A dynamic interval multi-objective optimization algorithm based on environmental change detection

Dynamic interval multi-objective optimization problems are a class of optimization problems whose interval parameters change with the environment. However, the existing algorithms fail to fully consider the characteristics of interval parameters and can not accurately assess the severity of environmental changes, resulting in a decline in the effectiveness of the detection mechanism. Therefore, effectively dealing with the inherent uncertainty of interval values becomes an important challenge. To address these problems, this paper proposes a dynamic interval multi-objective optimization algorithm based on environment change detection (IO-ECD). Firstly, a change severity detection operator is designed by using the average overlap degree of individual objective interval to classify different severity of environmental changes. Secondly, this paper uses the local search and the interval prediction mechanism based on feed-forward centroid and special points set to cope with various levels of environmental changes. Finally, inspired by hypervolume contribution and objective value inaccuracy, an interval crowding distance operator is constructed to guide population evolution. The algorithm is compared with six cutting-edge algorithms in eight test cases and a combinatorial optimization scenario. The experimental results show that the algorithm performs exceptionally well in most aspects and has strong competitiveness. © 2024 Elsevier Inc.