Multiobjective Optimization Differential Evolution Enhanced with Principle Component Analysis for Constrained Optimization

by   Wei Huang, et al.
Aberystwyth University
Nottingham Trent University
NetEase, Inc

Multiobjective optimization evolutionary algorithms have been successfully applied to solving constrained optimization problems. This paper proposes a new multiobjective optimization differential evolution algorithm for constrained optimization. Through a study of fitness landscapes using principle component analysis, we discover a statistic method of identifying the valley direction in a valley landscape. Based on this discovery, a new search operator called PCA-projection is constructed which projects an individual to a position along the valley direction. Then multiobjective optimization differential evolution using this projection operator is designed for constrained optimization. A comparative experiment has been implemented between the proposed algorithm and a state-of-the-art multiobjective differential evolution algorithm on a standard set of 24 benchmarks. Experimental results show that the new algorithm makes a significant improvement in terms of solution accuracy. The proposed algorithm is also competitive with ten evolutionary algorithms participated in an IEEE CEC 2006 competition and is ranked third in terms of the final rank.


page 1

page 2

page 3

page 4


Comparative analysis of evolutionary algorithms for image enhancement

Evolutionary algorithms are metaheuristic techniques that derive inspira...

Making up for the deficit in a marathon run

To predict the final result of an athlete in a marathon run thoroughly i...

A Feature-Based Analysis on the Impact of Set of Constraints for e-Constrained Differential Evolution

Different types of evolutionary algorithms have been developed for const...

Accelerating the Evolutionary Algorithms by Gaussian Process Regression with ε-greedy acquisition function

In this paper, we propose a novel method to estimate the elite individua...

Quick HyperVolume

We present a new algorithm to calculate exact hypervolumes. Given a set ...

Performance Analysis and Improvement of Parallel Differential Evolution

Differential evolution (DE) is an effective global evolutionary optimiza...

Multiobjective Multitasking Optimization Based on Decomposition with Dual Neighborhoods

This paper proposes a multiobjective multitasking optimization evolution...

Please sign up or login with your details

Forgot password? Click here to reset