Research on Modeling Method of Massive Launch Vehicle Time Series Data

Abstract

Massive time series data is produced with the newly proposed long-term test, with high data sampling frequency, usually 40Hz, and the sampling lasts for a long time, often more than one year. Therefore, it brings the storage problem of massive launch vehicle time series data. In view of the shortcomings that the traditional storage method based on files may be difficult to meet the storage requirements of high concurrent writing, high compression rate and high query speed, the data modeling method is studied in this paper. For storage method based on files, relational database storage and time series database, the data model is constructed, and the configuration parameters are optimized, and the optimal storage method is selected by the performance simulation carried out. The simulation results show that under the massive time series data scenario, the storage method based on time series database has twice the writing speed of the others; It has the highest storage compression rate, up to 80%, far exceeding the uncompressed storage method based on files and the relational database storage method with data expansion; It has the fastest time-related query speed, more than 100,000 records/s, 3 times that of relational database and 10 times that of files. Among them, the storage method based on time series database has the best performance, and meets the storage requirements of massive time series data in the future for launch vehicles.