Article
Computer Science, Information Systems
Fengxian Guo, Mugen Peng
Summary: Mobile edge computing is an essential technology for latency-critical applications by providing computing services in close proximity to mobile users. However, supporting user mobility remains challenging. This article proposes an efficient mobility management framework that is centered around users' performance and cost, and uses game theory and user-oriented deep reinforcement learning to handle the interactions in space and time.
IEEE INTERNET OF THINGS JOURNAL
(2023)
Article
Engineering, Electrical & Electronic
Zezu Liang, Yuan Liu, Tat-Ming Lok, Kaibin Huang
Summary: This paper addresses the challenge of supporting user mobility in cellular networks through optimizing migration/handover policies for tasks in MEC. By jointly managing computation-and-radio resources, the objectives of maximizing offloading rate and throughput while minimizing migration cost are achieved. The proposed solution approach demonstrates near-optimal performance in resource management for joint service migration and BS handover in multi-cell MEC networks.
IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS
(2021)
Article
Computer Science, Information Systems
Xiaobo Zhou, Shuxin Ge, Tie Qiu, Keqiu Li, Mohammed Atiquzzaman
Summary: Mobile edge computing is crucial for achieving ultra-low latency in 5G and beyond, by deploying services at the network edge. However, service migration in multi-user heterogeneous networks is challenging due to the difficulty in predicting user trajectories and interference among users. In this study, an optimization problem was formulated to minimize energy consumption and satisfy service latency requirements, and an efficient online algorithm called EGO was developed to solve the problem without predicting user trajectories.
IEEE TRANSACTIONS ON MOBILE COMPUTING
(2023)
Article
Computer Science, Information Systems
Yi Xu, Zhiqiang Zheng, Xiao Liu, Aiting Yao, Xuejun Li
Summary: In mobile edge computing, deploying three-way decisions for service migration can prevent wrong decisions and improve performance. Users are categorized into different regions based on their movement trajectory, and corresponding operations are executed accordingly.
INFORMATION SCIENCES
(2022)
Article
Computer Science, Information Systems
Muhammad Rizwan Anwar, Shangguang Wang, Muhammad Faisal Akram, Salman Raza, Shahid Mahmood
Summary: This article introduces a distributed traffic steering concept, which resolves the scalability problem of a large MEC network into a partitioned MEC network by differentiating different types of network elements. The article also proposes matrix-based dynamic shortest path selection and matrix-based dynamic multipath searching algorithms for dynamic path selection. Experimental results demonstrate the significant advantage of dynamic and adaptive path searching in a partitioned controlled MEC network over centralized approaches.
IEEE INTERNET OF THINGS JOURNAL
(2022)
Article
Computer Science, Artificial Intelligence
Guobing Zou, Zhen Qin, Shuiguang Deng, Kuan-Ching Li, Yanglan Gan, Bofeng Zhang
Summary: Mobile edge computing (MEC) aims to reduce response time for service invocations by deploying service instances on edge servers and selecting them based on user proximity. However, service instance selection faces challenges such as server limitations, user mobility, and request interference. A novel genetic algorithm-based approach called GASISMEC is proposed to tackle these challenges and outperforms six baseline approaches in extensive experiments.
KNOWLEDGE-BASED SYSTEMS
(2021)
Article
Computer Science, Hardware & Architecture
Chunlin Li, Lei Zhu, Weigang Li, Youlong Luo
Summary: In recent years, with the increasing demand for online streaming services, an edge cooperative caching method based on SDN in mobile edge computing has been proposed to minimize delay and energy consumption. Additionally, a dynamic service migration method based on deep Q learning was introduced to ensure service continuity and quality. Both methods were found to effectively optimize cache hit rates, reduce backhaul traffic load, control access delay and energy cost, as well as minimize the number of service migrations and transmission costs.
JOURNAL OF NETWORK AND COMPUTER APPLICATIONS
(2021)
Article
Telecommunications
Xiaoqian Li, Siyu Chen, Yakun Zhou, Jienan Chen, Gang Feng
Summary: Mobile edge computing enhances network performance and user experience, but service migration is necessary due to user mobility and limited server coverage. This paper proposes an intelligent service migration algorithm (iSMA) based on learning, which reduces service delay by inferring environment states and searching for the best migration strategy.
IEEE TRANSACTIONS ON COGNITIVE COMMUNICATIONS AND NETWORKING
(2022)
Article
Computer Science, Information Systems
Na Xie, Wenan Tan, Lu Zhao, Li Huang, Yong Sun
Summary: Mobile edge computing enables users to access services with low network latency, but selecting the appropriate service instances to minimize overall latency is a critical problem.
IEEE SYSTEMS JOURNAL
(2023)
Article
Computer Science, Information Systems
Wenxiong Chen, Mingliu Liu, Fan Wu, Huaqing Wu, Yuan Miao, Feng Lyu, Xuemin Shen
Summary: This article investigates the mobility-aware service migration problem in mobile-edge computing (MEC) and proposes a data-driven framework to address this problem. The service migration is formulated as an optimization problem, and a mobility-aware service migration scheme is introduced using deep reinforcement learning algorithm in a large-scale MEC scenario.
IEEE INTERNET OF THINGS JOURNAL
(2023)
Article
Computer Science, Information Systems
Bin Gao, Zhi Zhou, Fangming Liu, Fei Xu, Bo Li
Summary: With the rapid development and deployment of 5G wireless technology, mobile edge computing (MEC) has emerged as a new computing paradigm to reduce user-perceived communication delay. This study focuses on optimizing access network selection and service placement for MEC to improve quality-of-service (QoS) in a cost-efficient manner. An efficient online framework and a computationally-efficient two-phase algorithm are proposed to achieve near-optimal solutions.
IEEE TRANSACTIONS ON MOBILE COMPUTING
(2022)
Article
Computer Science, Hardware & Architecture
Wenhao Li, Hamid Faragardi, Mustafa Ozger, Cicek Cavdar, Bjorn Skubic
Summary: This paper investigates the problem of service selection in a marketplace and proposes two service selection algorithms. The experimental results show that the Improved version of Best Fit algorithm achieves better results in terms of monetary cost and execution time compared to the Best Fit algorithm and brute force algorithm.
Article
Chemistry, Multidisciplinary
Jiale Zhao, Yong Ma, Yunni Xia, Mengxuan Dai, Peng Chen, Tingyan Long, Shiyun Shao, Fan Li, Yin Li, Feng Zeng
Summary: The paper proposes a fault-tolerant approach, called Dynamic Redundant Path Selection service migration (DRPS), for vehicular edge computing. The DRPS approach includes path selection algorithm and service migration algorithm, which can evaluate failure rates and determine migration paths to improve the reliability and performance of edge service migration.
APPLIED SCIENCES-BASEL
(2022)
Article
Computer Science, Information Systems
Zhiyuan Wang, Lin Gao, Tong Wang, Jingjing Luo
Summary: This article focuses on the edge computing service in the mobile internet ecosystem and studies the economic interactions among mobile users, internet service providers, content providers, and edge service providers. By offloading computation tasks to edge servers, the edge computing service can alleviate the computation pressure of mobile users while maintaining the quality of service. The study finds that the edge computing service can stimulate content acquisition for mobile users and improve the payoffs of mobile users, internet service providers, and content providers.
IEEE TRANSACTIONS ON MOBILE COMPUTING
(2022)
Article
Multidisciplinary Sciences
Furong Li, Duan Wang
Summary: The paper explores the energy distribution problem on the migration data link from the terminal device to the edge node in the mobile edge network, utilizing competition among multiple data service packages to control migration strategy.
Article
Engineering, Electrical & Electronic
Hongman Wang, Yingxue Li, Ao Zhou, Yan Guo, Shangguang Wang
Summary: This paper proposes an efficient dynamic service migration algorithm based on reinforcement learning in mobile edge computing, which can reduce access latency and network costs, while considering trade-offs between migration costs and total service costs.
INTERNATIONAL JOURNAL OF COMMUNICATION SYSTEMS
(2023)
Article
Computer Science, Information Systems
Qing Li, Xiao Ma, Ao Zhou, Changhee Joo, Shangguang Wang
Summary: Vehicles on roads have increasingly powerful computing capabilities and edge nodes are being widely deployed. They can work together to provide computing services for onboard driving systems, passengers, and pedestrians. To address the critical challenges induced by the joint modeling of latency and reliability, system uncertainty, and performance and cost trade-off, we propose an online learning-based service request duplication algorithm based on a multi-armed bandit framework and Lyapunov optimization theory. The proposed algorithm achieves an upper-bounded regret compared to the oracle algorithm and outperforms the benchmarks in simulations based on real-world datasets.
IEEE TRANSACTIONS ON MOBILE COMPUTING
(2023)
Article
Computer Science, Theory & Methods
Zhichao Lu, Chuntao Ding, Felix Juefei-Xu, Vishnu Naresh Boddeti, Shangguang Wang, Yun Yang
Summary: This article proposes a transmission-friendly ViT model, called TFormer, for resource-constrained IoT devices with the assistance of a cloud server. TFormer achieves high performance with fewer model parameters and FLOPs through the use of a hybrid layer and a partially connected feed-forward network. Experimental results demonstrate that TFormer outperforms other state-of-the-art models in image classification, object detection, and semantic segmentation tasks.
IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS
(2023)
Article
Engineering, Electrical & Electronic
Shangguang Wang, Yan Guo, Xiao Liu, Ao Zhou
Summary: This paper investigates the service routing problem for efficient microservice-based service provision in multi-tier edge computing, and proposes a dependency-aware deferred acceptance algorithm based on matching game theory. The experimental results demonstrate that our proposed algorithm outperforms existing algorithms in terms of service delay and resource cost.
IEEE JOURNAL ON SELECTED AREAS IN COMMUNICATIONS
(2023)
Article
Computer Science, Information Systems
Jianbo Du, Yan Sun, Ning Zhang, Zehui Xiong, Aijing Sun, Zhiguo Ding
Summary: This article proposes a NOMA-based vehicle edge computing network model to minimize system cost through joint optimization of offloading decision-making, VUE clustering, resource allocation, and power control. Two heuristic algorithms are used to solve the task offloading and resource assignment problems, and closed-form solutions for cloud-related optimization problems are obtained.
IEEE SYSTEMS JOURNAL
(2023)
Article
Computer Science, Information Systems
Xiao Ma, Ao Zhou, Shan Zhang, Qing Li, Alex X. Liu, Shangguang Wang
Summary: The cloud-assisted mobile edge computing system is an important architecture for processing computation-intensive and delay-sensitive mobile applications efficiently. The paper proposes a Water-filling Based Dynamic Task Scheduling algorithm to solve the dynamic task scheduling problem, aiming at minimizing average task response time within the resource budget limit.
IEEE TRANSACTIONS ON MOBILE COMPUTING
(2023)
Article
Computer Science, Information Systems
Qing Li, Xiao Ma, Ao Zhou, Xiapu Luo, Fangchun Yang, Shangguang Wang
Summary: This paper addresses the issue of edge node grouping in mobile edge computing networks. It proposes a novel decentralized learning-based algorithm that guides users to make decisions based on historical feedback. The algorithm is proven to converge to the Nash equilibrium with an upper-bound learning loss. Simulation results demonstrate its performance can achieve up to 96.99% of the theoretical benchmark.
IEEE TRANSACTIONS ON MOBILE COMPUTING
(2023)
Article
Computer Science, Information Systems
Ying Wang, Naling Li, Peng Yu, Wenjing Li, Xuesong Qiu, Shangguang Wang, Mohamed Cheriet
Summary: 5G and beyond network will support vertical industry applications with varying resource requirements for each service. The introduction of network slices provides flexibility to meet customization requirements. However, existing solutions rarely consider multiple customized requirements such as delay, bandwidth, load balancing, and slice isolation. This article proposes algorithms based on deep reinforcement learning to optimize network slice orchestration and demonstrates significant improvements in bandwidth consumption, slice delay, and load balancing for typical slices.
IEEE TRANSACTIONS ON SERVICES COMPUTING
(2023)
Article
Engineering, Multidisciplinary
Xiaoming Yuan, Zedan Zhang, Chujun Feng, Yejia Cui, Sahil Garg, Georges Kaddoum, Keping Yu
Summary: The rapid expansion of wearable medical devices and health data of Internet of Medical Things (IoMT) poses new challenges to the high Quality of Service (QoS) of intelligent health care in the foreseeable 6G era. Traditional frame aggregation schemes in WBAN generate too much control frames during data transmission, which leads to high delay and energy consumption. In this paper, a Deep Q-learning Network (DQN) based Frame Aggregation and Task Offloading Approach (DQN-FATOA) is proposed, which effectively reduces delay and energy consumption, and improves the throughput and overall utilization of WBAN.
IEEE TRANSACTIONS ON NETWORK SCIENCE AND ENGINEERING
(2023)
Article
Engineering, Civil
Xiaoming Yuan, Jiahui Chen, Jiayu Yang, Ning Zhang, Tingting Yang, Tao Han, Amir Taherkordi
Summary: This paper proposes a Federated Deep Learning algorithm based on the Spatial-Temporal Long and Short-Term Networks (FedSTN) for predicting traffic flow. The algorithm utilizes distributed model training and data privacy protection to improve prediction accuracy by mining spatio-temporal information and semantic features.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2023)
Article
Computer Science, Information Systems
Chuntao Ding, Ao Zhou, Xiao Ma, Ning Zhang, Ching-Hsien Hsu, Shangguang Wang
Summary: This article proposes an IoT image recognition services framework for different needs in the MEC environment, which improves recognition accuracy by about 6% and reduces network traffic by up to 94% compared to the state-of-the-art approaches.
IEEE TRANSACTIONS ON CLOUD COMPUTING
(2023)
Article
Computer Science, Information Systems
Mingyue Wang, Yu Guo, Chen Zhang, Cong Wang, Hejiao Huang, Xiaohua Jia
Summary: Electronic Health Record (EHR) and its privacy have gained significant attention. Existing systems for EHR sharing are vulnerable to DDoS attacks and single point of failure. In this article, we propose MedShare, a decentralized framework that utilizes blockchain technology to establish a trusted platform for secure EHR sharing. Our system incorporates a constant-size attribute-based encryption scheme for fine-grained access control and supports efficient multi-keyword boolean search operations. Evaluation results on Ethereum demonstrate the efficiency of MedShare.
IEEE TRANSACTIONS ON SERVICES COMPUTING
(2023)
Article
Computer Science, Information Systems
Fatima Salahdine, Tao Han, Ning Zhang
Summary: 5G, 6G, and beyond networks aim to provide emerging services with new requirements and challenges through key enabler technologies. While these technologies have potential interests, they also bring security concerns and challenges, making network security a primary concern for future wireless communication networks.
SECURITY AND PRIVACY
(2023)
