Abstract
We propose an integrated framework for an intrusion detection system for SCADA (Supervisory Control and Data Acquisition)-based power grids. Our scheme combines RFE-XGBoost (Recursive Feature Elimination-eXtreme Gradient Boosting) based feature selection with a majority vote ensemble method. RFE selects features recursively based on Weighted Feature Importance (WFI) scores during the training process, while the majority vote ensemble method predicts the output label based on a total of nine heterogeneous classifiers - three bagging ensembles, namely, Random Forest (RF), Extra Tree (ET), and Decision Tree (DT), three boosting ensembles, namely, XGBoost (XGB), Gradient Boosting (GB), and AdaBoost-Decision Tree (AdB-DT) along with artificial neural network (ANN), Naive Bayes (NB), and k-nearest neighbors (KNN). This leads to a more accurate solution as a result of the combination of the most useful features and prediction from multiple heterogeneous classifiers. Experimental results show that our approach increases the accuracy, precision, recall, F1 score, and decreases the miss rate as compared to previous approaches. The model is also evaluated for four different class categories, namely binary, three-class, seven class and multi-class, using Precision Recall (PR) and Receiver Operating Characteristic (ROC) plot. In addition, an end-to-end IDS framework is proposed for efficient and accurate detection of intrusions.
Highlights
POWER grids are the underlying infrastructure that support our economies and daily lives by providing and sustaining a continuous supply of electricity
We have identified three bagging ensembles, namely, Random Forest (RF), Extra Tree (ET), and Decision Tree (DT), three boosting ensembles XGBoost (XGB), Gradient Boosting (GB) and AdaBoost-Decision Tree (AdB-DT) as the most promising classifiers
3) For the performance improvement, we apply the majority vote ensemble algorithm by considering nine heterogeneous classifiers to predict the output based on the majority of the class labels predicted by each of these nine classifiers
Summary
POWER grids are the underlying infrastructure that support our economies and daily lives by providing and sustaining a continuous supply of electricity. The sensors and actuators located at power grids frequently supply digital status information to the field control devices These devices further communicate this information to MTU, where the server will process the data according to acceptable parameter ranges. This approach helps us achieve a better predictive model by searching all the stable features instead of the most promising features while constructing the tree Another enhancement has been applied to the classification model by using a majority vote based ensemble method consisting of six tree-based classifiers along with artificial neural network (ANN), Naive Bayes (NB), and k-nearest neighbors. UPADHYAY et al.: INTRUSION DETECTION IN SCADA BASED POWER GRIDS: RECURSIVE FEATURE ELIMINATION MODEL WITH MAJORITY. The objective and major contributions of this work are listed below
Sign-in/Register to view highlights & summary 
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call