Enhancing the Whale Optimisation Algorithm with sub-population and hybrid techniques for single- and multi-objective optimisation

The Whale Optimisation Algorithm (WOA) is a meta-heuristic model inspired by the hunting behaviours of humpback whales. Similar to many other meta-heuristic models, e.g., Particle Swarm Optimisation (PSO), Artificial Bee Colony (ABC), and Ant Colony Optimisation (ACO), the WOA is susceptible to the...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Soft computing (Berlin, Germany) Ročník 28; číslo 5; s. 3941 - 3971
Hlavní autori: Cai, Zheng, Choo, Yit Hong, Le, Vu, Lim, Chee Peng, Liao, Mingyu
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: Berlin/Heidelberg Springer Berlin Heidelberg 01.03.2024
Springer Nature B.V
Predmet:
Accuracy
Algorithms
Ant colony optimization
Archives & records
Artificial Intelligence
Business metrics
Computational Intelligence
Confidence intervals
Control
Convergence
Engineering
Evolutionary computation
Exploitation
Genetic algorithms
Heuristic
Heuristic methods
Mathematical Logic and Foundations
Mechatronics
Multiple objective analysis
Mutation
Optimization
Particle swarm optimization
Problem solving
Robotics
Sorting algorithms
Swarm intelligence
Whales
Whales & whaling
Hybridisation method
Sub-population technique
Whale Optimisation Algorithm
Multi-objective optimisation
ISSN:1432-7643, 1433-7479
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:The Whale Optimisation Algorithm (WOA) is a meta-heuristic model inspired by the hunting behaviours of humpback whales. Similar to many other meta-heuristic models, e.g., Particle Swarm Optimisation (PSO), Artificial Bee Colony (ABC), and Ant Colony Optimisation (ACO), the WOA is susceptible to the issues of slow convergence and local optima. In this study, we address these short comings by first proposing an Enhanced WOA (EWOA) model for tackling single-objective optimisation. Specifically, EWOA integrates the WOA and Differential Evolution (DE). DE is a population-based algorithm that generates new candidate solutions by combining the existing ones, employing a simple yet robust formula. This amalgamation aids in generating diverse solutions during the exploration stage by utilising a non-linear coefficient vector, adaptive weight, and sub-population strategies. Furthermore, fast non-dominated sorting and crowding distance techniques from the Non-dominated Sorting Genetic Algorithm II (NSGA-II) are incorporated into EWOA, resulting in a multi-objective EWOA (MOEWOA) model. We evaluate both EWOA and MOEWOA with a broad spectrum of benchmark functions. The results from 51 single-objective optimisation problems indicate the usefulness of EWOA in terms of a fast convergence rate and with increased performance. On the other hand, MOEWOA demonstrates a better convergence rate and an effective balance between convergence and diversity in 12 multi-objective optimisation problems. In addition, MOEWOA successfully solves 21 complex multi-objective constrained mechanical design problems, outperforming other compared algorithms at the 95% confidence level. The empirical outcomes of our study indicate the potential of EWOA and MOEWOA for undertaking complex, real-world optimisation problems.
Bibliografia:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1432-7643
1433-7479
DOI:10.1007/s00500-023-09351-x