Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Data-Driven Graph Switching for Cyber-Resilient Control in Microgrids

Suman Rath, Subham Sahoo

TL;DR

A physics-guided, supervised Artificial Neural Network (ANN)-based framework that identifies communication-level cyberattacks in microgrids by analyzing whether incoming measurements will cause abnormal behavior of the secondary control layer, and eliminates the secondary control layer's dependence on inputs from compromised cyber devices helping it achieve resilience without instability.

Abstract

Distributed microgrids are conventionally dependent on communication networks to achieve secondary control objectives. This dependence makes them vulnerable to stealth data integrity attacks (DIAs) where adversaries may perform manipulations via infected transmitters and repeaters to jeopardize stability. This paper presents a physics-guided, supervised Artificial Neural Network (ANN)-based framework that identifies communication-level cyberattacks in microgrids by analyzing whether incoming measurements will cause abnormal behavior of the secondary control layer. If abnormalities are detected, an iteration through possible spanning tree graph topologies that can be used to fulfill secondary control objectives is done. Then, a communication network topology that would not create secondary control abnormalities is identified and enforced for maximum stability. By altering the communication graph topology, the framework eliminates the dependence of the secondary control layer on inputs from compromised cyber devices helping it achieve resilience without instability. Several case studies are provided showcasing the robustness of the framework against False Data Injections and repeater-level Man-in-the-Middle attacks. To understand practical feasibility, robustness is also verified against larger microgrid sizes and in the presence of varying noise levels. Our findings indicate that performance can be affected when attempting scalability in the presence of noise. However, the framework operates robustly in low-noise settings.

Data-Driven Graph Switching for Cyber-Resilient Control in Microgrids

TL;DR

A physics-guided, supervised Artificial Neural Network (ANN)-based framework that identifies communication-level cyberattacks in microgrids by analyzing whether incoming measurements will cause abnormal behavior of the secondary control layer, and eliminates the secondary control layer's dependence on inputs from compromised cyber devices helping it achieve resilience without instability.

Abstract

Distributed microgrids are conventionally dependent on communication networks to achieve secondary control objectives. This dependence makes them vulnerable to stealth data integrity attacks (DIAs) where adversaries may perform manipulations via infected transmitters and repeaters to jeopardize stability. This paper presents a physics-guided, supervised Artificial Neural Network (ANN)-based framework that identifies communication-level cyberattacks in microgrids by analyzing whether incoming measurements will cause abnormal behavior of the secondary control layer. If abnormalities are detected, an iteration through possible spanning tree graph topologies that can be used to fulfill secondary control objectives is done. Then, a communication network topology that would not create secondary control abnormalities is identified and enforced for maximum stability. By altering the communication graph topology, the framework eliminates the dependence of the secondary control layer on inputs from compromised cyber devices helping it achieve resilience without instability. Several case studies are provided showcasing the robustness of the framework against False Data Injections and repeater-level Man-in-the-Middle attacks. To understand practical feasibility, robustness is also verified against larger microgrid sizes and in the presence of varying noise levels. Our findings indicate that performance can be affected when attempting scalability in the presence of noise. However, the framework operates robustly in low-noise settings.

Paper Structure

This paper contains 14 sections, 24 equations, 11 figures, 5 tables.

Table of Contents

  1. Introduction
  2. Control Structure and Attack Formulation
  3. Primary Control
  4. Secondary Control
  5. DIAs in the Communication Layer
  6. ANN-Based Communication Graph Switching
  7. Physics-Guided Deep Learning for Cyber-Attack Indication
  8. Optimal Spanning Tree Switching for Attack Mitigation
  9. Rationale Behind the Proposed Method
  10. Performance Validation and Results
  11. Performance of estimation model
  12. Impact of cyberattacks
  13. Scalability analysis
  14. Conclusion

Figures (11)

  • Figure 1: Hierarchical control in distributed microgrids.
  • Figure 2: Schematic diagram of the proposed cyberattack detection and mitigation framework.
  • Figure 3: Working mechanism of the proposed ANN-based graph topology switching framework.
  • Figure 4: Demonstration of (a) resilience against repeater-level MITM attacks and (b) $(N-1)$ resilience against transmitter-level FDI attacks.
  • Figure 5: Performance of the deep ANN model without noise: (a) violin plot showing target and predicted value distributions, and (b) density histogram comparing target and predicted value frequencies.
  • ...and 6 more figures