相关参考文献
注意：仅列出部分参考文献，下载原文获取全部文献信息。
Article
Computer Science, Information Systems
Andrey V. V. Savkin et al.
Summary: This article proposes a joint path planning and communication scheduling problem for a team of unmanned aerial vehicles (UAVs) performing computing tasks for IoT devices on uneven terrain. Reconfigurable intelligent surfaces (RISs) are deployed to improve wireless communication between UAVs and IoT devices. The objective is to develop an algorithm that maximizes computing tasks performed by the UAVs and minimizes their energy consumption. An effective path planning algorithm is proposed and its asymptotic optimality is mathematically proven.
IEEE INTERNET OF THINGS JOURNAL
(2023)
Article
Engineering, Civil
Muhammad Asim et al.
Summary: This article presents a multi-intelligent reflecting surface (IRS) and multi-unmanned aerial vehicle (UAV)-assisted mobile edge computing system for 5G/6G networks. It proposes an algorithm called TPaPBA to optimize the trajectories of UAVs and phase shifts of IRSs, aiming to minimize the overall cost of UAVs. The simulation results show that TPaPBA significantly improves the system performance and outperforms other approaches in reducing the cost of UAVs.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2023)
Article
Engineering, Electrical & Electronic
Wei Wu et al.
Summary: In this paper, intelligent resource allocation driven by reinforcement learning is studied in intelligent reflecting surface (IRS) enhanced OFDM systems to maximize the system sum rate. The proposed scheme combines deep Q networks (DQN) and deep deterministic policy-gradient (DDPG) to tackle the challenging non-convex problems. In addition, spectrum sharing and duel action space issue under interference are considered and addressed using advanced techniques such as dueling double deep Q networks (D3QN) and twin delayed deep deterministic policy gradient (TD3).
IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS
(2023)
Article
Engineering, Civil
Jian Su et al.
Summary: This paper focuses on task offloading in an aerial edge network assisted by a UAV, aiming to minimize the energy consumption of all user equipment by optimizing task offloading decisions and the position of the UAV. The proposed ADMM algorithm effectively reduces energy consumption and ensures continuous operation of user equipment.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2023)
Article
Engineering, Electrical & Electronic
Wenqi Zhou et al.
Summary: In this paper, we investigate the joint impact of task priority and mobile computing service on mobile edge computing (MEC) networks. We measure the system performance by the computing utility of multiple users, incorporating a wide-range task priority. We analyze the impact of network wireless bandwidth and UAV computational capability on system performance and optimize the system through UAV hotspot selection and user task offloading. We employ a deep Q-learning algorithm to solve the optimization problem and validate the proposed studies through simulations.
IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY
(2023)
Article
Computer Science, Artificial Intelligence
Run Liu et al.
Summary: This paper proposes a UAV path planning scheme for IoT networks based on reinforcement learning. The scheme plans hover points for the UAV by learning the historical location of CHs and maximizes the probability of meeting CHs. It also plans the shortest path to visit all hover points using the simulated annealing method. Additionally, an algorithm named CHSA-AEP is proposed to search for the location of CHs, allowing the UAV to respond to changes in CH positions. Our proposed scheme outperforms other methods in energy efficiency and time utilization ratio, as demonstrated by comparison with area coverage algorithms and a random algorithm.
IEEE TRANSACTIONS ON INTELLIGENT VEHICLES
(2023)
Article
Computer Science, Information Systems
Xianglin Wei et al.
Summary: This article investigates the application of unmanned aerial vehicle (UAV)-empowered edge computing in complex scenarios with multiple obstacles and dependent tasks. The joint UAV trajectory planning, DAG task scheduling, and SF deployment are formulated as an optimization problem, and a deep reinforcement learning (DRL)-based algorithm is proposed to solve it. Experimental results show that the DRL-based algorithm outperforms three heuristic algorithms in terms of trajectory planning success rate, executed tasks, and task response latency.
IEEE INTERNET OF THINGS JOURNAL
(2023)
Article
Engineering, Electrical & Electronic
Ying Liu et al.
Summary: This paper proposes a method to minimize the latency of communication and computation in a maritime UAV swarm mobile edge computing network. By applying MEC technology on the top-UAV and using deep reinforcement learning algorithms to optimize the UAV trajectory and virtual machine configuration, the system latency can be effectively reduced.
IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY
(2022)
Article
Computer Science, Information Systems
Huan Zhou et al.
Summary: This article investigates the joint optimization of computation offloading and resource allocation in a dynamic multiuser Mobile-edge computing (MEC) system. The objective is to minimize the energy consumption of the entire MEC system by considering the delay constraint and uncertain resource requirements of heterogeneous computation tasks. The proposed reinforcement learning method and double deep Q network-based method outperform other baseline methods in different scenarios.
IEEE INTERNET OF THINGS JOURNAL
(2022)
Article
Computer Science, Information Systems
Ming Tang et al.
Summary: In this paper, a model-free deep reinforcement learning-based distributed algorithm is proposed to address the load problem in mobile edge computing systems. The algorithm can effectively reduce the ratio of dropped tasks and average delay.
IEEE TRANSACTIONS ON MOBILE COMPUTING
(2022)
Article
Engineering, Electrical & Electronic
Shubin Zhang et al.
Summary: This paper focuses on the wireless powered MEC network with an ECS and multiple EDs, and studies the joint optimization of WPT duration and partial offloading decision. By using an online DRL framework and an efficient optimization algorithm, it achieves near-maximal sum computation rate.
IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS
(2022)
Article
Engineering, Civil
Yang Liu et al.
Summary: This paper investigates the application of UAV-assisted mobile edge computing in a platoon of wireless power transmission-enabled vehicles and proposes a joint scheduling optimization model to maximize the system-wide computation capacity. The optimization problem is tackled using a successive convex programming method based on a second-order convex approximation, with theoretical proof of feasibility and convergence. Simulation results validate the effectiveness and superior performance of the proposed method compared to other conventional schemes.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2022)
Article
Engineering, Electrical & Electronic
Yuanjian Li et al.
Summary: This paper considers a minimization problem in a cellular-connected unmanned aerial vehicle (UAV) network. The problem involves both the time cost and expected outage duration. A UAV navigation approach is proposed to optimize these factors by utilizing the UAV's adjustable mobility. The effectiveness of the proposed approach is demonstrated through numerical results.
IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS
(2022)
Article
Computer Science, Hardware & Architecture
Wei Wu et al.
Summary: This article presents the latest advancements in UAV swarm-enabled edge computing, including applications, architectures, implementation considerations, and enabling technologies. Moreover, future research directions, challenges, and open issues are outlined.
IEEE WIRELESS COMMUNICATIONS
(2022)
Article
Engineering, Electrical & Electronic
Haixia Peng et al.
Summary: This paper investigates multi-dimensional resource management for unmanned aerial vehicles (UAVs) assisted vehicular networks, proposing a MADDPG-based method for resource allocation at MEC servers. Simulation results show that the MADDPG method can converge within 200 training episodes and achieve higher delay/QoS satisfaction ratios than SADDPG and random schemes.
IEEE JOURNAL ON SELECTED AREAS IN COMMUNICATIONS
(2021)
Article
Engineering, Electrical & Electronic
Wanmei Feng et al.
Summary: By combining beamforming and NOMA techniques, this paper optimizes the computation performance in a wireless-powered mobile edge computing system carried by a UAV.
IEEE JOURNAL ON SELECTED AREAS IN COMMUNICATIONS
(2021)
Article
Engineering, Electrical & Electronic
Shiwei Lai et al.
Summary: This paper studies the problem of computational task offloading at mobile edge servers in intelligent secure mobile edge computing (MEC) systems. An adaptive offloading strategy is proposed to reduce latency and energy consumption in communication and computation, incorporating wireless bandwidth allocation and transmit power allocation through deep reinforcement learning. The deep Q-network based strategy aims to automatically solve the optimization problem and achieve significant system cost saving for MEC networks compared to other schemes.
PHYSICAL COMMUNICATION
(2021)
Article
Computer Science, Information Systems
Abdenacer Naouri et al.
Summary: This article proposes a three-layer task offloading framework named DCC, which effectively offloads tasks with high computing requirements to the cloud while executing tasks with low computing requirements on end devices to reduce processing delay. Experimental and simulation results demonstrate that DCC outperforms other computational offloading techniques in terms of performance.
IEEE INTERNET OF THINGS JOURNAL
(2021)
Article
Computer Science, Information Systems
Jiadai Wang et al.
Summary: The development of mobile devices has led to an increase in complex and computation-intensive mobile applications. Mobile Edge Computing (MEC) is a promising solution to the capacity constraints of mobile devices, but it also faces challenges such as high infrastructure costs and pressure on MEC servers. The proposed Deep Reinforcement Learning based Resource Allocation (DRLRA) scheme aims to adaptively allocate resources to improve service times and balance resource usage in changing MEC environments.
IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTING
(2021)
Article
Computer Science, Hardware & Architecture
Fuhui Zhou et al.
IEEE WIRELESS COMMUNICATIONS
(2020)
Article
Automation & Control Systems
Jingjing Wang et al.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2020)
Article
Engineering, Electrical & Electronic
Qian Liu et al.
IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY
(2020)
Article
Automation & Control Systems
Xiaolong Xu et al.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2020)
Article
Engineering, Electrical & Electronic
Haijun Zhang et al.
IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS
(2020)
Article
Computer Science, Information Systems
Lei Yang et al.
IEEE INTERNET OF THINGS JOURNAL
(2020)
Article
Engineering, Electrical & Electronic
Giuseppe Faraci et al.
IEEE JOURNAL ON SELECTED AREAS IN COMMUNICATIONS
(2020)
Article
Computer Science, Information Systems
Liang Zhang et al.
IEEE INTERNET OF THINGS JOURNAL
(2020)
Article
Engineering, Electrical & Electronic
Zhaohui Yang et al.
IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS
(2019)
Article
Engineering, Electrical & Electronic
Yao Du et al.
IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY
(2019)
Article
Engineering, Electrical & Electronic
Chi Harold Liu et al.
IEEE JOURNAL ON SELECTED AREAS IN COMMUNICATIONS
(2018)
