A method, system and storage medium for identifying fault data of power internet of things

Abstract

The invention discloses a method and system for identifying fault data of the Internet of Things in electric power. multiple message data points; extract the timestamps in each message data, and use the improved DTW dynamic time warping algorithm to process the timestamps in the uploaded IoT message data; use the DBSCAN density clustering algorithm The voltage monitoring value, current monitoring value and power monitoring value are detected and combined with the PNN algorithm to establish features; according to the established features, the random forest algorithm is used to identify the final judgment result, which solves the current fault data type of the IoT system. The library aims at the problem of insufficient generalization ability of traditional single-class recognition algorithms.

Description

technical field [0001] The present invention relates to the field of computer technology, and in particular, to a method, system and storage medium for identifying fault data of the power Internet of things. Background technique [0002] The power IoT system is under the trend of the rapid development of the Internet of Things, combined with the development of the power system, the IoT system came into being. As State Grid officially proposed the strategic goal of "building a full-service ubiquitous power Internet of Things", the combination of power Internet of Things and big data analysis has become possible. Nowadays, data analysis technology has high requirements for the uniformity of data, but the data collected in the power system has many sources and different data forms, including static data including ID and various attribute values, and dynamic data including timestamps and monitoring values. data, which results in that the initial data collected cannot be directl...

AI Technical Summary

Problems solved by technology

[0003] At present, although there are data failures or abnormalities in the Internet of Things or the Internet of Things system, they are all for the partial failure analysis of the Internet of Things system, and there is no overall analysis of the Internet of Things system.

Images