A Trust-Based Framework and Deep Learning-Based Attack Detection for Smart Grid Home Area Network

Abstract

The Internet of things (IoT) can be used in our daily life. Home area network (HAN) is one of the applications of loT. The Smart Grid is an intelligent power network featured by its two-way flows of electricity and information. The integrated communication infrastructure allows Smart Grid systems to manage the operation of all connected components to provide reliable and sustainable electricity supplies. The Home Area Network is a dedicated network connecting devices in the home, as well as electrical vehicles. The HAN market is now emerging within the smart grid sector to serve home with different solutions. However, at the same time, due to the dependence on information technology and the deep integration of electrical components and computing information in cyber space, the system might become increasingly vulnerable to cyber-attacks. Cyber-attacks have led to numerous incidents and have been concerned by both power system operators and users. They can undermine or even completely disrupt the control system of the power grid. This paper presents an approach to modelling and validating the secure HAN network. Here a novel Trust-Based Iterative Energy-Efficient Routing Protocol (TBIEERP) is suggested with a data encryption scheme for secured data transmission in HAN. The Honeypot algorithm for encryption and decryption of data is employed. Finally, to detect the intrusion a deep auto encoder was used for attack detection and to protect HAN against cyber-attacks. The whole experimentation was carried out under Matlab environment. Thus, the techniques proposed produce the most promising outcome over attack detection. The proposed method obtained better detection accuracy compared to the existing methods.