Leveraging Multi-Task Learning for Multi-Label Power System Security Assessment

TL;DR

This paper presents a multi-task learning framework for power system security assessment, reformulating it as a multi-label classification problem to improve accuracy and interpretability across various stability types.

Contribution

It introduces a novel MTL approach with shared encoder and multiple decoders for simultaneous stability assessment, outperforming existing methods.

Findings

Superior accuracy on IEEE 68-bus system

Effective knowledge transfer between tasks

Enhanced interpretability of stability assessments

Abstract

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.