Skip to main content

Evolutionary Computation for Dynamic Constrained Optimization Problems

Periodic Reporting for period 1 - ECDCOP (Evolutionary Computation for Dynamic Constrained Optimization Problems)

Reporting period: 2015-12-01 to 2017-11-30

What is the problem/issue being addressed?

This project concentrates on the design, analysis, and applications of evolutionary computation (EC) for dynamic constrained optimization problems (DCOPs).

Why is it important for society?

This project has great potentials to fundamentally change the way in which DCOPs are treated, both from a real-world point of view and from the point of view of advancing our theoretical understanding. The research results of this project will be of great interest to academia in many fields and of significant benefit to many industries that involve DCOPs.

What are the overall objectives?

Firstly, we will design a set of benchmark dynamic constrained optimization test environments which can resemble real-world scenarios. Secondly, we intend to design standardized performance indicators to evaluate EC methods for DCOPs. Thirdly, based on the standardized dynamic test and evaluation environments, we will design some novel and effective EC methods to solve DCOPs. Fourthly, we will present theoretical analysis of EC with different constraint-handling techniques for DCOPs, with the aim of establishing the theoretical foundation of this area. Finally, applying the developed EC methods to deal with DCOPs in the real world is also one key aspect of this project.
During the past two years, we have carried out intensive research on dynamic constrained optimization through evolutionary computation. The main work can be summarized as follows:

1) We have designed a suite of benchmark test functions for dynamic constrained optimization and proposed a novel algorithm to deal with dynamic constrained optimization problems.

2) We have studied how to enhance the search ability of evolutionary algorithms by a two-phase optimization mechanism and by the adaptive tuning of coordinate systems.

3) We have conducted a comparative study of constraint-handling techniques in evolutionary algorithms and provided some theoretic analyses on the advantages and disadvantages of differential constraint-handling techniques in different scenarios.

4) We have proposed new scalarizing functions in decomposition-based multiobjective evolutionary algorithms to handle multiple conflicting objective functions.

5) We have carried out real-world applications in automotive lightweight design and wind farm layout design.

Overall, we have published six papers in top International Journals and two papers in International Conferences. In addition, we submitted one high-quality journal paper. The following are the publications during the past two years:

1) Y. Wang, D.-Q. Yin, S. Yang, and G. Sun. Global and local surrogate-assisted differential evolution for expensive constrained optimization problems with inequality constraints. IEEE Transactions on Cybernetics, in press, 2018. DOI: 10.1109/TCYB.2018.2809430 (2017 ISI Impact Factor: 8.803)

2) Z.-Z. Liu, Y. Wang, S. Yang, and K. Tang. An adaptive framework to tune the coordinate systems in nature-inspired optimization algorithms. IEEE Transactions on Cybernetics, in press, 2018. DOI: 10.1109/TCYB.2018.2802912 (2017 ISI Impact Factor: 8.803)

3) Y. Wang, H. Liu, H. Long, Z. Zhang, and S. Yang. Differential evolution with a new encoding mechanism for optimizing wind farm layout. IEEE Transactions on Industrial Informatics, vol. 14, no. 3, pp. 1040-1054, 2018. (2017 ISI Impact Factor: 5.43)

4) S. Jiang, S. Yang, Y. Wang, and X. Liu. Scalarizing functions in decomposition-based multiobjective evolutionary algorithms. IEEE Transactions on Evolutionary Computation, vol. 22, no. 2, pp. 296-313, 2018. (2017 ISI Impact Factor: 8.124)

5) W. Gong, Y. Wang, Z. Cai, and S. Yang. A weighted biobjective transformation technique for locating multiple optimal solutions of nonlinear equation systems. IEEE Transactions on Evolutionary Computation, vol. 21, no. 5, pp. 697-713, 2017. (2017 ISI Impact Factor: 8.124)

6) Y. Wang, B. Xu, G. Sun, and S. Yang. A two-phase differential evolution for uniform designs in constrained experimental domains. IEEE Transactions on Evolutionary Computation, vol. 21, no. 5, pp. 665-680, 2017. (2017 ISI Impact Factor: 8.124)

7) J.-P. Li, Y. Wang, S. Yang, and Z. Cai. A comparative study of constraint-handling techniques in evolutionary constrained multiobjective optimization, 2016 IEEE Congress on Evolutionary Computation (CEC), Vancouver, BC, 2016, pp. 4175-4182.

8) Z.-Z. Liu, Y. Wang, S. Yang, and Z. Cai. Differential evolution with a two-stage optimization mechanism for numerical optimization, 2016 IEEE Congress on Evolutionary Computation (CEC), Vancouver, BC, 2016, pp. 3170-3177.

9) Y. Wang, J. Yu, S. Yang, and S. Jiang. Evolutionary dynamic constrained optimization: Test suite construction and algorithm comparisons, IEEE Transactions on Systems, Man, and Cybernetics: Systems, submitted, 2018. (2017 ISI Impact Factor: 5.131)
Dynamic constrained optimization problems are of great practical significance. However, few attempts have been made on dynamic constrained optimization problems in the evolutionary computation research community. By this project, we have advanced the development of dynamic constrained optimization from theory, test function construction, algorithm design, and applications. Our work will play an important role in the future study. We have conducted some practical applications in automotive lightweight design. Currently, some automotive manufacturers in China have shown their great interests in our algorithms. We are developing software and collaborating with these automotive manufacturers in China. Therefore, our work will produce important socio-economic impact in the near future.
The abbreviation of Evolutionary Computation for Dynamic Constrained Optimization Problems