Analysis and techniques of cyberattack types classification in smart grids

Abstract

The smart electric grids rely on integrating the information and communication technologies (ICT) into the electric power grid infrastructure to facilitate the exchange of information for an enhanced and economic operation. Such integration of ICT into the existing electric grids makes them vulnerable to cybersecurity threats, ranging from data breaches to service disruptions. The work in this thesis investigates the use of machine learning techniques to detect and classify such cyberattacks. A novel approach that uses a fine tree bagging ensemble learning technique to detect and classify the cyberattack types from normal and power quality disturbances is developed. The proposed approach extracts the relevant features for classifying different cyber-attack types such as message suppression, denial-of-service and data manipulation. The proposed approach is tested on a publicly available dataset and the results are compared to three other machine learning techniques, namely decision tree, nearest neighbor, and support vector machine. The results have shown that the proposed approach is very effective in the detection and the classification of the cyberattack types as well as it is insensitive to the selection of the training and the testing datasets.