Multi-level parallel chaotic Jaya optimization algorithms for solving constrained engineering design problems

Several heuristic optimization algorithms have been applied to solve engineering problems. Most of these algorithms are based on populations that evolve according to different rules and parameters to reach the optimal value of a function cost through an iterative process. Different parallel strategi...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:The Journal of supercomputing Ročník 77; číslo 11; s. 12280 - 12319
Hlavní autoři: Migallón, H., Jimeno-Morenilla, A., Rico, H., Sánchez-Romero, J. L., Belazi, A.
Médium: Journal Article
Jazyk:angličtina
Vydáno: New York Springer US 01.11.2021
Springer Nature B.V
Témata:
Algorithms
Compilers
Computer Science
Computing time
Design engineering
Design optimization
Interpreters
Iterative methods
Optimization algorithms
Populations
Processor Architectures
Programming Languages
Jaya algorithm
Chaotic map
OpenMP
Parallel algorithms
Optimization
Constrained engineering problem
ISSN:0920-8542, 1573-0484
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Several heuristic optimization algorithms have been applied to solve engineering problems. Most of these algorithms are based on populations that evolve according to different rules and parameters to reach the optimal value of a function cost through an iterative process. Different parallel strategies have been proposed to accelerate these algorithms. In this work, we combined coarse-grained strategies, based on multi-populations, with fine-grained strategies, based on a diffusion grid, to efficiently use a large number of processes, thus drastically decreasing the computing time. The Chaotic Jaya optimization algorithm has been considered in this work due to its good optimization and computational behaviors in solving both the constrained optimization engineering problems (seven problems) and the unconstrained benchmark functions (a set of 18 functions). The experimental results show that the proposed parallel algorithms outperform the state-of-the-art algorithms in terms of optimization behavior, according to the quality of the obtained solutions, and efficiently exploit shared memory parallel platforms.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0920-8542
1573-0484
DOI:10.1007/s11227-021-03737-0