Transformer Topology Identification Method Based on GPU Acceleration

2018 1st International Conference on Environment Prevention and Pollution Control Technology

生态环境科学

Wan, Zhongbing^1 ; Xie, Zhi^1 ; Wang, Xiaohua^2 ; Zhang, Ran^1 ; Wang, Xiao^2 ; Lian, Libo^2

State Grid Sichuan Electric Power Corporation Metering Center, Chengdu, Sichuan

610000, China^1

Tsinghua Sichuan Energy Internet Research Institute, Chengdu, Sichuan, China^2

关键词: Engineering applications;    GPU accelerations;    Grey correlation analysis methods;    High-accuracy;    High-performance computing technology;    Methods. Data analysis;    Numerical experiments;    Topology identification;   

Others  :  https://iopscience.iop.org/article/10.1088/1755-1315/199/3/032102/pdf
DOI  :  10.1088/1755-1315/199/3/032102

学科分类：环境科学（综合）

来源: IOP

【 摘 要 】

Traditional transformer topology identification methods have poor accuracy and efficiency and are easy to be interfered. Aiming at these problems, this paper proposes a transformer topology identification based on GPU acceleration, which obtains and analyses the data from large quantities of smart meters and effectively identify the corresponding relationship between transformers and meters, via high performance computing technology and large data methods. Data analysis is implemented by GPU parallel accelerated grey correlation analysis method, which effectively improves the efficiency of the method. Numerical experiments show that the method proposed in this paper has high accuracy and computational efficiency, which has the value and potential of engineering applications.