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

Abnormal power consumption detection method based on deep weighted neural network

A technology of abnormal power consumption and neural network, which is applied in biological neural network models, neural architectures, data processing applications, etc.

Inactive Publication Date: 2019-10-22
HANGZHOU DIANZI UNIV
View PDF8 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] Aiming at the shortcomings of the traditional abnormal power consumption detection method, the present invention proposes an abnormal power consumption detection method based on a deep weighted neural network that is more suitable for unbalanced data sets

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
  • Abnormal power consumption detection method based on deep weighted neural network
  • Abnormal power consumption detection method based on deep weighted neural network
  • Abnormal power consumption detection method based on deep weighted neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0071] The present invention will be described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0072] Such as figure 1 As shown, firstly, the electricity consumption data is preprocessed, and feature extraction is performed on the preprocessed data, and then the training set after feature extraction is used to conduct electricity consumption anomaly detection modeling with the DWELM algorithm, and an anomaly detection model is obtained. Finally, the test set is put into the trained model for feature extraction and testing, and the test result of abnormal power is obtained.

[0073] figure 2 The basic structure of EH-DrELM in the DWELM algorithm is shown, which consists of k cascaded feature extraction blocks and a classifier. The k cascaded feature extraction blocks can perform feature extraction twice on the sample on the basis of one feature extraction of the sample.

[0074] The implementation steps of several common typical pow...

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 abnormal power consumption detection method based on a deep weighted neural network. The method comprises the following steps: 1, data preprocessing; 2, performing feature extraction on the preprocessed data to form a feature library; and 3, according to the extracted feature library, constructing a detection model of the abnormal electric quantity by using a DWELM algorithm. The DWELM algorithm adopted by the invention is formed by combining the EH-DrELM algorithm and the improved AdaBoost-ID algorithm, so that the recognition rate of a few samples is greatly improved, and the effectiveness of the algorithm is proved. The EH-DrELM better improves the representation capability than the original ELM, and the improved AdaBoost-ID solves the problem that the original AdaBoost algorithm is not suitable for unbalanced multi-class data, and is more suitable for detection of abnormal power consumption with extremely unbalanced data class.

Description

technical field [0001] The invention belongs to the fields of machine learning and power grid marketing data mining, and relates to an intelligent detection method for abnormal power consumption based on unbalanced data classification of a deep weighted random neural network. Background technique [0002] Frequent abnormal power consumption not only causes serious economic losses to power companies, but also threatens people's lives. According to the survey report on abnormal power consumption in more than 50 developing countries released by the American Intelligent Consulting and Service Company in 2017, most national power companies have suffered serious non-technical losses caused by abnormal power consumption, and the annual economic loss is as high as 64.7% billion U.S. dollars; the average annual growth rate of non-technical losses from 2013 to 2016 was about 11%. Therefore, intelligent and efficient abnormal power consumption detection is very important to the power ...

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): G06Q10/06G06Q50/06G06N3/04G06F16/35
CPCG06Q10/067G06Q50/06G06F16/35G06N3/045Y02D10/00
Inventor 曹九稳覃红云周后盘
Owner HANGZHOU DIANZI UNIV
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