Abnormal load data detection and correction method and system based on model optimization

A load data and abnormal data technology, which is applied in digital data information retrieval, system integration technology, data processing application, etc., can solve the problems of difficult selection of initial parameters and low accuracy of abnormal detection, so as to achieve planned power consumption management and improve economical efficiency. Benefit and social benefit, the effect of accurate load forecasting

Active Publication Date: 2021-04-30
NANJING UNIV OF POSTS & TELECOMM
View PDF1 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

With the development of data mining technology, a series of intelligent algorithms such as neural network, density analysis, and cluster analysis have been applied to the a

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 load data detection and correction method and system based on model optimization
  • Abnormal load data detection and correction method and system based on model optimization
  • Abnormal load data detection and correction method and system based on model optimization

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0102]Example 1:

[0103]If there is an accurate historical load data in the residential area, it will be anomalous for an abnormal load data for a certain day. Then, first, the historical power load data is used as the training sample data. The SVDD algorithm is optimized by gene expression programming (GEP), using the established SVDD model to perform abnormal load data detection of the day, if there is abnormal load data, subsequent use depth The length of the memory network (LSTM) performs load prediction and predicts the load value as an alternative value of abnormal data.

[0104]The specific embodiment is:

[0105](1) First, pretreatment of historical load data, data with less missing value, using a method of filling, and is directly deleted for missing amounts. Working with all load data.

[0106](2) Division of training sets, test sets, and verification sets of abnormal load data detection models and abnormal data correction models, respectively.

[0107](3) Application of gene expression...

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 relates to an abnormal load data detection and correction method and system based on model optimization, and the system comprises a load data preprocessor, an abnormal load data detector, and an abnormal load data corrector.The load data processor is connected with the abnormal load data detector; and the abnormal load data detector is connected with the abnormal load data corrector. According to the method, parameter optimization is carried out on an SVDD algorithm by adopting gene expression programming, abnormal load data detection is carried out by utilizing an SVDD model established by an optimal parameter, and then load prediction is carried out by utilizing a depth long-short-term memory network, the predicted load value is taken as a replacement value of the abnormal data. The method is used for processing the abnormal load of the power grid, and abnormal load data in the power load can be accurately detected through the method, so that accurate load prediction, planned power utilization management and reasonable power supply construction planning are facilitated, and the economic benefit and social benefit of a power system are improved.

Description

technical field [0001] The invention belongs to the technical field of power system data mining, and specifically relates to a method for detecting and correcting abnormal load data based on improved SVDD and a deep long-short-term memory network, which is mainly used for detecting and correcting abnormal load data in the electric power field. Background technique [0002] In order to meet the ever-increasing energy demand, establishing a safe, reliable, environmentally friendly, efficient and friendly power network has become a research hotspot. The concept of smart grid provides a good solution for the construction of new power grids. At the same time, the development of smart grids has promoted the establishment of grid automation information platforms, and the amount of various types of data transmitted and collected by power system equipment has also increased exponentially. The scale, type and structure of load data have undergone major changes. In the actual operatio...

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): G06F30/27G06N3/04G06N3/08G06K9/62G06F16/215G06Q50/06
CPCG06F30/27G06N3/08G06F16/215G06Q50/06G06N3/044G06N3/045G06F18/214Y04S10/50Y02E40/70
Inventor 邓松蔡清媛岳东李前亮袁玲玲
Owner NANJING UNIV OF POSTS & TELECOMM
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