Volume -3, Issue-5 ,May2025 International Journal of Modern Science and Research Technology

ISSN NO-2584-2706

Enhancing Whale Optimization Algorithm with

Pso: A Hybrid Benchmark Study
Soniya Wagh; Shital Bhairam
Sandhya Dahak; Neeraj Kumar Jha
Department of MCA G H Raisoni College of Engineering
and Management, India

Abstract the Particle Swarm Optimization (PSO)

Whale Optimization Algorithm (WOA) is algorithm excellent in exploration,
known for its exploration ability while allowing it to clarify solution to achieve
Particle Swarm Optimization (PSO) is faster convergence [5].
known for its exploitation ability. To take the advantages of both techniques,
Hybridizing them helps to improve this paper offers a hybrid WOA-PSO
convergence speed and solution accuracy. algorithm, which aims to improve the
This paper presents a hybrid WOA-PSO combination of speed and solution
algorithm which is evaluated on twenty- accuracy. The performance of hybrid
three benchmark functions and compared algorithm is improved by using twenty-
its performance with the original WOA and three benchmark functions compared to
is able to show better results. Hybrid original WOA. The Experimental Result
WOA-PSO algorithm giving better optimal demonstrate that the hybrid approach
solutions than the original one. achieves the better optimal solution [7].
Experimental results between WOA and By merging the global search capability of
PSO enhances balance between WOA with the local refinement power of
exploration and exploitation. PSO, the hybrid WOA-PSO algorithm
offers a more effective optimization
Keywords: technique. This study provides valuable
Optimization, Hybridization, algorithm, insight it how hybridization can improve
benchmark, WOA the metaheuristic algorithms, making them
more suitable for solving real world
1. Introduction optimization problems [6].
Optimization Algorithm plays a major role
in solving real word problems, where 2. Literature Review
finding the best possible solution Optimization Algorithms are classified
efficiently. Many practical applications into four categories: Nature-based,
such as machine learning, industrial Swarm-based, Physics-based, and Human-
automation, logistics, engineering design, based. Nature-based algorithm is an
and resource allocation, require robust optimization technique inspired by natural
optimization techniques to achieve better phenomena, such as evolution, natural
performance and efficiency. Among the selection, or biological processes. Nature-
widely used metaheuristic algorithm, The based algorithms, like Genetic Algorithm
Whale Optimization Algorithm (WOA) it (GA). Swarm-based algorithm is an
commonly known for its powerful optimization technique that simulates the
exploration ability, it allows to find the vast collective behaviour and social interaction
solution space effectively. instead, of swarms or groups of agents. Physics-
based algorithm is an optimization
technique that models physical processes

IJMSRT25MAY100 www.ijmsrt.com 531

DOI: https://doi.org/10.5281/zenodo.15567654
Volume -3, Issue-5 ,May2025 International Journal of Modern Science and Research Technology
ISSN NO-2584-2706

and natural laws to find optimal solutions.

Physics-based methods, such as Simulated 1. FLOW CHART
Annealing (SA), use physical processes like
energy minimization. Human-based algorithm
is an optimization technique inspired by
human behaviour, culture, or social dynamics.
Human-based algorithms, like Cultural
Algorithm (CA), replicate social and cultural
interactions [3].

Category Algorithms Description

Physics-based Sine Cosine Inspired by
Algorithm, physical
Equilibrium phenomena such as
Optimizer, gravitational
Gravitational forces, equilibrium
Search states, and
Algorithm sinusoidal motion.
Swarm- based Particle Based on the
Swarm collective behavior
Optimization, of biological
Ant Colony groups like birds,
Optimization, ants and 2. Mathematical Equations
Slime Mould grasshoppers.
Algorithm
Evolution- Genetic Mimics the
based Algorithm, principles of
Differential natural selection
Evolution, and evolution.
Backtracking
Search
Algorithm
Human 1brain Storm Inspired by human
Behaviour- Optimization, learning, teaching,
based Battle Royale brainstorming, and
Optimization strategic
Algorithm, behaviours.
Social
Engineering
Learning
Optimization

Table 1: Classification of Metaheuristic

Algorithm

Sr. No. Name of Algorithm Name of Author

1. Particle Swarm James Kennedy
Optimization and Russell
Eberhart (1995)
2. An idea Based on Honey Dervis Karaboga
Bee Swarm for Numerical (2005)
Optimization
3. A New Metaheuristic Bat- Xin-She Yang
Inspired Algorithm (2010)
4. Cuckoo Search via Levy Xin-She Yang and
Flights Suash Deb (2009)
5. Grey Wolf Optimizer Seyedali Mirjalili
et. al. (2014)
6. Elephant Herding Liang Wang et.
Optimization al. (2015)

Table 2: Metaheuristic Algorithms

IJMSRT25MAY100 www.ijmsrt.com 532

DOI: https://doi.org/10.5281/zenodo.15567654
Volume -3, Issue-5 ,May2025 International Journal of Modern Science and Research Technology
ISSN NO-2584-2706

Fig. 1: Search Space

3. Result and Discussion

From the below table this paper concludes
that, hybrid WOA-PSO giving more relevant
and small value as compared to original
algorithm. Some values are remained
unchanged and some are showing fluctuation
in values. Results of hybrid WOA-PSO are
impressive. Some function shows (F4, F6,
F7, F12, etc) enhancement in values. For ex.,
function 1 reduced from 6.8019e-80 to
1.143e-78.

Table 3: Benchmark
Functions
Function No. Original Value Hybrid Value

Function 1 6.8019e-80 1.143e-78

Function 2 6.6784e-55 2.8055e-53
Function 3 43708.8272 27734.5375
Function 4 4.0715 0.28816
Function 5 27.8255 27.7161
Function 6 0.13273 0.0973
Function 7 0.0032022 0.002682
Function 8 -11672.6931 -11405.443
Function 9 0 0
Function 10 3.9968e-15 3.9968e-15
Function 11 0 0
Function 12 0.011364 0.0057713
Function 13 0.5374 0.23443
Function 14 0.998 0.998
Function 15 0.00051 0.00033736
Function 16 -1.0316 -1.0316
Function 17 0.39789 0.39789
Function 18 3 3
Function 19 -3.8411 -3.7808
Function 20 -3.3122 -3.1869
Function 21 -10.1101 -10.0871
Function 22 -10.3895 -10.3755
Function 23 -2.8052 -1.6752

IJMSRT25MAY100 www.ijmsrt.com 533

DOI: https://doi.org/10.5281/zenodo.15567654
Volume -3, Issue-5 ,May2025 International Journal of Modern Science and Research Technology
ISSN NO-2584-2706

4. Conclusion problem,” J. Intell. Manuf., 2018, doi:

The proposed hybrid WOA-PSO algorithm 10.1007/s10845-015-1039-3.
combines the strengths of Whale [8] Y. Li, J. Wang, D. Zhao, G. Li, and
Optimization and Particle Swarm C. Chen, “A two-stage approach for
Optimization, it leads to improve accuracy. combined heat and power economic
Out of twenty-three benchmarks functions, emission dispatch: Combining multi-
the sixteen functions achieved better optimal objective optimization with integrated
values compared to the original one which decision making,” Energy, 2018, doi:
demonstrating an improvement in WOA’s 10.1016/j.energy.2018.07.200.
performance. [9] D. Yousri, T. S. Babu, and A. Fathy,
“Recent methodology-based Harris hawks
5. Reference optimizer for designing load frequency
[1] W. Y. Lin, “A novel 3D fruit fly control incorporated in multi-
optimization algorithm and its applications interconnected renewable energy plants,”
in economics,” Neural Comput. Appl., Sustain. Energy, Grids Networks, 2020,
2016, doi: 10.1007/s00521-015-1942-8. doi: 10.1016/j.segan.2020.100352.
[2] Y. Cheng, S. Zhao, B. Cheng, S. [10] R. Al-Hajj and A. Assi, “Estimating
Hou, Y. Shi, and J. Chen, “Modeling and solar irradiance using genetic programming
optimization for collaborative business technique and meteorological records,”
process towards IoT applications,” Mob. AIMS Energy, 2017, doi:
Inf. Syst., 2018, doi: 10.3934/energy.2017.5.798.
10.1155/2018/9174568. [11] R. Al-Hajj, A. Assi, and F. Batch,
[3] X. Wang, T. M. Choi, H. Liu, and “An evolutionary computing approach for
X. Yue, “A novel hybrid ant colony estimating global solar radiation,” in 2016
optimization algorithm for emergency IEEE International Conference on
transportation problems during post- Renewable Energy Research and
disaster scenarios,” IEEE Trans. Syst. Applications, ICRERA 2016, 2017. doi:
Man, Cybern. Syst., 2018, doi: 10.1109/ICRERA.2016.7884553.
10.1109/TSMC.2016.2606440. [12] R. A. Meyers, “Classical and
[4] I. E. Grossmann, Global Nonclassical Optimization Methods
Optimization in Engineering Design Classical and Nonclassical Optimization
(Nonconvex Optimization and Its Methods 1 Introduction 1 1.1 Local and
Applications), vol. 9. 1996. Global Optimality 2 1.2 Problem Types 2
[5] R. V. Rao and G. G. Waghmare, 1.3 Example Problem: Fitting Laser-
“A new optimization algorithm for solving induced Fluorescence Spectra 3 1.4
complex constrained design optimization Criteria for Optimization 4 1.5
problems,” vol. 0273, no. April, 2016, doi: Multicriteria Optimization 4,” Encycl.
10.1080/0305215X.2016.1164855. Anal. Chem., pp. 9678–9689, 2000,
[6] E.-S. M. El-Kenawy, M. M. Eid, [Online]. Available:
M. Saber, and A. Ibrahim, “MbGWO-SFS: https://pdfs.semanticscholar.org/5c5c/908b
Modified Binary Grey Wolf Optimizer b00a54439dcee50ec1ada6b735694a94.pdf
Based on Stochastic Fractal Search for [13] N. Steffan and G. T. Heydt,
Feature Selection,” IEEE Access, 2020, “Quadratic programming and related
doi: 10.1109/access.2020.3001151. techniques for the calculation of locational
[7] M. Nouiri, A. Bekrar, A. Jemai, S. marginal prices in distribution systems,” in
Niar, and A. C. Ammari, “An effective and 2012 North American Power Symposium
distributed particle swarm optimization (NAPS), 2012, pp. 1–6. doi:
algorithm for flexible job-shop scheduling 10.1109/NAPS.2012.6336310.

IJMSRT25MAY100 www.ijmsrt.com 534

DOI: https://doi.org/10.5281/zenodo.15567654
Volume -3, Issue-5 ,May2025 International Journal of Modern Science and Research Technology
ISSN NO-2584-2706

[14] M. Mafarja et al.,

“Evolutionary Population Dynamics
and Grasshopper Optimization
approaches for feature selection
problems,” Knowledge-Based Syst.,
vol. 145, pp. 25–45, 2018, doi:
10.1016/j.knosys.2017.12.037.
[15] A. A. Heidari, R. Ali
Abbaspour, and A. Rezaee Jordehi,
“An efficient chaotic water cycle
algorithm for optimization tasks,”
Neural Comput. Appl., vol. 28, no. 1,
pp. 57–85, 2017, doi:
10.1007/s00521-015-203

IJMSRT25MAY100 www.ijmsrt.com 535

DOI: https://doi.org/10.5281/zenodo.15567654