Tutorial at ACM e-Energy 2025
Date:
This tutorial on “Power System Reliability with Deep Learning” focuses on methods from deep learning applied to reliability assessment. Expanding grids with renewable energy challenges their reliability.
Abstact: Expanding grids with renewable energy challenges their reliability. Methods from deep learning offer vast opportunities for monitoring the reliability of the distribution and transmission system. This talk briefly introduces the fundamentals of neural networks over convolutional to graph neural networks. However, when applying supervised learning neural networks training data is needed. Power systems have inherent data imbalances and noise. From data to model, this talk develops a machine-learning workflow for grids on two examples (a) transmission system dynamic security assessment and (b) distribution system state estimation. Topics covered:
Part A: Reliability management and data in control rooms
- Introduction to reliability management
- Machine learning approaches
- Security assessment with cost-sensitive supervised learning
Part B: Learning models for secure system operation>
- Learning with domain knowledge
- State estimation with graph neural networks
- Weakly-supervised learning for secure operation
- Open challenges applying ML to reliability
Slides:
The tutorial is sponsored by SIGEnergy and Association for Computing Machinery. More information about the tutorial are here