Identification method for abnormal data of residential electrical load

A technology for abnormal data and residential electricity consumption, applied in neural learning methods, character and pattern recognition, instruments, etc., can solve problems such as low efficiency and difficulty in troubleshooting, reducing hardware costs, improving responsiveness, and easy data acquisition. Effect

Pending Publication Date: 2022-03-01
STATE GRID LIAONING ELECTRIC POWER RES INST +1
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, this door-to-door investigation method is too inefficient
And it is difficult to find out the common stealing technology, such as the undercurrent stealing method

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
  • Identification method for abnormal data of residential electrical load
  • Identification method for abnormal data of residential electrical load
  • Identification method for abnormal data of residential electrical load

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0024] The present invention will be described in further detail below in conjunction with the accompanying drawings and specific embodiments, which are explanations rather than limitations of the present invention.

[0025] Such as figure 1 As shown, a method for identifying abnormal data of residential electricity load in the present invention comprises the following steps:

[0026] Due to the different structures of different electrical equipment, the load characteristics are different. The detected non-intrusive load features can be divided into transient features and steady-state features. The main steady-state characteristics mainly include the following points: active power, reactive power, steady-state fundamental wave component, and harmonic component. Among these features, the easy-to-obtain steady-state power is selected as the load feature for electric load identification.

[0027] First of all, the first step: because the obtained raw power load data is disorde...

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 a method for identifying abnormal data of residential electricity load. Comprising the following steps: firstly, processing original power load data by using an AP clustering algorithm, dividing a large amount of actually measured sampling data into a plurality of clusters, discretizing the load of continuous variable state equipment to obtain a limited number of states, obtaining a working power set of sample equipment, and establishing a load classification LSTM network model; and substituting the processed data into the network model, and predicting the data of the next sequence by using the data input into the model. Predicted data is used as a standard value, and a threshold range floating up and down is set. And if the measured value is lower than the threshold value, determining that an abnormal electricity stealing phenomenon exists. According to the method, the steady-state power serves as a load characteristic, the time sequence of data is fully considered, abnormal data can be compared, and the purpose of electricity stealing prevention is achieved.

Description

technical field [0001] The invention relates to a method for identifying abnormal data of residential electricity load. Background technique [0002] Smart power consumption is an important part of the smart grid, and non-intrusive power load identification and prediction is a key link in smart power consumption. Further collection and analysis of user electricity consumption data can make it easier for the power grid to implement anti-stealing policies, and at the same time it will be more convenient for demand-side management and improve energy utilization. At present, the existing methods are mainly intrusive and non-invasive. The non-invasive method is low in cost and strong in practicability, which is of great help to the development of intelligent electricity consumption. Regarding the anti-stealing of electricity, at present, it is mainly relying on employees to gradually investigate and judge whether there is electricity theft or abnormal electricity consumption. H...

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
IPC IPC(8): G06K9/62G06N3/04G06N3/08
CPCG06N3/049G06N3/08G06N3/045G06F18/23G06F18/241
Inventor 刘碧琦乔林陈硕王飞杨壮观夏菲薛凯今王丹妮李曦李云鹏吴赫徐立波程蕾姚晶华张富翔
Owner STATE GRID LIAONING ELECTRIC POWER RES INST
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap