Learning to Solve the Agile Earth Observation Satellite Scheduling Problem by a Hybrid Repair Construction Method

The agile earth observation satellite scheduling problem (AEOSSP) is a complex problem focused on maximizing observation rewards by optimizing the task observation sequence and the specific start times for each task. Existing methods have faced challenges in striking a balance between computational efficiency and solution quality. In this paper, we present a hybrid repair construction method (HRCM) that integrates baseline policy models (BPMs) and incorporates a slack and insertion (SI) mechanism to effectively address this challenge. Our method begins with the utilization of the BPM as an initial solution construction method, in which we design an observation construction model (OCM). Subsequently, the SI mechanism is introduced to rectify decision-making errors that may occur during the initial construction process. Experimental results present the significant enhancements in solution quality achieved by HRCM. Furthermore, we conduct a rigorous validation of the contributions made by OCM and SI to the overall improvement in solution quality. This research presents a promising method for enhancing the efficiency of earth observation satellite scheduling, with potential applications in various fields requiring optimal resource allocation and task sequencing.