Statistical machine learning defensive mechanism against cyber intrusion in smart grid cyber-physical network. Issue 123 (December 2022)

• Record Type: Journal Article
• Authors: Singh, Neeraj Kumar; Majeed, Mahshooq Abdul; Mahajan, Vasundhara
• Is Part Of: Computers & security. Issue 123(2022)
• Publication Date: 2022-12
• Subjects: Statistical Machine Learning Defensive Mechanism (SML-DM) -- Data Prediction Error (DPE) -- Sensor Reliability Score (SRS) -- Cyber-Physical Network -- False Data Injection Attacks (FDIA); Computer security -- Periodicals; Electronic data processing departments -- Security measures -- Periodicals; 005.805
• DOI: 10.1016/j.cose.2022.102941
• Languages: English
• ISSNs: 0167-4048

Abstract

Abstract: Cyber-Physical Systems are becoming more susceptible to cyber intrusion, compromising the critical infrastructure of the smart grid. This emerging concern requires the urgent help of researchers to find a practical and better approach to secure an intelligent power grid against cyber-attack. This research article proposes a "Statistical Machine Learning Defensive Mechanism (SML-DM)" for Smart Grid Cyber-Physical Networks (SGCPN) against cyber intrusion by using a Gaussian mixture model merged with wireless sensor data. Using SML-DM, two new indices are proposed to evaluate the performance of the defensive mechanism. The first index, Data Prediction Error (DPE), calculates actual and predicted data errors during a cyber-attack. The second index, Sensor Reliability Score (SRS), is used to assess the reliability status of wireless sensors. MATLAB software was used to validate this research, and data was taken from the National Renewable Energy Laboratory (NREL). Using the proposed defence mechanism, it is found that the data integrity and reliability of the sensors can increase by up to 90%.