Anomaly Detection in Smart Grid Network Using FC-Based Blockchain Model and Linear SVM

Abstract

AbstractTraditional grid network has played a major role in society by distributing and transmitting electric supply to consumers. However, with the advancement in technology in Industry 4.0 has evolved the role of the Smart Grid (SG) network. SG network is a two-way bi-directional communication Cyber-Physical System (CPS). Whereas traditional grid network is a one-way directional physical system. SG is a part of the most revolutionary application of Internet-of-Things (IoT). The information related to power consumption and supplies can be transmitted and recorded in real-time. The connection of SG with the internet has also created a lot of space for different types of anomalies injection and cyber-physical attacks. SG network is open and vulnerable to an outside hacker. The detection of an anomaly in real-time is of utmost importance otherwise it may lead to huge power loss, security, and monetary loss to the consumer, producer, and smart city society. In this paper, we have proposed a private blockchain system model for anomaly detection in SG along with a novel Linear Support Vector Machine Anomaly Detection (LSVMAD) algorithm in a fog computing (FC) environment. Here FC nodes will act as miners to support and make real-time decisions for anomaly detection in an SG network. The anomaly detection accuracy of the LSVMAD algorithm in the FC environment is 89% and in the cloud is 78%. The proposed LSVMAD algorithm easily outperforms the existing techniques and algorithms when compared for anomaly detection accuracy percentage. The simulation tool used in the implementation of works is iFogSim, Anaconda (Python), Geth version 1.9.25, Ganache, Truffle (Compile) and ATOM as a text editor for creating smart contracts.KeywordsSmart gridFog computingLinear SVMInternet-of-ThingsSmart meterCyber-physical systemMachine learning