Knowledge-transfer based genetic programming algorithm for multi-objective dynamic agile earth observation satellite scheduling problem

Created by W.Langdon from gp-bibliography.bib Revision:1.7686

@Article{WEI:2024:swevo,

• author = "Luona Wei and Ming Chen and Lining Xing and Qian Wan and Yanjie Song and Yuning Chen and Yingwu Chen",
• title = "Knowledge-transfer based genetic programming algorithm for multi-objective dynamic agile earth observation satellite scheduling problem",
• journal = "Swarm and Evolutionary Computation",
• volume = "85",
• pages = "101460",
• year = "2024",
• ISSN = "2210-6502",
• DOI = "doi:10.1016/j.swevo.2023.101460",
• URL = "https://www.sciencedirect.com/science/article/pii/S2210650223002328",
• keywords = "genetic algorithms, genetic programming, Agile satellite scheduling, Multi-objective, Knowledge transfer",
• abstract = "The multi-objective dynamic agile earth observation satellite scheduling problem (MO-DAEOSSP) aims to schedule a set of real-time arrival requests and form a reasonable observation plan to satisfy various criteria. According to the requirements in practical applications, the total profit and the average image quality of scheduled requests are taken as optimization goals in this study. Compared to manually designed heuristics and iterative-based methods used in previous research, genetic programming based hyper heuristics (GPHH) can automatically evolve high-quality heuristic rules (HRs) for real-time scheduling without being highly dependent on expert knowledge. In this paper, a knowledge-transfer based multi-objective GPHH framework (KT-MOGP) is proposed, equipped with a heuristic-based simulation considering the idle monitoring, to evolve non-dominated HRs for solving MO-DAEOSSP. The heuristic-based simulation generates feasible schedules and returns fitness values for given HRs, which are the individuals evolved by KT-MOGP. KT-MOGP applies a knowledge transfer mechanism to accelerate convergence. Once a source problem is trained, its non-dominated solutions are extracted and their feature importance is transferred to guide the initialization of another target problem, by which the knowledge generated during the training process can be fully used. Experimental results on three sets of instances show that KT-MOGP outperforms the existing GPHH-based method and that the evolved HRs are competitive compared to several classical constructive heuristics and multi-objective evolutionary algorithms. The results also show the effectiveness of the proposed knowledge transfer-based initialization. To the best of our knowledge, this study is the first attempt to consider both multi-objective scenarios and real-time arrival requests",

}

Genetic Programming entries for Luona Wei Ming Chen Lining Xing Qian Wan Yanjie Song Yuning Chen Yingwu Chen

Citations