.png){kind=icon}
Return
Learning-driven many-objective evolutionary algorithms for satellite-ground time synchronization task planning problem
.png){kind=icon}
PRE
AI
DOI：10.1016/j.swevo.2017.05.011.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
The satellite-ground time synchronization task planning problem (SGTSTP) is a complex many-objective ground station scheduling problem in navigation systems. In this paper, we first provide a mathematical formulation of the SGTSTP. To solve this complex problem, we propose a decomposition and integration method, based on which the task planning problem is transformed into a multi-period 0-1 programming problem. Given that many-objective evolutionary algorithms (MaOEAs) are time-consuming and the SGTSTP focuses on optimality rather than solution diversity, we integrate learning concepts with conventional MaOEAs to form a learning-driven MaOEA (LD-MaOEA). The LD-MaOEA generates a partial solution with genetic operators, and completes the partial solution using the dynamic learning-based roll planning algorithm (DLRPA). Additionally, we design two learning strategies in the DLRPA. Finally, we design two sets of instances. The computational results demonstrate that LD-MaOEAs have obvious performance promotion in terms of the solving effect and efficiency compared with MaOEAs. Furthermore, we propose a comprehensive metric to help to identify a preferable solution from the solution set obtained using MaOEAs.
Keywords:
Many-objective optimization
Scheduling
Dynamic learning
Evolutionary algorithm
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
8.5
Papers:
2.2K
Citations:
1.0W
Organization
Cited Papers
.png){kind=icon}
ShareSaveShareSaveShareSaveShareSave
ShareSave
View more