Digital Twinning in Non-Terrestrial Networks: Increasing the Operational Life of Satellite Batteries
Translated title
Digital Twinning in Non-Terrestrial Networks
Author
Term
4. semester
Education
Publication year
2025
Submitted on
2025-06-03
Pages
60
Abstract
This project focuses on developing a Physical Twin simulator of a Geostationary Orbit satellite constellation and the corresponding Digital Twin model and service. The main goal is to use the Digital Twin to ensure long life expectancy of the satellite batteries. Regarding the battery modeling in the Digital Twin, the report introduces and compares Discrete Time Markov Chains and Auto-regressive models. It is found that, in terms of accuracy, the Markov model performs better. For the service implementation, Reinforcement Learning is used for satellite resource allocation, ensuring battery stability, highly related to battery durability. The results show how it is possible to use the Digital Twin to guarantee battery stability, fulfilling the initial design purpose of extending the battery life expectation.
Keywords
Documents