Starfish optimization algorithm (SFOA): A bio-inspired metaheuristic algorithm for global optimization with comparing 100 optimizers

Zhong, Changting, Li, Gang, Meng, Zeng, Li, Haijiang ORCID: https://orcid.org/0000-0001-6326-8133, Yildiz, Ali Riza and Mirjalili, Sevedali 2024. Starfish optimization algorithm (SFOA): A bio-inspired metaheuristic algorithm for global optimization with comparing 100 optimizers. Neural Computing and Applications Item availability restricted.

	PDF (Provisional file) - Accepted Post-Print Version Download (17kB)
	PDF - Accepted Post-Print Version Restricted to Repository staff only Download (3MB)

Abstract

This work presents the Starfish Optimization Algorithm (SFOA), a novel bio-inspired metaheuristic for solving optimization problems, which simulates behaviors of starfish, including exploration, preying, and regeneration. SFOA consists of two main phases of exploration and exploitation. The exploration phase mimics the explorative behavior of starfish by the hybrid search pattern of combining with the five-dimensional and unidimensional search patterns to increase the computational efficiency and ensure the search capacity. The exploitation phase simulates the preying and regeneration behaviors of starfish, with a two-directional search strategy and special movement, to ensure convergence in exploitation. This work validates SFOA’s performance on 62 benchmark functions from classical functions, CEC 2017 and CEC 2022 test suites, and compares with 100 different metaheuristic algorithms, including state-of-the-art optimizers, such as marine predators algorithm (MPA), water flow optimizer (WFO), LSHADE, LSHADE-cnEpSin, LSHADE-SPACMA, and so on. Statistical results from 1-on-1 comparisons demonstrate that the proposed SFOA outperforms 95 compared algorithms in accuracy and 97 algorithms in efficiency, which is only worse than WFO both in accuracy and efficiency. The scalability analysis also demonstrates that SFOA has the capacity to solve high-dimensional benchmark functions. Furthermore, ten real-world engineering optimization problems illustrate the effectiveness of SFOA to achieve global solutions and exhibit stable results. In conclusion, SFOA can be nominated as a high-performance optimizer, which is promising for solving various optimization problems.

Item Type:	Article
Status:	In Press
Schools:	Engineering
Publisher:	Springer Verlag (Germany)
ISSN:	0941-0643
Date of First Compliant Deposit:	28 October 2024
Date of Acceptance:	7 October 2024
Last Modified:	06 Nov 2024 10:15
URI:	https://orca.cardiff.ac.uk/id/eprint/173474

Actions (repository staff only)

Edit Item