Adaboost ensemble learning power grid fault diagnosis system and method based on data resampling

Abstract

The invention relates to an Adaboost ensemble learning power grid fault diagnosis system and method based on data resampling. The system comprises a fault information database, a data preprocessing module and a fault diagnosis module; the data preprocessing module calls data of the fault information database to perform data preprocessing, and the data preprocessing module sends the preprocessed data to the module fault diagnosis module. The fault information database is used for storing fault information packets; the data preprocessing module is used for carrying out vacancy value filling andnormalization operation on the data; the fault diagnosis module comprises a data resampling module used for carrying out balance operation on data, a decision tree base classifier module used for carrying out modeling training and fault prediction on fault data, and an Adaboost integrated classifier module used for carrying out multiple rounds of learning and fault prediction on a decision tree base classifier. According to the invention, the integrity of the fault data is ensured, and the diagnosis of the fault data is more accurate.

Description

technical field [0001] The invention designs the smart grid application field, and specifically designs an Adaboost integrated learning grid fault diagnosis system and method based on data resampling. Background technique [0002] With the application of information technology in power grid dispatching and the continuous expansion of power grid scale, a large number of rich fault information is sent to the dispatching center. How to propose effective information from massive fault data is an urgent problem to be solved at this stage. Power grid faults often contain correct alarm information, misinformation, repeated information, and irrelevant information. This information brings great difficulties to the work of operators, especially the response mechanism is very important when complex faults occur in the power system. Therefore, it is very necessary to establish a grid fault diagnosis system to realize automatic and rapid diagnosis of grid faults. [0003] The current ...

AI Technical Summary

Problems solved by technology

[0004] (1) Incompleteness of fault data The data generated by power grid equipment is often incomplete. The traditional missing data processing method is to delete missing samples, that is to say, if a certain attribute of a sample is missing, then delete the sample

This deletion method may cause some important sample information to be deleted, seriously affecting the objectivity of the data and the correctness of the results

[0005] (2) Instability of decision tree algorithm

[0007] (3) Imbalance of fault data

However, misclassification is more costly for minority class failure data

Therefore, the imbalance of fault data greatly affects the diagnostic performance of traditional algorithms

Images