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

TL;DR

This paper proposes a GNN-based deep reinforcement learning algorithm for efficient joint resource allocation and task offloading in TeraHertz space networks, addressing the NP-hard optimization challenge.

Contribution

It introduces the GRANT algorithm that leverages GNNs and multi-agent DRL to optimize resource use and task offloading in Tera-SpaceCom, a novel approach in this domain.

Findings

Achieves highest resource efficiency among benchmarks.

Reduces latency compared to existing solutions.

Uses fewer trainable parameters and runs faster.

Abstract

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.