Journal
SOFT COMPUTING
Volume 23, Issue 11, Pages 3723-3739Publisher
SPRINGER
DOI: 10.1007/s00500-018-3033-0
Keywords
Evolutionary dynamic multi-objective optimization; Prediction; Boundary point; Knee point; Adaptive diversity maintenance strategy
Categories
Funding
- National Natural Science Foundation of China [61502408, 61673331, 61772178]
- Education Department Major Project of Hunan Province [17A212]
- CERNET Innovation Project [NGII20150302]
- MOE Key Laboratory of Intelligent Computing and Information Processing
- Science and Technology Plan Project of Hunan Province [2016TP1020]
- [2017JJ4001]
Ask authors/readers for more resources
There are some real-world problems in which multiple objectives conflict with each other and the objectives change with time. These problems require an optimization algorithm to track the moving Pareto front or Pareto set over time. In this paper, we propose a predictive strategy based on special points (SPPS) which consists of three mechanisms. The first one is that the non-dominated set is predicted directly by feed-forward center points, which can eliminate many useless individuals predicted by traditional prediction using feed-forward center points. The second one is that a special point set (such as boundary point and knee point) is introduced into the predicted population which can track Pareto front or Pareto set more accurately. The third one is the adaptive diversity maintenance mechanism based on boundary points and center points. The mechanism can introduce diverse individuals of the corresponding number according to the degree of difficulty of the problem to keep the diversity of the population. The number of these diverse individuals is strongly related to the center points. Then, they are generated evenly throughout the decision space between the boundary points. The proposed strategy is compared with the four other state-of-the-art strategies. The experimental results show that SPPS can do well for dynamic multi-objective optimization.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available