Real-time estimation of power imbalance during contingency events : A data-driven approach

Tools

Shen, Lu and Hong, Qiteng and Han, Jiaxuan and Wang, Jianxiao and Booth, Campbell; (2025) Real-time estimation of power imbalance during contingency events : A data-driven approach. In: 2025 IEEE PES Innovative Smart Grid Technologies Conference Europe (ISGT Europe). IEEE, MLT, pp. 1-5. ISBN 979-8-3315-2503-3 (https://doi.org/10.1109/isgteurope64741.2025.11305...)

[thumbnail of Shen-etal-2025-Real-time-estimation-of-power-imbalance-during-contingency-events]
Preview
 Text. Filename: Shen-etal-2025-Real-time-estimation-of-power-imbalance-during-contingency-events.pdf
Final Published Version
License: Creative Commons Attribution 4.0 logo
Download (2MB)| Preview

Abstract

Fast and accurate estimation of active power imbalance during frequency contingency events is crucial for effective power system monitoring and frequency control. Conventional power imbalance estimation methods are typically based on the swing equation, where both system inertia and the Rate of Change of Frequency (RoCoF) are required for the calculation. However, accurate real-time system inertia level is often unavailable, and measuring RoCoF reliably remains challenging. As a result, the conventional methods are not effective, particularly with the increasing penetration of renewables, where system uncertainties have increased with power quality degraded. This paper explores the feasibility of applying a data-driven approach to address the aforementioned challenges, where the Extreme Gradient Boosting (XGBoost) algorithm is used to train a model that only requires frequency and system operating conditions as inputs for accurate estimation of power imbalance. Through appropriate training, the proposed method does not require the accurate system inertia data and avoids the need for RoCoF measurement. Case studies are presented, which demonstrate that the proposed approach can achieve a highly satisfactory accuracy, providing an effective solution for estimating the power imbalance size during contingency events.

ORCID iDs

Shen, Lu, Hong, Qiteng ORCID logoORCID: https://orcid.org/0000-0001-9122-1981, Han, Jiaxuan ORCID logoORCID: https://orcid.org/0000-0002-4823-4178, Wang, Jianxiao and Booth, Campbell ORCID logoORCID: https://orcid.org/0000-0003-3869-4477;
CORE (COnnecting REpositories)