Method for judging neighbor relationship of Internet of Things monitoring points

Abstract

The invention provides a method for judging a neighbor relationship of Internet of Things monitoring points. The method comprises the following steps: firstly, reading historical monitoring data of monitoring points in a set time window to obtain a monitoring data sequence set, and then using a plurality of clustering algorithms to perform clustering on monitoring data sequences in the monitoringdata sequence set, obtaining a plurality of clustering results by each clustering algorithm by changing the number of clusters, then calculating a contour coefficient of each clustering result, and using the clustering result with the largest contour coefficient as an optimal result, and finally, judging the neighbor relationship of the Internet of Things monitoring points according to the optimalresult. According to the method provided by the invention, the logic neighbor relationship is determined by using the clustering algorithms based on the historical monitoring data and according to the inherent similarity between the data of the monitoring points, an experimental result shows that the neighbor relationship of the monitoring points judged by the method is stable, compared with thetraditional method, the method has the advantages of being more in line with the objective reality and being able to provide a more scientific and reasonable basis for the validity auditing of the Internet of Things monitoring data and other data processing.

Description

technical field [0001] The invention relates to a method for analyzing and judging adjacent relationships of monitoring points of the Internet of Things based on clustering, and belongs to the technical fields of data mining and Internet of Things monitoring. Background technique [0002] In the current monitoring systems of the Internet of Things, due to the influence of factors such as sensing equipment and transmission network failures, and even human intentions, there are generally a large amount of invalid or abnormal data. For example, in the air quality real-time monitoring system, there are about 0.95% to 3.18% of various abnormal data. These abnormal data affect the availability of the overall data and require a data validity audit. When judging data anomalies and correcting abnormal data, it is usually necessary to refer to similar monitoring values ​​of neighboring monitoring points. For example, when finding abnormal data, use the average value (general process...

AI Technical Summary

Problems solved by technology

The meaning of this judgment method is intuitive and simple to implement. However, due to the irregular shape of many administrative regions, some monitoring points are too far away from other nodes in the same adjacent area. In addition, the monitoring objects are complex and changeable, so that the existing methods cannot meet the actual needs well, so it is necessary to explore more scientific and reasonable judgment methods

Images