Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Resilient Temporal GCN for Smart Grid State Estimation Under Topology Inaccuracies

Seyed Hamed Haghshenas, Mia Naeini

TL;DR

Two variations of the TGCN architecture are introduced to integrate the knowledge graph, and their performances are evaluated and compared to demonstrate improved resilience against topology uncertainties.

Abstract

State Estimation is a crucial task in power systems. Graph Neural Networks have demonstrated significant potential in state estimation for power systems by effectively analyzing measurement data and capturing the complex interactions and interrelations among the measurements through the system's graph structure. However, the information about the system's graph structure may be inaccurate due to noise, attack or lack of accurate information about the topology of the system. This paper studies these scenarios under topology uncertainties and evaluates the impact of the topology uncertainties on the performance of a Temporal Graph Convolutional Network (TGCN) for state estimation in power systems. In order to make the model resilient to topology uncertainties, modifications in the TGCN model are proposed to incorporate a knowledge graph, generated based on the measurement data. This knowledge graph supports the assumed uncertain system graph. Two variations of the TGCN architecture are introduced to integrate the knowledge graph, and their performances are evaluated and compared to demonstrate improved resilience against topology uncertainties. The evaluation results indicate that while the two proposed architecture show different performance, they both improve the performance of the TGCN state estimation under topology uncertainties.

Resilient Temporal GCN for Smart Grid State Estimation Under Topology Inaccuracies

TL;DR

Two variations of the TGCN architecture are introduced to integrate the knowledge graph, and their performances are evaluated and compared to demonstrate improved resilience against topology uncertainties.

Abstract

State Estimation is a crucial task in power systems. Graph Neural Networks have demonstrated significant potential in state estimation for power systems by effectively analyzing measurement data and capturing the complex interactions and interrelations among the measurements through the system's graph structure. However, the information about the system's graph structure may be inaccurate due to noise, attack or lack of accurate information about the topology of the system. This paper studies these scenarios under topology uncertainties and evaluates the impact of the topology uncertainties on the performance of a Temporal Graph Convolutional Network (TGCN) for state estimation in power systems. In order to make the model resilient to topology uncertainties, modifications in the TGCN model are proposed to incorporate a knowledge graph, generated based on the measurement data. This knowledge graph supports the assumed uncertain system graph. Two variations of the TGCN architecture are introduced to integrate the knowledge graph, and their performances are evaluated and compared to demonstrate improved resilience against topology uncertainties. The evaluation results indicate that while the two proposed architecture show different performance, they both improve the performance of the TGCN state estimation under topology uncertainties.

Paper Structure

This paper contains 20 sections, 8 equations, 5 figures.

Table of Contents

  1. Introduction
  2. Related Work
  3. Problem Formulation
  4. Power Systems as Graphs
  5. Topology Inaccuracies
  6. A Review of TGCN Model for State Estimation
  7. Resilient TGCN Framework
  8. Knowledge Graph
  9. Cosine Similarity-based Knowledge Graph
  10. Correlation-based Knowledge Graph
  11. Graph Attention Networks (GAT) Generated Knowledge Graph
  12. Knowledge Graph Infused Model (KGIM) for SE
  13. Parallel Knowledge Graph Infused Model (PKGIM) for SE
  14. Single-Layer Perceptron (SLP) Aggregation
  15. Multi-Layer Perceptron (MLP) Aggregation
  16. ...and 5 more sections

Figures (5)

  • Figure 1: The overview of the Knowledge Graph Infused Model (KGIM).
  • Figure 2: The overview of the Parallel Knowledge Graph Infused Model (PKGIM).
  • Figure 3: Performance of KGIM with inaccurate topology scenarios: incorrect missing edges (a) and extra edges (b), using cosine similarity-, correlation- and the GAT model-generated knowledge graphs.
  • Figure 4: Performance of PKGIM with inaccurate topology scenarios: incorrect missing edges (a) and extra edges (b), using cosine similarity-, correlation- and the GAT model-generated knowledge graphs.
  • Figure 5: The overall performance of KGIM and PKGIM with knowledge graphs generate by the cosine similarity method vs. the correlation analysis vs. the GAT model under incorrect missing edges (LR) and extra edges (LA) inaccurate topology scenarios.