# Tera-SpaceCom: GNN-based Deep Reinforcement Learning for Joint Resource Allocation and Task Offloading in TeraHertz Band Space Networks

arXiv: https://arxiv.org/abs/2409.07911 · HTML: https://mlsanity.com/paper/2409.07911/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 16 of its 77 references that are in the map.
- First posted on arXiv 12 Sep 2024.

## Builds on (most cited first, 16 of 16)

- [Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments](https://mlsanity.com/paper/1706.02275/) (2017)
- [Actor-Attention-Critic for Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/1810.02912/) (2018)
- [CRPO: A New Approach for Safe Reinforcement Learning with Convergence Guarantee](https://mlsanity.com/paper/2011.05869/) (2020)
- [Efficient Multi-User Computation Offloading for Mobile-Edge Cloud Computing](https://mlsanity.com/paper/1510.00888/) (2015)
- [Dynamic RAN Slicing for Service-Oriented Vehicular Networks via Constrained Learning](https://mlsanity.com/paper/2012.01991/) (2020)
- [TeraHertz Band Communication: An Old Problem Revisited and Research Directions for the Next Decade](https://mlsanity.com/paper/2112.13187/) (2021)
- [Satellite edge computing for real-time and very-high resolution Earth observation](https://mlsanity.com/paper/2212.12912/) (2022)
- [Deep Reinforcement Learning Based Spectrum Allocation in Integrated Access and Backhaul Networks](https://mlsanity.com/paper/2004.13133/) (2020)
- [Age-Based Scheduling for Mobile Edge Computing: A Deep Reinforcement Learning Approach](https://mlsanity.com/paper/2312.00279/) (2023)
- [Hybrid Beamforming for Terahertz Wireless Communications: Challenges, Architectures, and Open Problems](https://mlsanity.com/paper/2101.08469/) (2021)
- [Network Characteristics of LEO Satellite Constellations: A Starlink-Based Measurement from End Users](https://mlsanity.com/paper/2212.13697/) (2022)
- [Joint Offloading and Resource Allocation for Hybrid Cloud and Edge Computing in SAGINs: A Decision Assisted Hybrid Action Space Deep Reinforcement Learning Approach](https://mlsanity.com/paper/2401.01140/) (2024)
- [Constrained Deep Reinforcement Based Functional Split Optimization in Virtualized RANs](https://mlsanity.com/paper/2106.00011/) (2021)
- [Network Massive MIMO Transmission Over Millimeter-Wave and Terahertz Bands: Mobility Enhancement and Blockage Mitigation](https://mlsanity.com/paper/2005.02650/) (2020)
- [A Universal Attenuation Model of Terahertz Wave in Space-Air-Ground Channel Medium](https://mlsanity.com/paper/2308.00966/) (2023)
- [Deep Reinforcement Learning Based Cross-Layer Design in Terahertz Mesh Backhaul Networks](https://mlsanity.com/paper/2310.05034/) (2023)

## Abstract (arXiv)

Terahertz (THz) space communications (Tera-SpaceCom) is envisioned as a promising technology to enable various space science and communication applications. Mainly, the realm of Tera-SpaceCom consists of THz sensing for space exploration, data centers in space providing cloud services for space exploration tasks, and a low earth orbit (LEO) mega-constellation relaying these tasks to ground stations (GSs) or data centers via THz links. Moreover, to reduce the computational burden on data centers as well as resource consumption and latency in the relaying process, the LEO mega-constellation provides satellite edge computing (SEC) services to directly compute space exploration tasks without relaying these tasks to data centers. The LEO satellites that receive space exploration tasks offload (i.e., distribute) partial tasks to their neighboring LEO satellites, to further reduce their computational burden. However, efficient joint communication resource allocation and computing task offloading for the Tera-SpaceCom SEC network is an NP-hard mixed-integer nonlinear programming problem (MINLP), due to the discrete nature of space exploration tasks and sub-arrays as well as the continuous nature of transmit power. To tackle this challenge, a graph neural network (GNN)-deep reinforcement learning (DRL)-based joint resource allocation and task offloading (GRANT) algorithm is proposed with the target of long-term resource efficiency (RE). Particularly, GNNs learn relationships among different satellites from their connectivity information. Furthermore, multi-agent and multi-task mechanisms cooperatively train task offloading and resource allocation. Compared with benchmark solutions, GRANT not only achieves the highest RE with relatively low latency, but realizes the fewest trainable parameters and the shortest running time.