A Data-driven Under Frequency Load Shedding Scheme in Power Systems

TL;DR

This paper introduces a novel data-driven predictive control algorithm for under frequency load shedding in power systems, enhancing adaptability and safety through a latent extractor network and safety margin tuning.

Contribution

It develops a new KLS algorithm that uses a latent extractor network for dynamic parameter tracking and a safety margin scheme for improved load shedding accuracy.

Findings

Demonstrates adaptability to varying operating conditions

Shows improved prediction accuracy of system frequency

Ensures system frequency remains within safety limits

Abstract

Under frequency load shedding (UFLS) constitutes the very last resort for preventing total blackouts and cascading events. Fluctuating operating conditions and weak resilience of the future grid require UFLS strategies adapt to various operating conditions and non-envisioned faults. This paper develops a novel data-enabled predictive control algorithm KLS to achieve the optimal one-shot load shedding for power system frequency safety. The algorithm utilizes a latent extractor network to track parameter variations in the system dynamic model, enabling a coordinate transformation from the delay embedded space to a new space where the dynamics can be linearly represented. To address approximation inaccuracies and the discrete nature of load shedding, a safety margin tuning scheme is integrated into the KLS framework, ensuring that the system frequency trajectory remains within the safety range. Simulation results show the adaptability, prediction capability and control effect of the proposed UFLS strategy.