Method of constructing binary electric-power sequential data index based on Geohash

Abstract

The invention relates to a method of constructing a binary electric-power sequential data index based on Geohash. The method comprises the following steps of 1, obtaining original binary electric-power sequential data, and conducting dimensionality reduction on the data; 2, conducting Geohash coding on the binary electric-power sequential data after the dimensionality reduction, and obtaining a BTSAX expression of the binary electric-power sequential data; 3, constructing the binary electric-power sequential BTSAX data index according to the BTSAX expression, and adopting an HBase database to store the original binary electric-power sequential data and the binary electric-power sequential data index. Compared with the prior art, the method of constructing the binary electric-power sequential data index based on the Geohash has the advantages of dynamic partition, assignable precision, non-overlapping nodes and the like.

Description

technical field [0001] The invention relates to the field of power data processing, in particular to a Geohash-based binary power time series data index construction method. Background technique [0002] User electricity load data is a kind of massive time series data, which has the characteristics of large user scale, high data collection density, and close correlation with a large amount of economic and social data. Time series data indexing technology is very important to reduce the time cost of data query and retrieval and improve the efficiency of time series mining (such as classification, clustering, outlier monitoring, pattern discovery, etc.). Time series is a series of data arranged in chronological order. According to the number of variables contained in the time series, it can be divided into univariate time series and multivariate time series. The user's electricity load data contains multiple information such as daily electricity consumption, voltage, and curr...

AI Technical Summary

Problems solved by technology

[0007] The current method based on space division retains the approximate information of the multivariate time series, but basically divides the space fixedly. For the index, the data distribution may not be uniform, which will reduce the query efficiency

Indexes based on feature compression find similar time series through dimensionality reduction, but usually cannot preserve the original multivariate time series information

Indexes based on metric spaces use triangular inequality and other lower-bound filtering techniques to improve query efficiency, but such indexes are still difficult to overcome the "curse of dimensionality" faced by high-dimensional data indexes

Images