Improved butterfly optimisation algorithm based on guiding weight and population restart

Guo, Yanju; Liu, Xianjie; Chen, Lei

doi:10.1080/0952813x.2020.1725651

Cited by 19 publications

(9 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To address this shortcoming, a new fuzzy decision-making strategy and a auxiliary concept called "virtual butterfly'' were introduced in Fuzzy BOA (FBOA) [179] to enhance the search capability of the standard BOA. Owing to the poor performance of the FBOA algorithm for high-dimensional optimization problems, a guiding weight and population restart strategy were applied to the original algorithm in [180]. In [181], the bidirectional search applied in the structure of the BOA helped to conduct local searches in the forward and backward directions, which improved the performance of the BOA to some extent, however, the improvement of the algorithm was targeted and could not satisfy the solution of more complex combinatorial problems (e.g., constrained discrete problems).…”

Section: G Research Progress Regarding Theory and Applications Of But...mentioning

confidence: 99%

A survey on several new popular swarm intelligence optimization algorithms

Wei

Huang

2023

Preprint

View full text Add to dashboard Cite

Traditional optimization methods rely on parameter selection and a require high mathematical performance of the objective function. Thus, swarm intelligence optimization algorithms have attracted extensive attention as modern optimization methods in recent years, achieving remarkable results in the fields of machine learning, engineering optimization, process control, and elsewhere. Swarm intelligence optimization algorithms are a form of computing technology built upon the laws of biological group behavior, they are simple, fast, and place low requirements upon the objective functions. The traditional swarm intelligence algorithm offers new ideas for solving certain practical problems, however, it suffers from shortcomings in several experiments. In recent years, numerous scholars have proposed new swarm intelligence optimization algorithms, this paper selects several of the more typical swarm intelligence algorithms proposed in recent years at home and abroad, including the Whale Optimization Algorithm, Moth-Flame Optimization Algorithm, Fireworks Algorithm, Dragonfly Algorithm, Crow Search Algorithm, Butterfly Optimization Algorithm, and Pigeons Algorithm. Furthermore, the experimental performances of these algorithms are compared with respect to their convergence speed, accuracy, and stability, using 18 standard test functions, and the relative improvement methods are compared and analyzed. Finally, the characteristics of the swarm intelligence optimization algorithm are summarized, and its future development potential is discussed.

show abstract

Section: G Research Progress Regarding Theory and Applications Of But...mentioning

confidence: 99%

A survey on several new popular swarm intelligence optimization algorithms

Wei

Huang

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…This section conducts simulation experiments based on 10 commonly used benchmark functions (Mirjalili and Lewis, 2016). Firstly, the definitions of these 10 functions are given in Table 1 and Table 2, and then IBA performance is compared with other seven algorithms including CBA (Adarsh et al, 2016), QBA (Zhu et al, 2016), PSOBA (Tchapda et al, 2017), WPBOA (Guo et al, 2021), MSCA (Wang and Lu, 2021), ISCA (Zadehparizi and Jam, 2022) and IISCA (Long et al, 2019). All experiments in this study are conducted in a PC with Windows 10 system, 3.8 GHz Intel Core, 8 GB RAM, and MATLAB R2018b.…”

Section: Gaussian Mutationmentioning

confidence: 99%

Economic dispatch using modified bat algorithm

Yang

Yuan

et al. 2022

Front. Energy Res.

View full text Add to dashboard Cite

Due to the frequent opening and shutting of turbine valves in the power system, valve point effect (VPE) that makes the economic dispatching (ED) problem non-linear, non-smooth and non-convex may be generated. Moreover, various constraints appear in the operation process, such as network transmission loss, and power balance during unit operation, which make it more difficult to find the global optimum through traditional mathematical methods. Nowadays, intelligent algorithms have successfully become a useful optimization tool to deal with nonlinear problems. In this paper, an improved bat algorithm (IBA), into which random black hole strategy and Gaussian mutation are introduced, is proposed to solve the ED problem. Furthermore, the random black hole strategy can enhance the diversity of the population and improve the convergence speed of IBA. Gaussian mutation is adopted to help jumping out of the local optimum. IBA is tested in 50 and 100 dimensions on 10 sets of well-known benchmark functions respectively, and compared with the methods in literature to verify its feasibility. Then, three different scales economic dispatching problems (3 units, 13 units, 40 units) are solved by this method, which further proves its effectiveness. The results show that IBA has obvious advantages and practical application value compared with other optimization methods.

show abstract

“…[45] improved BOA by using a cross-entropy method and applied it to benchmark functions and engineering design problems. [46] improved BOA by using the inertia weight of the PSO algorithm and random population restart strategy for optimising some benchmark functions. [47] proposed an unbiased version of BOA and applied it to some functions.…”

Section: Related Workmentioning

confidence: 99%

Dynamic Butterfly Optimization Algorithm for Feature Selection

et al. 2020

View full text Add to dashboard Cite

Feature selection represents an essential pre-processing step for a wide range of Machine Learning approaches. Datasets typically contain irrelevant features that may negatively affect the classifier performance. A feature selector can reduce the number of these features and maximise the classifier accuracy. This paper proposes a Dynamic Butterfly Optimization Algorithm (DBOA) as an improved variant to Butterfly Optimization Algorithm (BOA) for feature selection problems. BOA represents one of the most recently proposed optimisation algorithms. BOA has demonstrated its ability to solve different types of problems with competitive results compared to other optimisation algorithms. However, the original BOA algorithm has problems when optimising high-dimensional problems. Such issues include stagnation into local optima and lacking solutions diversity during the optimisation process. To alleviate these weaknesses of the original BOA, two significant improvements are introduced in the original BOA: the development of a Local Search Algorithm Based on Mutation (LSAM) operator to avoid local optima problem and the use of LSAM to improve BOA solutions diversity. To demonstrate the efficiency and superiority of the proposed DBOA algorithm, 20 benchmark datasets from the UCI repository are employed. The classification accuracy, the fitness values, the number of selected features, the statistical results, and convergence curves are reported for DBOA and its competing algorithms. These results demonstrate that DBOA significantly outperforms the comparative algorithms on the majority of the used performance metrics. INDEX TERMS Butterfly optimisation algorithm, feature selection, local search algorithm based on mutation.

show abstract

Improved butterfly optimisation algorithm based on guiding weight and population restart

Cited by 19 publications

References 35 publications

A survey on several new popular swarm intelligence optimization algorithms

A survey on several new popular swarm intelligence optimization algorithms

Economic dispatch using modified bat algorithm

Dynamic Butterfly Optimization Algorithm for Feature Selection

Contact Info

Product

Resources

About