Power System Transient Stability Assessment Based on Machine Learning Algorithms and Grid Topology
Problem
Assessing the dynamic (transient) stability of modern power grids, whose structure and parameters change due to renewables and low inertia, in order to support emergency control.
Why it matters
Instability in power systems can trigger blackouts with major economic and safety consequences.
What the AI did
Ensemble machine learning algorithms (XGBoost and Random Forest) were used to develop and test a dynamic stability assessment technique that does not require a priori power system model parameters.
Results
not stated in source
Impact
The evidence only supports that an adaptable ML-based stability assessment technique was developed and tested.
Record
| Venue | Mathematics |
|---|---|
| Published | 2023 |
| Work type | article |
| Authors | Mihail D. Senyuk, Murodbek Safaraliev, Firuz Kamalov, Hana Sulieman |
| Citations | 42 (OpenAlex, at import time) |
| References | 35 |
| Model or method | XGBoost, Random Forest |
| Organization | not stated in source |
| Primary source | https://doi.org/10.3390/math11030525 |
| Open access | gold |
| Keywords | transient stability, machine learning, XGBoost, Random Forest, power systems, emergency control |
Importance rating
significant — thousands to millions affected
Grid transient instability risks blackouts; emergency control for low-inertia renewable-rich systems called a prominent modern problem, but abstract gives no impact scale.