Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

A Dataset Generation Toolbox for Dynamic Security Assessment: On the Role of the Security Boundary

Bastien Giraud, Lola Charles, Agnes Marjorie Nakiganda, Johanna Vorwerk, Spyros Chatzivasileiadis

TL;DR

This paper proposes a novel method for generating a high number of samples close to the security boundary, considering both AC feasibility and small-signal stability, and highlights the critical role of accurately capturing security boundaries for effective security assessment.

Abstract

Dynamic security assessment (DSA) is crucial for ensuring the reliable operation of power systems. However, conventional DSA approaches are becoming intractable for future power systems, driving interest in more computationally efficient data-driven methods. Efficient dataset generation is a cornerstone of these methods. While importance and generic sampling techniques often focus on operating points near the system's security boundary, systematic methods for sampling in this region remain scarce. Furthermore, the impact of sampling near the security boundary on the performance of data-driven DSA methods has yet to be established. This paper highlights the critical role of accurately capturing security boundaries for effective security assessment. As such, we propose a novel method for generating a high number of samples close to the security boundary, considering both AC feasibility and small-signal stability. Case studies on the PGLib-OPF 39-bus and PGLib-OPF 162-bus systems demonstrate the importance of including boundary-adjacent operating points in training datasets while maintaining a balanced distribution of secure and insecure points.

A Dataset Generation Toolbox for Dynamic Security Assessment: On the Role of the Security Boundary

TL;DR

This paper proposes a novel method for generating a high number of samples close to the security boundary, considering both AC feasibility and small-signal stability, and highlights the critical role of accurately capturing security boundaries for effective security assessment.

Abstract

Dynamic security assessment (DSA) is crucial for ensuring the reliable operation of power systems. However, conventional DSA approaches are becoming intractable for future power systems, driving interest in more computationally efficient data-driven methods. Efficient dataset generation is a cornerstone of these methods. While importance and generic sampling techniques often focus on operating points near the system's security boundary, systematic methods for sampling in this region remain scarce. Furthermore, the impact of sampling near the security boundary on the performance of data-driven DSA methods has yet to be established. This paper highlights the critical role of accurately capturing security boundaries for effective security assessment. As such, we propose a novel method for generating a high number of samples close to the security boundary, considering both AC feasibility and small-signal stability. Case studies on the PGLib-OPF 39-bus and PGLib-OPF 162-bus systems demonstrate the importance of including boundary-adjacent operating points in training datasets while maintaining a balanced distribution of secure and insecure points.
Paper Structure (31 sections, 17 equations, 11 figures, 3 tables, 1 algorithm)

This paper contains 31 sections, 17 equations, 11 figures, 3 tables, 1 algorithm.

Table of Contents

  1. Introduction
  2. Dynamic Security Assessment
  3. Feasibility
  4. AC Optimal Power Flow
  5. Quadratic Convex (QC) Relaxation
  6. Stability
  7. Security Boundary
  8. Dataset Generation Considering the Security Boundary
  9. Reducing the Search Space
  10. Optimization-Based Bound Tightening
  11. Infeasibility Certificates
  12. Convex Polytope Construction
  13. Initialization Points Directed Walks
  14. Directed Walks
  15. Directed Walk Algorithm
  16. ...and 16 more sections

Figures (11)

  • Figure 1: Flowchart of the proposed methodology.
  • Figure 2: Description of the datasets generated for dataset evaluation and decision tree training. In total, six datasets are generated and six corresponding decision trees are trained.
  • Figure 3: Share of feasible, stable, secure, and HIC-region samples for the 39-bus system (top) and 162-bus system (bottom).
  • Figure 4: Spread of secure and insecure OPs for the 39-bus system, plotted for generator 5 and 9.
  • Figure 5: Spread of secure and insecure OPs for the 39-bus system, plotted for generator 5 and 8.
  • ...and 6 more figures