English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Most existing data-driven power system short-term voltage stabilityassessment (STVSA) approaches presume class-balanced input data. However, inpractical applications, the occurrence of short-term voltage instabilityfollowing a disturbance is minimal, leading to a significant class imbalanceproblem and a consequent decline in classifier performance. This work proposesa Transformer-based STVSA method to address this challenge. By utilizing thebasic Transformer architecture, a stability assessment Transformer (StaaT) isdeveloped {as a classification model to reflect the correlation between theoperational states of the system and the resulting stability outcomes}. Tocombat the negative impact of imbalanced datasets, this work employs aconditional Wasserstein generative adversarial network with gradient penalty(CWGAN-GP) for synthetic data generation, aiding in the creation of a balanced,representative training set for the classifier. Semi-supervised clusteringlearning is implemented to enhance clustering quality, addressing the lack of aunified quantitative criterion for short-term voltage stability. {Numericaltests on the IEEE 39-bus test system extensively demonstrate that the proposedmethod exhibits robust performance under class imbalances up to 100:1 and noisyenvironments, and maintains consistent effectiveness even with an increasedpenetration of renewable energy}. Comparative results reveal that the CWGAN-GPgenerates more balanced datasets than traditional oversampling methods and thatthe StaaT outperforms other deep learning algorithms. This study presents acompelling solution for real-world STVSA applications that often face classimbalance and data noise challenges.

Deep learning based on Transformer architecture for power system short-term voltage stability assessment with class imbalance