A method and system for cleaning mass data of an energy storage power station

Abstract

The present invention provides a method and system for cleaning mass data of an energy storage power station, the method comprising the following steps: I, locating and replacing the default value in the data set of the energy storage power station; II, locating and replacing the abnormal value in the data set; III. According to the characteristics of different categories of the energy storage battery data, determine unreasonable data in the data set obtained after replacement, and replace them. The method and system of the present invention can not only realize the cleaning of massive battery data, but also ensure the distributed processing requirements of massive data, and realize the optimal cleaning of massive battery data of energy storage power stations with comprehensive consideration of K-nearest neighbor algorithm, Raida criterion method, distributed processing, etc. The purpose of preprocessing is to improve the effect of preprocessing and utilization of massive data of large-capacity battery energy storage power stations.

Description

technical field [0001] The present invention relates to a method and system in the technical field of energy storage, in particular to a method and system for cleaning massive data of an energy storage power station. Background technique [0002] At present, the data collection, storage and management methods of energy storage power stations are not yet standardized, and further research on massive data management and mining technologies for energy storage power stations is needed. The massive data of the energy storage power station mainly has the following characteristics: (1) Large amount of data: due to the large number of batteries in the energy storage power station, each battery has a lot of monitoring equipment, and the amount of data collected per second is huge, so it is required to be able to clean it correctly and quickly These data. (2) The reasons for abnormal data are complicated: due to the large number of monitoring equipment, which are affected by various ...

AI Technical Summary

Problems solved by technology

(2) The reasons for abnormal data are complex: due to the large number of monitoring equipment, which are affected by various objective and unpredictable factors such as accuracy and network signals, there are abnormal data in the data

[0005] 1. The range of single-batch processing is limited, resulting in a small number of mathematical statistical analysis each time and low cleaning accuracy;

[0006] 2. It cannot cope with the parallel processing of massive data, and single-line cleaning takes a long time, is slow, and is not efficient

[0007] 3. There are many types of data, and various situations need to be considered in a single batch, and the processing is more complicated, which increases the difficulty of calculation

Images