Jiyun Zhang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Jiyun Zhang has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
- Quyuan Luo
Key Laboratory of Information Coding and Transmission, CSNMT Int Coop. Res. Centre, Southwest Jiaotong University, Chengdu, China
3 shared publications - Dongping Zheng
Information Coding and Transmission Key Laboratory of Sichuan Province, Czech Society for New Materials and Technologies International Cooperation Research Center, Southwest Jiaotong University, Chengdu, China
2 shared publications - Zheng Ma
Southwest Jiaotong University
2 shared publications - Erdal Panayirci
Kadir Has University
1 shared publication - Pingzhi Fan
Southwest Jiaotong University
1 shared publication - Shihong Hu
Key Laboratory of Water Big Data Technology of Ministry of Water Resources, Hohai University, Nanjing, China
1 shared publication
Latest Publications
- 15 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Vehicular Technology
- Vol. 75 (4) , 6630-6644
High- and Low-Frequency Cooperation Based Resource Allocation in Vehicular Edge Computing via Deep Reinforcement Learning
In vehicular edge computing (VEC) environment, the increasing task offloading requirements from diverse vehicular applications pose significant challenges to the limited and single communication resources. High- and low-frequency cooperation (HL-FC) has the advantages of large capacity, low latency, large coverage capability, and stable communication link during task offloading. However, how to efficiently allocate communication resources for task offloading in the presence of high- and low-frequency communication resources is a challenge. Furthermore, coupled with the allocation of computing resources and the offloading-decision making, the allocation of high- and low-frequency communication resources is even more complex and challenging. To cope with these challenges, in this paper, we investigate the resource allocation scheme under the high- and low-frequency cooperation in VEC. Specifically, to facilitate the processing of latency-sensitive and computation-intensive tasks, a multi-queue model for task caching is first designed to prioritize latency-sensitive workloads, enabling efficient data buffering and processing. Considering vehicle mobility, we then develop the communication model, task migration model, and the computing model. After that, we formulate a long-term average cost optimization problem that jointly optimizes resource expenditure and latency, which is a NP-hard problem. To obtain the optimal strategy, we leverage the Markov decision process (MDP) to model the optimization problem, which is then solved by our proposed twin delayed deep deterministic policy gradient (TD3)-based two-phase resource allocation scheme (TTRAS). Finally, extensive simulations are conducted to assess and validate the effectiveness of the TTRAS.
- 15 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Vehicular Technology
- Vol. 75 (4) , 6630-6644
High- and Low-Frequency Cooperation Based Resource Allocation in Vehicular Edge Computing via Deep Reinforcement Learning
In vehicular edge computing (VEC) environment, the increasing task offloading requirements from diverse vehicular applications pose significant challenges to the limited and single communication resources. High- and low-frequency cooperation (HL-FC) has the advantages of large capacity, low latency, large coverage capability, and stable communication link during task offloading. However, how to efficiently allocate communication resources for task offloading in the presence of high- and low-frequency communication resources is a challenge. Furthermore, coupled with the allocation of computing resources and the offloading-decision making, the allocation of high- and low-frequency communication resources is even more complex and challenging. To cope with these challenges, in this paper, we investigate the resource allocation scheme under the high- and low-frequency cooperation in VEC. Specifically, to facilitate the processing of latency-sensitive and computation-intensive tasks, a multi-queue model for task caching is first designed to prioritize latency-sensitive workloads, enabling efficient data buffering and processing. Considering vehicle mobility, we then develop the communication model, task migration model, and the computing model. After that, we formulate a long-term average cost optimization problem that jointly optimizes resource expenditure and latency, which is a NP-hard problem. To obtain the optimal strategy, we leverage the Markov decision process (MDP) to model the optimization problem, which is then solved by our proposed twin delayed deep deterministic policy gradient (TD3)-based two-phase resource allocation scheme (TTRAS). Finally, extensive simulations are conducted to assess and validate the effectiveness of the TTRAS.
- 26 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Vehicular Technology
- Vol. 75 (3) , 5071-5084
Task Classification Based Resource Allocation in Parked Vehicle Assisted Vehicle Edge Computing: A Deep Reinforcement Learning Approach
With the development of the Internet of Vehicles (IoV), Vehicular Edge Computing (VEC) is proposed and widely studied as a solution to solve the problem that in-vehicle applications need a lot of computing resources to maintain operation. However, the computing resources of edge servers in VEC are limited compared to cloud servers. To improve computational efficiency, more accurate computational strategies need to be provided for different types of tasks, and available computing resources should also be fully explored. In this paper, we first construct a multi-vehicle VEC offloading model that takes into account the computing resources of parked vehicles. Considering different execution time and energy consumption constraints of tasks, we then classify tasks into different types, to make more appropriate decisions. After that, an optimization problem is formulated to minimize the average weighted cost of time slots. We leverage the Markov Decision Process (MDP) to model the optimization problem. To solve this problem, we propose a value decomposition network based task offloading and resource allocation algorithm (VDNBA), so that each vehicle can independently make its partial offloading decision and computing resources allocation strategy. Eventually, extensive simulations with comparative benchmarks are conducted to evaluate the effectiveness of our proposed algorithm.
- 26 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Vehicular Technology
- Vol. 75 (3) , 5071-5084
Task Classification Based Resource Allocation in Parked Vehicle Assisted Vehicle Edge Computing: A Deep Reinforcement Learning Approach
With the development of the Internet of Vehicles (IoV), Vehicular Edge Computing (VEC) is proposed and widely studied as a solution to solve the problem that in-vehicle applications need a lot of computing resources to maintain operation. However, the computing resources of edge servers in VEC are limited compared to cloud servers. To improve computational efficiency, more accurate computational strategies need to be provided for different types of tasks, and available computing resources should also be fully explored. In this paper, we first construct a multi-vehicle VEC offloading model that takes into account the computing resources of parked vehicles. Considering different execution time and energy consumption constraints of tasks, we then classify tasks into different types, to make more appropriate decisions. After that, an optimization problem is formulated to minimize the average weighted cost of time slots. We leverage the Markov Decision Process (MDP) to model the optimization problem. To solve this problem, we propose a value decomposition network based task offloading and resource allocation algorithm (VDNBA), so that each vehicle can independently make its partial offloading decision and computing resources allocation strategy. Eventually, extensive simulations with comparative benchmarks are conducted to evaluate the effectiveness of our proposed algorithm.
- 5 February 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Vehicular Technology
- Vol. 74 (6) , 9476-9490
Joint Task Migration and Resource Allocation in Vehicular Edge Computing: A Deep Reinforcement Learning-Based Approach
With the rise of the Internet of Vehicles (IoV), a growing number of in-vehicle applications have been developed, significantly enhancing the driving experience, while simultaneously imposing excessive higher demands on computing resources. Vehicle Edge Computing (VEC) emerges as a promising solution by offloading computational tasks to edge servers positioned near vehicles. However, the limited computing capacity of these edge servers necessitates the efficient allocation of resources to adequately meet the demands of all vehicles. In this paper, we introduce a multi-vehicle VEC offloading framework that considers both the execution time of tasks and the costs incurred when utilizing edge server resources and transmitting tasks between Roadside Units (RSUs). Building on this framework, we design an optimization problem to minimize the average weighted cost, modeled as a Markov Decision Process (MDP). To address this, we propose a DDPG-based Resource Allocation and Offloading Decision Algorithm (DRAODA). This algorithm enables the control center to generate resource allocation strategies while allowing individual vehicles to make task offloading decisions independently, based solely on their own data and the edge server's status, without relying on information from other vehicles. Additionally, we propose an Optimal Task Offloading Destination Selection Algorithm (OTODSA) to further minimize the average weighted cost, enhancing the overall efficiency and effectiveness of the resource allocation process.
- 5 February 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Vehicular Technology
- Vol. 74 (6) , 9476-9490
Joint Task Migration and Resource Allocation in Vehicular Edge Computing: A Deep Reinforcement Learning-Based Approach
With the rise of the Internet of Vehicles (IoV), a growing number of in-vehicle applications have been developed, significantly enhancing the driving experience, while simultaneously imposing excessive higher demands on computing resources. Vehicle Edge Computing (VEC) emerges as a promising solution by offloading computational tasks to edge servers positioned near vehicles. However, the limited computing capacity of these edge servers necessitates the efficient allocation of resources to adequately meet the demands of all vehicles. In this paper, we introduce a multi-vehicle VEC offloading framework that considers both the execution time of tasks and the costs incurred when utilizing edge server resources and transmitting tasks between Roadside Units (RSUs). Building on this framework, we design an optimization problem to minimize the average weighted cost, modeled as a Markov Decision Process (MDP). To address this, we propose a DDPG-based Resource Allocation and Offloading Decision Algorithm (DRAODA). This algorithm enables the control center to generate resource allocation strategies while allowing individual vehicles to make task offloading decisions independently, based solely on their own data and the edge server's status, without relying on information from other vehicles. Additionally, we propose an Optimal Task Offloading Destination Selection Algorithm (OTODSA) to further minimize the average weighted cost, enhancing the overall efficiency and effectiveness of the resource allocation process.