RIS-empowered MEC for URLLC systems with digital-twin-driven architecture

Kurma, S., Katwe, M., Singh, K., Pan, C., Mumtaz, S. ORCID: 0000-0001-6364-6149 and Li, C.-P., 2023. RIS-empowered MEC for URLLC systems with digital-twin-driven architecture. IEEE Transactions on Communications. ISSN 0090-6778

1837146_Mumtaz.pdf - Post-print

Download (4MB) | Preview


This paper investigates a digital twin (DT) and reconfigurable intelligent surface (RIS)-aided mobile edge computing (MEC) system under given constraints on ultra-reliable low latency communication (URLLC). In particular, we focus on the problem of total end-to-end (E2E) latency minimization for the considered system under the joint optimization of beamforming design at the RIS, power, bandwidth allocation, processing rates, and task offloading parameters using DT architecture. To tackle the formulated non-convex optimization problem, we first model it as a Markov decision process (MDP). Later, we adopt deep deterministic policy gradient (DDPG) based deep reinforcement learning (DRL) algorithm to solve it effectively. We have compared the DDPG results with proximal policy optimization (PPO), modified PPO (M-PPO), and conventional alternating optimization (AO) algorithms. Simulation results depict that the proposed DT-enabled resource allocation scheme for the RIS-empowered MEC network using DDPG algorithm achieves up to 60% lower transmission delay and 20% lower energy consumption compared to the scheme without an RIS. This confirms the practical advantages of leveraging RIS technology in MEC systems. Results demonstrate that DDPG outperforms M-PPO and PPO in terms of higher reward value and better learning efficiency, while M-PPO and PPO exhibit lower execution time than DDPG and AO due to their advanced policy optimization techniques. Thus, the results validate the effectiveness of the DRL solutions over AO for dynamic resource allocation w.r.t. reduced execution time.

Item Type: Journal article
Publication Title: IEEE Transactions on Communications
Creators: Kurma, S., Katwe, M., Singh, K., Pan, C., Mumtaz, S. and Li, C.-P.
Publisher: Institute of Electrical and Electronics Engineers
Date: 16 November 2023
ISSN: 0090-6778
Rights: © 2023 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Divisions: Schools > School of Science and Technology
Record created by: Jonathan Gallacher
Date Added: 20 Nov 2023 16:18
Last Modified: 20 Nov 2023 16:18
URI: https://irep.ntu.ac.uk/id/eprint/50403

Actions (login required)

Edit View Edit View


Views per month over past year


Downloads per month over past year