Unlock instant, AI-driven research and patent intelligence for your innovation.

MOEA/D (multi-objective evolutionary algorithm) domain partition method, device and equipment and computer storage medium

A technology for partitioning and computing frameworks, applied in the field of optimization algorithms

Active Publication Date: 2018-06-29
我知盘中餐(厦门)电子商务有限公司
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in the field of decomposition-based multi-objective evolutionary algorithm MOEA / D (Multi-objective evolutionary algorithm, MOEA), it is more common to do parallel computing, and MOEA / D has not yet been implemented in Spark. Therefore, in the era of rapid data growth In this situation, it is urgent to provide a MOEA / D partitioning method based on master-slave mode

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
  • MOEA/D (multi-objective evolutionary algorithm) domain partition method, device and equipment and computer storage medium
  • MOEA/D (multi-objective evolutionary algorithm) domain partition method, device and equipment and computer storage medium
  • MOEA/D (multi-objective evolutionary algorithm) domain partition method, device and equipment and computer storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0034] Embodiment 1 of the present application provides a MOEA / D partitioning method based on the spark computing framework, such as figure 1 As shown, the method is based on the master-slave mode, including:

[0035]Step 101: The host divides the population through the configuration input step, weight vector sorting step, and weight vector partitioning step, and distributes each sub-problem after the population division to each secondary computer for calculation, and outputs the final partition result.

[0036] Step 102: After the sub-problems are calculated by each auxiliary computer, the calculation results are summarized to the main computer.

[0037] Specifically, as an executable program, such as figure 2 As shown, the host in step 101 divides the population through the configuration input step, weight vector sorting step, and weight vector partition step, and distributes each sub-problem after the population division to each secondary computer for calculation, and out...

Embodiment 2

[0059] Based on the same inventive concept as Embodiment 1 of the present application, Embodiment 2 of the present application provides a MOEA / D partitioning device based on the spark computing framework, such as Figure 5 As shown, the device is based on the master-slave mode, including a master 51 and several slaves 52;

[0060] The host 51 can be used to divide the population by configuring the input step, the weight vector sorting step, and the weight vector partition step, and distribute each sub-problem after the population division to each auxiliary computer for calculation, and output the final result;

[0061] The auxiliary machine 52 can be used to calculate sub-problems and report the calculation results to the main machine.

[0062] Further, as an executable solution, the host 1 can be specifically used to configure the relevant parameters required for inputting the MOEA / D partition; wherein, the relevant parameters required for the MOEA / D partition include multi-o...

Embodiment 3

[0066] Embodiment 3 of the present application also provides a computing device, which may specifically be a desktop computer, a portable computer, a smart phone, a tablet computer, a personal digital assistant (Personal Digital Assistant, PDA), and the like. The computing device may include a central processing unit (Center Processing Unit, CPU), a memory, an input device, an output device, etc., the input device may include a keyboard, a mouse, a touch screen, etc., and the output device may include a display device, such as a liquid crystal display (Liquid Crystal Display , LCD), cathode ray tube (Cathode Ray Tube, CRT) and so on.

[0067] The memory may include read only memory (ROM) and random access memory (RAM), and provides the processor with program instructions and data stored in the memory. In the embodiment of the present application, the memory may be used to store program instructions of the MOEA / D partitioning method. The processor calls the program instruction...

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 spark computing framework based MOEA / D (multi-objective evolutionary algorithm) domain partition method, device and equipment and a computer storage medium. The method includesthat a host divides population through a configuration input step, a weight vector sorting step and a weight vector division step on the basis of a master / slave mode and distributes sub-problems after population division to auxiliary engines for computing, computed results are summarized to the host after computing of the sub-problems of the auxiliary engines is finished, final division results are output through the host, and the problem about population division is thereby solved. Parallelization is realized through the computing framework adapting to distributed computing, new ways for solving problems of multi-objective dynamic optimization are provided for the age of big data, and new ways are put forward for realizing MOEA / D under Spark by means of division of weight vectors.

Description

technical field [0001] The present application relates to the technical field of optimization algorithms, and in particular to a spark computing framework-based MOEA / D partitioning method, device, equipment and computer storage medium. Background technique [0002] Optimization problems in real life can be divided into two categories: single-objective optimization problems (Single-objective Optimization Problem, SOP) and multi-objective optimization problems (Multi-objective Optimization Problem, MOP). Single-objective optimization problems, that is, only one objective is considered in optimization, otherwise, it is called multi-objective optimization problems. Multi-objective optimization problems are often encountered in reality. For example, in industrial design, cost and quality are a pair of conflicting goals. Usually people hope to get the best quality products at the same cost level. However, at different cost levels, different optimal quality products can be obtain...

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): G06F17/50
CPCG06F30/20G06F2111/02G06F2111/06
Inventor 张德富陈晓锋
Owner 我知盘中餐(厦门)电子商务有限公司