Mitigating Missing Rate and Early Cyberattack Discrimination Using Optimal Statistical Approach with Machine Learning Techniques in a Smart Grid

Aug 2, 2026

Upload by Miles

In the Industry 4.0 era of smart grids, cyberattacks can trigger blackouts and cascading failures, while conventional intrusion detection systems struggle with missing rates, response times, and detection accuracy. This work proposes a robust anomaly-based intelligent IDS that uses a statistical approach combined with machine learning classifiers to distinguish cyberattacks from natural faults and human-made events. The method leverages Neighborhood Component Analysis, ExtraTrees, and AdaBoost with optimal hyperparameter tuning for early discrimination. Experiments on the Triple Class dataset and IEEE 14-bus/57-bus FDI scenarios show higher accuracy, lower missing rates, fewer false alarms, and reduced response time versus existing approaches.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages34

Reading Time1 h 26 min

AccessFree to download

Introduction

Background and motivation for early cyberattack discrimination

Limitations of existing IDS approaches

Abstract-level proposed approach (statistical ML anomaly-based IDS)

Feature extraction and classification pipeline

Datasets and evaluation setup

energies Article Mitigating Missing Rate and Early Cyberattack Discrimination Using Optimal Statistical Approach with Machine Learning Techniques in a Smart Grid Nakkeeran Murugesan 1, Anantha Narayanan Velu 1, *, Bagavathi Sivakumar Palaniappan 1, Balamurugan Sukumar 2 and Md. Jahangir Hossain 3 Citation: Murugesan, N.; Velu, A.N.; Palaniappan, B.S.; Sukumar, B.; Hossain, M.J. Mitigating Missing Rate and Early Cyberattack Discrimination Using Optimal Statistical Approach with Machine Learning Techniques ina Smart Grid. Energies 2024, 17, 1965 . [https://doi.org/10.3390/en17081965](https://doi.org/10.3390/en17081965) Academic Editors: José Matas, Jorge El Mariachet and Sen Tan Received: 21 March 2024 Revised: 12 April 2024 Accepted: 15 April 2024 Published: 20 April 2024 Copyright: © 2024 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license ([https://](https://)[ ](https://)[creativecommons.org/licenses/by/](creativecommons.org/licenses/by/)[ ](creativecommons.org/licenses/by/)[4.0/](4.0/)) . 1 Department of Computer Science and Engineering, Amrita School of Computing, Amrita Vishwa Vidyapeetham, Coimbatore 641112, India; [m_nakkeeran@cb.students.amrita.edu](m_nakkeeran@cb.students.amrita.edu) (N.M.); [pbsk@cb.amrita.edu](pbsk@cb.amrita.edu) (B.S.P.) 2 Department of Electrical and Electronics Engineering, Amrita School of Engineering, Amrita Vishwa Vidyapeetham, Coimbatore 641112, India; [s_balamurugan@cb.amrita.edu](s_balamurugan@cb.amrita.edu) 3 School of Electrical and Data Engineering, University of Technology Sydney, Ultimo, NSW 2007, Australia; [jahangir.hossain@uts.edu.au](jahangir.hossain@uts.edu.au) * [Correspondence: v_ananthanarayanan@cb.amrita.edu](Correspondence: v_ananthanarayanan@cb.amrita.edu) Abstract: In the Industry 4.0 era of smart grids, the real-world problem of blackouts and cascading failures due to cyberattacks is a significant concern and highly challenging because the existing Intrusion Detection System (IDS) falls behind in handling missing rates, response times, and detection accuracy. Addressing this problem with an early attack detection mechanism with a reduced missing rate and decreased response time is critical. The development of an Intelligent IDS is vital to the mission-critical infrastructure of a smart grid to prevent physical sabotage and processing downtime. This paper aims to develop a robust Anomaly-based IDS using a statistical approach with a machine learning classifier to discriminate cyberattacks from natural faults and man-made events to avoid blackouts and cascading failures. The novel mechanism of a statistical approach with a machine learning (SAML) classifier based on Neighborhood Component Analysis, ExtraTrees, and AdaBoost for feature extraction, bagging, and boosting, respectively, is proposed with optimal hyperparameter tuning for the early discrimination of cyberattacks from natural faults and man-made events. The proposed model is tested using the publicly available Industrial Control Systems Cyber Attack Power System (Triple Class) dataset with a three-bus/two-line transmission system from Mississippi State University and Oak Ridge National Laboratory. Furthermore, the proposed model is evaluated for scalability and generalization using the publicly accessible IEEE 14-bus and 57-bus system datasets of False Data Injection (FDI) attacks. The test results achieved higher detection accuracy, lower missing rates, decreased false alarm rates, and reduced response time compared to the existing approaches. Keywords: blackouts; cascading failures; cyberattacks; feature extraction; intrusion detection system; machine learning; smart grid 1. Introduction The mission-critical infrastructure of Cyber–Physical Power Systems [1](CPPS), such as a smart grid, has been targeted for cyberwarfare to cause physical sabotag

FAQs

Why are existing intrusion detection systems insufficient for smart-grid cyberattacks?

They fall behind in handling missing rates, response times, and detection accuracy, making it harder to detect threats early and reliably in real-world network conditions.

What is the core idea of the proposed anomaly-based IDS?

It uses a statistical approach with machine learning classifiers to discriminate cyberattacks from natural faults and man-made events, enabling early detection.

Which datasets are used to evaluate the method and what improvements are reported?

The model is tested on the Triple Class dataset and evaluated for scalability/generalization on IEEE 14-bus and 57-bus FDI datasets, achieving higher detection accuracy, lower missing rates, reduced false alarms, and shorter response time than prior approaches.

Aug 2, 2026

Upload by Miles