Two-Population Coevolutionary Algorithm with Dynamic Learning Strategy for Many-Objective Optimization

Abstract

Due to the complexity of many-objective optimization problems, the existing many-objective optimization algorithms cannot solve all the problems well, especially those with complex Pareto front. In order to solve the shortcomings of existing algorithms, this paper proposes a coevolutionary algorithm based on dynamic learning strategy. Evolution is realized mainly through the use of Pareto criterion and non-Pareto criterion, respectively, for two populations, and information exchange between two populations is used to better explore the whole objective space. The dynamic learning strategy acts on the non-Pareto evolutionary to improve the convergence and diversity. Besides, a dynamic convergence factor is proposed, which can be changed according to the evolutionary state of the two populations. Through these effective heuristic strategies, the proposed algorithm can maintain the convergence and diversity of the final solution set. The proposed algorithm is compared with five state-of-the-art algorithms and two weight-sum based algorithms on a many-objective test suite, and the results are measured by inverted generational distance and hypervolume performance indicators. The experimental results show that, compared with the other five state-of-the-art algorithms, the proposed algorithm achieved the optimal performance in 47 of the 90 cases evaluated by the two indicators. When the proposed algorithm is compared with the weight-sum based algorithms, 83 out of 90 examples achieve the optimal performance.

Advanced orthogonal opposition‐based learning‐driven dynamic salp swarm algorithm: Framework and case studies

“…Zhang et al [47] enhanced the dynamic nature of the NSGA-III algorithm by embedding a second-order difference strategy and random mechanism, and the proposed algorithm exhibited outstanding performance on real-world problems. Li et al [48] proposed a multi-objective evaluation algorithm with dynamic learning strategy, where dynamic convergence factor and dynamic learning strategy were used to balance the dynamicity and diversity of the algorithm.…”

“…Li et al. [48] proposed a multi‐objective evaluation algorithm with dynamic learning strategy, where dynamic convergence factor and dynamic learning strategy were used to balance the dynamicity and diversity of the algorithm.…”

Strengthened Initialization of Adaptive Cross-Generation Differential Evolution

“…However, real-world problems are usually composed of multiple objectives, where increasing the value of one objective will inevitably lead to the loss of other objectives. Now many algorithms are improved in order to meet the needs of practical problems to solve the specific problem [5][6][7][8]. In multi-objective optimization problems, the difficulty of achieving Pareto optimality is attributed to the trade-off between multiple goals.…”

CovH2SD: A COVID-19 detection approach based on Harris Hawks Optimization and stacked deep learning

“…Examples of these algorithms are Genetic Algorithms (GA) ( Holland, 1992 ), Particle Swarm Optimization (PSO) ( Kennedy & Eberhart, 1995 ), Cuckoo Search (CS) algorithm ( Yang & Deb, 2010 ), Grasshopper Optimization Algorithm (GOA) ( Balaha and Saafan, 2021 , Saremi et al, 2017 ), and Grey Wolf Optimizer (GWO) ( Mirjalili et al, 2014 ). Also, many learning techniques have been used to improve the performance of the metaheuristic algorithms ( El-Gendy et al, 2020 , Feng et al, 2018 , Li, Li, Tian, and Xia, 2019 , Li, Li, Tian, and Zou, 2019 , Li and Wang, 2021 , Li, Wang, and Alavi, 2020 , Li, Wang, Dong, et al, 2021 , Li, Wang, and Gandomi, 2021 , Li, Wang, and Wang, 2021 , Li, Xiao, et al, 2020 , Nan et al, 2017 , Saafan and El-Gendy, 2021 , Wang, Deb, et al, 2016 ).…”