Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Machine Learning based Post Event Analysis for Cybersecurity of Cyber-Physical System

Kuchan Park, Junho Hong, Wencong Su, HyoJong Lee

TL;DR

A machine learning (ML) based post event analysis of the power system in order to respond to cybersecurity issues and can successfully distinguish between power system faults and cyber-attacks.

Abstract

As Information and Communication Technology (ICT) equipment continues to be integrated into power systems, issues related to cybersecurity are increasingly emerging. Particularly noteworthy is the transition to digital substations, which is shifting operations from traditional hardwired-based systems to communication-based Supervisory Control and Data Acquisition (SCADA) system operations. These changes in the power system have increased the vulnerability of the system to cyber-attacks and emphasized its importance. This paper proposes a machine learning (ML) based post event analysis of the power system in order to respond to these cybersecurity issues. An artificial neural network (ANN) and other ML models are trained using transient fault measurements and cyber-attack data on substations. The trained models can successfully distinguish between power system faults and cyber-attacks. Furthermore, the results of the proposed ML-based methods can also identify 10 different fault types and the location where the event occurred.

Machine Learning based Post Event Analysis for Cybersecurity of Cyber-Physical System

TL;DR

A machine learning (ML) based post event analysis of the power system in order to respond to cybersecurity issues and can successfully distinguish between power system faults and cyber-attacks.

Abstract

As Information and Communication Technology (ICT) equipment continues to be integrated into power systems, issues related to cybersecurity are increasingly emerging. Particularly noteworthy is the transition to digital substations, which is shifting operations from traditional hardwired-based systems to communication-based Supervisory Control and Data Acquisition (SCADA) system operations. These changes in the power system have increased the vulnerability of the system to cyber-attacks and emphasized its importance. This paper proposes a machine learning (ML) based post event analysis of the power system in order to respond to these cybersecurity issues. An artificial neural network (ANN) and other ML models are trained using transient fault measurements and cyber-attack data on substations. The trained models can successfully distinguish between power system faults and cyber-attacks. Furthermore, the results of the proposed ML-based methods can also identify 10 different fault types and the location where the event occurred.
Paper Structure (11 sections, 4 equations, 4 figures, 4 tables)

This paper contains 11 sections, 4 equations, 4 figures, 4 tables.

Table of Contents

  1. Introduction
  2. PROPOSED POST EVENT ANALYSIS
  3. Proposed Post Event Analysis
  4. Machine Learning Algorithm Analysis for Fault Type and Location Classification
  5. Cyber attack Implementation
  6. CASE STUDIES
  7. System Configuration
  8. Single Fault Post Event Analysis Result
  9. N-1 Contingency Event (with Single Fault) Analysis Result
  10. Simultaneous Event (Two Faults) Analysis Result
  11. Conclusion

Figures (4)

  • Figure 1: An example of post event analysis applied to an IEEE 14 bus system.
  • Figure 2: The flowchart of proposed post event analysis.
  • Figure 3: An example of three phase bus voltages: (a) without fault and (b) fault at line 4-5.
  • Figure 4: An example of spoofing attacks for SV messages 9361308.