Paper Info
Title
A new resource allocation strategy based on the relationship between subproblems for MOEA/D.
Abstract
Multi-objective evolutionary algorithms based on decomposition (MOEA/D) decomposes a multi-objective optimization problem (MOP) into a set of simple scalar objective optimization sub-problems and solves them in a collaborative way. Since the sub-problems are different in optimization difficulty and computational resource demanding, it is critical to reasonably allocate computational resources among them, which can optimize the usage of resources and improve the performance of an algorithm. This paper proposes a new resource allocation strategy based on the relationship between sub-problems for MOEA/D. A probability vector is maintained based on the relationship between sub-problems, which is used to guide the selection of sub-problems for optimization. In the optimization process, we explored the role of priority optimization of boundary sub-problems and used it to assist in the update of probability vector in the early optimization phase. A steady-state algorithm is designed and tested experimentally. The results suggest that the designed algorithms have some advantages over existing state-of-the-art algorithms.
Year
DOI
Venue
2019
10.1016/j.ins.2019.06.001
Information Sciences
Keywords
Field
DocType
Decomposition,Evolutionary algorithm,Multi-objective optimization,Resource allocation
Mathematical optimization,Evolutionary algorithm,Scalar (physics),Resource allocation,Artificial intelligence,Probability vector,Optimization problem,Computational resource,Mathematics,Machine learning
Journal
Volume
ISSN
Citations 
501
0020-0255
1
PageRank 
References 
Authors
0.36
0
8
Name
Order
Citations
PageRank
Peng Wang15010.52
Wen Zhu2466.60
Haihua Liu310.36
Bo Liao415622.53
lijun cai5214.84
Xiaohui Wei639154.44
Siqi Ren7212.32
Jialiang Yang8507.20