Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Electric power system analysis parallel computing method and system based on grid computation

A power system and parallel computing technology, applied in the direction of concurrent instruction execution, machine execution device, program startup/switching, etc. Problems such as task parallelization, to achieve the effect of reducing hardware costs

Inactive Publication Date: 2013-04-10
ALSTOM GRID
View PDF6 Cites 14 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0014] 2. The combination of the two parallel methods of single-task parallelization and multi-task parallelization has not been realized. The main reason is that the computing nodes in a cluster are limited, and it is difficult to balance the number N of simultaneous computing tasks and the network partition of each task. Number Mi (the total number of computing nodes is fixed)
[0015] 3. This is a typical large-scale cluster machine (Cluster) application solution, which requires the use of a dedicated computer. The application area is narrow and the cost is high, and it requires regular overall update investment
[0016] Solution 4 is suitable for fine-grained parallelization due to the shared storage and the extremely small communication delay between threads; this solution can only use a single multi-processor computer to process a single task when used alone, and in the face of multi-task It is not possible to use multiple computers to parallelize the calculation; at the same time, this solution can only complete the calculation task of a single function, and cannot meet the needs of multiple calculation functions in power system analysis

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
  • Electric power system analysis parallel computing method and system based on grid computation
  • Electric power system analysis parallel computing method and system based on grid computation
  • Electric power system analysis parallel computing method and system based on grid computation

Examples

Experimental program
Comparison scheme
Effect test

example 1

[0078] Use a single computer to solve the transient stability simulation in parallel using the shared memory parallel programming method. The program is a self-compiled software based on the OpenMP shared memory parallel library. The test object is a case of a power system network with 3872 bus nodes (hereinafter referred to as the 3872 case) ), the test environment is an AMD PhenomII 2.5GHz quad-core computer, and the test results are shown in Table 1 below:

[0079]

[0080] Table 1

[0081] In order to simulate an old computer, the processor was downclocked to 800MHz and re-tested. The results are as follows:

[0082]

[0083] Table 2

[0084] It can be seen that the calculation program based on the shared memory parallel programming method can obtain almost the same ideal speedup ratio on computers with different performances, and the parallelization performance is significantly improved.

example 2

[0086] The power network division module executed on the server side can also be parallelized by using the shared memory parallel programming method. For the power system network case with 3872 bus nodes, the test results in Table 3 are as follows:

[0087] Threads

1

2

4

operation hours

94ms

46ms

31ms

Speedup ratio

1.00

2.04

3.03

core efficiency

100%

102%

76%

[0088] table 3

[0089] It proves that the shared memory parallel programming method has effective acceleration performance for multiple processes of power system calculation, and because the network division process takes less time, it can be carried out on the server side without affecting the real-time performance of the system designed by the present invention.

example 3

[0091] Use five Dell Optiplex 360 type computers (possess Core 22.6GHz dual-core processor, 2GBRAM, Windows XP operating system) to build a set of evaluation platform according to the embodiment of the present invention, wherein one computer is as service end, and four computers are as client computers , Five computers are connected using 100M LAN.

[0092] The following tests are designed: one computer calculates one calculation task in series, one computer calculates one calculation task in parallel, a single computer calculates 11 and 16 calculation tasks in serial mode, a single computer calculates 16 calculation tasks in parallel mode, four The computer serial mode calculates 11 and 16 calculation tasks, four computers calculate 11 and 16 tasks in parallel, adopts the mode of the present invention to calculate 11 and 16 tasks, and the test object is the case of 3872 nodes. The results are shown in Table 4 below:

[0093]

[0094] Table 4

[0095] It can be seen that ...

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 relates to an electric power system analysis parallel computing method and system based on grid computation. According to the method and the system, a parallel computation task of electric power system analysis is executed in a net-connected computer environment containing a server and a plurality of clients. The computation task and available computation resources of each client are obtained in the server, and a queue of tasks to be computed is constructed. Then the computation task and a computation mode are sent to one or a plurality of available clients by the queue of tasks to be computed and the available computation resources for computation. The computation mode is set to be that when fewer computation tasks exist, parallel programs based on a shared memory parallel method are executed by a plurality of processors of the client, when more computation tasks exist, serial programs are executed respectively by the processors of the client, and the tasks to be computed can be completed in as little time as possible.

Description

technical field [0001] The invention relates to a computing system for power system analysis, in particular to a parallel computing method and system for power system analysis based on grid computing. Background technique [0002] The current power system computing programs are mainly divided into the following four types: traditional serial computing programs, parallel programs that execute serial programs on multiple computers to achieve parallel processing of multiple tasks; single-task parallel algorithms implemented using distributed memory parallel systems; and A single-task parallel algorithm implemented using a shared-memory parallel system. The various implementations are detailed below. [0003] Option 1, that is, the traditional serial program is the most common. The widely used BPA, EMTSP from EPRI, PSS / E from Simens PTI, non-commercial software InterPSS, and MatPower-based toolbox all adopt this method. The serial program is to use the computer in a serial ma...

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): G06F9/48G06F9/38
Inventor 唐聪周挺辉杜浩严正李乃湖景雷
Owner ALSTOM GRID
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products