Abstract
A Hybrid Model for Anomalies Detection in AMI System Combining K-means Clustering and Deep Neural Network
Highlights
In recent years, there has been a global trend to optimize the use of electrical networks by automating and transforming all parts of the traditional electrical power grid: from the user’s household electrical appliances to the power-generating stations into an interactive and intelligent grid
The main contributions of this paper can be summarized as explained below: 1. We present a novel and robust hybrid approach for anomaly detection in advanced metering infrastructure (AMI) data, by combining the advantages of both unsupervised clustering and supervised classification, K-means-Deep Neural Network (DNN) approach is effective for anomaly detection in the case of unlabeled and large data sets
We identify groups of customers with similar electricity consumption patterns to understand different types of normal behavior
Summary
There has been a global trend to optimize the use of electrical networks by automating and transforming all parts of the traditional electrical power grid: from the user’s household electrical appliances to the power-generating stations into an interactive and intelligent grid. Many cyber-security experts [Zetter (2015); Weaver (2015); Ayers (2017)] have proven that the smart meter, which is the foremost component of AMI system, has become a potential target of cyber-attacks and hacking attempts. These malicious attempts (on AMI system) usually aim to realize several outcomes: 1) data theft; 2) electricity theft; and 3) localized or widespread denial of electricity [Wilshusen (2015); Weaver (2017); Foreman and Gurugubelli (2015); Hansen, Staggs and Shenoi (2017)]. Electricity theft is among the most dangerous and popular attacks on the AMI system
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
