open access publication

Article, 2024

Aerial STAR-RIS Empowered MEC: A DRL Approach for Energy Minimization

IEEE Wireless Communications Letters, ISSN 2162-2337, 2162-2345, Volume 13, 5, Pages 1409-1413, 10.1109/lwc.2024.3372623

Contributors

Aung, Pyae Sone 0000-0001-8331-6729 [1] Nguyen, Loc X 0000-0001-5911-5847 [1] Tun, Yan Kyaw 0000-0002-8557-0082 [2] Han, Zhu [1] [3] 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] University of Houston
    4. [NORA names: United States; America, North; OECD]

Abstract

Multi-access Edge Computing (MEC) addresses computational and battery limitations in devices by allowing them to offload computation tasks. To overcome the difficulties in establishing line-of-sight connections, integrating unmanned aerial vehicles (UAVs) has proven beneficial, offering enhanced data exchange, rapid deployment, and mobility. The utilization of reconfigurable intelligent surfaces (RIS), specifically simultaneously transmitting and reflecting RIS (STAR-RIS) technology, further extends coverage capabilities and introduces flexibility in MEC. This letter explores the integration of UAV and STAR-RIS to facilitate communication between IoT devices and an MEC server. The formulated problem aims to minimize energy consumption for IoT devices and aerial STAR-RIS by jointly optimizing task offloading, aerial STAR-RIS trajectory, amplitude and phase shift coefficients, and transmit power. Given the non-convexity of the problem and the dynamic environment, solving it directly within a polynomial time frame is challenging. Therefore, deep reinforcement learning (DRL), particularly proximal policy optimization (PPO), is introduced for its sample efficiency and stability. Simulation results illustrate the effectiveness of the proposed system compared to benchmark schemes in the literature.

Keywords

IoT, IoT devices, Multi-access Edge Computing, STAR-RIS, aerial vehicles, amplitude, approach, battery, battery limitations, capability, coefficient, communication, computational tasks, computer, connection, consumption, coverage, coverage capability, data exchange, deep reinforcement learning, deep reinforcement learning approach, deployment, devices, difficulties, dynamic environment, edge computing, effect, efficiency, energy, energy consumption, energy minimization, environment, exchange, flexibility, frame, integration, integration of unmanned aerial vehicles, intelligent surface, learning, letter, limitations, line-of-sight connection, literature, minimization, mobility, multi-access edge computing server, non-convex, offloading, offloading computation tasks, optimization, phase, phase shift coefficients, policy optimization, power, problem, proximal policy optimization, reconfigurable intelligent surface, reinforcement learning, results, samples, sampling efficiency, scheme, server, shift coefficients, simulation, simulation results, stability, surface, system, task, task offloading, time frame, trajectory, transmit power, unmanned aerial vehicles, utilization, vehicle

Funders

  • National Research Foundation of Korea
  • Ministry of Science and ICT

Data Provider: Digital Science

LINKS
-

Matching Records in NORA

SUBJECTS
+

METRICS
+