Yihuai Yang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Yihuai Yang has a total of 12 co-authors. Here are the top co-authors by number of shared publications:
- Bin Yang
Chuzhou University
3 shared publications - Eryk Dutkiewicz
University of Technology Sydney
3 shared publications - Shikai Shen
Dianchi College
3 shared publications - Tarik Taleb
Ruhr University Bochum
3 shared publications - Ying He
School of Electrical and Data Engineering, University of Technology Sydney, Sydney, NSW, Australia
3 shared publications Yumei She
Yunnan Minzu University
3 shared publications
Latest Publications
- 1 November 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 25 (11) , 20074-20087
Covert and Secure Transmissions for IRS-Enabled Wireless Communication Systems
- 1 November 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 25 (11) , 20074-20087
Covert and Secure Transmissions for IRS-Enabled Wireless Communication Systems
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Communications
- Vol. 74, 15253-15267
Hybrid Model-Based and Meta-Reinforcement Learning Optimization for STAR-RIS-Assisted V2X Communications
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Communications
- Vol. 74, 15253-15267
Hybrid Model-Based and Meta-Reinforcement Learning Optimization for STAR-RIS-Assisted V2X Communications
- 24 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Vehicular Technology
- Vol. 75 (5) , 7673-7687
Hybrid Resource Allocation in RIS-Assisted V2X Networks via Enhanced DRL
Efficient resource allocation is crucial for ensuring reliable and low-latency connectivity in vehicle-to-everything (V2X) communications. This study investigates a reconfigurable intelligent surface (RIS)-assisted V2X system, aiming to maximize the achievable downlink sum rate through the joint optimization of resource block (RB) indicators, power allocation, and RIS configuration under the constraints of quality of service (QoS) requirements, fairness, power limitations, and RIS design parameters. To achieve this, we propose a hybrid double deep Q-network (DDQN)-twin delayed deep deterministic policy gradient (TD3) resource allocation framework, named HDTA, which first derives analytical lower bounds and subsequently employs an event-triggered deep reinforcement learning (DRL) optimizer. These analytical results serve as both lower bounds and initial conditions for the DRL process. The DRL optimizer adopts a hierarchical DRL structure: RB indicators are optimized first using DDQN. The resulting RB allocation is then used as input for a second-stage optimization, where TD3 is applied for power allocation among assigned users, while a multi-agent DDQN concurrently optimizes the RIS configuration. This structured approach effectively reduces the action space, accelerates convergence, and enhances stability, leading to a more efficient resource allocation strategy. Simulation results demonstrate that our framework outperforms existing benchmark methods, achieving superior system sum rate performance.
- 24 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Vehicular Technology
- Vol. 75 (5) , 7673-7687
Hybrid Resource Allocation in RIS-Assisted V2X Networks via Enhanced DRL
Efficient resource allocation is crucial for ensuring reliable and low-latency connectivity in vehicle-to-everything (V2X) communications. This study investigates a reconfigurable intelligent surface (RIS)-assisted V2X system, aiming to maximize the achievable downlink sum rate through the joint optimization of resource block (RB) indicators, power allocation, and RIS configuration under the constraints of quality of service (QoS) requirements, fairness, power limitations, and RIS design parameters. To achieve this, we propose a hybrid double deep Q-network (DDQN)-twin delayed deep deterministic policy gradient (TD3) resource allocation framework, named HDTA, which first derives analytical lower bounds and subsequently employs an event-triggered deep reinforcement learning (DRL) optimizer. These analytical results serve as both lower bounds and initial conditions for the DRL process. The DRL optimizer adopts a hierarchical DRL structure: RB indicators are optimized first using DDQN. The resulting RB allocation is then used as input for a second-stage optimization, where TD3 is applied for power allocation among assigned users, while a multi-agent DDQN concurrently optimizes the RIS configuration. This structured approach effectively reduces the action space, accelerates convergence, and enhances stability, leading to a more efficient resource allocation strategy. Simulation results demonstrate that our framework outperforms existing benchmark methods, achieving superior system sum rate performance.
- 11 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Wireless Communications Letters
- Vol. 14 (10) , 3179-3183
Adaptive Resource Allocation in Covert V2X Systems via Multi-Agent DRL
This letter investigates adaptive resource allocation in a covert Vehicle-to-Everything (V2X) communication system comprising a Vehicle-to-Vehicle (V2V) pair, multiple wardens, and multiple cellular vehicular users. The goal is to maximize total system capacity while satisfying covertness, power, bandwidth, and latency constraints. The optimal detection threshold and total detection error probability for the warden are first derived analytically. To solve the resulting constrained optimization problem, a decentralized Adaptive Constraint-Aware Multi-Agent Deep Deterministic Policy Gradient (ACA-MADDPG) framework is proposed. Each agent independently learns transmit strategies using local observations and constraint feedback, enabling scalable deployment in dynamic environments. Simulation results verify that the proposed method outperforms DQN-and DDPG-based benchmarks in both capacity and reward convergence.
- 11 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Wireless Communications Letters
- Vol. 14 (10) , 3179-3183
Adaptive Resource Allocation in Covert V2X Systems via Multi-Agent DRL
This letter investigates adaptive resource allocation in a covert Vehicle-to-Everything (V2X) communication system comprising a Vehicle-to-Vehicle (V2V) pair, multiple wardens, and multiple cellular vehicular users. The goal is to maximize total system capacity while satisfying covertness, power, bandwidth, and latency constraints. The optimal detection threshold and total detection error probability for the warden are first derived analytically. To solve the resulting constrained optimization problem, a decentralized Adaptive Constraint-Aware Multi-Agent Deep Deterministic Policy Gradient (ACA-MADDPG) framework is proposed. Each agent independently learns transmit strategies using local observations and constraint feedback, enabling scalable deployment in dynamic environments. Simulation results verify that the proposed method outperforms DQN-and DDPG-based benchmarks in both capacity and reward convergence.
- 27 June 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 24 (11) , 12239-12251
Covert Communications for Intelligent Reflecting Surface-Enabled D2D Networks
In this paper, we explore covert communications in a device-to-device (D2D) network consisting of an intelligent reflecting surface (IRS), a base station, a cellular user, a D2D pair, and an adversary warden. With the help of the IRS, the D2D pair attempts to perform covert communication, while the warden also tries to detect the very existence of such a transmission. To investigate the covert performance under the scenario, we derive the detection error probability at Warden, the optimal detection threshold for minimizing the probability, and the transmission outage probabilities for D2D and cellular communications, respectively. We further jointly optimize the transmission powers of the cellular user and the D2D transmitter, the reflection phase shifts, and the amplitudes of the IRS reflecting elements to improve covert communication performance. Finally, we provide numerical results to reveal the impact of system parameters on the covert performance and also to exhibit the merits of IRS-enabled D2D networks for achieving covert communications.
- 27 June 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 24 (11) , 12239-12251
Covert Communications for Intelligent Reflecting Surface-Enabled D2D Networks
In this paper, we explore covert communications in a device-to-device (D2D) network consisting of an intelligent reflecting surface (IRS), a base station, a cellular user, a D2D pair, and an adversary warden. With the help of the IRS, the D2D pair attempts to perform covert communication, while the warden also tries to detect the very existence of such a transmission. To investigate the covert performance under the scenario, we derive the detection error probability at Warden, the optimal detection threshold for minimizing the probability, and the transmission outage probabilities for D2D and cellular communications, respectively. We further jointly optimize the transmission powers of the cellular user and the D2D transmitter, the reflection phase shifts, and the amplitudes of the IRS reflecting elements to improve covert communication performance. Finally, we provide numerical results to reveal the impact of system parameters on the covert performance and also to exhibit the merits of IRS-enabled D2D networks for achieving covert communications.
- Open Access
- 6 April 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 10 (17) , 15223-15237
Covert Rate Study for Full-Duplex D2D Communications Underlaid Cellular Networks
Device-to-device (D2D) communications underlaid cellular networks have emerged as a promising network architecture to provide extended coverage and high data rate for various Internet of Things (IoT) applications. However, because of the inherent openness and broadcasting nature of wireless communications, such networks face severe risks of data privacy disclosure. This paper investigates the covert communications in such networks for providing enhanced privacy protection. Specifically, this paper explores the critical covert rate performance in a full-duplex D2D communication underlaid cellular network consisting of a base station, a cellular user, a D2D pair with a transmitter and a full-duplex receiver, and a warden, where the D2D receiver can operate over either the full-duplex (FD) mode or the half-duplex (HD) mode. We first derive transmission outage probabilities of cellular and D2D links under the FD and HD modes, respectively. Based on these probabilities, we further provide theoretical modelling for the covert rate under each mode and explore the corresponding covert rate maximization by jointly optimizing the transmit powers of the D2D pair and the cellular user. To improve the covert rate performance, we propose a general mode in which the D2D receiver can flexibly switch between these two modes. Under the general mode, we also investigate the theoretical modelling and maximization problems of covert rate. Finally, we present extensive numerical results to illustrate the covert rate performances under the FD, HD, and general modes.
- 6 April 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 10 (17) , 15223-15237
Open AccessCovert Rate Study for Full-Duplex D2D Communications Underlaid Cellular Networks
Device-to-device (D2D) communications underlaid cellular networks have emerged as a promising network architecture to provide extended coverage and high data rate for various Internet of Things (IoT) applications. However, because of the inherent openness and broadcasting nature of wireless communications, such networks face severe risks of data privacy disclosure. This paper investigates the covert communications in such networks for providing enhanced privacy protection. Specifically, this paper explores the critical covert rate performance in a full-duplex D2D communication underlaid cellular network consisting of a base station, a cellular user, a D2D pair with a transmitter and a full-duplex receiver, and a warden, where the D2D receiver can operate over either the full-duplex (FD) mode or the half-duplex (HD) mode. We first derive transmission outage probabilities of cellular and D2D links under the FD and HD modes, respectively. Based on these probabilities, we further provide theoretical modelling for the covert rate under each mode and explore the corresponding covert rate maximization by jointly optimizing the transmit powers of the D2D pair and the cellular user. To improve the covert rate performance, we propose a general mode in which the D2D receiver can flexibly switch between these two modes. Under the general mode, we also investigate the theoretical modelling and maximization problems of covert rate. Finally, we present extensive numerical results to illustrate the covert rate performances under the FD, HD, and general modes.