TY - JOUR
T1 - Aerial STAR-RIS Empowered MEC
T2 - A DRL Approach for Energy Minimization
AU - Aung , Pyae Sone
AU - Nguyen, Xuan Loc
AU - Tun, Yan Kyaw
AU - Han, Zhu
AU - Hong, Choong Seon
PY - 2024/5
Y1 - 2024/5
N2 - 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.
AB - 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.
KW - Reconfigurable intelligent surface (RIS)
KW - STAR-RIS
KW - deep reinforcement learning (DRL)
KW - multi-access edge computing (MEC)
KW - proximal policy optimization (PPO)
KW - simultaneous transmission and reflection
KW - unmanned aerial vehicle (UAV)
UR - http://www.scopus.com/inward/record.url?scp=85187338501&partnerID=8YFLogxK
U2 - 10.1109/LWC.2024.3372623
DO - 10.1109/LWC.2024.3372623
M3 - Journal article
SN - 2162-2337
VL - 13
SP - 1409
EP - 1413
JO - I E E E Wireless Communications Letters
JF - I E E E Wireless Communications Letters
IS - 5
M1 - 10458888
ER -