Timeliness optimization of real-time scheduling for satellite dynamic tasks based on deep reinforcement learning

With the rapid growth of the number of satellites worldwide and the vigorous development of space-basednetworks, optimizing satellite task scheduling to ensure the timeliness of task observation has becomecrucial. The task scheduling method not only affects the efficiency of observation data acquisition but alsodirectly relates to the ability of the space-based satellite system to respond promptly to multiple real-timeapplication requirements. However, for aperiodic dynamic tasks, the traditional batch scheduling methodshave limitations, and the decision can only be made after collecting information from all tasks. Existing real-time scheduling methods based on deep reinforcement learning cannot guarantee the observationtimeliness of urgent tasks. Given this, this study first proposes the problem of timeliness-optimized agilesatellite real-time scheduling for dynamic tasks. The problem aims to maximize the observation timelinessof all tasks by defining the task observation timeliness metrics, which take into account the task observationdelay and the total benefit of receiving tasks. In order to solve the problem, a two-stage timelinessoptimization algorithm PPODL-HR is designed in this paper. In the task selection stage, proximal policyoptimization with deep neural network and long short-term memory network (PPODL) is proposed toaccelerate the convergence of the model training; while in the resource allocation stage, a heuristic rule HRis designed to reduce further the satellite transition time required for task switching through task merging.Numerical simulation and STK simulation verified that the PPODL-HR algorithm outperforms the traditionalstatic batch scheduling and existing dynamic real-time scheduling algorithms in terms of task observationtimeliness, and it can be applied to different task densities and proportions of emergency tasks. Inparticular, compared with the classical dynamic task real-time scheduling algorithm, the timeliness of taskobservations is improved by 21.14%, observational latency for tasks is reduced by 4.55%, and the totalprofit of received tasks is increased by 20.70%.