T-MOEA/D: MOEA/D with Objective Transform in Multi-objective Problems

To approximate the Pareto optimal solutions of a multi-objective optimization problem, Zhang and Li have recently developed a novel multi-objective evolutionary algorithm based on decomposition(MOEA/D). It can work well if the curve shape of the Pareto-optimal front is friendly. Otherwise, it might...

Full description

Saved in:
Bibliographic Details
Published in2010 International Conference of Information Science and Management Engineering Vol. 2; pp. 282 - 285
Main Authors Hai-Lin Liu, Fang-qing Gu, Yiu-ming Cheung
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.08.2010
Subjects
evolutionary algorithm
Evolutionary computation
Frequency modulation
Measurement
Multi-objective optimization
Optimization
Pareto front
Search problems
Shape
Transforms
uniformly distribution
Online AccessGet full text

Cover

More Information
Summary:To approximate the Pareto optimal solutions of a multi-objective optimization problem, Zhang and Li have recently developed a novel multi-objective evolutionary algorithm based on decomposition(MOEA/D). It can work well if the curve shape of the Pareto-optimal front is friendly. Otherwise, it might fail. In this paper, we propose an improved MOEA/D algorithm (denoted as TMOEA/D), which utilizes a monotonic increasing function to transform each individual objective function into the one so that the curve shape of the non-dominant solutions of the transformed multi-objective problem is close to the hyper-plane whose intercept of coordinate axes is equal to one in the original objective function space. Consequently, we can approximate the Pareto optimal solutions that are uniformly distributed over the Pareto front using the advanced decomposition technique of MOEA/D. Numerical results show that the proposed algorithm has a good performance.
ISBN:9781424476695
1424476690
DOI:10.1109/ISME.2010.274