Data-driven approach to capturing wide-area frequency response dynamics

Brown, Alinane B. and Papadopoulos, Panagiotis N. and Hamilton, Robert I. (2024) Data-driven approach to capturing wide-area frequency response dynamics. In: International Universities Power Engineering Conference, 2024-09-02 - 2024-09-06, Cardiff University. (In Press)

[thumbnail of Kilembe-etal-IUPEC-2024-Data-driven-approach-to-capturing-wide-area-frequency-response-dynamics] Text. Filename: Kilembe-etal-IUPEC-2024-Data-driven-approach-to-capturing-wide-area-frequency-response-dynamics.pdf
Final Published Version
Restricted to Repository staff only until 1 January 2099.
License: Strathprints license 1.0
Download (1MB) | Request a copy

Abstract

The increase in Converter Interfaced Generation (CIG) is leading to the system frequency response becoming an increasingly local phenomenon. Traditionally, in frequency studies, the conventional Centre of Inertia (COI)-based approach, which assumes a global frequency response, is usually used. As such, the COI-based approach cannot adequately capture locational frequency variations. Consequently, there is a higher risk of unforeseen relay activation, which may lead to large-scale blackouts. This paper first demonstrates the potential locational frequency variations due to high CIG penetration, which purely COI-based methods may fail to capture. Next, the paper proposes a machine learning (ML) approach to effectively capture and represent these nonlinear frequency dynamics. Simulation results on the modified IEEE 39-bus test network indicate that the proposed ML approach can be computationally efficient while providing accuracy similar to that of the computationally intensive time-domain dynamic simulations.

CORE (COnnecting REpositories)