Junshen Chen
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Junshen Chen has a total of 4 co-authors. Here are the top co-authors by number of shared publications:
- Huiyi Ding
Department of Electrical and Electronic Engineering, The University of Hong Kong, Pokfulam, Hong Kong
1 shared publication Qihao Yuan
School of Mathematical Sciences, Shenzhen University, Shenzhen, China
1 shared publication- Shiyao Zhang
School of Advanced Engineering, Great Bay University, Dongguan City, China
1 shared publication - Xingzheng Zhu
Institute of Applied Artificial Intelligence of the Guangdong-Hong Kong-Macao Greater Bay Area, Undergraduate School of Artificial Intelligence, Shenzhen Polytechnic University, Shenzhen 518055, China
1 shared publication
Latest Publications
- 30 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Communications Letters
- Vol. 28 (11) , 2568-2572
Low-Latency NOMA-Enabled Vehicle Platoon Resource Allocation Scheme: A Deep Deterministic Policy Gradient-Based Approach
Non-orthogonal multiple access (NOMA) techniques are widely used to increase quality-of-experience and network performance requirements in vehicle-to-everything (V2X) communication. However, dynamic vehicular communication conditions lead to the base station (BS) with limited knowledge about perfect channel state information (CSI), which incurs a challenging problem on spectrum resource allocation for complex communication systems with multiple transmission links. In particular, unstable communication of high-mobility vehicles degrades the performance of NOMA-V2X networks. To address these difficulties, this paper proposes a resource allocation scheme for vehicular communication to comprehensively consider user scheduling and power allocation, whereas it considers the channel fading in time-varying networks. By satisfying the constraints on the transmission power and rate of each user, the formulated problem aims to minimize the total system delay. To effectively solve the formulated problem, a deep deterministic policy gradient (DDPG) is deployed to find the solutions of the proposed scheme. Simulation results show that the proposed algorithm significantly outperforms the baseline in terms of both delay and convergence stability while satisfying realistic V2X constraints.
- 30 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Communications Letters
- Vol. 28 (11) , 2568-2572
Low-Latency NOMA-Enabled Vehicle Platoon Resource Allocation Scheme: A Deep Deterministic Policy Gradient-Based Approach
Non-orthogonal multiple access (NOMA) techniques are widely used to increase quality-of-experience and network performance requirements in vehicle-to-everything (V2X) communication. However, dynamic vehicular communication conditions lead to the base station (BS) with limited knowledge about perfect channel state information (CSI), which incurs a challenging problem on spectrum resource allocation for complex communication systems with multiple transmission links. In particular, unstable communication of high-mobility vehicles degrades the performance of NOMA-V2X networks. To address these difficulties, this paper proposes a resource allocation scheme for vehicular communication to comprehensively consider user scheduling and power allocation, whereas it considers the channel fading in time-varying networks. By satisfying the constraints on the transmission power and rate of each user, the formulated problem aims to minimize the total system delay. To effectively solve the formulated problem, a deep deterministic policy gradient (DDPG) is deployed to find the solutions of the proposed scheme. Simulation results show that the proposed algorithm significantly outperforms the baseline in terms of both delay and convergence stability while satisfying realistic V2X constraints.