Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Intelligent electric meter fault diagnosis method and device based on federated learning

A smart meter and fault diagnosis technology, applied in neural learning methods, measurement of electrical variables, biological neural network models, etc., can solve problems such as violation of user privacy, and achieve the effect of improving the ability of fault detection

Active Publication Date: 2020-08-14
ELECTRIC POWER RESEARCH INSTITUTE, CHINA SOUTHERN POWER GRID CO LTD
View PDF6 Cites 30 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] To sum up, considering the large scale of smart meter clusters in the power system and the privacy protection of user data, traditional methods will inevitably violate user privacy when obtaining data.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Intelligent electric meter fault diagnosis method and device based on federated learning
  • Intelligent electric meter fault diagnosis method and device based on federated learning
  • Intelligent electric meter fault diagnosis method and device based on federated learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0025] In order to enable those skilled in the art to better understand the solution of the present invention, the present invention will be further described in detail below in conjunction with the accompanying drawings and specific embodiments. Apparently, the described embodiments are only some of the embodiments of the present invention, but not all of them. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.

[0026] Such as figure 1 As shown, based on the concept of joint modeling of local data under federated learning, the user privacy information in the data collected by smart meters is protected, and the shared training of smart meter fault diagnosis models is completed through cluster terminals. Specifically, the method includes the following steps:

[0027] Step 1: Deploy a lightweight local data model and u...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses an intelligent electric meter fault diagnosis method and device based on federated learning. The diagnosis method comprises the steps that setting a lightweight fault detectionmodel capable of operating at an intelligent electric meter end; extracting intelligent electric meter cluster data features, namely extracting public overlapping features from intelligent electric meter acquisition data; training a fault detection model on each intelligent electric meter terminal; uploading the intermediate training parameters to a server of an electric power data center; enabling the server to perform parameter fusion calculation and return the parameters to each local model for updating; and completing training of shared models. By applying the technical scheme provided bythe invention, on the premise of protecting the user privacy data of the intelligent electric meter, huge cluster data can be fully utilized to improve the fault detection capability of the intelligent electric meter on the user side.

Description

technical field [0001] The invention relates to the technical field of smart meter fault detection in power systems, in particular to a federated learning-based smart meter fault detection method and equipment. Background technique [0002] Aiming at the problem of fault diagnosis of smart meters in the power system, the existing diagnosis model is deployed in the operation center of the metering system, and the data collected by smart meters, metering point monitoring data, and meter reading data are obtained through traditional operation means to detect faults. diagnosis. In the context of big data and the Internet of Things era, smart devices are gradually developing towards high-performance computing and high intelligence. The use of big data to build machine learning models, build user data portraits, and mine data information has become a hot spot in the field of data research. However, the issues of information security and data privacy have received great attention ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G01R35/04G06F16/27G06N3/04G06N3/08
CPCG01R35/04G06F16/27G06N3/08G06N3/045Y04S10/50
Inventor 肖勇周密郑楷洪钱斌
Owner ELECTRIC POWER RESEARCH INSTITUTE, CHINA SOUTHERN POWER GRID CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com