Anomaly detection in Internet of Things using feature selection and classification based on Logistic Regression and Artificial Neural Network on N-BaIoT dataset

Fereshteh Abbasi

M.Sc. student of Artificial Intelligence, Department of Computer Engineering, Shahid Chamran University of Ahvaz, Ahvaz, Iran

f-abasi@scu.ac.ir

Marjan Naderan

Associate Professor, Department of Computer Engineering, Shahid Chamran University of Ahvaz, Ahvaz, Iran

m.naderan@scu.ac.ir

Seyed Enayatallah Alavi

Assistant Professor, Department of Computer Engineering, Shahid Chamran University of Ahvaz, Ahvaz, Iran

se.alavi@scu.ac.ir

Abstract—As technology advances and world population grows, there is greater need for power consumption. From technologies used on a daily basis to the latest and most advanced all require electrical power. Thus, there is a necessity for managing this power distribution in an optimal way. To meet demands for electrical power, a reliable framework to monitor and analyze the grid behavior is required. The purpose of this paper was to present a framework architecture, its implementation, and evaluate its performance over a real-life dataset. This framework utilized the latest technologies such as the Internet of Things (IoT), big data, fog and cloud computing to decrease network traffic, increase data analysis speed and illustrate real-time data analysis on a web-based dashboard on the current state of the power grid. These features give administrators the ability to control the grid in a crisis situation and clients to consume electric power more efficiently.

Keywords: Internet of Things (IoT), fog computing, cloud computing, demand side management, smart grid.