Bento, Murilo E. C. (Federal University of Rio de Janeiro)

Load Margin Assessment of Power Systems Using Recurrent Neural Network and Greylag Goose Optimization

Scheduled for presentation during the Regular Session "High renewable energy penetration grid analysis and stability" (FriS1T2), Friday, July 12, 2024, 10:20−10:40, Grand Amphitheater

12th IFAC Symposium on Control of Power & Energy Systems, July 10-12, 2024, Rabat, Morocco

This information is tentative and subject to change. Compiled on January 2, 2025

Abstract

The complexity of operating power systems requires the development of methods capable of assisting in system monitoring. The Voltage Stability Margin or Load Margin (LM) represents an index that informs how much the system's load level can increase without causing a case of instability. The LM is determined using voltage stability criteria, but low-frequency modes can arise with increasing load and can cause system instability. This article proposes a method based on Recurrent Neural Networks (RNNs) for monitoring LM. Furthermore, a metaheuristic called Greylag Goose Optimization is applied to choose the system buses whose measurements will be RNN inputs.