Enhancing grid reliability through Transformer-LSTM model in smart grids

Dong Liang; Jun Wu; Xia Xu; Chenglin Xiu; Yuxuan Wang

doi:10.1117/12.3055786

9 January 2025 Enhancing grid reliability through Transformer-LSTM model in smart grids

Dong Liang, Jun Wu, Xia Xu, Chenglin Xiu, Yuxuan Wang

Author Affiliations +

Proceedings Volume 13486, Fourth International Conference on Computer Vision, Application, and Algorithm (CVAA 2024); 134861K (2025) https://doi.org/10.1117/12.3055786
Event: Fourth International Conference on Computer Vision, Application, and Algorithm (CVAA 2024), 2024, Chengdu, China

Abstract

In the evolving landscape of global energy and information technology sectors in the early 21st century, the concept of smart grids has emerged as pivotal for enhancing the efficiency and reliability of power systems. This paper explores the integration of modern communication, computer, network, and control technologies within smart grids, highlighting their role in ensuring grid reliability, intelligence, and responsiveness. Despite varying definitions globally, smart grids universally aim to optimize grid operations through advanced technology integration. This article introduces a novel Transformer-LSTM encoder-decoder structure that integrates LSTM 's robust capability to capture long-term dependencies with Transformer's proficiency in capturing global dependencies. The proposed model is applied to forecast fluctuations in power grid data traffic, facilitating real-time adjustments to the grid's operational and maintenance strategies. Experimental results validate that the traffic prediction accuracy of the Transformer-LSTM model exceeds that of the independent Transformer and LSTM models.

(2025) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Dong Liang, Jun Wu, Xia Xu, Chenglin Xiu, and Yuxuan Wang "Enhancing grid reliability through Transformer-LSTM model in smart grids", Proc. SPIE 13486, Fourth International Conference on Computer Vision, Application, and Algorithm (CVAA 2024), 134861K (9 January 2025); https://doi.org/10.1117/12.3055786

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

;

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE