Equal interval time series compression method, device, equipment and storage medium

Abstract

The present disclosure relates to a time series compression method, device, equipment and storage medium at equal intervals, which can be applied to time series data compression processing in power systems, such as compressing time series data related to new energy power generation such as wind power output time series etc., wherein the method includes: using the interleaved maximum and minimum points in the original time series data as the characteristic key points of the original time series data; fixed points; from the time series data between any two adjacent fixed points in the original time series data, multiple insertion points corresponding to the number of insertion points are determined at equal intervals, and finally compressed time series data is generated. The disclosure can achieve a better compression ratio on the premise of retaining the time series characteristics of the original data as much as possible, and the difference in data characteristics before and after compression is small, which improves the subsequent calculation accuracy and operation efficiency based on time series data.

Description

technical field [0001] The present disclosure relates to the technical field of data compression, and in particular to a compression method, device, device and storage medium for an equal-interval time series. Background technique [0002] A time series is a sequence in which the values ​​of the same statistical index are arranged in chronological order. Through in-depth study of these time series, we can dig out the hidden laws behind the series to obtain valuable information, which has great social significance and economic value. Time series analysis is widely used in fields such as electric power, economy, construction, medical treatment, meteorology, and environment. However, with the continuous development of social informatization and the continuous expansion of information technology application fields, more and more data have been accumulated in various application fields. The research and analysis of data directly in time series is not only heavy workload, but als...

AI Technical Summary

Problems solved by technology

[0006] 1) This method uses the mean value to represent the k data points of the original data, and information loss will occur;

[0007] 2) When the data compression ratio is larger, the mean value represents more data points, and the time series obtained after compression cannot effectively reflect the characteristics of the original sequence;

[0011] 1) The algorithm uses cumulative error for segmentation, which is not sensitive to data with large fluctuations in a short period of time, and the segmentation effect is poor;

[0012] 2) The algorithm is not sensitive to the inflection points of some state changes, and cannot effectively describe the state changes of some inflection points;

[0013] 3) The threshold of the algorithm is not easy to determine;

[0014] 4) The algorithm cannot choose the degree of compression according to the user's requirements, and cannot make the data point intervals equal

Images