.png){kind=icon}
Return
Knowledge-guided evolutionary algorithm for multi-satellite resource scheduling optimization
.png){kind=icon}
PRE
AI
DOI：10.1016/j.future.2024.03.006.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
The Multi -Satellite Resource Scheduling Optimization Problem (MSRSOP) represents a complex optimization challenge, focusing on the allocation of limited ground tracking resources to satellite Tracking, Telemetry, and Command (TT&C) tasks, each with complex requirements. This paper introduces a novel mathematical model and a Knowledge -guided Evolutionary Algorithm (KgEA) tailored for the MSRSOP. Our model integrates previously overlooked requirements, such as the specific number of TT&C operations in both ascending and descending orbits, along with the continuity constraints of these operations. The KgEA employs a tri-layer encoding technique to represent the allocation of ground tracking resources to the TT&C operations and orbits. Additionally, KgEA leverages conflict knowledge between tasks to steer the search process, thereby enhancing both the solution quality and the solution efficiency. Experimental results indicate that KgEA surpasses several contemporary algorithms in solving various instances of the MSRSOP. Empirical ablation studies demonstrate that the knowledge -guided approach proposed in this paper can effectively improve the efficiency of problemsolving. Simulation experiments with publicly available satellite data prove that our model and algorithm can effectively solve practical problems. This study underscores the efficacy of KgEA in addressing the MSRSOP, offering significant insights into the scheduling of TT&C tasks for satellites.
Keywords:
Multi-satellite resource scheduling
optimization problem
Complex requirements
Knowledge-guided evolutionary algorithm
Conflict extraction
Journal
F
IF:
6.1
Papers:
6.8K
Citations:
2.3W
Organization
Cited Papers
.png){kind=icon}
ShareSaveShareSaveShareSave
View more