EOS-Bench: A Comprehensive Benchmark for Earth Observation Satellite Scheduling

2026-04-28

AI Summary

This study addresses the lack of a unified, open benchmark for evaluating Earth observation satellite scheduling algorithms, which hinders fair performance comparisons. We present a high-fidelity, reproducible evaluation framework that integrates orbital dynamics and platform constraints to generate 1,390 scenarios and 13,900 instances. For the first time, we introduce a scenario characterization scheme capturing dimensions such as task density, flexibility, and conflict intensity. Using this framework, we systematically assess the performance of mixed-integer programming, heuristic, metaheuristic, and deep reinforcement learning approaches under both agile and non-agile satellite configurations. The resulting open benchmark enables multi-algorithm, multi-scale, and multi-metric comparisons, effectively revealing trade-offs between solution quality and computational efficiency, thereby providing a reliable foundation and deeper insights for satellite scheduling research.

Abstract

Earth observation satellite imaging scheduling is a challenging NP-hard combinatorial optimisation problem central to space mission operations. While next-generation agile Earth observation satellites (EOS) increase operational flexibility, they also significantly raise scheduling complexity. The lack of a unified, open-source benchmark makes it difficult to compare algorithms across studies. This paper introduces EOS-Bench, a comprehensive framework for systematic and reproducible evaluation of scheduling methods. By integrating high-fidelity orbital dynamics and platform constraints, EOS-Bench generates 1,390 scenarios and 13,900 benchmark instances, spanning from small-scale validation cases to large coordination problems with up to 1,000 satellites and 10,000 requests. We further propose a scenario characterisation scheme to quantify structural difficulty based on factors such as opportunity density, task flexibility, conflict intensity, and satellite congestion. A multidimensional evaluation protocol is introduced, assessing performance across five metrics: task profit, completion rate, workload balance, timeliness, and runtime. The framework is evaluated using mixed-integer programming, heuristics, meta-heuristics, and deep reinforcement learning across both agile and non-agile settings. Results show that EOS-Bench effectively distinguishes solver performance across scales and conditions, revealing trade-offs between solution quality and computational efficiency, and providing deeper insight into scenario complexity. EOS-Bench offers a unified and extensible open testbed for advancing research in Earth observation satellite scheduling. The code and data are available at https://github.com/Ethan19YQ/EOS-Bench.

Problem

• Earth observation satellite scheduling
• benchmark
• combinatorial optimisation
• algorithm evaluation
• scenario complexity

Innovation

• Earth observation satellite scheduling
• benchmark framework
• scenario characterisation
• multidimensional evaluation
• NP-hard combinatorial optimisation