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
Xieling Chen et al.
Summary: With the rapid development of information technologies and artificial intelligence, smart healthcare and the integration of various healthcare data have gained significant momentum. This study provides a comprehensive analysis of information fusion for healthcare with AI, including major research topics, trends, and correlations, as well as the primary concerns of top countries/regions, institutions, and authors. The findings offer valuable insights for the future development of smart health with AI and guidance for international collaborations.
INFORMATION PROCESSING & MANAGEMENT
(2023)
Article
Engineering, Electrical & Electronic
Mohd Javed Khan et al.
Summary: In a high-speed vehicular scenario, power saving is a critical concern due to vehicle penetration loss (VPL) and fast signal fluctuations. Previous studies have focused on the effect of VPL in moving relay (MR)-based heterogeneous network (HetNet) models, but the issue of power saving for vehicular HetNet has not been studied yet. This paper proposes an energy-efficient algorithm for selecting the best number of cooperative MRs in a NOMA-based wireless network to efficiently utilize transmission power.
INTERNATIONAL JOURNAL OF COMMUNICATION SYSTEMS
(2023)
Article
Computer Science, Theory & Methods
Linbo Liao et al.
Summary: This paper discusses a mobile edge computing system with a server and multiple mobile devices that need to perform computation tasks with priorities. By providing computational support, mobile edge computing solves the problem of limited computing power and battery capacity of mobile devices. To minimize delay and energy consumption in the long term, an online algorithm called the double reinforcement learning computation offloading (DRLCO) algorithm is proposed.
JOURNAL OF PARALLEL AND DISTRIBUTED COMPUTING
(2023)
Article
Multidisciplinary Sciences
Prashant Shukla et al.
Summary: This study addresses the complex issues of task offloading and resource allocation in a heterogeneous fog-cloud computing environment (HFCE) by utilizing two popular multi-criteria decision-making (MCDM) techniques, AHP and TOPSIS. A rank-based computation offloading algorithm is proposed, which evaluates five performance criteria and uses AHP to calculate priority weights and TOPSIS to rank fog, cloud, and end devices. Simulation results show that the proposed algorithm outperforms conventional offloading algorithms in the HFCE, especially with a large number of tasks.
PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES INDIA SECTION A-PHYSICAL SCIENCES
(2023)
Article
Computer Science, Information Systems
Abdeladim Sadiki et al.
Summary: This paper studies the computation offloading problem in a massive MIMO-based MEC system and proposes two deep reinforcement learning algorithms to learn the optimal offloading policy without prior knowledge of the environment dynamics. Simulation results show that our DRL-based solutions outperform the state-of-the-art algorithms.
Article
Computer Science, Information Systems
Xiaohan Jiang et al.
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
Feng Ke et al.
Summary: This paper investigates the problem of task caching, offloading, and stable matching in UDRNs with MEC deployed in the relays. Improved branch-and-bound and low-complexity suboptimal algorithms are proposed for task caching and offloading. An improved stable matching algorithm based on mutual preference lists is also proposed. Simulation results demonstrate significant performance gains compared with conventional algorithms.
IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY
(2023)
Article
Computer Science, Hardware & Architecture
Prashant Shukla et al.
Summary: With the development of current computing technology, workflow applications have become more important in various fields. Researchers are paying more attention to workflow scheduling algorithms (WSA) as a real-time concern. However, it remains challenging to develop a single coherent algorithm that meets multiple criteria. This paper presents an efficient meta-heuristic approach called Multi-objective Artificial Algae (MAA) algorithm for scheduling scientific workflows in a hierarchical fog-cloud environment. The proposed approach shows significant improvements in execution time, energy consumption, and total cost compared to previous methodologies.
JOURNAL OF SUPERCOMPUTING
(2023)
Article
Computer Science, Hardware & Architecture
Zheng Wan et al.
Summary: This study aims to maximize the computation power of a mobile edge computing enabled dense network by optimizing offloading decision and resource allocation. The problem is formulated as a mixed-variable nonlinear programming problem and is decoupled into two sub-problems. An improved differential evolution algorithm is developed to address the knapsack problem. Experimental results show that our scheme provides superior computation power compared to benchmark schemes and the performance gain expands with growing connection density.
Article
Computer Science, Hardware & Architecture
Jiadi Liu et al.
Summary: Mobile cloud computing (MCC) enhances computation capability and energy saving by offloading computation-intensive tasks from resource-constrained smart mobile devices (SMDs) to resource-rich central cloud. Edge cloud provides services with lower latency, but its mobility and limited resources present challenges to optimal offloading policy. This paper proposes an optimal offloading selection strategy based on game model and an edge cloud payoff competition algorithm to minimize total execution cost.
Article
Engineering, Multidisciplinary
Jun He
Summary: This paper addresses the challenges in designing computing offloading schemes for mobile edge networks, considering distributed base station deployment, limited server resources, and dynamically changing end users. A deep reinforcement learning-based optimal computing offloading and resource allocation strategy is proposed. The authors consider a multi-user scenario and formulate the communication and calculation overheads in detail. They propose a Deep Deterministic Policy Gradient (DDPG) algorithm to minimize system energy consumption. Simulation experiments demonstrate the effectiveness of the proposed algorithm in optimizing the target value and achieving better system energy consumption compared to other algorithms. It is also shown to have excellent communication resource allocation ability.
JOURNAL OF ENGINEERING-JOE
(2023)
Article
Computer Science, Information Systems
RuiZhong Du et al.
Summary: In this study, we address the challenge of meeting the real-time requirements of medical users in the Internet of Medical Things (IoMT). We propose a novel network communication model that integrates collaborative cloud-edge-end computing and non-orthogonal multiple access (NOMA) to provide energy-efficient and low-latency services to medical users. Through a deep learning algorithm, we find the optimal offloading solution and demonstrate through simulations that our proposed solution reduces system costs significantly compared to traditional approaches.
JOURNAL OF GRID COMPUTING
(2022)
Article
Cell Biology
Jiacheng Sun et al.
Summary: In this paper, a model based on Q-learning algorithm and Neighborhood Regularized Logistic Matrix Factorization (QLNRLMF) is proposed to predict drug-target interactions (DTIs) by fusing heterogeneous information. The model has achieved better effect compared to existing methods in benchmark datasets.
FRONTIERS IN CELL AND DEVELOPMENTAL BIOLOGY
(2022)
Article
Engineering, Electrical & Electronic
Sabyasachi Gupta et al.
Summary: This article proposes a novel framework for a multi-user mobile edge computing (MEC) network, where users with high downlink rate demands and users with intensive computation tasks can collaborate to reduce task completion time and improve downlink user rates. By using non-orthogonal multiple access (NOMA), the users with computation tasks can offload part of the tasks to the edge cloud and the downlink users, while forwarding information received from the base station (BS) to the downlink users. A joint optimization of communication and computational resources, user pairings, task sharing, and relay bits is performed to minimize task completion time and satisfy downlink user incentives. Simulation results demonstrate significant reductions in task completion time and computational energy savings at the edge cloud, as well as improved downlink user rates compared to orthogonal transmission.
IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY
(2022)
Article
Computer Science, Information Systems
Jin Qi et al.
Summary: In this paper, an intelligent computing offloading model is proposed to address the problems of computing power, reliability, and cost when intelligent vehicles deal with computationally intensive and delay-sensitive emerging applications. The model uses the DDPG algorithm to minimize the total system cost and improve the success rate of computational offloading.
IEEE TRANSACTIONS ON NETWORK AND SERVICE MANAGEMENT
(2022)
Article
Telecommunications
Mohd Javed Khan et al.
Summary: This study proposes an MR-based HetNet model using NOMA technique and Rayleigh fading channels for downlink communication. Through joint analysis and simulation experiments, it is found that cooperative NOMA has lower outage performance compared to cooperative OMA, and the outage probability of vehicular users is related to the residual interference value.
TRANSACTIONS ON EMERGING TELECOMMUNICATIONS TECHNOLOGIES
(2022)
Article
Computer Science, Information Systems
Azza H. Ahmed et al.
Summary: This article proposes a novel control framework, Intelligent Control for Self-driving RAN (ICRAN), to maximize radio resources utilization and minimize performance degradation in the radio access network (RAN). By utilizing two deep reinforcement learning approaches, ICRAN achieves centralized and distributed control and successfully fulfills its design goals.
IEEE TRANSACTIONS ON NETWORK AND SERVICE MANAGEMENT
(2022)
Article
Computer Science, Information Systems
Yangguang Lu et al.
Summary: This paper investigates the problem of task offloading and resource scheduling in Ultra-Dense Networks (UDN) with Mobile Edge Computing (MEC). The authors propose algorithms to solve the sub-problems and validate their effectiveness through experiments.
IEEE TRANSACTIONS ON NETWORK AND SERVICE MANAGEMENT
(2022)
Article
Computer Science, Information Systems
Laha Ale et al.
Summary: This research proposes a novel deep reinforcement learning algorithm, D3PG, to optimize task partitioning and computational power allocation in mobile-edge computing. The algorithm can handle constrained distribution-continuous hybrid action spaces and achieves good performance in multiobjective optimization, task processing quantity, energy cost, and service latency.
IEEE INTERNET OF THINGS JOURNAL
(2022)
Proceedings Paper
Computer Science, Information Systems
Lingxiao Chen et al.
Summary: This paper investigates the joint optimization problem of computation offloading, resource allocation, and service caching replacement in a collaborative MEC system, and proposes a DDPG-based algorithm to solve the problem.
IEEE INFOCOM 2022 - IEEE CONFERENCE ON COMPUTER COMMUNICATIONS WORKSHOPS (INFOCOM WKSHPS)
(2022)
Proceedings Paper
Computer Science, Information Systems
Ziqi Lin et al.
Summary: This paper studies the task offloading problem in an MEC-enabled UDN architecture, and proposes an online task offloading algorithm based on DRL technique, which can effectively meet the energy budget constraints of mobile devices without knowing the channel state information and computational capabilities of the base stations.
2022 IEEE WIRELESS COMMUNICATIONS AND NETWORKING CONFERENCE (WCNC)
(2022)
Article
Computer Science, Hardware & Architecture
Junfeng Zou et al.
Summary: This article proposes a dual offloading framework to address the complexity and resource utilization issues in offloading tasks from edge devices. By modeling the offloading process as MDP and utilizing the A3C algorithm as the decision-making strategy, it achieves workload balancing for edge servers and reduces energy and time overhead.
IEEE TRANSACTIONS ON COMPUTERS
(2021)
Article
Engineering, Electrical & Electronic
Lixin Li et al.
Summary: The article studies the resource allocation problem of a NOMA-MEC system in an ultra-dense network, proposing the UCM and MF-DDPG algorithms to minimize the system computation cost.
IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS
(2021)
Article
Computer Science, Information Systems
Yunpeng Wang et al.
Summary: In this study, a UAV-assisted Mobile Edge Computing system is optimized to minimize processing delay by jointly optimizing user scheduling, task offloading ratio, UAV flight angle, and flight speed. A Deep Deterministic Policy Gradient algorithm is proposed for uncontrollable dynamic environments, achieving significant improvements in processing delay over baseline algorithms.
Article
Computer Science, Information Systems
Tong Liu et al.
Summary: This article introduces an optimized task offloading strategy based on mobile-edge computing in an ultradense network. A double deep Q network (DDQN) approach is proposed using reinforcement learning, along with a context-aware attention mechanism. Extensive simulations demonstrate the effectiveness of the proposed method.
IEEE INTERNET OF THINGS JOURNAL
(2021)
Article
Engineering, Electrical & Electronic
Ying Zhang et al.
Summary: This paper proposes a reinforcement learning-based opportunistic routing protocol (RLOR) for underwater acoustic sensor networks, which comprehensively considers nodes' peripheral status to select appropriate relay nodes and employs a recovery mechanism to improve data delivery rates. In underwater dynamic network environments, RLOR performs well in terms of end-to-end delay, reliability, and energy efficiency.
IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY
(2021)
Article
Computer Science, Information Systems
Shihong Hu et al.
IEEE INTERNET OF THINGS JOURNAL
(2020)
Article
Computer Science, Information Systems
Shi Yang
COMPUTER COMMUNICATIONS
(2020)
Proceedings Paper
Engineering, Electrical & Electronic
Samrat Nath et al.
ICC 2020 - 2020 IEEE INTERNATIONAL CONFERENCE ON COMMUNICATIONS (ICC)
(2020)
Article
Engineering, Electrical & Electronic
Siyang Liu et al.
IET COMMUNICATIONS
(2020)
Article
Computer Science, Information Systems
A. Ravishankar Rao et al.
INTERNET OF THINGS
(2020)
Article
Engineering, Electrical & Electronic
Wen Sun et al.
IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY
(2020)
Article
Engineering, Electrical & Electronic
Zhiguo Ding et al.
IEEE TRANSACTIONS ON COMMUNICATIONS
(2019)
Article
Engineering, Electrical & Electronic
Simeng Feng et al.
IEEE TRANSACTIONS ON COMMUNICATIONS
(2019)
Article
Engineering, Electrical & Electronic
Hong Xing et al.
IEEE TRANSACTIONS ON COMMUNICATIONS
(2019)
Article
Computer Science, Information Systems
Xianfu Chen et al.
IEEE INTERNET OF THINGS JOURNAL
(2019)
