Intrusion Detection System for AMI in Smart Grid Using Hybrid Tree-based Classifier

Abstract

The current research suggests an IDS for AMI in smart grids as an effective approach to the detection of any threats. The approach utilizes a hybrid tree-based classifier along with information gain as a method of feature selection in order to improve the performance of detection in the neighborhood area network (NAN).

For the identification of the features that should be selected from the data, information gain is utilized, as it shows the relation between the features and the attack type. In addition, the classifier is enhanced by the utilization of the stacking algorithm.

The performance of the suggested model was tested using the UNSW-NB15 dataset. It turned out that the suggested approach is more efficient than other machine learning approaches such as Logistic Regression (LR), Support Vector Machines (SVM), Random Forest (RF), and K-Nearest Neighbors (KNN).