Randomized Decomposition Methods in Multi-objective Evolutionary Algorithm based on Decomposition for Many-objective Optimization Problems
Year: 2022
Type: article
Abstract: As the number of objectives are increased in the optimization problem, the objective space is increased therefore it is not possible to use conventional methods to get answers for these problems. Therefore, some methods are proposed to solve this problem. As one of the solutions is called the decomposition. In decomposition the objectives are applied to the scalarization functions, and many sub-problems are obtained. Based on their neighborhood, the best members in the current generation of the evolutionary algorithm will be survived to the next generation. The algorithm which uses that idea is called Multi-objective Evolutionary Algorithm based on Decomposition (MOEA/D). Different typed of decomposition methods can be used with the MOEA/D algorithm. However, each of them has their own weaknesses or advantages. Therefore, to reduce the disadvantage of the decomposition methods, a hybrid approach is proposed in this research such that instead of a single decomposition method, two methods will be use randomly. The performance of the proposed hybrid method will be demonstrated on seven benchmark problems by using two metrics.
Author: Tolga ALTİNOZ
Institution: Ankara University
Language: English
Subfield: Computational Theory and Mathematics
Field: Computer Science
Domain: Physical Sciences
Open Access status: diamond
OpenAlex ID: W4220764244