Article
Automation & Control Systems
Yueyue Dai, Ke Zhang, Sabita Maharjan, Yan Zhang
Summary: The rapid development of IIoT requires industrial production to move towards digitalization for improved network efficiency. Utilizing technologies like Digital Twin and computation offloading can help optimize resources and enhance data processing efficiency in IIoT systems.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2021)
Article
Engineering, Electrical & Electronic
Clement Ruah, Osvaldo Simeone, Bashir M. Al-Hashimi
Summary: Digital twin platforms are increasingly used in manufacturing and aerospace sectors for controlling, monitoring, and analyzing software-based communication systems. This paper proposes a Bayesian framework to address the challenge of model uncertainty in digital twin systems and enables core functionalities such as control and monitoring through multi-agent reinforcement learning.
IEEE JOURNAL ON SELECTED AREAS IN COMMUNICATIONS
(2023)
Article
Automation & Control Systems
Yunlong Lu, Xiaohong Huang, Ke Zhang, Sabita Maharjan, Yan Zhang
Summary: The article introduces digital twin wireless networks (DTWN) and a blockchain empowered federated learning framework for collaborative computing and enhanced data privacy in industrial Internet of Things. By jointly considering digital twin association, training data batch size, and bandwidth allocation, an optimization problem is formulated and solved using multiagent reinforcement learning to find the optimal solution.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2021)
Article
Engineering, Civil
Xiaoming Yuan, Jiahui Chen, Ning Zhang, Jianbing Ni, Fei Richard Yu, Victor C. M. Leung
Summary: This paper proposes a Digital Twin-Driven Vehicular Task Offloading and IRS Configuration Framework (DTVIF) to efficiently monitor, learn, and manage the Internet of Vehicles (IoV) by utilizing Mobile Edge Computing (MEC) and Intelligent Reflective Surface (IRS). The authors also introduce a Two-Stage Optimization algorithm (TSJTI) based on Deep Reinforcement Learning (DRL) and Transfer Learning (TFL) to reduce the processing latency of task offloading and energy consumption in DTVIF.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2022)
Article
Telecommunications
Peng Yang, Jiawei Hou, Li Yu, Wenxiong Chen, Ye Wu
Summary: In this study, we investigate real-time video analytics based on cameras mounted on mobile devices with edge coordination, aiming to develop an energy-efficient digital twin in 6G. We propose a deep reinforcement learning based framework that considers energy consumption, analytics accuracy, and latency to achieve joint offloading decision and configuration selection. The simulation results demonstrate that our framework outperforms the benchmarks in terms of accuracy improvement and energy and latency reduction.
CHINA COMMUNICATIONS
(2023)
Article
Engineering, Electrical & Electronic
Latif U. Khan, Walid Saad, Dusit Niyato, Zhu Han, Choong Seon Hong
Summary: The article discusses the framework requirements for enabling IoE applications over 6G wireless systems using digital twins. It presents the architectural components and trends of edge-based, cloud-based, and edge-cloud-based twins, and provides a comparative description of various twins. The article concludes with recommendations for future research directions.
IEEE COMMUNICATIONS MAGAZINE
(2022)
Article
Engineering, Civil
Xuanhong Zhou, Muhammad Bilal, Ruihan Dou, Joel J. P. C. Rodrigues, Qingzhan Zhao, Jianguo Dai, Xiaolong Xu
Summary: In this research, a Computation Offloading method with Demand prediction and Reinforcement learning (CODR) is proposed to provide low-delay in-vehicle services in the Internet of Vehicles (IoV) using the powerful communication capability of 6G. CODR utilizes prediction based on Spatial-Temporal Graph Neural Network (STGNN) for demand, caching decision based on simplex algorithm, and computation offloading based on twin delayed deterministic policy gradient (TD3) to achieve optimal offloading scheme in 6G-enabled IoV.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2023)
Article
Automation & Control Systems
Ke Zhang, Jiayu Cao, Yan Zhang
Summary: Technological advancements in urban informatics and vehicular intelligence have made smart vehicles ubiquitous edge computing platforms for various applications. However, the different capacities of smart vehicles, diverse application requirements, and unpredictable vehicular topology pose challenges for efficient edge computing services. To address these challenges, we propose incorporating digital twin technology and artificial intelligence into a vehicular edge computing network, enabling centralized service matching and distributed task offloading and resource allocation using multiagent deep reinforcement learning. We also introduce a coordination graph-driven task offloading scheme that integrates service matching and intelligent offloading scheduling in both digital twin and physical networks to minimize costs. Numerical results based on real urban traffic datasets demonstrate the efficiency of our proposed schemes.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2022)
Article
Computer Science, Information Systems
Nikolaos Nomikos, Spyros Zoupanos, Themistoklis Charalambous, Ioannis Krikidis
Summary: This survey investigates reinforcement learning-aided mobile edge caching solutions and classifies them based on networking architecture and optimization targets. The study finds that these solutions can outperform traditional policy-based methods in high-heterogeneity network scenarios.
Article
Engineering, Electrical & Electronic
Qi Guo, Fengxiao Tang, Nei Kato
Summary: In this paper, a UAV-assisted mobile network is proposed to provide efficient communication in high-density and high-traffic environments. The network utilizes an intelligent resource allocation strategy and digital twin technology to meet various resource allocation requirements for different node types, and makes decisions using a reinforcement learning mechanism. Simulation results demonstrate significant improvement in network performance compared to baseline algorithms.
IEEE JOURNAL ON SELECTED AREAS IN COMMUNICATIONS
(2023)
Article
Computer Science, Hardware & Architecture
Bilgehan Erman, Catello Di Martino
Summary: This article discusses the vision of the 6G era and the concept of digital twin. Challenges remain in designing, delivering, and maintaining private wireless networks for autonomous industrial settings, including immediate detection of performance problems and use-case-dependent SLA compliance prediction. The article presents a solution that utilizes deep neural network models and generative adversarial network methods for continuous testing and SLA management of networks.
Article
Engineering, Multidisciplinary
Pin Lv, Wenbiao Xu, Jiangtian Nie, Yanli Yuan, Chao Cai, Zhe Chen, Jia Xu
Summary: The most basic requirement for autonomous vehicles is accurate environmental perception. By using edge computing technology and 6G networks, vehicles can offload computing tasks to edge servers for execution, solving the problem of insufficient onboard resources. This study focuses on the environmental perception task offloading problem for autonomous vehicles. An offloading decision algorithm based on deep reinforcement learning is designed to select edge nodes for task execution and improve the overall performance.
IEEE TRANSACTIONS ON NETWORK SCIENCE AND ENGINEERING
(2023)
Article
Engineering, Electrical & Electronic
Yongchao Zhang, Jia Hu, Geyong Min
Summary: The paper proposes a digital twin-driven intelligent task offloading framework for collaborative mobile edge computing (MEC). By mapping the MEC system into a virtual space using digital twin and optimizing task offloading decisions with deep reinforcement learning, the proposed framework effectively adapts to dynamic environments and significantly improves the MEC system's income.
IEEE JOURNAL ON SELECTED AREAS IN COMMUNICATIONS
(2023)
Article
Computer Science, Information Systems
Xiaoyu Zhu, Yueyi Luo, Anfeng Liu, Md Zakirul Alam Bhuiyan, Shaobo Zhang
Summary: This article explores the vehicular computation offloading problem in mobile-edge computing and proposes a multiagent deep reinforcement learning-based offloading scheme. The effectiveness and superiority of the proposed scheme are verified through a large number of simulations.
IEEE INTERNET OF THINGS JOURNAL
(2021)
Article
Computer Science, Information Systems
Yunlong Lu, Bo Ai, Zhangdui Zhong, Yan Zhang
Summary: This article proposes the model of wireless computing power networks (WCPNs) and solves the problems encountered by conventional mobile edge computing systems in 6G networks. By jointly unifying the computing resources from end devices and MEC servers, and optimizing the allocation of computation and communication resources through a deep reinforcement learning (DRL) algorithm, the objective of minimizing execution latency and energy consumption is achieved. Numerical results show improvement in computation efficiency, convergence rate, and utility performance.
IEEE INTERNET OF THINGS JOURNAL
(2023)
Article
Engineering, Electrical & Electronic
Xuelin Cao, Bo Yang, Yulong Shen, Chau Yuen, Yan Zhang, Zhu Han, H. Vincent Poor, Lajos Hanzo
Summary: Sixth-Generation (6G) technologies will revolutionize the wireless ecosystem through satellite-terrestrial integrated networks (STINs). This research investigates the application of edge computing paradigm to low Earth orbit satellite (LEOS) networks for supporting computation-intensive and delay-sensitive services. A LEOS edge-assisted multi-layer multi-access edge computing (MEC) system is proposed, which enhances the coverage and solves computing problems in congested and isolated areas. Optimization problems are formulated and solved using an alternating optimization (AO) method to achieve low computing latency and energy dissipation.
IEEE JOURNAL ON SELECTED AREAS IN COMMUNICATIONS
(2023)
Article
Automation & Control Systems
Haijun Liao, Zhenyu Zhou, Nian Liu, Yan Zhang, Guangyuan Xu, Zhenti Wang, Shahid Mumtaz
Summary: Digital twin (DT) is a cutting-edge technology for intelligent optimization of electrical equipment management, but it still faces reliability and communication efficiency problems. This paper proposes a Cloud-edge-device Collaborative reliable and Communication-efficient DT named C-3-FLOW. By jointly optimizing device scheduling, channel allocation, and computational resource allocation, C-3-FLOW minimizes the long-term global loss function and time-average communication cost. Simulation results verify its superior performance in loss function, communication efficiency, and carbon emission reduction.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2023)
Article
Engineering, Electrical & Electronic
Yu Gong, Yifei Wei, Zhiyong Feng, F. Richard Yu, Yan Zhang
Summary: This paper proposes a holistic network virtualization architecture that integrates digital twin and network slicing for service-centric and user-centric network management. It also introduces a new environment aware offloading mechanism based on the integrated sensing and communication system to solve the joint optimization problem of task scheduling and resource allocation. Simulation results demonstrate the effectiveness and superiority of the proposed schemes.
IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY
(2023)
Article
Computer Science, Information Systems
Wen Sun, Zongjun Li, Qubeijian Wang, Yan Zhang
Summary: In this article, a wireless computing power network (WCPN) is proposed to orchestrate the computing and networking resources of heterogeneous nodes for specific computing tasks. A task and resource-aware federated learning model (FedTAR) is designed to optimize the energy consumption of computing nodes through the joint optimization of computing strategies and collaborative learning strategies. An energy-efficient asynchronous aggregation algorithm is also proposed to accelerate the convergence speed of federated learning in WCPN.
IEEE INTERNET OF THINGS JOURNAL
(2023)
Article
Computer Science, Information Systems
Xinran Fang, Wei Feng, Yunfei Chen, Ning Ge, Yan Zhang
Summary: The sixth-generation (6G) network aims to integrate communication and sensing functions to improve efficiency and support novel applications. The MIMO technique plays a crucial role in balancing communication and sensing performance, but it also brings challenges in terms of cost, power consumption, and complexity. This survey discusses the application of MIMO in joint communication and sensing (JCAS), outlines its roles in wireless communication and radar sensing, and explores current advances and potential solutions.
IEEE INTERNET OF THINGS JOURNAL
(2023)
Article
Computer Science, Information Systems
Yunlong Lu, Bo Ai, Zhangdui Zhong, Yan Zhang
Summary: This article proposes the model of wireless computing power networks (WCPNs) and solves the problems encountered by conventional mobile edge computing systems in 6G networks. By jointly unifying the computing resources from end devices and MEC servers, and optimizing the allocation of computation and communication resources through a deep reinforcement learning (DRL) algorithm, the objective of minimizing execution latency and energy consumption is achieved. Numerical results show improvement in computation efficiency, convergence rate, and utility performance.
IEEE INTERNET OF THINGS JOURNAL
(2023)
Article
Computer Science, Information Systems
Xueqing Yang, Xin Guan, Ning Wang, Yongnan Liu, Huayang Wu, Yan Zhang
Summary: Smart grid integrates distributed energy resources and massive information to facilitate energy flow in industries. Accommodating renewable energy is crucial for achieving energy efficiency, but optimal policies are difficult to obtain due to intermittency. To capture renewable energy statuses for decision-making, heterogeneous information is collected by end devices in smart grid, posing challenges for existing algorithms. This article proposes a cloud-edge-end computing scheme to efficiently repair missing values and obtain optimal policies in two separate layers using deep learning and deep reinforcement learning algorithms. Simulations on a real power grid dataset demonstrate the effectiveness of the proposed fault-tolerant renewable energy accommodation algorithm.
IEEE TRANSACTIONS ON CLOUD COMPUTING
(2023)
Article
Engineering, Multidisciplinary
Yunlong Song, Yaqiong Liu, Yan Zhang, Zhifu Li, Guochu Shou
Summary: This paper proposes a proximity detection scheme for dynamic road networks based on Mobile Edge Computing (MEC), and formulates the proximity detection problem as a nonlinear optimization problem. By using the SLSQP algorithm and DDPG algorithm, the computational time can be effectively reduced, and the computational time of the DDPG algorithm is two orders of magnitude lower than that of the SLSQP algorithm.
IEEE TRANSACTIONS ON NETWORK SCIENCE AND ENGINEERING
(2023)
Article
Engineering, Multidisciplinary
Wen Sun, Sijia Lian, Haibin Zhang, Yan Zhang
Summary: The sixth-generation (6G) wireless network aims to provide universal and reliable network access through effective inter-networking among space, air, and terrestrial networks, which poses significant challenges for dynamic network orchestration. Digital twin (DT) offers an alternative approach to real-time resource allocation by mapping and learning the complex network topology. However, establishing a digital twin on aerial networks is difficult due to limited energy capacity and insufficient computing power of unmanned aerial vehicles. In this paper, a lightweight DT empowered air-ground network architecture is proposed, where the modelling task is distributed to ground devices using federated learning, and a distributed incentive mechanism is designed to incentivize high-performance ground devices.
IEEE TRANSACTIONS ON NETWORK SCIENCE AND ENGINEERING
(2023)
Article
Automation & Control Systems
Shunfan He, Wei Tian, Rongbo Zhu, Yan Zhang, Sun Mao
Summary: This article proposes an electrical signature analysis method for the detection of inverter open-circuit faults (OCFs) in the distribution grid, which is capable of handling various disturbances. The method uses the fundamental value, rated harmonics, and direct current component of three-phase currents as fault electrical signatures. The signatures are estimated using the unscented Kalman filter (UKF) and recognized using the extreme learning machine (ELM) for fault detection. Simulations and experiments demonstrate the accuracy and robustness of the method, even in the presence of direct and indirect disturbances.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2023)
Article
Engineering, Civil
Bingcheng Jiang, Qian He, Peng Liu, Sabita Maharjan, Yan Zhang
Summary: The growing trend of vehicles equipped with driving camera recorders has enabled real-time crowdsourced video sharing in vehicular edge computing. However, data security and privacy concerns are key challenges for video sharing in this environment. In this article, a blockchain empowered publish/subscribe scheme is proposed to enable secure video sharing in vehicular edge computing. An attribute-based encryption algorithm with static and dynamic attributes is also designed to achieve fine-grained access control in a mobile environment. Simulation results show that the proposed scheme is secure and efficient.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2023)
Article
Computer Science, Information Systems
Jia Xu, Zhuangye Luo, Chengcheng Guan, Dejun Yang, Linfeng Liu, Yan Zhang
Summary: This paper proposes a two-tiered social crowdsourcing architecture to address the insufficient participation problem in budget-constrained online crowdsourcing systems. Through theoretical analysis and simulations, the incentive mechanisms are shown to achieve computational efficiency, individual rationality, budget feasibility, cost truthfulness, and time truthfulness. The proposed mechanisms outperform offline algorithms in terms of value.
IEEE TRANSACTIONS ON MOBILE COMPUTING
(2023)
Article
Engineering, Electrical & Electronic
Peng Wang, Wen Sun, Haibin Zhang, Wenqiang Ma, Yan Zhang
Summary: This article proposes a provable secure and decentralized federated learning based on blockchain for Wireless Computing Power Network (WCPN). It integrates a blockchain with proof-of-accuracy (PoAcc) consensus scheme to prioritize high-accuracy local models in the federated learning process, accelerating convergence and improving efficiency. Experimental results show that the proposed scheme ensures consistency and security while outperforming benchmarks in terms of model accuracy and resource consumption.
IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY
(2023)
Article
Computer Science, Information Systems
Hamza Djigal, Jia Xu, Linfeng Liu, Yan Zhang
Summary: This paper discusses the importance of Multiaccess Edge Computing (MEC) in extending cloud computing and storage capabilities to the edge of cellular networks. Effective resource allocation mechanisms are crucial for MEC systems, and Machine Learning (ML) and Deep Learning (DL) play a key role in addressing the challenges of resource allocation. The paper provides a comprehensive survey of ML/DL-based resource allocation mechanisms in MEC, covering task offloading, task scheduling, and joint resource allocation.
IEEE COMMUNICATIONS SURVEYS AND TUTORIALS
(2022)
Article
Computer Science, Information Systems
Hwei-Ming Chung, Sabita Maharjan, Yan Zhang, Frank Eliassen, Kai Strunz
Summary: This article proposes a computational architecture combining energy trading and demand responses based on cloud computing for managing virtual power plants (VPPs) in smart grids. EVs can be charged rapidly by purchasing energy in the cloud, while users with storage devices can sell surplus energy to the market. By modeling the interactions between EV owners and VPPs as a non-cooperative game, a Nash equilibrium is sought to maximize revenue and minimize charging costs.
IEEE TRANSACTIONS ON CLOUD COMPUTING
(2022)