Int. J. High Performance Computing and Networking, Vol. 11, No. 3, 2018 223
Copyright © 2018 Inderscience Enterprises Ltd.
Constrained evolution algorithm based on adaptive
differential evolution
Kangshun Li*
College of Mathematics and Informatics,
South China Agricultural University,
Guangzhou, 510642, China
and
Shenzhen Suodi Statistician Company Limited,
Shenzhen, 518000, China
Email: likangshun@sina.com
*Corresponding author
Liang Zhong, Lei Zuo and Zhaopeng Wang
College of Mathematics and Informatics,
South China Agricultural University,
Guangzhou, 510642, China
Email: 423462718@qq.com
Email: 853483687@qq.com
Email: 329956595@qq.com
Abstract: Solving constrained optimisation is widely used in science and engineering, but
the slow convergence speed and premature are the biggest problems researchers face. Research
on a constrained evolution algorithm (CO-JADE) based on adaptive differential evolution
(JADE) for solving the constrained optimisation problems is proposed in this paper. According to
features of the Gaussian distribution, the Cauchy distribution and the mutation factor, we
exploited the crossover probability of each individual to improve the search strategy. Aimed to
effectively evaluate the relationship between the value of the objective function and the degree of
constraint violation, the paper used an improved adaptive tradeoff model to evaluate the
individuals of the population. This tradeoff model used different treatment scheme for different
stages of the population and implemented on night standard test functions. The experimental
shows that the CO-JADE has better accuracy and stability than the COEA/ODE and the HCOEA.
Keywords: adaptive differential evolution; adaptive tradeoff model; constrained optimisation.
Reference to this paper should be made as follows: Li, K., Zhong, L., Zuo, L. and Wang, Z.
(2018) ‘Constrained evolution algorithm based on adaptive differential evolution’, Int. J. High
Performance Computing and Networking, Vol. 11, No. 3, pp.223–230.
Biographical notes: Kangshun Li is currently a Full Professor with South China Agricultural
University, Guangzhou, China. He received his BSc in Computational Mathematics from
Nanchang University, Nanchang, China and PhD in Computer Software and Theory from Wuhan
University, Wuhan, China in 1983 and 2006, respectively. His current research interests are
intelligent computation, image identification, data mining, soft engineering, embedded system,
evolvable hardware, evolutionary modelling, parallel computation, and neural network.
Liang Zhong is a Master degree student at South China Agricultural University, Guangzhou,
China. His research interests include evolutionary algorithm, evolutionary computing, differential
evolution and applications of artificial intelligence.
Lei Zuo is a Master degree student at South China Agricultural University, Guangzhou, China.
His research interests include evolutionary algorithm, evolutionary computing, and particle
swarm optimisation.
Zhaopeng Wang is an undergraduate from South China Agricultural University, Guangzhou,
China. His research interests include evolutionary computing.