open access publication

Article, 2024

SpaceRIS: LEO Satellite Coverage Maximization in 6G Sub-THz Networks by MAPPO DRL and Whale Optimization

IEEE Journal on Selected Areas in Communications, ISSN 1558-0008, 0733-8716, Volume 42, 5, Pages 1262-1278, 10.1109/jsac.2024.3369665

Contributors

Hassan, Salman 0000-0002-5317-6494 [1] Park, Yu Min 0000-0001-8836-4500 [1] Tun, Yan Kyaw 0000-0002-8557-0082 [2] Saad, Walid S 0000-0003-2247-2458 [3] Han, Zhu [1] [4] Hong, Choong-Seong 0000-0003-3484-7333 (Corresponding author) [1]

Affiliations

  1. [1] Kyung Hee University
    2. [NORA names: South Korea; Asia, East; OECD];
  2. [2] Aalborg University
    3. [NORA names: AAU Aalborg University; University; Denmark; Europe, EU; Nordic; OECD];
  3. [3] Virginia Tech
    4. [NORA names: United States; America, North; OECD];
  4. [4] University of Houston
    5. [NORA names: United States; America, North; OECD]

Abstract

Satellite systems face a significant challenge in effectively utilizing limited communication resources to meet the demands of ground network traffic, characterized by asymmetrical spatial distribution and time-varying characteristics. Moreover, the coverage range and signal transmission distance of low Earth orbit (LEO) satellites are restricted by notable propagation attenuation, molecular absorption, and space losses in sub-terahertz (THz) frequencies. This paper introduces a novel approach to maximize LEO satellite coverage by leveraging reconfigurable intelligent surface (RIS) within 6G sub-THz networks. Optimization objectives include improving end-to-end (E2E) data rate, optimizing satellite-remote user equipment (RUE) associations, data packet routing within satellite constellations, RIS phase shift, and ground base station (GBS) transmit power (i.e., active beamforming). The formulated joint optimization problem poses significant challenges because of its time-varying environment, non-convex characteristics, and NP-hard complexity. To address these challenges, we propose a block coordinate descent (BCD) algorithm that integrates balanced K-means clustering, multi-agent proximal policy optimization (MAPPO) deep reinforcement learning (DRL), and whale optimization algorithm (WOA) techniques. The performance of the proposed approach is demonstrated through comprehensive simulation results, demonstrating its superiority over existing baseline methods in the literature.

Keywords

E2E, Earth orbit, K-means clustering, NP-hard complexity, RIS phase shifts, RUE, Satellite System, THz, absorption, algorithm, association, asymmetric spatial distribution, attenuation, base station, baseline, baseline methods, block, block coordinate descent, challenges, characteristics, clusters, communication, communication resources, complex, comprehensive simulation results, constellation, coordinate descent, coverage, coverage maximization, data, data rate, deep reinforcement learning, descent, distribution, end-to-end (E2E, environment, equipment, frequency, ground, ground base station, intelligent surface, joint optimization problem, learning, leverage reconfigurable intelligent surface, literature, loss, low Earth orbit, maximization, method, molecular absorption, multi-agent proximal policy optimization, network, network traffic, non-convex characteristics, objective, optimization, optimization algorithm, optimization objectives, optimization problem, orbit, packet routing, performance, phase shift, policy optimization, power, problem, propagation, propagation attenuation, proximal policy optimization, range, rate, reconfigurable intelligent surface, reinforcement learning, resources, results, route, satellite, satellite constellation, satellite coverage, shift, signal, signal transmission distance, simulation results, space, space loss, spatial distribution, stations, sub-terahertz, superiority, surface, system, technique, time-varying characteristics, time-varying environment, traffic, transmit power, user equipment, whale optimization, whale optimization algorithm, whales

Funders

  • Directorate for Computer & Information Science & Engineering
  • Ministry of Education
  • Directorate for Engineering
  • United States Department of Transportation
  • National Research Foundation of Korea
  • Ministry of Science and ICT

Data Provider: Digital Science

LINKS
-

Matching Records in NORA

SUBJECTS
+

METRICS
+