QR decomposition method of power flow Jacobian matrix for GPU acceleration

A technology of QR decomposition and power flow, applied in the field of GPU thread design, can solve complex and other problems, achieve the effect of improving efficiency, improving computing efficiency, and solving the time-consuming effect of power flow calculation

Active Publication Date: 2016-10-12
SOUTHEAST UNIV
View PDF5 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0010] Parallel computing: Compared with serial computing, it is an algorithm that can execute multiple instructions at a time. The purpose is to improve the computing speed and solve large and complex computing problems by expanding the scale of problem solving.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • QR decomposition method of power flow Jacobian matrix for GPU acceleration
  • QR decomposition method of power flow Jacobian matrix for GPU acceleration
  • QR decomposition method of power flow Jacobian matrix for GPU acceleration

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0084] Such as image 3 As shown, the QR decomposition method of a GPU-accelerated power flow Jacobian matrix of the present invention, the method includes:

[0085] (1) Perform QR symbolic decomposition on the Jacobian matrix J in the CPU to obtain the sparse structure of the Household transformation matrix V and the upper triangular matrix R matrix. The sparse structure of J after symbolic decomposition is equal to V+R; according to the sparse structure of the R matrix, Parallelize and stratify each column of matrix J.

[0086] (2) Calculate the layered QR decomposition kernel function SparseQR in the order of increasing levels in the GPU.

[0087] 1. QR symbolic decomposition method for power flow Jacobian matrix J in CPU

[0088] First, perform QR symbolic decomposition on the Jacobian matrix J in the CPU to obtain the sparse structure of the Household transformation matrix V and the upper triangular matrix R. The sparse structure of J after the symbolic decomposition is...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses a QR decomposition method of a power flow Jacobian matrix for GPU acceleration. The QR decomposition method comprises the steps of carrying out QR symbol decomposition on a Jacobian matrix J in a CPU so as to acquire a Household transformation matrix V and a sparse structure of an upper triangular matrix R; carrying out parallelized layering on each column of the matrix J according to the sparse structure of the matrix R; and calculating a sub-layer QR decomposition kernel function SparseQR according to a level increasing order in a GPU. According to the invention, the efficiency of QR decomposition of the power flow Jacobian matrix is improved by using a mode of combining the process of a CPU control program for processing basic data and the GPU for processing intensive floating-point calculation, and a problem great time consumption of flow calculation in power system steady-state security analysis is solved.

Description

technical field [0001] The invention belongs to the application field of high-performance computing in electric power systems, and in particular relates to a GPU thread design method for QR decomposition of a GPU-accelerated power flow Jacobian matrix. Background technique [0002] Power flow calculation is the most widely used, basic and important electrical calculation in power system. In the study of power system operation mode and planning scheme, power flow calculation is required to compare the feasibility, reliability and economy of the operation mode or planning power supply scheme. At the same time, in order to monitor the operating status of the power system in real time, a large number of fast power flow calculations are also required. Therefore, when planning and designing the system and arranging the operation mode of the system, the offline power flow calculation is used; in the real-time monitoring of the power system operating status, the online power flow c...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): H02J3/06
CPCH02J3/06H02J2203/20
Inventor 周赣孙立成张旭柏瑞冯燕钧秦成明傅萌
Owner SOUTHEAST UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap