Ning Chen
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Ning Chen has a total of 42 co-authors. Here are the top co-authors by number of shared publications:
- Lianfen Huang
Xiamen University
12 shared publications - Xuwei Fan
Fujian Agriculture and Forestry University
11 shared publications - Zhipeng Cheng
Soochow University
9 shared publications - Yifeng Zhao
Xiamen University
8 shared publications - Bangzhen Huang
Xiamen University
7 shared publications - Honglong Chen
China University of Petroleum (East China)
7 shared publications
Latest Publications
- 1 November 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 13 (22) , 52888-52900
PhyARS: Physics-Aware Risk-Sensitive Mobility Management for Stateful Vehicular Edge Services
- 1 November 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 13 (22) , 52888-52900
PhyARS: Physics-Aware Risk-Sensitive Mobility Management for Stateful Vehicular Edge Services
- 1 November 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Vehicular Technology
- Vol. 75 (11) , 28349-28361
Q-TOP: Queue-Aware Task Offloading and Path Planning for Multi-UAV Assisted Vehicular Edge Computing Networks
- 1 November 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Vehicular Technology
- Vol. 75 (11) , 28349-28361
Q-TOP: Queue-Aware Task Offloading and Path Planning for Multi-UAV Assisted Vehicular Edge Computing Networks
- 12 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Vehicular Technology
- Vol. PP (00189545) , 1-12
An RSU-Assisted Trusted and Efficient Task Offloading Strategy for Vehicular Edge Computing
The rapid development of vehicles and communication technologies has resulted in a large number of delay sensitive and computation-intensive tasks for vehicular applications. Traditional cloud computing faces the problem of high transmission delay, while roadside unit (RSU)-based mobile edge computing faces the problem of high deployment cost and limited scalability. Collaborative computing among vehicles has emerged as an effective solution to meet the stringent requirements of delay-sensitive and computation-intensive tasks execution in Vehicular Edge Computing (VEC) network by utilizing the growing computing power of vehicles. However, the existence of untrustworthy nodes in the VEC network makes task offloading a security risk. Malicious vehicles can perform malicious behaviors such as invalid services, collusion attacks, and slander attacks, leading to a series of traffic safety issues. To ensure trusted task offloading between vehicles, in this paper, we first design a VEC system that jointly considers trust evaluation and task offloading with the assistance of the RSU. Specifically, a multi-feedback trust mechanism based on signature encryption and time decay is proposed, enabling the RSU to calculate global trust dynamically. After that, a multi-armed bandit-based dynamic trusted task offloading algorithm is developed to efficiently select trusted service vehicles for task processing. Extensive simulation results demonstrate that the proposed method achieves an effective balance between system delay and trust reliability, significantly enhancing the security and performance of the VEC network.
- 12 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Vehicular Technology
- Vol. PP (00189545) , 1-12
An RSU-Assisted Trusted and Efficient Task Offloading Strategy for Vehicular Edge Computing
The rapid development of vehicles and communication technologies has resulted in a large number of delay sensitive and computation-intensive tasks for vehicular applications. Traditional cloud computing faces the problem of high transmission delay, while roadside unit (RSU)-based mobile edge computing faces the problem of high deployment cost and limited scalability. Collaborative computing among vehicles has emerged as an effective solution to meet the stringent requirements of delay-sensitive and computation-intensive tasks execution in Vehicular Edge Computing (VEC) network by utilizing the growing computing power of vehicles. However, the existence of untrustworthy nodes in the VEC network makes task offloading a security risk. Malicious vehicles can perform malicious behaviors such as invalid services, collusion attacks, and slander attacks, leading to a series of traffic safety issues. To ensure trusted task offloading between vehicles, in this paper, we first design a VEC system that jointly considers trust evaluation and task offloading with the assistance of the RSU. Specifically, a multi-feedback trust mechanism based on signature encryption and time decay is proposed, enabling the RSU to calculate global trust dynamically. After that, a multi-armed bandit-based dynamic trusted task offloading algorithm is developed to efficiently select trusted service vehicles for task processing. Extensive simulation results demonstrate that the proposed method achieves an effective balance between system delay and trust reliability, significantly enhancing the security and performance of the VEC network.
- 10 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 13 (8) , 17658-17670
THUS: A Two-Phase Cross-Platform Hybrid User Recruitment Strategy in Mobile Crowdsensing
In recent years, the mobile crowdsensing (MCS) paradigm has enabled a diverse array of emerging sensing applications by harnessing the collective efforts of ubiquitous mobile users, who collaborate to carry out specific sensing tasks using smart devices. However, the majority of existing works concentrate on a single MCS platform, which struggles to accommodate diverse service requirements. Moreover, these existing studies either consider opportunistic users (OUs) or participatory users (PUs) for task execution, which leads to low task coverage or high recruitment costs while reducing the sensing quality of tasks. Therefore, in this article, we introduce a multiplatform scenario where OUs and PUs are combined to complement each other. Then, we formulate a multiplatform hybrid user recruitment (MPHUR) problem within the limited platform budget and user time budget (TB) and decompose it into two NP-hard subproblems. To maximize the total sensing quality of tasks, we propose a two-phase cross-platform hybrid user recruitment strategy called THUS. In the first phase, we present a greedy-based OU recruitment algorithm (GORA) to match the user–task pair iteratively with maximum sensing quality according to the shortage degree of PUs. In the second phase, the MCS platforms assign PUs to complete the tasks that OUs fail to cover based on their residual budget. We propose a multitask minimum-cost flow algorithm (MMCF) to recruit PUs for the remaining tasks. The extensive experiments are conducted on two real-world datasets to demonstrate the effectiveness of our proposed THUS.
- 10 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 13 (8) , 17658-17670
THUS: A Two-Phase Cross-Platform Hybrid User Recruitment Strategy in Mobile Crowdsensing
In recent years, the mobile crowdsensing (MCS) paradigm has enabled a diverse array of emerging sensing applications by harnessing the collective efforts of ubiquitous mobile users, who collaborate to carry out specific sensing tasks using smart devices. However, the majority of existing works concentrate on a single MCS platform, which struggles to accommodate diverse service requirements. Moreover, these existing studies either consider opportunistic users (OUs) or participatory users (PUs) for task execution, which leads to low task coverage or high recruitment costs while reducing the sensing quality of tasks. Therefore, in this article, we introduce a multiplatform scenario where OUs and PUs are combined to complement each other. Then, we formulate a multiplatform hybrid user recruitment (MPHUR) problem within the limited platform budget and user time budget (TB) and decompose it into two NP-hard subproblems. To maximize the total sensing quality of tasks, we propose a two-phase cross-platform hybrid user recruitment strategy called THUS. In the first phase, we present a greedy-based OU recruitment algorithm (GORA) to match the user–task pair iteratively with maximum sensing quality according to the shortage degree of PUs. In the second phase, the MCS platforms assign PUs to complete the tasks that OUs fail to cover based on their residual budget. We propose a multitask minimum-cost flow algorithm (MMCF) to recruit PUs for the remaining tasks. The extensive experiments are conducted on two real-world datasets to demonstrate the effectiveness of our proposed THUS.
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Network Science and Engineering
- Vol. 13, 10479-10495
Digital Twin-Assisted Resource Allocation in ISCC-Enabled IoV: When DRL Meets LLMs
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Network Science and Engineering
- Vol. 13, 10479-10495
Digital Twin-Assisted Resource Allocation in ISCC-Enabled IoV: When DRL Meets LLMs
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Vehicular Technology
- Vol. 75 (6) , 11634-11646
Dependency-Aware and Energy Efficient Task Offloading in Vehicular Edge Computing Systems
The development of Artificial Intelligence and Internet of Things has not only paved the way to realize real-time intelligent tasks in vehicular edge computing systems, but also caused a series of problems such as system overload. Task offloading based on edge-terminal cooperation is one of the efficient paradigms to solve these problems. However, the dependency between the subtasks in vehicular intelligent tasks, as well as the resource shortage of terminal vehicles and edge servers, all pose serious challenges to efficient task offloading. In this paper, we investigate the optimization problem of task offloading in vehicular edge computing systems with the consideration of the above challenges, aiming to minimize the system consumption including processing delay and energy consumption, and prove it as a mixed integer nonlinear and NP-hard problem. To address this problem, we construct directed acyclic graphs to represent the complex dependency between the subtasks and utilize pipeline diagrams to calculate the task processing delay. Then, an efficient Dependency-aware and Energy efficient task offloading schedule DESR is proposed, which utilizes a cyclic iterative method to decouple the problem into sub-problems and introduces multi-layer activity on edge networks and the interior point method to jointly optimize offloading Selection and Resource allocation. Extensive simulations are conducted to evaluate the proposed DESR, and the results illustrate its superior performance.
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Vehicular Technology
- Vol. 75 (6) , 11634-11646
Dependency-Aware and Energy Efficient Task Offloading in Vehicular Edge Computing Systems
The development of Artificial Intelligence and Internet of Things has not only paved the way to realize real-time intelligent tasks in vehicular edge computing systems, but also caused a series of problems such as system overload. Task offloading based on edge-terminal cooperation is one of the efficient paradigms to solve these problems. However, the dependency between the subtasks in vehicular intelligent tasks, as well as the resource shortage of terminal vehicles and edge servers, all pose serious challenges to efficient task offloading. In this paper, we investigate the optimization problem of task offloading in vehicular edge computing systems with the consideration of the above challenges, aiming to minimize the system consumption including processing delay and energy consumption, and prove it as a mixed integer nonlinear and NP-hard problem. To address this problem, we construct directed acyclic graphs to represent the complex dependency between the subtasks and utilize pipeline diagrams to calculate the task processing delay. Then, an efficient Dependency-aware and Energy efficient task offloading schedule DESR is proposed, which utilizes a cyclic iterative method to decouple the problem into sub-problems and introduces multi-layer activity on edge networks and the interior point method to jointly optimize offloading Selection and Resource allocation. Extensive simulations are conducted to evaluate the proposed DESR, and the results illustrate its superior performance.
- 29 November 2025
- Published by Elsevier in Computer Networks
- Vol. 275
Joint optimization of service placement, task offloading and resource allocation for dependent subtasks in hierarchical edge computing systems
- 29 November 2025
- Published by Elsevier in Computer Networks
- Vol. 275
Joint optimization of service placement, task offloading and resource allocation for dependent subtasks in hierarchical edge computing systems
- 4 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 13 (1) , 637-649
Collaborative Offloading for Interacting Users in Cloud–Edge–Terminal Networks
The rapid growth of Internet of Things devices has led to an increase in computation-intensive and latency-sensitive tasks, making traditional cloud computing insufficient. Cloud–edge–terminal collaboration can enhance offload efficiency by optimizing processing latency, energy consumption, and price cost. However, in real-world networks, computational results often need to be transmitted to multiple users, increasing the offloading complexity. This article proposes a three-tier collaborative offloading architecture for interacting users, considering constraints such as service caching and various types of resources. The optimization problem of computation latency and price cost is modeled as a Markov decision process. To address the problem, we propose a deep reinforcement learning algorithm based on the soft actor–critic framework. Given the discrete-continuous hybrid action space, the algorithm incorporates a dual-head mechanism. After that, transfer learning is incorporated into the training strategy to improve adaptability in dynamic environments. The simulation results demonstrate that the proposed approach outperforms existing performance, convergence, and adaptability methods.
- 4 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 13 (1) , 637-649
Collaborative Offloading for Interacting Users in Cloud–Edge–Terminal Networks
The rapid growth of Internet of Things devices has led to an increase in computation-intensive and latency-sensitive tasks, making traditional cloud computing insufficient. Cloud–edge–terminal collaboration can enhance offload efficiency by optimizing processing latency, energy consumption, and price cost. However, in real-world networks, computational results often need to be transmitted to multiple users, increasing the offloading complexity. This article proposes a three-tier collaborative offloading architecture for interacting users, considering constraints such as service caching and various types of resources. The optimization problem of computation latency and price cost is modeled as a Markov decision process. To address the problem, we propose a deep reinforcement learning algorithm based on the soft actor–critic framework. Given the discrete-continuous hybrid action space, the algorithm incorporates a dual-head mechanism. After that, transfer learning is incorporated into the training strategy to improve adaptability in dynamic environments. The simulation results demonstrate that the proposed approach outperforms existing performance, convergence, and adaptability methods.
- 8 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Services Computing
- Vol. 18 (5) , 3079-3092
Privacy-Aware Joint DNN Model Deployment and Partitioning Optimization for Collaborative Edge Inference Services
Edge inference (EI) has emerged as a promising paradigm to address the growing limitations of cloud-based Deep Neural Network (DNN) inference services, such as high response latency, limited scalability, and severe data privacy exposure. However, deploying DNN models on resource-constrained edge devices introduces additional challenges, including limited computation/storage resources, dynamic service demands, and heightened privacy risks. To address these challenges, this paper presents a novel privacy-aware optimization framework that jointly tackles DNN model deployment, user-server association, and model partitioning, aiming to minimize long-term average inference delay under resource and privacy constraints. We formulate the problem as a complex, NP-hard stochastic optimization problem, emphasizing its inherent complexity. To efficiently handle system dynamics and computational complexity, we adopt a Lyapunov-based approach to transform the long-term objective into tractable per-slot decisions. Additionally, we introduce a coalition formation game model to facilitate adaptive user-server association, and design a greedy algorithm for model deployment within each coalition. Extensive simulations demonstrate that the proposed algorithm significantly reduces inference delay while consistently satisfying privacy constraints, outperforming baselines across diverse scenarios.
- 8 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Services Computing
- Vol. 18 (5) , 3079-3092
Privacy-Aware Joint DNN Model Deployment and Partitioning Optimization for Collaborative Edge Inference Services
Edge inference (EI) has emerged as a promising paradigm to address the growing limitations of cloud-based Deep Neural Network (DNN) inference services, such as high response latency, limited scalability, and severe data privacy exposure. However, deploying DNN models on resource-constrained edge devices introduces additional challenges, including limited computation/storage resources, dynamic service demands, and heightened privacy risks. To address these challenges, this paper presents a novel privacy-aware optimization framework that jointly tackles DNN model deployment, user-server association, and model partitioning, aiming to minimize long-term average inference delay under resource and privacy constraints. We formulate the problem as a complex, NP-hard stochastic optimization problem, emphasizing its inherent complexity. To efficiently handle system dynamics and computational complexity, we adopt a Lyapunov-based approach to transform the long-term objective into tractable per-slot decisions. Additionally, we introduce a coalition formation game model to facilitate adaptive user-server association, and design a greedy algorithm for model deployment within each coalition. Extensive simulations demonstrate that the proposed algorithm significantly reduces inference delay while consistently satisfying privacy constraints, outperforming baselines across diverse scenarios.
- 10 February 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Vehicular Technology Magazine
- Vol. 20 (2) , 83-94
Generative artificial intelligence-oriented synthetic network: Toward Integrated Fine-Tuning and Inference When Generative Artificial Intelligence Meets Edge Intelligence in the Intelligent Internet of Vehicles
Generative artificial intelligence (GAI) and edge intelligence (EI) are driving the evolution of traditional vehicular networks toward the intelligent Internet of Vehicles (IIoV) by providing foundational and personalized knowledge. However, their inherently contradictory characteristics present significant challenges to direct knowledge sharing. Furthermore, conventional methods that independently optimize fine-tuning and inference lack the foresight to achieve long-term network benefits. To address these challenges, we propose the GAI-oriented synthetic network (GaisNet), a collaborative cloud-edge-end intelligence framework that integrates fine-tuning and inference. GaisNet, specifically, can mitigate contradictions by leveraging data-free knowledge relays, where bidirectional knowledge flow facilitates a virtuous cycle of model fine-tuning and task inference with a long-term perspective, fostering mutualism between GAI and EI in the IIoV. A case study illustrates the effectiveness of the proposed mechanisms. Finally, we discuss the future challenges and directions in the interplay between GAI and EI.
- 10 February 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Vehicular Technology Magazine
- Vol. 20 (2) , 83-94
Generative artificial intelligence-oriented synthetic network: Toward Integrated Fine-Tuning and Inference When Generative Artificial Intelligence Meets Edge Intelligence in the Intelligent Internet of Vehicles
Generative artificial intelligence (GAI) and edge intelligence (EI) are driving the evolution of traditional vehicular networks toward the intelligent Internet of Vehicles (IIoV) by providing foundational and personalized knowledge. However, their inherently contradictory characteristics present significant challenges to direct knowledge sharing. Furthermore, conventional methods that independently optimize fine-tuning and inference lack the foresight to achieve long-term network benefits. To address these challenges, we propose the GAI-oriented synthetic network (GaisNet), a collaborative cloud-edge-end intelligence framework that integrates fine-tuning and inference. GaisNet, specifically, can mitigate contradictions by leveraging data-free knowledge relays, where bidirectional knowledge flow facilitates a virtuous cycle of model fine-tuning and task inference with a long-term perspective, fostering mutualism between GAI and EI in the IIoV. A case study illustrates the effectiveness of the proposed mechanisms. Finally, we discuss the future challenges and directions in the interplay between GAI and EI.