PMU measurements based short-term voltage stability assessment of power systems via deep transfer learning

TL;DR

This paper introduces a deep transfer learning approach using PMU data for short-term voltage stability assessment in power systems, effectively addressing dataset limitations and topological changes with improved accuracy and adaptability.

Contribution

It proposes a novel PMU-based STVSA method utilizing deep transfer learning, temporal ensembling, and LSGAN for data augmentation, enhancing performance on small datasets and adaptability to system topology changes.

Findings

Improves model accuracy by approximately 20% with transfer learning.

Demonstrates strong adaptability to topological changes.

Outperforms shallow and other deep learning methods.

Abstract

Deep learning has emerged as an effective solution for addressing the challenges of short-term voltage stability assessment (STVSA) in power systems. However, existing deep learning-based STVSA approaches face limitations in adapting to topological changes, sample labeling, and handling small datasets. To overcome these challenges, this paper proposes a novel phasor measurement unit (PMU) measurements-based STVSA method by using deep transfer learning. The method leverages the real-time dynamic information captured by PMUs to create an initial dataset. It employs temporal ensembling for sample labeling and utilizes least squares generative adversarial networks (LSGAN) for data augmentation, enabling effective deep learning on small-scale datasets. Additionally, the method enhances adaptability to topological changes by exploring connections between different faults. Experimental results on the IEEE 39-bus test system demonstrate that the proposed method improves model evaluation accuracy by approximately 20% through transfer learning, exhibiting strong adaptability to topological changes. Leveraging the self-attention mechanism of the Transformer model, this approach offers significant advantages over shallow learning methods and other deep learning-based approaches.