Summary
The energy transition is rapidly transforming numerous aspects of the real-time operation of power transmission systems. Ensuring network stability within this evolving scenario requires considerable effort, particularly in accurately predicting potentially critical situations and guaranteeing the effectiveness of preventive and corrective control actions. Currently, dynamic stability assessment relies on massive dynamic simulations, which are computationally highly demanding.
Read more Read lessThis paper aims at developing novel ML ensemble algorithm based on Extreme Gradient
Boosting (XGBoost) and deep Neural Network (NN), capable of classifying the current state of the power grid in real-time, avoiding the computational burden associated with time-domain simulations. The contribution demonstrates methodology effectiveness by means of three realtime applications for national control room of the proposed approach.
Additional informations
| Publication type | Session Materials |
|---|---|
| Reference | C2_11123_2026 |
| Publication year | |
| Publisher | CIGRE |
| Country | Italy |
| Study committees | |
| File size | 1 MB |
| Price for non member | 30 € |
| Price for member | 30 € |
Authors
GIANNUZZI Giorgio - TERNA
Keywords
Machine Learning, Power Grids, Dynamic Stability Assessment, Awareness System
