Sorry, you need to enable JavaScript to visit this website.

GlassoFormer: a Query-Sparse Transformer for Post-Fault Power Grid Voltage Prediction

Citation Author(s):
Yunling Zheng, Carson Hu, Guang Lin, Meng Yue, Bao Wang, Jack Xin
Submitted by:
Yunling Zheng
Last updated:
8 May 2022 - 8:17pm
Document Type:
Presentation Slides
Document Year:
2022
Event:
Presenters:
Yunling Zheng

Abstract

We propose GLassoformer, a novel and efficient transformer architecture leveraging group Lasso regularization to reduce the number of queries of the standard self-attention mechanism. Due to the sparsified queries, GLassoformer is more computationally efficient than the standard transformers. On the power grid post-fault voltage prediction task, GLassoformer shows remarkably better prediction than many existing benchmark algorithms in terms of accuracy and stability.

up
1 user has voted: Yunling Zheng

Files

PPT_for_Glasso_Former.pdf

(38)