摘要
基于GPU的并行计算作为一种计算方法,因其强大的计算能力已被广泛应用于各个领域。由于计算量的急剧增加,电力系统各项问题的计算处理,普通的串行计算已不能满足。基于GPU的编程架构CUDA,针对电力系统静态安全分析技术的核心——潮流计算进行并行化加速。同时,针对计算量最大的解线性方程组部分,采用QR分解的方法进行并行化处理。
Parallel computing is a kind of calculation method based on GPU,it has been widely applied in various fields because of its powerful computing power.Due to the rapid increase of amount of calculation,the ordinary serial calculation can't meet for the processing of calculation of power system.This paper use CUDA programming based on GPU architecture,mainly for electric power system static security analysis technology of core flow calculation for parallel speed up.At the same time,in view of the maximum amount of calculation of solving linear equations,using QR decomposition method for parallel processing.
作者
朱启凌
周越
ZHU Qiling;ZHOU Yue(State Grid Shanghai Northern Power Supply Company)
出处
《上海节能》
2020年第6期619-623,共5页
Shanghai Energy Saving
