A Data-Driven Parallel Scheduling Approach for Multiple Agile Earth Observation Satellites

Abstract

To address the large-scale and time-consuming multiple agile earth observation satellite (multi-AEOS) scheduling problems, this article proposes a data-driven parallel scheduling approach, which is composed of a probability prediction model, a task assignment strategy, and a parallel scheduling manner. In this approach, given the historical data of satellite scheduling, a prediction model is trained based on the cooperative neuro-evolution of augmenting topologies (C-NEAT) to predict the probabilities that a task will be fulfilled by different satellites. Driven by the probability prediction model, an assignment strategy is adopted for dividing the multi-AEOS scheduling problem into several single-AEOS scheduling subproblems, which can adaptively assign each task to the satellite with the highest predicted probability and greatly decrease the problem size. In a parallel manner, the single-AEOS scheduling subproblems are optimized, respectively, leading to an acceleration in the optimization efficiency of the original problem. Computational experiments indicate that the proposed approach presents better overall performance than other state-of-the-art methods within a very limited scheduling time. As the two main components of the proposed approach, the prediction model based on C-NEAT and the task assignment strategy also outperform other models with traditional training algorithms and inadaptive assignment strategies, respectively.