Safe Hierarchical Reinforcement Learning for CubeSat Task Scheduling Based on Energy Consumption
Authors:
- Mahya RamezaniMRMahya Ramezani
- M. Amin AlandihallajMAM. Amin Alandihallaj
- Jose Luis Sanchez-LopezJose Luis Sanchez-Lopez
- Andreas HeinAHAndreas Hein
Preprint
Abstract
This paper presents a Hierarchical Reinforcement Learning methodology tailored for optimizing CubeSat task scheduling in Low Earth Orbits (LEO). Incorporating a high-level policy for global task distribution and a low-level policy for real-time adaptations as a safety mechanism, our approach integrates the Similarity Attention-based Encoder (SABE) for task prioritization and an MLP estimator for energy consumption forecasting. Integrating this mechanism creates a safe and fault-tolerant system for CubeSat task scheduling. Simulation results validate the Hierarchical Reinforcement Learning superior convergence and task success rate, outperforming both the MADDPG model and traditional random scheduling across multiple CubeSat configurations.Keywords
All Related Versions
This publication has 16 references indexed in Scilit:
- Satellite replacement and task reallocation for multiple-payload fractionated Earth observation missionActa Astronautica, 2022
- Multiple-payload fractionated spacecraft for earth observationActa Astronautica, 2022
- A nanosatellite task scheduling framework to improve mission value using fuzzy constraintsExpert Systems with Applications, 2021
- Task-level decision-making for dynamic and stochastic human-robot collaboration based on dual agents deep reinforcement learningThe International Journal of Advanced Manufacturing Technology, 2021
- A Survey on Model-Based Mission Planning and Execution for Autonomous SpacecraftIEEE Systems Journal, 2017
- A state-of the-art survey of TOPSIS applicationsExpert Systems with Applications, 2012
- Task assignment policies in distributed server systems: A surveyJournal of Network and Computer Applications, 2011
- A Unified Framework for Max-Min and Min-Max Fairness With ApplicationsIEEE/ACM Transactions on Networking, 2007
- Selecting and scheduling observations of agile satellitesAerospace Science and Technology, 2002
- Three Scheduling Algorithms Applied to the Earth Observing Systems DomainManagement Science, 2000