Article
Telecommunications
Junwei Wang, Xianglin Wei, Jianhua Fan, Qiang Duan, Jianwei Liu, Yangang Wang
Summary: Wireless edge caching reduces content request latency and core network traffic by caching popular contents at the network edge. However, popularity-based caching strategies are vulnerable to Cache Pollution Attacks (CPAs). This paper proposes an edge caching mechanism that includes cache pollution detection and cache defense algorithms to defend against CPAs.
DIGITAL COMMUNICATIONS AND NETWORKS
(2023)
Article
Computer Science, Information Systems
Ruyan Wang, Zunwei Kan, Yaping Cui, Dapeng Wu, Yan Zhen
Summary: This article proposes a cooperative caching strategy with content request prediction (CCCRP) in IoV to reduce content acquisition delay by precaching contents requested by vehicles with greater probability in other vehicles or the roadside unit (RSU).
IEEE INTERNET OF THINGS JOURNAL
(2021)
Article
Computer Science, Hardware & Architecture
Shaohua Cao, Di Liu, Congcong Dai, Chengqi Wang, Yansheng Yang, Weishan Zhang, Danyang Zheng
Summary: With the development of autonomous and intelligent techniques, vehicles are equipped with computation and communication modules to handle on-vehicle computing requests. However, due to limited computation capacities, these requests are offloaded to special devices like roadside units or intelligent vehicles. Two challenges arise in vehicular edge computing networks: accurately determining peak or low hours and effectively offloading requests. This paper investigates computational requests offloading in different vehicular networking scenarios and proposes algorithms based on fuzzy inference and reinforcement learning to address these challenges. Experimental results show significant improvement in resource utilization compared to the benchmark.
Article
Computer Science, Information Systems
Xu Zhao, Mingzhen Liu, Maozhen Li
Summary: This study focuses on the infiltration of networks and communication technologies into IoT applications, particularly in urban infrastructure like automatic driving, driven by the construction of smart cities. Due to the limited computing power of in-vehicle terminals, the researchers propose a task offloading model in a Mobile Edge Computing (MEC) environment and design a collaboration scheme considering delay and energy consumption. By formulating the problem as a Markov Decision Process (MDP) and using Deep Reinforcement Learning (DRL) methods, a Deep Deterministic Policy Gradient (DDPG) algorithm is proposed to optimize task offloading and scheduling in a high-dimensional continuous action space. Simulation results demonstrate the effectiveness of the scheme in terms of convergence, system delay, average task energy consumption, and system cost.
Article
Chemistry, Analytical
Shuo Xiao, Shengzhi Wang, Jiayu Zhuang, Tianyu Wang, Jiajia Liu
Summary: This study introduces a task offloading algorithm for the Internet of Vehicles, utilizing local-edge clouds and reinforcement learning to optimize computing efficiency. The algorithm increases task success probability and achieves a balance between various constraints on utility.
Article
Engineering, Civil
Leilei Wang, Xiaoheng Deng, Jinsong Gui, Xuechen Chen, Shaohua Wan
Summary: The integration of Mobile Edge Computing (MEC) and microservice architecture enables the implementation of sustainable Internet of Vehicles (IoV). With MEC, microservices can be dynamically placed on Edge Service Providers (ESPs) to reduce latency and resource consumption. However, the growth of IoV leads to high computation and resource overheads, calling for judicious service placement. In this paper, we propose a Microservice-oriented Service Placement (MOSP) mechanism to address these issues and achieve improved resource savings, latency reduction, and service speed.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2023)
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
Computer Science, Information Systems
Liming Chen, Xiaoyun Kuang, Fusheng Zhu, Junjuan Xia
Summary: This study focuses on an intelligent mobile edge computing network for IoT in eavesdropping environments, optimizing system design to reduce latency and energy consumption. By using a deep Q-network to adjust offloading ratio and transmission bandwidth, the proposed strategy efficiently suppresses eavesdropping and achieves lower costs compared to conventional strategies.
Article
Engineering, Electrical & Electronic
Jiadong Yu, Yang Li, Xiaolan Liu, Bo Sun, Yuan Wu, Danny Hin-Kwok Tsang
Summary: This paper investigates the joint offloading, communication, and computation resource allocation for the intelligent reflecting surfaces (IRS)-assisted non-orthogonal multiple access (NOMA) mobile edge computing (MEC) system. By proposing the Lyapunov-function-based Mixed Integer Deep Deterministic Policy Gradient (LMIDDPG) algorithm, energy efficiency maximization is achieved. Numerical results show that the proposed algorithms achieve superior energy efficiency performance compared to the benchmark algorithms while maintaining queue stability.
IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS
(2023)
Article
Computer Science, Hardware & Architecture
Lucas Brehon-Grataloup, Rahim Kacimi, Andre-Luc Beylot
Summary: This article discusses the application of mobile edge computing (MEC) in vehicular networks. By bringing cloud resources closer to the edge of the network, MEC reduces the delay in task offloading and satisfies the real-time requirements of applications. The article categorizes the latest V2X architectures and explores the impact of network availability, reliability, large data handling, and task offloading on performance.
Article
Computer Science, Information Systems
Ziru Zhang, Nianfu Wang, Huaming Wu, Chaogang Tang, Ruidong Li
Summary: With the rapid development of IoT and next-generation communication technologies, mobile devices face challenges in meeting the demand of resource-hungry applications. To cope with this, offloading tasks from devices to edge cloud servers using mobile-edge computing can improve task processing efficiency. However, finding optimal offloading decisions is difficult and conventional methods have limitations.
IEEE INTERNET OF THINGS JOURNAL
(2023)
Article
Computer Science, Information Systems
Degan Zhang, Lixiang Cao, Haoli Zhu, Ting Zhang, Jinyu Du, Kaiwen Jiang
Summary: The paper discusses the higher requirements for network bandwidth and delay in the emerging Internet of Vehicles (IoV) technology compared to traditional network tasks. It focuses on the important issue of completing task offloading and calculation with lower task delay and lower energy consumption. By considering multiple MEC servers and proposing a dynamic task offloading scheme based on deep reinforcement learning, the paper improves upon the traditional Q-Learning algorithm and shows better performance in delay, energy consumption, and total system overhead through simulation results.
CLUSTER COMPUTING-THE JOURNAL OF NETWORKS SOFTWARE TOOLS AND APPLICATIONS
(2022)
Article
Computer Science, Hardware & Architecture
Qi Wu, Xiaolong Xu, Qingzhan Zhao, Fei Dai
Summary: Internet of vehicles (IoV) is combined with connected autonomous vehicles (CAV) to accelerate CAV development, and mobile edge computing (MEC) provides a novel paradigm for IoV services. The vehicle tasks offloading problem requires maintaining load balance of edge servers, and our proposed VTO method optimizes this issue.
MOBILE NETWORKS & APPLICATIONS
(2022)
Article
Engineering, Electrical & Electronic
Xiangjun Zhang, Weiguo Wu, Zhihe Zhao, Jinyu Wang, Song Liu
Summary: Mobile edge computing (MEC) enables smart vehicles in the Internet of Vehicles (IoV) to offload computation-intensive tasks to edge devices, but faces challenges in minimizing delay and energy consumption while ensuring data privacy security and resource load balancing. We propose a novel multi-objective reinforcement learning (MORL) algorithm based on double deep Q-network (DDQN) to optimize computation offloading, and show through numerical experiments that it outperforms traditional reinforcement learning methods by reducing overall energy consumption by 30.24%.
IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY
(2023)
Article
Remote Sensing
Zhiyang Zhang, Die Wu, Fengli Zhang, Ruijin Wang
Summary: In this paper, a universal intelligent collaborative task scheduling framework named DECCo is proposed to handle the complexity of task scheduling in the drone edge cluster (DEC). by utilizing deep reinforcement learning (DRL), DECCo autonomously learns task scheduling strategies with high response rates and low communication latency. DECCo switches between heuristic and DRL-based scheduling solutions based on real-time scheduling performance to avoid suboptimal decisions that affect Quality of Service (QoS) and Quality of Experience (QoE) in a real drone collaborative scheduling scenario.