Method and system for processing abnormal data of operation index data of power distribution network
A technology for operating indicators and abnormal data, applied in data processing applications, instruments, character and pattern recognition, etc., can solve problems such as missing data, inaccurate accuracy, large data, etc., to increase accuracy, improve accuracy, and realize Precisely Mastered Effects
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Example Embodiment
[0027]Example one
[0028]This embodiment provides a method for processing abnormal data of distribution network operation index data, which includes the following steps:
[0029]Step 1: Obtain real-time operation index data of the distribution network;
[0030]There are n running index data, each data has m dimensions, S(t0) Collect data samples at the current time, and at different times tkThe collected distribution network operation index data sample is S(tk).
[0031]Step 2: Cluster the real-time operation index data at the current moment, and divide the clusters into normal clusters, suspected clusters, and abnormal clusters according to the cluster density;
[0032]The step 1 specifically includes:
[0033](1) Calculate the correlation coefficient between each data point in data set D and the remaining n-1 data;
[0034]Assumption Xi, Xj∈D, correlation coefficientThe correlation coefficient can be used to calculate the correlation between any two distribution network operation index data.
[0035]among
Example Embodiment
[0060]Example two
[0061]The purpose of this embodiment is to provide a data processing system for abnormal operation index data of a distribution network, including:
[0062]Data acquisition module to acquire real-time operation index data of the distribution network;
[0063]The data clustering module clusters the current real-time operation index data, and divides the clusters into normal clusters, suspected clusters, and abnormal clusters according to the cluster density;
[0064]Anomaly degree calculation module, which calculates the anomaly degree of data at the current moment according to Manhattan distance;
[0065]The abnormal data recognition module, according to the data belongs to the cluster and abnormality, to identify abnormal data.
[0066]Further, it also includes an abnormal data repair module, which repairs abnormal data according to normal data of neighbors.
Example Embodiment
[0067]Example three
[0068]The purpose of this embodiment is to provide an electronic device.
[0069]An electronic device includes a memory, a processor, and a computer program stored on the memory and capable of running on the processor. When the processor executes the program, the following steps are implemented, including:
[0070]Obtain real-time operation index data of the distribution network;
[0071]Cluster the current real-time operation index data, and divide the clusters into normal clusters, suspected clusters, and abnormal clusters according to the cluster density;
[0072]Calculate the anomaly degree of the data at the current moment based on Manhattan distance;
[0073]Identify abnormal data according to the cluster and degree of abnormality of the data.
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
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