Comentropy-based improved evolutionary multi-objective optimization method

A multi-objective optimization and information entropy technology, applied in the direction of genetic models, etc., can solve problems such as complicated operations and difficult reflections

Inactive Publication Date: 2012-08-01
NANJING UNIV OF POSTS & TELECOMM
View PDF0 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The operation is cumbersome and complicated, and it is difficult to reflect the population evolution information simply and conveniently, helping researchers judge whether the population evolution has reached a mature stage, so as to end the optimization process of the PESA algorithm as soon as possible

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
  • Comentropy-based improved evolutionary multi-objective optimization method
  • Comentropy-based improved evolutionary multi-objective optimization method
  • Comentropy-based improved evolutionary multi-objective optimization method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0049] Considering that both the PESA algorithm and the information entropy measurement index use the grid method as the core method, we introduce the entropy value measurement index into the PESA algorithm and propose an improved C-PESA algorithm. Through the continuous information entropy value index calculation rules, observe the process of the evolution solution set from the gradual evolution and development process to the mature stage. That is to say, according to the change of the information entropy index, it is judged whether the population evolution has reached the mature stage. End the optimization process of PESA algorithm as soon as possible according to the evolutionary degree of population individuals obtained.

[0050] Described PESA algorithm, concrete steps are as follows:

[0051] 1. Generate an initial IP (internal population (IP, internal population)), and evaluate it. Also initialize EP to be empty.

[0052] 2. Incorporate non-dominated individuals in I...

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 provides a comentropy-based improved evolutionary multi-objective optimization method. Based on a comentropy-based improved Pareto envelope-based selection algorithm (PESA), comentropy measurement indexes are introduced into the PESA, and the evolutionary degrees of individuals in a population are considered in time after the PESA is evolved by utilizing the distribution characteristics of the comentropy indexes in a quantitative measurement Pareto solution set, such as the outstanding behaviors in the aspects of uniformity, diversity and convergence. After the population is evolved to be uniform and varied in population distribution, a comentropy numerical value is kept constant at the moment. According to the characteristic, when the solved comentropy numerical value is stably constant within a certain range, an optimization effect of the PESA is achieved, and hereon, an optimization computational process can be ended. Consequently, the complicated evolutionary process is avoided, and the time complexity is reduced.

Description

technical field [0001] The invention is an improved evolutionary multi-objective optimization method based on information entropy, which belongs to the field of evolutionary multi-objective optimization. Background technique [0002] In the past two decades, evolutionary algorithms have been successfully applied in the field of multi-objective optimization, and have developed into a relatively hot research direction, that is, evolutionary multi-objective optimization (EMO for short). From the typical representative vector-evaluated genetic algorithms (VEGA) of the first generation of evolutionary multi-objective optimization algorithm, and the PESA algorithm (The Pareto Envelope-based Selection Algorithm, PESA) of the second generation of evolutionary multi-objective optimization algorithm ), to the current new multi-objective optimization algorithms based on particle swarm optimization, ant colony algorithm, artificial immune system, distribution estimation algorithm, co-ev...

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): G06N3/12
Inventor 王堃王琳琳暴建民胡海峰郭篁于悦房硕
Owner NANJING UNIV OF POSTS & TELECOMM
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