An Adaptive Version of Differential Evolution for Solving CEC2014, CEC 2017 and CEC 2022 Test Suites
- Publisher:
- Institute of Electrical and Electronics Engineers (IEEE)
- Publication Type:
- Conference Proceeding
- Citation:
- Proceedings of the 2022 IEEE Symposium Series on Computational Intelligence, SSCI 2022, 2022, 00, pp. 1644-1649
- Issue Date:
- 2022-12-07
Closed Access
| Filename | Description | Size | |||
|---|---|---|---|---|---|
| An_Adaptive_Version_of_Differential_Evolution_for_Solving_CEC2014_CEC_2017_and_CEC_2022_Test_Suites.pdf | Published version | 231.33 kB |
Copyright Clearance Process
- Recently Added
- In Progress
- Closed Access
This item is closed access and not available.
In this paper, an extended version of LSHADE, an enhanced variant of Differential evolution (DE), is proposed by adding equation modifications and self-adaptive characteristics to the basic LSHADE algorithm. The proposed algorithm is named as adaptive LSHADE (ALSHADE) and incorporates some major changes in the crossover, mutation and population adaptation operations of LSHADE algorithm. The modifications proposed include the introduction of linearly decreasing distribution for crossover rate and scaling factor using chaotic mutation operator. Apart from these modifications, the algorithm also employs linear population size reduction to reduce the computational burden of the algorithm. The proposed algorithm is tested on CEC 2014, CEC 2017 CEC 2022 benchmark suits and is compared with respect to some major algorithms in literature. WIlcoxon's rank-sum tests have been performed to test the significance of the algorithm statistically. Experimental and statistical results prove that the proposed ALSHADE performs significantly better with respect to other algorithms in literature and can be considered as a potential candidate to become a state-of-the-art algorithm.
Please use this identifier to cite or link to this item: