Related Experiment Video
Updated: Jun 13, 2026
07:49
Automated Deployment of an Internet Protocol Telephony Service on Unmanned Aerial Vehicles Using Network Functions Virtualization
Published on: November 26, 2019
Deep Reinforcement Learning for Secure and Low-Latency Communications in UAV-Mounted STAR-RIS Assisted Urban
Jian Tang1,2, Jun Yuan1, Hu Zhao1
1School of Artificial Intelligence, Shaoyang Industry Polytechnic College, Shaoyang 422000, China.
Sensors (Basel, Switzerland)
|June 12, 2026
Summary
This study introduces a novel Hierarchical Constrained Soft Actor-Critic (HC-SAC) algorithm for secure and low-latency communications in urban vehicular networks using UAV-mounted reconfigurable intelligent surfaces. The HC-SAC algorithm optimizes UAV trajectory, STAR-RIS configuration, and power control for enhanced performance.
Area of Science:
- Wireless Communications
- Intelligent Transportation Systems
- Optimization Theory
- Artificial Intelligence
Background:
- Urban vehicular networks face challenges including severe blockage, high mobility, and eavesdropping threats, impacting delay-sensitive services.
- Simultaneously Transmitting and Reflecting Reconfigurable Intelligent Surfaces (STAR-RIS) offer potential for enhanced wireless communication environments.
- Unmanned Aerial Vehicles (UAVs) can serve as mobile platforms and intelligent controllers to dynamically adapt to network conditions.
Purpose of the Study:
- To develop a secure and low-latency communication system model for UAV-STAR-RIS-assisted urban vehicular networks.
- To formulate a dynamic optimization problem for maximizing long-term average secure and low-latency utility.
- To propose an adaptive joint control algorithm for UAV trajectory, STAR-RIS configuration, and power allocation.
Main Methods:
- A system model is developed considering urban blockage, vehicle mobility, eavesdropping, queueing dynamics, and UAV flight constraints.
- The problem is formulated as a high-dimensional, non-convex dynamic optimization problem.
- A Hierarchical Constrained Soft Actor-Critic (HC-SAC) algorithm is proposed, modeling the problem as a Markov decision process.
Main Results:
- The proposed HC-SAC algorithm demonstrates superior performance compared to DDPG and PPO in terms of average delay and secrecy outage probability.
- HC-SAC achieves an average delay of 10.85 slots and a secrecy outage probability of 0.7160.
- A normalized composite utility analysis shows HC-SAC attains the highest utility value (0.9254), indicating a favorable security-latency trade-off.
Conclusions:
- The HC-SAC algorithm effectively enables adaptive UAV movement, STAR-RIS configuration, and power control in complex dynamic urban vehicular environments.
- The proposed approach provides a competitive balance between secure communication capability and service reliability.
- This research offers a promising solution for enhancing the performance of future intelligent transportation systems.
