Article
Computer Science, Information Systems
Chunlin Li, Zewu Ke, Qiang Liu, Cong Hu, Chengwei Lu, Youlong Luo
Summary: This paper discusses the challenges of mobile edge computing caused by the growth of communication traffic and data generated by mobile devices. A multi-user-oriented edge server selection strategy is proposed to minimize network latency and energy consumption. Additionally, a resource allocation strategy is devised to maximize energy efficiency. Experimental results show improvements in energy consumption, latency, and resource utilization.
Article
Computer Science, Information Systems
Feiyan Guo, Bing Tang, Mingdong Tang, Wei Liang
Summary: This paper studies the problem of microservice selection based on the dynamic and heterogeneous characteristics of the cloud-edge collaborative environment. It proposes a Deep Deterministic Policy Gradient algorithm called MS_DDPG to solve this problem, and the algorithm outperforms other baseline algorithms according to performance evaluations.
CLUSTER COMPUTING-THE JOURNAL OF NETWORKS SOFTWARE TOOLS AND APPLICATIONS
(2023)
Article
Computer Science, Information Systems
Xiaohan Jiang, Peng Hou, Hongbin Zhu, Bo Li, Zongshan Wang, Hongwei Ding
Summary: This paper studies the efficient and intelligent dynamic edge server placement problem considering time-varying network states and placement costs. Two deep reinforcement learning-based algorithms are proposed to achieve intelligent decision-making and performance improvement. Experimental results show that the proposed algorithms outperform comparison algorithms by 13.20% to 61.84% and 23.09% to 66.32%, respectively.
Article
Engineering, Electrical & Electronic
Hao Hao, Changqiao Xu, Wei Zhang, Shujie Yang, Gabriel-Miro Muntean
Summary: This paper investigates the fairness-guaranteed computing offloading problem in edge computing and proposes an innovative deep reinforcement learning algorithm to solve it. Simulation experiments show that the algorithm has good performance in terms of service delay and fairness.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
(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
Engineering, Electrical & Electronic
Heting Liu, Guohong Cao
Summary: Mobile Edge Computing (MEC) enables offloading of computational intensive applications to nearby edge servers, supporting latency-sensitive applications on mobile devices. To address the challenge of achieving long-term optimum in edge server selection, a Deep Reinforcement Learning (DRL) based algorithm is proposed to automatically select the optimal server by inferring future knowledge of dynamically changing factors from historical information. Extensive evaluations show that the proposed DRL-based algorithm outperforms existing solutions in terms of overall cost.
IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY
(2021)
Article
Telecommunications
Zhao Chen, Lei Zhang, Yukui Pei, Chunxiao Jiang, Liuguo Yin
Summary: This paper investigates dynamic computation offloading in a non-orthogonal multiple access based multi-user network and proposes a cooperative multi-agent deep reinforcement learning framework. Numerical simulations demonstrate that the proposed framework can learn efficient dynamic offloading policies and outperform the conventional independent Q-learning framework.
IEEE TRANSACTIONS ON COGNITIVE COMMUNICATIONS AND NETWORKING
(2022)
Article
Telecommunications
Tongyu Song, Xuebin Tan, Jing Ren, Wenyu Hu, Sheng Wang, Shizhong Xu, Xiong Wang, Gang Sun, Hongfang Yu
Summary: Mobile Edge Computing (MEC) and 5G technology enable access to computing resources at the network frontier, facilitating Mobile Augmented Reality (MAR) applications. Resource allocation becomes a critical challenge when multiple MAR clients compete for limited resources. This paper proposes a deep reinforcement learning-based resource allocation scheme called DRAM for MAR services in MEC, considering both high quality of experience and fairness performance. Experimental results demonstrate that DRAM achieves high quality of experience and good fairness performance in coordination with client adaptation algorithms.
DIGITAL COMMUNICATIONS AND NETWORKS
(2023)
Article
Telecommunications
Jie Li, Zhiping Yang, Xingwei Wang, Yichao Xia, Shijian Ni
Summary: This study focuses on computation offloading in MEC to improve QoS. The proposed algorithm combines the QoS model and deep reinforcement learning algorithm to obtain an optimal offloading policy while considering factors such as computational cost, dimensional disaster, user privacy, and catastrophic forgetting of new users, thereby reducing energy consumption and task processing delay.
DIGITAL COMMUNICATIONS AND NETWORKS
(2023)
Article
Computer Science, Information Systems
Liwei Geng, Hongbo Zhao, Jiayue Wang, Aryan Kaushik, Shuai Yuan, Wenquan Feng
Summary: This article proposes a computation offloading policy based on deep reinforcement learning in a vehicle-assisted vehicular edge computing network. The goal is to provide excellent Quality-of-Service by utilizing the idle resources of vehicles. The article presents a task scheduling algorithm and formulates the computation offloading problem to minimize system cost.
IEEE INTERNET OF THINGS JOURNAL
(2023)
Article
Computer Science, Information Systems
Bahareh Bahrami, Mohammad Reza Khayyambashi, Seyedali Mirjalili
Summary: MEC is a promising communication paradigm that utilizes edge servers near end users to enable IoT and 5G scenarios. These servers provide virtualized resources and host various MEC applications, allowing user equipment and IoT devices to offload tasks. Optimizing edge server placement can greatly enhance the performance of mobile applications.
CLUSTER COMPUTING-THE JOURNAL OF NETWORKS SOFTWARE TOOLS AND APPLICATIONS
(2023)
Article
Computer Science, Information Systems
Sheuli Chakraborty, Kaushik Mazumdar
Summary: This study proposes a scheme that dynamically selects edge cloud for offloading tasks and checks task dependencies, achieving good performance in sensor mobile edge computing.
JOURNAL OF KING SAUD UNIVERSITY-COMPUTER AND INFORMATION SCIENCES
(2022)
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, Information Systems
Hao Xu, Chengfeng Jian
Summary: Mobile edge computing requires more high-performance servers, resulting in increased energy consumption. Virtual machine placement (VMP) is an effective method to reduce energy consumption, but existing algorithms may take a long time to converge. To overcome this, we propose a virtual machine placement algorithm based on meta-reinforcement learning, which accelerates convergence capability and quickly obtains efficient decisions in a new environment.
CLUSTER COMPUTING-THE JOURNAL OF NETWORKS SOFTWARE TOOLS AND APPLICATIONS
(2023)
Article
Computer Science, Information Systems
Zhenpeng Liu, Sichen Duan, Shuo Wang, Yi Liu, Xiaofei Li
Summary: This research proposes a multi-level federated edge learning algorithm that leverages the advantages of Edge Computing Paradigm. The model aggregation is moved from a cloud center server to edge servers in a hierarchical manner. Additionally, a client and edge server selection algorithm based on a greedy algorithm is introduced to address the heterogeneity issue. The simulation results demonstrate that the proposed algorithm can improve efficiency and accuracy compared to traditional federated learning methods.
Article
Engineering, Electrical & Electronic
Liang Xiao, Hailu Zhang, Yilin Xiao, Xiaoyue Wan, Sicong Liu, Li-Chun Wang, H. Vincent Poor
IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS
(2020)
Article
Engineering, Electrical & Electronic
Xiaozhen Lu, Liang Xiao, Tangwei Xu, Yifeng Zhao, Yuliang Tang, Weihua Zhuang
IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY
(2020)
Article
Computer Science, Information Systems
Wen Bai, Yuxiao Zhang, Weiwei Huang, Yipeng Zhou, Di Wu, Gang Liu, Liang Xiao
MULTIMEDIA TOOLS AND APPLICATIONS
(2020)
Article
Telecommunications
Wei Su, Jincheng Tao, Yuehua Pei, Xudong You, Liang Xiao, En Cheng
Summary: The proposed algorithm utilizes reinforcement learning to continuously estimate image quality and communication performance parameters, selecting the most suitable modulation and coding method to enhance underwater image communication efficiency. Sea test results demonstrate significant improvements in sensor performance.
IEEE COMMUNICATIONS LETTERS
(2021)
Article
Computer Science, Information Systems
Yilin Xiao, Liang Xiao, Xiaozhen Lu, Hailu Zhang, Shui Yu, H. Vincent Poor
Summary: This study introduces a deep reinforcement learning model for recommendation systems, which uses differential privacy to protect user privacy and leverages deep reinforcement learning to optimize the tradeoff between privacy protection and recommendation quality. Simulation results demonstrate that this scheme enhances user privacy protection without compromising recommendation quality compared to benchmark schemes.
IEEE INTERNET OF THINGS JOURNAL
(2021)
Article
Engineering, Electrical & Electronic
Liang Xiao, Yuzhen Ding, Jinhao Huang, Sicong Liu, Yuliang Tang, Huaiyu Dai
Summary: This paper proposes a reinforcement learning-based UAV anti-jamming video transmission scheme, which can improve video quality, reduce transmission latency and energy consumption, and uses deep learning to accelerate the learning process.
IEEE TRANSACTIONS ON COMMUNICATIONS
(2021)
Article
Computer Science, Hardware & Architecture
Yilin Xiao, Liang Xiao, Zefang Lv, Guohang Niu, Yuzhen Ding, Wenyuan Xu
Summary: This article proposes a low-latency VIoT video streaming scheme based on reinforcement learning, allowing base stations to choose streaming policies based on received signal strength, buffer queue length, jamming power, and video quality, with a deep RL version for base stations with sufficient computational resources.
IEEE WIRELESS COMMUNICATIONS
(2021)
Article
Engineering, Electrical & Electronic
Helin Yang, Jun Zhao, Zehui Xiong, Kwok-Yan Lam, Sumei Sun, Liang Xiao
Summary: The paper presents an asynchronous federated learning framework for multi-UAV-enabled networks, which allows for distributed computing and enhances federated convergence speed and accuracy through device selection strategy and A3C-based algorithm.
IEEE JOURNAL ON SELECTED AREAS IN COMMUNICATIONS
(2021)
Article
Engineering, Electrical & Electronic
Minghui Min, Liang Xiao, Jiahao Ding, Hongliang Zhang, Shiyin Li, Miao Pan, Zhu Han
Summary: This paper focuses on location privacy protection in indoor 3D space and proposes a rigorous and provable measurement method called geo-indistinguishability (3D-GI). A mechanism is developed to guarantee geo-indistinguishability by considering the height dimension of location data. The discretization noise-adding mechanism under finite precision of hardware/devices is also studied. Furthermore, a truncation mechanism is proposed to limit the generated perturbed locations within a specific region.
IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS
(2022)
Article
Computer Science, Information Systems
Xu Chen, Liang Xiao, Wei Feng, Ning Ge, Xianbin Wang
Summary: The proliferation of DDoS attacks in IoT poses threats to security and system performance, and collaborative packet sampling can effectively detect and block such attacks.
IEEE INTERNET OF THINGS JOURNAL
(2022)
Proceedings Paper
Computer Science, Information Systems
Siyuan Hong, Xiaozhen Lu, Liang Xiao, Guohang Niu, Helin Yang
Summary: In this paper, a reinforcement learning based sensor encryption and power control scheme is proposed to resist active eavesdropping in wireless body area networks. The scheme significantly decreases the eavesdropping rate and transmission latency through a secure sensing data transmission game between the coordinator and the eavesdropper.
WIRELESS ALGORITHMS, SYSTEMS, AND APPLICATIONS, WASA 2021, PT II
(2021)
Article
Telecommunications
Minghui Min, Weihang Wang, Liang Xiao, Yilin Xiao, Zhu Han
Summary: This paper introduces a sensitive semantic location privacy protection scheme based on reinforcement learning and differential privacy, which optimizes perturbation policy to balance privacy and quality of service loss. In addition, a deep deterministic policy gradient-based semantic location perturbation scheme is developed and simulations demonstrate its outperformance compared to benchmark schemes.
CHINA COMMUNICATIONS
(2021)
Article
Computer Science, Theory & Methods
Liang Xiao, Xiaozhen Lu, Tangwei Xu, Weihua Zhuang, Huaiyu Dai
Summary: This paper proposes a CAN bus authentication framework that leverages physical layer features and reinforcement learning to improve authentication accuracy. A deep learning version is also introduced to enhance authentication efficiency. Experimental results confirm the improvements in authentication accuracy achieved by the proposed schemes.
IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Kexin Liu, Xiaozhen Lu, Liang Xiao, Li Xu
2020 IEEE GLOBAL COMMUNICATIONS CONFERENCE (GLOBECOM)
(2020)
Proceedings Paper
Computer Science, Hardware & Architecture
Xudong You, Zefang Lv, Yuzhen Ding, Wei Su, Liang Xiao
2020 12TH INTERNATIONAL CONFERENCE ON WIRELESS COMMUNICATIONS AND SIGNAL PROCESSING (WCSP)
(2020)
