Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Efficient Policy Learning with Hybrid Evaluation-Based Genetic Programming for Uncertain Agile Earth Observation Satellite Scheduling

Junhua Xue, Yuning Chen

Abstract

The Uncertain Agile Earth Observation Satellite Scheduling Problem (UAEOSSP) is a novel combinatorial optimization problem and a practical engineering challenge that aligns with the current demands of space technology development. It incorporates uncertainties in profit, resource consumption, and visibility, which may render pre-planned schedules suboptimal or even infeasible. Genetic Programming Hyper-Heuristic (GPHH) shows promise for evolving interpretable scheduling policies; however, their simulation-based evaluation incurs high computational costs. Moreover, the design of the constructive method, denoted as Online Scheduling Algorithm (OSA), directly affects fitness assessment, resulting in evaluation-dependent local optima within the policy space. To address these issues, this paper proposes a Hybrid Evaluation-based Genetic Programming (HE-GP) for effectively solving UAEOSSP. A Hybrid Evaluation (HE) mechanism is integrated into the policy-driven OSA, combining exact and approximate filtering modes: exact mode ensures evaluation accuracy through elaborately designed constraint verification modules, while approximate mode reduces computational overhead via simplified logic. HE-GP dynamically switches between evaluation models based on real-time evolutionary state information. Experiments on 16 simulated instance sets demonstrate that HE-GP significantly outperforms handcrafted heuristics and single-evaluation based GPHH, achieving substantial reductions in computational cost while maintaining excellent scheduling performance across diverse scenarios. Specifically, the average training time of HE-GP was reduced by 17.77\% compared to GP employing exclusively exact evaluation, while the optimal policy generated by HE-GP achieved the highest average ranks across all scenarios.

Efficient Policy Learning with Hybrid Evaluation-Based Genetic Programming for Uncertain Agile Earth Observation Satellite Scheduling

Abstract

The Uncertain Agile Earth Observation Satellite Scheduling Problem (UAEOSSP) is a novel combinatorial optimization problem and a practical engineering challenge that aligns with the current demands of space technology development. It incorporates uncertainties in profit, resource consumption, and visibility, which may render pre-planned schedules suboptimal or even infeasible. Genetic Programming Hyper-Heuristic (GPHH) shows promise for evolving interpretable scheduling policies; however, their simulation-based evaluation incurs high computational costs. Moreover, the design of the constructive method, denoted as Online Scheduling Algorithm (OSA), directly affects fitness assessment, resulting in evaluation-dependent local optima within the policy space. To address these issues, this paper proposes a Hybrid Evaluation-based Genetic Programming (HE-GP) for effectively solving UAEOSSP. A Hybrid Evaluation (HE) mechanism is integrated into the policy-driven OSA, combining exact and approximate filtering modes: exact mode ensures evaluation accuracy through elaborately designed constraint verification modules, while approximate mode reduces computational overhead via simplified logic. HE-GP dynamically switches between evaluation models based on real-time evolutionary state information. Experiments on 16 simulated instance sets demonstrate that HE-GP significantly outperforms handcrafted heuristics and single-evaluation based GPHH, achieving substantial reductions in computational cost while maintaining excellent scheduling performance across diverse scenarios. Specifically, the average training time of HE-GP was reduced by 17.77\% compared to GP employing exclusively exact evaluation, while the optimal policy generated by HE-GP achieved the highest average ranks across all scenarios.
Paper Structure (26 sections, 34 equations, 10 figures, 6 tables, 3 algorithms)

This paper contains 26 sections, 34 equations, 10 figures, 6 tables, 3 algorithms.

Table of Contents

  1. Introduction
  2. Background
  3. Uncertain Agile Earth Observation Satellite Scheduling Problem
  4. Related Work
  5. Genetic Programming Hyper-Heuristic for UAEOSSP
  6. The Overall Framework of GPHH
  7. Individual Representation and Initialization
  8. A Constructive Method for Fitness Evaluation
  9. Genetic Operators
  10. Selection
  11. Crossover
  12. Mutation
  13. Reproduction
  14. Hybrid Evaluation Mechanism
  15. Exact Filtering Mode
  16. ...and 11 more sections

Figures (10)

  • Figure 1: An example of the tree representation of a scheduling policy.
  • Figure 2: An example of the AEOS attitude transition is provided. The duration necessary for the attitude transition between two identical candidate requests exhibits variability.
  • Figure 3: Flowchart of the exact filtering mode.
  • Figure 4: Flowchart of the approximate filtering mode.
  • Figure 5: Probability density function curves are presented with a fixed mean of 20 and varying values of the parameter $\alpha$. $\alpha$ takes values from 20 to 100 in increments of 20. It is evident that the larger the $\alpha$, the steeper the curve.
  • ...and 5 more figures