Global Optimizasyon Problemleri için Kaotik Bonobo Algoritması

Abstract

Optimizasyon algoritmaları, global optimumdan feragat edilerek yaklaşık en iyi çözümü bulmayı amaçlayan algoritmalardır. Bu çalışmada incelenen Bonobo Optimizasyon (BO) Algoritması ise sürü zekasına dayanan bir algoritma olup, bonoboların sosyal davranışlarının ve üreme stratejilerinin matematiksel modellenmesine dayanmaktadır. Bonobolar, yaşadıkları topluluk içinde çeşitli büyüklük ve özelliklerde gruplar oluşturarak, farklı amaçlar için birbirlerinden ayrılıp bir süre sonra yeniden bir araya gelmektedirler. Bonoboların üreme stratejisi incelendiğinde rasgele çiftleşme, kısıtlayıcı çiftleşme, konsorsiyum ve grup dışı çiftleşme gibi dört farklı stratejiyi benimsedikleri görülmektedir. Bonoboların bu doğal davranışları çeşitli optimizasyon problemlerini çözmek için kullanılmıştır. BO’yu diğer sürü zekasına dayalı algoritmalardan ayıran en önemli özelliği ise arama ajanlarının güncelleme mekanizmaları ve bunlarla ilişkili parametreler ve çiftleşme ortaklarının seçim yöntemidir. Bu çalışmada BO incelenip, algoritmada kullanılan parametreler Chebyshev, Circle, Gauss, Iterative, Logistic ve Tent kaotik haritaları kullanılarak yeniden üretilmiştir. Performansları karşılaştırmak için sekiz adet kalite testi fonksiyonu kullanılmıştır. Buna göre kaotik haritalar kullanılarak oluşturulan yeni algoritmalardan elde edilen sonuçların, klasik BO’ya göre daha verimli olduğu görülmüştür.

Keywords

• Bonobo Optimizasyonu
• Kaotik Haritalar
• Metasezgisel Algoritmalar

Chaotic Bonobo Algorithm for Global Optimization Problems

Abstract

Optimization algorithms are algorithms that aim to find the approximate best solution by sacrificing the global optimum. The Bonobo Optimization Algorithm examined in this study is an algorithm based on herd intelligence and is based on mathematical modeling of bonobos' social behavior and reproductive strategies. Bonobos form groups of various sizes and characteristics within the community they live in, leaving each other for different purposes and reuniting after a while. When the reproductive strategy of bonobos is examined, it is seen that they adopt four different strategies such as random mating, restrictive mating, consortium and out-group mating. These natural behaviors of bonobos have been used to solve various optimization problems. The most important feature that distinguishes the Bonobo Optimization Algorithm from other algorithms based on swarm intelligence is the update mechanisms of the search agents and the parameters associated with them, and the selection method of mating partners. In this study, the Bonobo Algorithm was examined and the results obtained by reproducing the random parameters used in the algorithm with chaotic maps were evaluated. It was analyzed in this study and reconstructed with the Chebyshev, Circle, Gauss, Iterative, Logistics and Tent chaotic maps used here. Eight quality tests were used for their performance. Accordingly, chaotic maps seem to be more efficient than classical BO from the results obtained from the new models.

Keywords

• Bonobo Optimization
• Chaotic Maps
• Metaheuristic Algorithms

References

1. A. K. Das and D. K. Pratihar, (2019, June). A new bonobo optimizer (BO) for real-parameter optimization, 2019 IEEE Region 10 Symposium (TENSYMP), pp. 108-113. IEEE.
2. A. K. Das and D. K. Pratihar, (2018). A directional crossover (DX) operator for real parameter optimization using genetic algorithm, Applied Intelligence.
3. Das, A. K., & Pratihar, D. K. (2019). A New Search Space Reduction Technique for Genetic Algorithms. In Contemporary Advances in Innovative and Applicable Information Technology (pp. 111-119). Springer, Singapore.
4. Das, A. K., & Pratihar, D. K. (2017, December). A novel restart strategy for solving complex multi-modal optimization problems using real-coded genetic algorithm. In International Conference on Intelligent Systems Design and Applications (pp. 32-41). Springer, Cham.
5. Yun, Y., Chung, H., & Moon, C. (2013). Hybrid genetic algorithm approach for precedence-constrained sequencing problem. Computers & Industrial Engineering, 65(1), 137-147.
6. Holland, J. H. (1975). An introductory analysis with applications to biology, control, and artificial intelligence. Adaptation in Natural and Artificial Systems. First Edition, The University of Michigan, USA.
7. Storn, R., & Price, K. (1997). Differential evolution–a simple and efficient heuristic for global optimization over continuous spaces. Journal of global optimization, 11(4), 341-359.
8. Kennedy, J., & Eberhart, R. (1995, November). Particle swarm optimization. In Proceedings of ICNN'95-international conference on neural networks (Vol. 4, pp. 1942-1948). IEEE.

9. Yang, X. S. (2010). A new metaheuristic bat-inspired algorithm. In Nature inspired cooperative strategies for optimization (NICSO 2010) (pp. 65-74). Springer, Berlin, Heidelberg.
10. Shi, Y. (2015). An optimization algorithm based on brainstorming process. In Emerging Research on Swarm Intelligence and Algorithm Optimization (pp. 1-35). IGI Global.
11. Rao, R. V., Savsani, V. J., & Vakharia, D. P. (2011). Teaching–learning-based optimization: a novel method for constrained mechanical design optimization problems. Computer-Aided Design, 43(3), 303-315.
12. Abdelghany, R. Y., Kamel, S., Sultan, H. M., Khorasy, A., Elsayed, S. K., & Ahmed, M. (2021). Development of an Improved Bonobo Optimizer and Its Application for Solar Cell Parameter Estimation. Sustainability, 13(7), 3863.
13. Sultan, H. M., Menesy, A. S., Kamel, S., Tostado-Véliz, M., & Jurado, F. (2020, June). Parameter identification of proton exchange membrane fuel cell stacks using bonobo optimizer. In 2020 IEEE International Conference on Environment and Electrical Engineering and 2020 IEEE Industrial and Commercial Power Systems Europe (EEEIC/I&CPS Europe) (pp. 1-7). IEEE.
14. Das, A. K., & Pratihar, D. K. (2021). Bonobo optimizer (BO): an intelligent heuristic with self-adjusting parameters over continuous spaces and its applications to engineering problems. Applied Intelligence, 1-33.
15. Das, A. K., & Pratihar, D. K. (2019, July). Optimal preventive maintenance interval for a Crankshaft balancing machine under reliability constraint using Bonobo Optimizer. In IFToMM World Congress on Mechanism and Machine Science (pp. 1659-1668). Springer, Cham.
16. Das, A. K., Nikum, A. K., Krishnan, S. V., & Pratihar, D. K. (2020). Multi-objective Bonobo Optimizer (MOBO): an intelligent heuristic for multi-criteria optimization. Knowledge and Information Systems, 62(11), 4407-4444.
17. D. H. Wolpert and W. G. Macready, "No free lunch theorems for optimization," IEEE transactions on evolutionary computation, vol. 1, pp. 67-82, 1997.