Supercharge Your Innovation With Domain-Expert AI Agents!

Abnormal data detection method and device based on Lasso algorithm

A technology of abnormal data detection and abnormal data, which is applied in the field of big data, can solve problems such as the limitation of model application flexibility, and achieve the effect of fast detection speed and high model accuracy

Inactive Publication Date: 2020-10-02
STATE GRID ZHEJIANG ELECTRIC POWER +1
View PDF5 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Common abnormal data mining methods include methods based on statistical models, distance models, density models, and deviation models. Among them, using statistical methods to deal with abnormal data mining has an independent and complete set of theories and methods, but it is necessary to know in advance when using the model. Model parameters, distribution parameters, and overdue abnormal point data, the flexibility of model application is greatly limited

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 data detection method and device based on Lasso algorithm
  • Abnormal data detection method and device based on Lasso algorithm
  • Abnormal data detection method and device based on Lasso algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0050] figure 1 A schematic flowchart of a method for detecting abnormal data based on the Lasso algorithm in one embodiment of the present application is shown. As shown in the figure, the abnormal data detection method based on the Lasso algorithm of this embodiment includes:

[0051] S10. Obtain the data set to be tested and the training sample set from the power big data collection and application system. The data set to be tested is a time series data sequence composed of actual electricity consumption data generated on different dates, and the training sample set is the data set before the data set to be tested. Time-series data series composed of generated historical electricity consumption data;

[0052] S20. Using the data generation date of the training sample as a variable, taking the calendar feature of the data generation date and the numerical feature of the historical electricity consumption data before the current training sample as the variable feature, the ...

Embodiment 2

[0087] figure 2 It is a schematic flow chart of an abnormal data detection method based on Lasso algorithm in another embodiment of the present application, such as figure 2 As shown, the method includes:

[0088] Step 1. Divide the data into a training set and a testing set according to the date requirements of the data to be tested.

[0089] In this embodiment, input the time-series data set to be detected, including two fields of date and index value, and set the starting date a to detect whether the data is abnormal, thereby dividing the data set with date <a into a training set, and The dataset with date ≥ a is divided into the detection set.

[0090] Step 2. Based on the training set divided in step 1, use S-H-ESD for noise recognition, and mine abnormal data in the training set.

[0091] In this embodiment, step 2 specifically includes the following steps:

[0092] Step 21, using the STL algorithm to decompose the time series data into a trend component, a period ...

Embodiment 3

[0151] The second aspect of the present application proposes an abnormal data detection device based on the Lasso algorithm. image 3 It is a schematic diagram of the structure of an abnormal data detection device based on the Lasso algorithm in one embodiment of the present application. As shown in the figure, the abnormal data detection device 100 based on the Lasso algorithm in this embodiment may include:

[0152] The data set acquisition module 101 is used to obtain the data set to be tested and the training sample set from the power big data collection and application system. The data set to be tested is a time series data sequence composed of actual electricity consumption data generated on different dates, and the training sample set is a time series data sequence composed of historical electricity consumption data generated before the data set to be detected;

[0153] The electricity consumption data prediction model generation module 102 is used to use the data gene...

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 belongs to the technical field of big data, and particularly relates to an abnormal data detection method and device based on a Lasso algorithm. The method comprises the steps of obtaining a to-be-detected data set and a training sample set from an electric power big data acquisition and application system, learning the training sample set based on a Lasso algorithm, and performing training optimization to obtain an electricity utilization data prediction model; taking the generation date of each piece of actual power consumption data in the to-be-detected data set as input, andobtaining predicted power consumption data corresponding to each piece of actual power consumption data through the power consumption data prediction model; and performing anomaly detection based on the predicted power consumption data. According to the method, the power utilization data prediction model is established based on the Lasso algorithm, the model precision is high, the detection speedis high, and the data can be detected in real time in the power data acquisition process.

Description

technical field [0001] The present application belongs to the technical field of big data, and in particular relates to a method and device for detecting abnormal data based on Lasso algorithm. Background technique [0002] With the accumulation of time, power grid companies have accumulated massive multi-dimensional power data in their production and operation. Since power data is related to residents’ lives and the production of enterprises, through the integration and mining technology of various power data values, artificial intelligence-based power data can be created. The big data application universal platform can reflect people's livelihood and economic development in a timely, accurate and multi-perspective manner. Such as enterprise resumption of work and production data monitoring, enterprise credit evaluation, "electricity consumption index" monitoring, identification of power supply enterprises, etc. [0003] Time-series data such as daily load, daily electrici...

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): G06F16/215G06F17/18G06Q10/04G06Q50/06
CPCG06F17/18G06Q10/04G06Q50/06G06F16/215Y02D10/00
Inventor 胡若云张宏达李国良柴成亮林森姚力许灵杰徐永进林少娃吕几凡王庆娟
Owner STATE GRID ZHEJIANG ELECTRIC POWER
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com