Collaborative acceleration of CPU/GPU for electric power digital twin applications

Rundong Gan; Xun Li; Yujiang Long; Jun Liu; Zhu Zhan

doi:10.1117/12.3015078

4 March 2024 Collaborative acceleration of CPU/GPU for electric power digital twin applications

Rundong Gan, Xun Li, Yujiang Long, Jun Liu, Zhu Zhan

Proceedings Volume 12981, Ninth International Symposium on Sensors, Mechatronics, and Automation System (ISSMAS 2023); 1298126 (2024) https://doi.org/10.1117/12.3015078
Event: 9th International Symposium on Sensors, Mechatronics, and Automation (ISSMAS 2023), 2023, Nanjing, China

Abstract

Positioning and navigation functions are often required in grid design and operation and maintenance, general grid model building, and power plant operation. GDOP (Geometric Dilution of Position Precision) is often used to evaluate positioning accuracy. The smaller the GDOP value, the higher the positioning accuracy, and vice versa. Through the calculation and analysis of GDOP, it can help the positioning and navigation functions in the power digital twin application to more accurately locate equipment or monitoring points. This is of great significance to the operation and maintenance of the power system. In order to improve the calculation of DOP value using CPU/GPU collaborative acceleration in this paper, this paper uses GPU to optimize the core operator in GDOP calculation, and proposes a CPU/GPU collaborative computing solution. The experimental results show that the GDOP value calculation time is reduced from the original 3753 seconds to 232 seconds, and the performance is improved by 16.18x.

(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Rundong Gan, Xun Li, Yujiang Long, Jun Liu, and Zhu Zhan "Collaborative acceleration of CPU/GPU for electric power digital twin applications", Proc. SPIE 12981, Ninth International Symposium on Sensors, Mechatronics, and Automation System (ISSMAS 2023), 1298126 (4 March 2024); https://doi.org/10.1117/12.3015078

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

Includes PDF, HTML & Video, when available