Weighted cosine similarity-based power consumption behavior abnormity analysis method for key personnel

Abstract

The invention relates to a weighted cosine similarity-based power consumption behavior abnormity analysis method for key personnel, which comprises the following steps of: marking information of key personnel through a demand department, selecting power consumption behavior analysis characteristics, collecting power consumption load identification data of the key personnel at the current moment and environment variable characteristic information at the current moment; according to the environment variable characteristic information at the current moment, obtaining corresponding historical electricity consumption behavior characteristics at the historical moment, performing weighted cosine similarity calculation on the current electricity consumption behavior characteristics and the electricity consumption behavior characteristics at the historical moment, obtaining the similarity degree of a historical day and a day to be detected, and setting a similarity threshold value; and when the historical data volume is larger, the feature selection is richer, and the obtained similarity is closer to the real power consumption behavior. According to the invention, the accuracy of abnormal behavior study and judgment can be effectively improved, and the efficiency is improved. And the sample similarity is reflected more accurately, so that the calculation result is closer to reality. And the supervision mode that supervision power is mobilized by a human center is reduced.

Description

technical field [0001] The invention relates to a weighted cosine similarity-based analysis method for abnormal power consumption behavior of key personnel, and belongs to the technical field of smart grids. Background technique [0002] As the world enters the era of informationization and digitalization, China's urbanization and urbanization development is becoming more and more mature, and technologies such as big data mining, cloud computing, artificial intelligence, and advanced measurement are increasingly widely used. , technical means and other aspects put forward new requirements. Electric power data has huge potential value, but the support of electric power data for multi-field subjects serving municipal social governance is relatively weak. At the same time, government departments are also actively promoting the development of digital transformation. Considering that social governance has put forward higher requirements for refined city management, precise staff...

AI Technical Summary

Problems solved by technology

However, the existing technology lacks a data application method that uses this technology to conduct abnormal behavior analysis for key personnel power data and multivariate data mining, and assist demand departments to manage key personnel.

Images