Enhancing Remote-Sensing Satellite Task Scheduling Using Reinforcement Learning and Multi-Objective Optimization

The optimization of satellite planning to improve system performance has always been a topic of interest. The problem of planning a remote-sensing satellite involves selecting and scheduling tasks from a set of user requests to optimize one or more objective functions. In recent years, artificial intelligence has proven to be an effective planning tool for remote-sensing satellites. This paper investigates the planning of an observation mission by a remote-sensing satellite, with the goal of optimizing two objective functions (failure rate and timely execution of missions) using artificial intelligence. Reinforcement learning and multi-objective optimization using the Pareto front are used as the solving method. This research considers the dynamic characteristics of energy, memory, and attitude in addition to its baseline research characteristics. By using this method, several optimal agents have been identified. The results indicate that integrating realistic operational constraints, such as memory usage, updated databases, and power/transition management, into the optimization framework reduces the solution space but leads to more practical and deployable outcomes. A clear tradeoff exists between solution diversity and realism. While incorporating operational factors restricts optimization flexibility, it simultaneously improves the applicability and reliability of the solutions.