Leveraging Multi-Task Learning for Multi-Label Power System Security Assessment
By: Muhy Eddin Za'ter, Amir Sajad, Bri-Mathias Hodge
Potential Business Impact:
Checks power grids for problems faster and better.
This paper introduces a novel approach to the power system security assessment using Multi-Task Learning (MTL), and reformulating the problem as a multi-label classification task. The proposed MTL framework simultaneously assesses static, voltage, transient, and small-signal stability, improving both accuracy and interpretability with respect to the most state of the art machine learning methods. It consists of a shared encoder and multiple decoders, enabling knowledge transfer between stability tasks. Experiments on the IEEE 68-bus system demonstrate a measurable superior performance of the proposed method compared to the extant state-of-the-art approaches.
Similar Papers
StableMTL: Repurposing Latent Diffusion Models for Multi-Task Learning from Partially Annotated Synthetic Datasets
CV and Pattern Recognition
Teaches computers many jobs with less training.
Multi-task Learning with Active Learning for Arabic Offensive Speech Detection
Computation and Language
Finds bad words online better, even with little data.
MTL-UE: Learning to Learn Nothing for Multi-Task Learning
Machine Learning (CS)
Stops bad guys from training smart AI models.