of a disaster situation of a distribution network during a typhoon into static data and dynamic data, extracting features of the static data by using a feedforward neural network, and extracting features of the dynamic data by using a long short-term memory network strengthened by a multi-head self-attention mechanism; and finally fusing all of the extracted features by using a linear layer, and establishing a mapping relationship between the multiple influencing factors and the disaster situation of the distribution network. By fully considering the stability of the effect of static data on the disaster situation of a distribution network and the time variation and accumulation of the effect of dynamic data on the disaster situation of a distribution network, a more accurate and interpretable model for predicting distribution network failure during a typhoon is constructed.

Inventors:
XIE HAIPENG (CN)
TANG LINGFENG (CN)
ZHU HAO (CN)
BIE ZHAOHONG (CN)
LI GENGFENG (CN)
Application Number:
PCT/CN2022/081314
Publication Date:
March 30, 2023
Filing Date:
March 17, 2022
Export Citation:
Click for automatic bibliography generation   Help
Assignee:
UNIV XI AN JIAOTONG (CN)
International Classes:
G06N3/08; G06Q10/04
Foreign References:
CN113837477A2021-12-24
CN111191832A2020-05-22
CN113191585A2021-07-30
US20130132045A12013-05-23
Attorney, Agent or Firm:
XI'AN TONG DA PATENT AGENCY CO., LTD. (CN)
Download PDF: