Anomaly detection method based on time series

Abstract

The invention discloses an anomaly detection method based on a time series. The anomaly detection method based on the time series comprises intra-node data correlation analysis and inter-node data correlation analysis. The intra-node data correlation analysis describes time correlation of sensor node data and is to compute the data correlation between current data and historical data. The inter-node data correlation analysis describes spatial data correlation between different sensor nodes and is to compute the data correlation between the sensor node data and data of neighbor nodes of sensor nodes. The anomaly detection method based on the time series can be used for effectively detecting abnormal data, and good performance can still be kept under the influence of wrong data. Meanwhile, an approximation method of the time series data is applied so that the time series data can be effectively compressed, a method for measuring the similarity between the compressed time series is put forward and used for clustering analysis of the time series, and consequently anomaly detection based on the time series is achieved.

Description

technical field [0001] The invention relates to an abnormal detection method of a wireless sensor network, in particular to an abnormal detection method based on time series. Background technique [0002] Anomaly detection in wireless sensor networks is mainly used to detect whether the data collected by sensor nodes is abnormal, that is, to detect which node data deviates from the majority of node data or does not meet the normal data characteristics, and feedback the results to the user so that the user can make a decision. corresponding decision. [0003] In wireless sensor networks, the continuous data generated periodically by sensor nodes can be expressed as time series. Therefore, time series anomaly detection technology can be used to realize data anomaly detection of sensor network. Since the time series is a large amount of streaming data, if the original time series is directly analyzed, processed and sent to the base station, the energy consumption and network ...

AI Technical Summary

Problems solved by technology

Literature E.Keogh, K.Chakrabarti, S.Mehrotra et al.Locally Adaptive Dimensionality Reduction for Indexing Large Time Series Databases[C].In:ACM SIGMOD2001,Santa Barbara,California,2001. Proposed an adaptive piecewise constant approximation method (APCA), which gives a similarity measurement method, but it is more complicated

Although the data compression rate of this method meets the given error requirements, it only analyzes the similarity measurement method between the compressed time series and other original time series, and does not give the similarity measurement method between the compressed time series

Images