首页 > 最新文献

IEEE Transactions on Network and Service Management最新文献

英文 中文
MobiFi: Mobility-Aware Reactive and Proactive Wireless Resource Management in LiFi-WiFi Networks MobiFi:LiFi-WiFi 网络中的移动感知、反应式和主动式无线资源管理
IF 4.7 2区 计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS Pub Date : 2024-09-05 DOI: 10.1109/TNSM.2024.3455105
Hansini Vijayaraghavan;Wolfgang Kellerer
This paper presents MobiFi, a framework addressing the challenges in managing LiFi-WiFi heterogeneous networks focusing on mobility-aware resource allocation. Our contributions include introducing a centralized framework incorporating reactive and proactive strategies for resource management in mobile LiFi-only and LiFi-WiFi networks. This framework reacts to current network conditions and proactively anticipates the future, considering user positions, line-of-sight blockages, and channel quality. Recognizing the importance of long-term network performance, particularly for use cases such as video streaming, we tackle the challenge of optimal proactive resource allocation by formulating an optimization problem that integrates access point assignment and wireless resource allocation using the alpha-fairness objective over time. Our proactive strategy significantly outperforms the reactive resource allocation, ensuring 7.7% higher average rate and 63.3% higher minimum user rate for a 10-user LiFi-WiFi network. We employ sophisticated techniques, including a Branch and Bound-based Mixed-Integer solver and a low-complexity, Evolutionary Game Theory-based algorithm to achieve this. Lastly, we introduce a novel approach to simulate errors in predictive user position modeling to assess the robustness of our proactive allocation strategy against real-world uncertainties. The contributions of MobiFi advance the field of resource management in mobile LiFi-WiFi networks, enabling efficiency and reliability.
本文介绍了MobiFi,这是一个解决管理wifi - wifi异构网络挑战的框架,专注于移动感知资源分配。我们的贡献包括引入一个集中框架,将被动和主动策略结合起来,用于移动LiFi-only和LiFi-WiFi网络的资源管理。该框架对当前网络条件作出反应,并考虑到用户位置、视距阻塞和信道质量,主动预测未来。认识到长期网络性能的重要性,特别是对于视频流等用例,我们通过制定一个优化问题来解决最优主动资源分配的挑战,该问题集成了接入点分配和无线资源分配,随着时间的推移使用α -公平目标。我们的主动策略显著优于被动资源分配,确保10用户LiFi-WiFi网络的平均速率提高7.7%,最低用户速率提高63.3%。我们采用了复杂的技术,包括基于分支和边界的混合整数求解器和低复杂度的基于进化博弈论的算法来实现这一目标。最后,我们引入了一种新的方法来模拟预测用户位置建模中的误差,以评估我们的主动分配策略对现实世界不确定性的鲁棒性。MobiFi的贡献推动了移动LiFi-WiFi网络资源管理领域的发展,提高了效率和可靠性。
{"title":"MobiFi: Mobility-Aware Reactive and Proactive Wireless Resource Management in LiFi-WiFi Networks","authors":"Hansini Vijayaraghavan;Wolfgang Kellerer","doi":"10.1109/TNSM.2024.3455105","DOIUrl":"10.1109/TNSM.2024.3455105","url":null,"abstract":"This paper presents MobiFi, a framework addressing the challenges in managing LiFi-WiFi heterogeneous networks focusing on mobility-aware resource allocation. Our contributions include introducing a centralized framework incorporating reactive and proactive strategies for resource management in mobile LiFi-only and LiFi-WiFi networks. This framework reacts to current network conditions and proactively anticipates the future, considering user positions, line-of-sight blockages, and channel quality. Recognizing the importance of long-term network performance, particularly for use cases such as video streaming, we tackle the challenge of optimal proactive resource allocation by formulating an optimization problem that integrates access point assignment and wireless resource allocation using the alpha-fairness objective over time. Our proactive strategy significantly outperforms the reactive resource allocation, ensuring 7.7% higher average rate and 63.3% higher minimum user rate for a 10-user LiFi-WiFi network. We employ sophisticated techniques, including a Branch and Bound-based Mixed-Integer solver and a low-complexity, Evolutionary Game Theory-based algorithm to achieve this. Lastly, we introduce a novel approach to simulate errors in predictive user position modeling to assess the robustness of our proactive allocation strategy against real-world uncertainties. The contributions of MobiFi advance the field of resource management in mobile LiFi-WiFi networks, enabling efficiency and reliability.","PeriodicalId":13423,"journal":{"name":"IEEE Transactions on Network and Service Management","volume":"21 6","pages":"6597-6613"},"PeriodicalIF":4.7,"publicationDate":"2024-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10666849","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142187257","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Multi-Agent DRL-Based Two-Timescale Resource Allocation for Network Slicing in V2X Communications 基于 DRL 的多代理双时标资源分配用于 V2X 通信中的网络分片
IF 4.7 2区 计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS Pub Date : 2024-09-05 DOI: 10.1109/TNSM.2024.3454758
Binbin Lu;Yuan Wu;Liping Qian;Sheng Zhou;Haixia Zhang;Rongxing Lu
Network slicing has been envisioned to play a crucial role in supporting various vehicular applications with diverse performance requirements in dynamic Vehicle-to-Everything (V2X) communications systems. However, time-varying Service Level Agreements (SLAs) of slices and fast-changing network topologies in V2X scenarios may introduce new challenges for enabling efficient inter-slice resource provisioning to guarantee the Quality of Service (QoS) while avoiding both resource over-provisioning and under-provisioning. Moreover, the conventional centralized resource allocation schemes requiring global slice information may degrade the data privacy provided by dedicated resource provisioning. To address these challenges, in this paper, we propose a two-timescale resource management mechanism for providing diverse V2X slices with customized resources. In the long timescale, we propose a Proximal Policy Optimization-based multi-agent deep reinforcement learning algorithm for dynamically allocating bandwidth resources to different slices for guaranteeing their SLAs. Under the coordination of agents, each agent only observes its partial state space rather than the global information to adjust the resource requests, which can enhance the privacy protection. Moreover, an expert demonstration mechanism is proposed to guide the action policy for reducing the invalid action exploration and accelerating the convergence of agents. In the short-term time slot, with our proposed Cross Entropy and Successive Convex Approximation algorithm, each slice allocates its available physical resource blocks and optimizes its transmit power to meet the QoS. Simulation results show our proposed two-timescale resource allocation scheme for network slicing can achieve maximum 8.4% performance gains in terms of spectral efficiency while guaranteeing the QoS requirements of users compared to the baseline approaches.
网络切片被设想为在支持动态车联网(V2X)通信系统中具有不同性能要求的各种车辆应用方面发挥关键作用。然而,在V2X场景中,切片的时变服务水平协议(sla)和快速变化的网络拓扑可能会给实现高效的片间资源配置带来新的挑战,从而保证服务质量(QoS),同时避免资源过度配置和不足配置。此外,传统的集中式资源分配方案需要全局片信息,可能会降低专用资源分配所提供的数据保密性。为了应对这些挑战,在本文中,我们提出了一种双时间尺度资源管理机制,用于提供具有定制资源的各种V2X片。在长时间尺度下,我们提出了一种基于近端策略优化的多智能体深度强化学习算法,用于动态分配带宽资源到不同的片,以保证其sla。在agent协调下,每个agent只观察其局部状态空间而不是全局信息来调整资源请求,增强了对隐私的保护。此外,提出了一种专家示范机制来指导行动策略,以减少无效行动探索,加速智能体的收敛。在短时时隙内,利用交叉熵和连续凸逼近算法,每个分片分配其可用的物理资源块,并优化其发射功率以满足QoS要求。仿真结果表明,与基线方法相比,我们提出的网络切片双时间尺度资源分配方案在保证用户QoS要求的同时,在频谱效率方面的性能提升最大可达8.4%。
{"title":"Multi-Agent DRL-Based Two-Timescale Resource Allocation for Network Slicing in V2X Communications","authors":"Binbin Lu;Yuan Wu;Liping Qian;Sheng Zhou;Haixia Zhang;Rongxing Lu","doi":"10.1109/TNSM.2024.3454758","DOIUrl":"10.1109/TNSM.2024.3454758","url":null,"abstract":"Network slicing has been envisioned to play a crucial role in supporting various vehicular applications with diverse performance requirements in dynamic Vehicle-to-Everything (V2X) communications systems. However, time-varying Service Level Agreements (SLAs) of slices and fast-changing network topologies in V2X scenarios may introduce new challenges for enabling efficient inter-slice resource provisioning to guarantee the Quality of Service (QoS) while avoiding both resource over-provisioning and under-provisioning. Moreover, the conventional centralized resource allocation schemes requiring global slice information may degrade the data privacy provided by dedicated resource provisioning. To address these challenges, in this paper, we propose a two-timescale resource management mechanism for providing diverse V2X slices with customized resources. In the long timescale, we propose a Proximal Policy Optimization-based multi-agent deep reinforcement learning algorithm for dynamically allocating bandwidth resources to different slices for guaranteeing their SLAs. Under the coordination of agents, each agent only observes its partial state space rather than the global information to adjust the resource requests, which can enhance the privacy protection. Moreover, an expert demonstration mechanism is proposed to guide the action policy for reducing the invalid action exploration and accelerating the convergence of agents. In the short-term time slot, with our proposed Cross Entropy and Successive Convex Approximation algorithm, each slice allocates its available physical resource blocks and optimizes its transmit power to meet the QoS. Simulation results show our proposed two-timescale resource allocation scheme for network slicing can achieve maximum 8.4% performance gains in terms of spectral efficiency while guaranteeing the QoS requirements of users compared to the baseline approaches.","PeriodicalId":13423,"journal":{"name":"IEEE Transactions on Network and Service Management","volume":"21 6","pages":"6744-6758"},"PeriodicalIF":4.7,"publicationDate":"2024-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142187259","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
A Deep Learning System for Detecting IoT Web Attacks With a Joint Embedded Prediction Architecture (JEPA) 利用联合嵌入式预测架构 (JEPA) 检测物联网网络攻击的深度学习系统
IF 4.7 2区 计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS Pub Date : 2024-09-05 DOI: 10.1109/TNSM.2024.3454777
Yufei An;F. Richard Yu;Ying He;Jianqiang Li;Jianyong Chen;Victor C. M. Leung
The advancement of Internet of Things (IoT) technology has significantly transformed the dynamic between humans and devices, as well as device-to-device interactions. This paradigm shift has led to profound changes in human lifestyles and production processes. Through the interconnectedness of numerous sensors and controllers via networks, the IoT facilitates the seamless integration of humans with diverse devices, leading to substantial economic advantages. Nevertheless, the burgeoning IoT industry and the rapid proliferation of various IoT devices have also introduced a multitude of security vulnerabilities. Cyber attackers frequently exploit cyber attacks to compromise IoT devices, jeopardizing user privacy and property security, thereby posing a grave menace to the overall security of the IoT ecosystem. In this paper, we propose a novel IoT Web attack detection system based on a joint embedded prediction architecture (JEPA), which effectively alleviates the security issues faced by IoT. It can obtain high-level semantic features in IoT traffic data through non-generative self-supervised learning. These features can more effectively distinguish normal data from attack data and help improve the overall detection performance of the system. Moreover, we propose a feature interaction module based on a dual-branch network, which effectively fuses low-level features and high-level features, and comprehensively aggregates global features and local features. Simulation results on multiple datasets show that our proposed system has better detection performance and robustness.
物联网(IoT)技术的进步极大地改变了人与设备之间的动态,以及设备与设备之间的交互。这种模式的转变导致了人类生活方式和生产过程的深刻变化。通过网络将众多传感器和控制器互连起来,物联网促进了人类与各种设备的无缝集成,从而带来了巨大的经济优势。然而,蓬勃发展的物联网行业和各种物联网设备的快速扩散也带来了大量的安全漏洞。网络攻击者频繁利用网络攻击危害物联网设备,危害用户隐私和财产安全,对物联网生态系统整体安全构成严重威胁。本文提出了一种基于联合嵌入式预测架构(JEPA)的物联网Web攻击检测系统,有效缓解了物联网面临的安全问题。它可以通过非生成式自监督学习获得物联网流量数据中的高级语义特征。这些特征可以更有效地区分正常数据和攻击数据,提高系统的整体检测性能。此外,我们提出了基于双分支网络的特征交互模块,有效融合了低级特征和高级特征,综合聚合了全局特征和局部特征。在多个数据集上的仿真结果表明,该系统具有较好的检测性能和鲁棒性。
{"title":"A Deep Learning System for Detecting IoT Web Attacks With a Joint Embedded Prediction Architecture (JEPA)","authors":"Yufei An;F. Richard Yu;Ying He;Jianqiang Li;Jianyong Chen;Victor C. M. Leung","doi":"10.1109/TNSM.2024.3454777","DOIUrl":"10.1109/TNSM.2024.3454777","url":null,"abstract":"The advancement of Internet of Things (IoT) technology has significantly transformed the dynamic between humans and devices, as well as device-to-device interactions. This paradigm shift has led to profound changes in human lifestyles and production processes. Through the interconnectedness of numerous sensors and controllers via networks, the IoT facilitates the seamless integration of humans with diverse devices, leading to substantial economic advantages. Nevertheless, the burgeoning IoT industry and the rapid proliferation of various IoT devices have also introduced a multitude of security vulnerabilities. Cyber attackers frequently exploit cyber attacks to compromise IoT devices, jeopardizing user privacy and property security, thereby posing a grave menace to the overall security of the IoT ecosystem. In this paper, we propose a novel IoT Web attack detection system based on a joint embedded prediction architecture (JEPA), which effectively alleviates the security issues faced by IoT. It can obtain high-level semantic features in IoT traffic data through non-generative self-supervised learning. These features can more effectively distinguish normal data from attack data and help improve the overall detection performance of the system. Moreover, we propose a feature interaction module based on a dual-branch network, which effectively fuses low-level features and high-level features, and comprehensively aggregates global features and local features. Simulation results on multiple datasets show that our proposed system has better detection performance and robustness.","PeriodicalId":13423,"journal":{"name":"IEEE Transactions on Network and Service Management","volume":"21 6","pages":"6885-6898"},"PeriodicalIF":4.7,"publicationDate":"2024-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142187260","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Distributed Traffic Engineering in Hybrid Software Defined Networks: A Multi-Agent Reinforcement Learning Framework 混合软件定义网络中的分布式流量工程:多代理强化学习框架
IF 4.7 2区 计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS Pub Date : 2024-09-04 DOI: 10.1109/TNSM.2024.3454282
Yingya Guo;Bin Lin;Qi Tang;Yulong Ma;Huan Luo;Han Tian;Kai Chen
Traffic Engineering (TE) is an efficient technique to balance network flows and thus improves the performance of a hybrid Software Defined Network (SDN). Previous TE solutions mainly leverage heuristic algorithms to centrally optimize link weight setting or traffic splitting ratios under the static traffic demand. Note that as the network scale becomes larger and network management gains more complexity, it is notably that the centralized TE methods suffer from a high computation overhead and a long reaction time to optimize routing of flows when the network traffic demand dynamically fluctuates or network failures happen. To enable adaptive and efficient routing in distributed TE, we propose a Multi-agent Reinforcement Learning method CMRL that divides the routing optimization of a large network into multiple small-scale routing decision-making problems. To coordinate the multiple agents for achieving a global optimization goal in a hybrid SDN scenario, we construct a reasonable virtual environment to meet different routing constraints brought by legacy routers and SDN switches for training the routing agents. To train the routing agents for determining the local routing policies according to local network observations, we introduce the difference reward assignment mechanism for encouraging agents to cooperatively take optimal routing action. Extensive simulations conducted on the real traffic traces demonstrate the superiority of CMRL in improving TE performance, especially when traffic demands change or network failures happen.
流量工程(TE)是一种有效的网络流量平衡技术,可以提高混合型软件定义网络(SDN)的性能。以往的TE解决方案主要利用启发式算法,在静态流量需求下集中优化链路权重设置或分流比例。请注意,随着网络规模的扩大和网络管理的复杂性的增加,当网络流量需求动态波动或发生网络故障时,集中式TE方法的计算开销较高,优化流路由的反应时间较长。为了在分布式TE中实现自适应和高效路由,我们提出了一种多智能体强化学习方法CMRL,该方法将大型网络的路由优化划分为多个小规模路由决策问题。为了在混合SDN场景下协调多个agent实现全局优化目标,我们构建了一个合理的虚拟环境来满足传统路由器和SDN交换机带来的不同路由约束,以训练路由agent。为了训练路由智能体根据本地网络观察来确定本地路由策略,我们引入了差分奖励分配机制来鼓励智能体合作采取最优路由行为。在真实流量轨迹上进行的大量仿真表明,CMRL在提高TE性能方面具有优势,特别是在流量需求发生变化或网络发生故障时。
{"title":"Distributed Traffic Engineering in Hybrid Software Defined Networks: A Multi-Agent Reinforcement Learning Framework","authors":"Yingya Guo;Bin Lin;Qi Tang;Yulong Ma;Huan Luo;Han Tian;Kai Chen","doi":"10.1109/TNSM.2024.3454282","DOIUrl":"10.1109/TNSM.2024.3454282","url":null,"abstract":"Traffic Engineering (TE) is an efficient technique to balance network flows and thus improves the performance of a hybrid Software Defined Network (SDN). Previous TE solutions mainly leverage heuristic algorithms to centrally optimize link weight setting or traffic splitting ratios under the static traffic demand. Note that as the network scale becomes larger and network management gains more complexity, it is notably that the centralized TE methods suffer from a high computation overhead and a long reaction time to optimize routing of flows when the network traffic demand dynamically fluctuates or network failures happen. To enable adaptive and efficient routing in distributed TE, we propose a Multi-agent Reinforcement Learning method CMRL that divides the routing optimization of a large network into multiple small-scale routing decision-making problems. To coordinate the multiple agents for achieving a global optimization goal in a hybrid SDN scenario, we construct a reasonable virtual environment to meet different routing constraints brought by legacy routers and SDN switches for training the routing agents. To train the routing agents for determining the local routing policies according to local network observations, we introduce the difference reward assignment mechanism for encouraging agents to cooperatively take optimal routing action. Extensive simulations conducted on the real traffic traces demonstrate the superiority of CMRL in improving TE performance, especially when traffic demands change or network failures happen.","PeriodicalId":13423,"journal":{"name":"IEEE Transactions on Network and Service Management","volume":"21 6","pages":"6759-6769"},"PeriodicalIF":4.7,"publicationDate":"2024-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142187261","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Multi-Agent DRL-Based Energy Harvesting for Freshness of Data in UAV-Assisted Wireless Sensor Networks 基于 DRL 的多代理能量收集,提高无人机辅助无线传感器网络的数据新鲜度
IF 4.7 2区 计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS Pub Date : 2024-09-04 DOI: 10.1109/TNSM.2024.3454217
Mesfin Leranso Betalo;Supeng Leng;Hayla Nahom Abishu;Abegaz Mohammed Seid;Maged Fakirah;Aiman Erbad;Mohsen Guizani
In sixth-generation (6G) networks, unmanned aerial vehicles (UAVs) are expected to be widely used as aerial base stations (ABS) due to their adaptability, low deployment costs, and ultra-low latency responses. However, UAVs consume large amounts of power to collect data from multiple sensor nodes (SNs). This can limit their flight time and transmission efficiency, resulting in delays and low information freshness. In this paper, we present a multi-access edge computing (MEC)-integrated UAV-assisted wireless sensor network (WSN) with a laser technology-based energy harvesting (EH) system that makes the UAV act as a flying energy charger to address these issues. This work aims to minimize the age of information (AoI) and improve energy efficiency by jointly optimizing the UAV trajectories, EH, task scheduling, and data offloading. The joint optimization problem is formulated as a Markov decision process (MDP) and then transformed into a stochastic game model to handle the complexity and dynamics of the environment. We adopt a multi-agent deep Q-network (MADQN) algorithm to solve the formulated optimization problem. With the MADQN algorithm, UAVs can determine the best data collection and EH decisions to minimize their energy consumption and efficiently collect data from multiple SNs, leading to reduced AoI and improved energy efficiency. Compared to the benchmark algorithms such as deep deterministic policy gradient (DDPG), Dueling DQN, asynchronous advantage actor-critic (A3C) and Greedy, the MADQN algorithm has a lower average AoI and improves energy efficiency by 95.5%, 89.9%, 78.02% and 65.52% respectively.
在第六代(6G)网络中,无人驾驶飞行器(uav)由于其适应性强、部署成本低、超低延迟响应等优点,有望广泛应用于空中基站(ABS)。然而,无人机从多个传感器节点(SNs)收集数据需要消耗大量的功率。这限制了他们的飞行时间和传输效率,导致延误和信息新鲜度低。在本文中,我们提出了一种集成多接入边缘计算(MEC)的无人机辅助无线传感器网络(WSN),该网络具有基于激光技术的能量收集(EH)系统,使无人机充当飞行能量充电器来解决这些问题。本研究旨在通过联合优化无人机轨迹、EH、任务调度和数据卸载,最大限度地减少信息时代(AoI),提高能源效率。将联合优化问题表述为马尔可夫决策过程(MDP),然后将其转化为随机博弈模型来处理环境的复杂性和动态性。我们采用多智能体深度q -网络(MADQN)算法来解决公式化的优化问题。利用MADQN算法,无人机可以确定最佳的数据收集和EH决策,以最小化其能量消耗,并有效地从多个SNs收集数据,从而降低AoI并提高能源效率。与deep deterministic policy gradient (DDPG)、Dueling DQN、asynchronous advantage actor-critic (A3C)和Greedy等基准算法相比,MADQN算法的平均AoI更低,能效分别提高了95.5%、89.9%、78.02%和65.52%。
{"title":"Multi-Agent DRL-Based Energy Harvesting for Freshness of Data in UAV-Assisted Wireless Sensor Networks","authors":"Mesfin Leranso Betalo;Supeng Leng;Hayla Nahom Abishu;Abegaz Mohammed Seid;Maged Fakirah;Aiman Erbad;Mohsen Guizani","doi":"10.1109/TNSM.2024.3454217","DOIUrl":"10.1109/TNSM.2024.3454217","url":null,"abstract":"In sixth-generation (6G) networks, unmanned aerial vehicles (UAVs) are expected to be widely used as aerial base stations (ABS) due to their adaptability, low deployment costs, and ultra-low latency responses. However, UAVs consume large amounts of power to collect data from multiple sensor nodes (SNs). This can limit their flight time and transmission efficiency, resulting in delays and low information freshness. In this paper, we present a multi-access edge computing (MEC)-integrated UAV-assisted wireless sensor network (WSN) with a laser technology-based energy harvesting (EH) system that makes the UAV act as a flying energy charger to address these issues. This work aims to minimize the age of information (AoI) and improve energy efficiency by jointly optimizing the UAV trajectories, EH, task scheduling, and data offloading. The joint optimization problem is formulated as a Markov decision process (MDP) and then transformed into a stochastic game model to handle the complexity and dynamics of the environment. We adopt a multi-agent deep Q-network (MADQN) algorithm to solve the formulated optimization problem. With the MADQN algorithm, UAVs can determine the best data collection and EH decisions to minimize their energy consumption and efficiently collect data from multiple SNs, leading to reduced AoI and improved energy efficiency. Compared to the benchmark algorithms such as deep deterministic policy gradient (DDPG), Dueling DQN, asynchronous advantage actor-critic (A3C) and Greedy, the MADQN algorithm has a lower average AoI and improves energy efficiency by 95.5%, 89.9%, 78.02% and 65.52% respectively.","PeriodicalId":13423,"journal":{"name":"IEEE Transactions on Network and Service Management","volume":"21 6","pages":"6527-6541"},"PeriodicalIF":4.7,"publicationDate":"2024-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142187263","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
QoE-Driven Cross-Layer Bitrate Allocation Approach for MEC-Supported Adaptive Video Streaming 支持 MEC 的自适应视频流的 QoE 驱动型跨层比特率分配方法
IF 4.7 2区 计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS Pub Date : 2024-09-03 DOI: 10.1109/TNSM.2024.3453992
Yashar Farzaneh Yeznabad;Markus Helfert;Gabriel-Miro Muntean
The Software-Defined Mobile Network (SDMN), Multi-Access Edge Computing (MEC), Cloud RAN (C-RAN), and Network Slicing are the promising solutions that have been defined for the next generation of the wireless mobile networks in order to fulfill the increasing Quality of Experience (QoE) demand of the mobile users and the Quality of Service (QoS) concerns of high-performance, innovative services. In today’s complex telecommunications network, coupled with continuous traffic growth, and users’ demand for higher speeds, it is vital for mobile operators to allocate their available resources efficiently. This paper focuses on the joint resource allocation problem of delivering adaptive video streams to users located in different slices of a wireless network enabled by MEC, SDMN, and C-RAN technologies. It proposes a novel Cross-Layer QoE-Driven Bitrate Allocation (CLQDBA) algorithm, that aims to improve system utilization by using information from the higher layers regarding traffic patterns and desired video quality of HTTP Adaptive Streaming (HAS) users. The mixed-integer nonlinear program is formulated, taking into account network slice requirements, radio resource limitations, storage and transcoding capacity of MEC servers, and users’ quality of experience. CLQDBA is a low complexity greedy-based algorithm aims to maximize users’ quality of experience (QoE) and minimize the deviation between the achievable throughput at the MAC-layer for users and the value of allocated bit rates for video frames at the application layer. The simulation result shows that compared to the baseline scheme, our introduced algorithm, on average, achieves a 15% higher system utilization, 17% higher video quality, and 13% improvement of Jain’s Fairness index for HAS users.
软件定义移动网络(SDMN)、多接入边缘计算(MEC)、云RAN (C-RAN)和网络切片是为下一代无线移动网络定义的有前途的解决方案,以满足移动用户日益增长的体验质量(QoE)需求和高性能创新服务的服务质量(QoS)关注。在当今复杂的电信网络中,随着流量的不断增长和用户对更高速度的需求,移动运营商如何有效地分配其可用资源至关重要。本文重点研究了通过MEC、SDMN和C-RAN技术向位于无线网络不同切片的用户提供自适应视频流的联合资源分配问题。提出了一种新颖的跨层qos驱动比特率分配(CLQDBA)算法,该算法旨在通过利用来自高层的有关HTTP自适应流(HAS)用户的流量模式和所需视频质量的信息来提高系统利用率。考虑到网络切片要求、无线电资源限制、MEC服务器的存储和转码能力以及用户体验质量,制定了混合整数非线性规划。CLQDBA是一种低复杂度的基于贪婪的算法,其目的是最大化用户的体验质量(QoE),最小化用户在mac层可实现的吞吐量与在应用层为视频帧分配的比特率值之间的偏差。仿真结果表明,与基线方案相比,本文算法的系统利用率平均提高了15%,视频质量平均提高了17%,Jain公平性指数平均提高了13%。
{"title":"QoE-Driven Cross-Layer Bitrate Allocation Approach for MEC-Supported Adaptive Video Streaming","authors":"Yashar Farzaneh Yeznabad;Markus Helfert;Gabriel-Miro Muntean","doi":"10.1109/TNSM.2024.3453992","DOIUrl":"10.1109/TNSM.2024.3453992","url":null,"abstract":"The Software-Defined Mobile Network (SDMN), Multi-Access Edge Computing (MEC), Cloud RAN (C-RAN), and Network Slicing are the promising solutions that have been defined for the next generation of the wireless mobile networks in order to fulfill the increasing Quality of Experience (QoE) demand of the mobile users and the Quality of Service (QoS) concerns of high-performance, innovative services. In today’s complex telecommunications network, coupled with continuous traffic growth, and users’ demand for higher speeds, it is vital for mobile operators to allocate their available resources efficiently. This paper focuses on the joint resource allocation problem of delivering adaptive video streams to users located in different slices of a wireless network enabled by MEC, SDMN, and C-RAN technologies. It proposes a novel Cross-Layer QoE-Driven Bitrate Allocation (CLQDBA) algorithm, that aims to improve system utilization by using information from the higher layers regarding traffic patterns and desired video quality of HTTP Adaptive Streaming (HAS) users. The mixed-integer nonlinear program is formulated, taking into account network slice requirements, radio resource limitations, storage and transcoding capacity of MEC servers, and users’ quality of experience. CLQDBA is a low complexity greedy-based algorithm aims to maximize users’ quality of experience (QoE) and minimize the deviation between the achievable throughput at the MAC-layer for users and the value of allocated bit rates for video frames at the application layer. The simulation result shows that compared to the baseline scheme, our introduced algorithm, on average, achieves a 15% higher system utilization, 17% higher video quality, and 13% improvement of Jain’s Fairness index for HAS users.","PeriodicalId":13423,"journal":{"name":"IEEE Transactions on Network and Service Management","volume":"21 6","pages":"6857-6874"},"PeriodicalIF":4.7,"publicationDate":"2024-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10663668","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142187262","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
ANDE: Detect the Anonymity Web Traffic With Comprehensive Model ANDE: 利用综合模型检测匿名网络流量
IF 4.7 2区 计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS Pub Date : 2024-09-03 DOI: 10.1109/TNSM.2024.3453917
Yunlong Deng;Tao Peng;Bangchao Wang;Gan Wu
The escalating growth of network technology and users poses critical challenges to network security. This paper introduces ANDE, a novel framework designed to enhance the classification accuracy of anonymity networks. ANDE incorporates both raw data features and statistical features extracted from network traffic. Raw data features are transformed into images, enabling recognition and classification using robust image domain models. ANDE combines an enhanced Squeeze-and-Excitation (SE) ResNet with Multilayer Perceptrons (MLP), facilitating concurrent learning and classification of both feature types. Extensive experiments on two publicly available datasets demonstrate the superior performance of ANDE compared to traditional machine learning and deep learning methods. The comprehensive evaluation underscores ANDE’s effectiveness in accurately classifying network traffic within anonymity networks. Additionally, this study empirically validates the efficacy of the SE block in augmenting the classification capabilities of the proposed framework, establishing ANDE as a promising solution for network traffic classification in the realm of network security.
网络技术和用户的不断增长对网络安全提出了严峻的挑战。本文介绍了一种用于提高匿名网络分类精度的新框架ANDE。ANDE结合了从网络流量中提取的原始数据特征和统计特征。将原始数据特征转换为图像,使用鲁棒图像域模型实现识别和分类。ANDE结合了增强的压缩激励(SE) ResNet和多层感知器(MLP),促进了两种特征类型的并发学习和分类。在两个公开可用的数据集上进行的大量实验表明,与传统的机器学习和深度学习方法相比,ANDE具有优越的性能。综合评估强调了ANDE在匿名网络中准确分类网络流量的有效性。此外,本研究通过实证验证了SE块在增强所提出框架的分类能力方面的有效性,确立了ANDE作为网络安全领域中网络流量分类的一个有前途的解决方案。
{"title":"ANDE: Detect the Anonymity Web Traffic With Comprehensive Model","authors":"Yunlong Deng;Tao Peng;Bangchao Wang;Gan Wu","doi":"10.1109/TNSM.2024.3453917","DOIUrl":"10.1109/TNSM.2024.3453917","url":null,"abstract":"The escalating growth of network technology and users poses critical challenges to network security. This paper introduces ANDE, a novel framework designed to enhance the classification accuracy of anonymity networks. ANDE incorporates both raw data features and statistical features extracted from network traffic. Raw data features are transformed into images, enabling recognition and classification using robust image domain models. ANDE combines an enhanced Squeeze-and-Excitation (SE) ResNet with Multilayer Perceptrons (MLP), facilitating concurrent learning and classification of both feature types. Extensive experiments on two publicly available datasets demonstrate the superior performance of ANDE compared to traditional machine learning and deep learning methods. The comprehensive evaluation underscores ANDE’s effectiveness in accurately classifying network traffic within anonymity networks. Additionally, this study empirically validates the efficacy of the SE block in augmenting the classification capabilities of the proposed framework, establishing ANDE as a promising solution for network traffic classification in the realm of network security.","PeriodicalId":13423,"journal":{"name":"IEEE Transactions on Network and Service Management","volume":"21 6","pages":"6924-6936"},"PeriodicalIF":4.7,"publicationDate":"2024-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142187269","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Node-Oriented Slice Reconfiguration Based on Spatial and Temporal Traffic Prediction in Metro Optical Networks 基于城域光网络时空流量预测的节点导向切片重组
IF 4.7 2区 计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS Pub Date : 2024-09-02 DOI: 10.1109/TNSM.2024.3453381
Bowen Bao;Hui Yang;Qiuyan Yao;Jie Zhang;Bijoy Chand Chatterjee;Eiji Oki
Given the spring-up of diverse new applications with different requirements in metro optical networks, network slicing provides a virtual end-to-end resource connection with customized service provision. To improve the quality-of-service (QoS) of slices with long-term operation in networks, it is beneficial to reconfigure the slice adaptively, referring to the future traffic state. Considering the busy-hour Internet traffic with daily human mobility, the tidal pattern of traffic flow occurs in metro optical networks, expressing both temporal and spatial features. To achieve high QoS of slices, this paper proposes a node-oriented slice reconfiguration (NoSR) scheme to reduce the penalty of slices, where a gradient-based priority strategy is designed to reduce the penalties of slices overall penalties in reconfiguration. Besides, given that a precise traffic prediction model is essential for efficient slice reconfiguration with future traffic state, this paper presents the model combining the graph convolutional network (GCN) and gated recurrent unit (GRU) to extract the traffic features in space and time dimensions. Simulation results show that the presented GCN-GRU traffic prediction model achieves a high forecasting accuracy, and the proposed NoSR scheme efficiently reduces the penalty of slices to guarantee a high QoS in metro optical networks.
针对城域光网络中各种不同需求的新应用的涌现,网络切片提供了一种虚拟的端到端资源连接,并提供定制化的服务。为了提高网络中长期运行的分片的服务质量(QoS),可以根据未来的流量状态自适应地重新配置分片。考虑到繁忙时段的互联网流量和日常的人口流动,城域光网络中出现潮汐型交通流,表现出时间和空间特征。为了实现高QoS的分片,本文提出了一种面向节点的分片重构(NoSR)方案来减少分片的损失,其中设计了一种基于梯度的优先级策略来减少分片在重构过程中的总体损失。此外,考虑到精确的交通预测模型对于有效地对未来交通状态进行切片重构至关重要,本文提出了将图卷积网络(GCN)和门控循环单元(GRU)相结合的模型来提取空间和时间维度的交通特征。仿真结果表明,所提出的GCN-GRU流量预测模型具有较高的预测精度,所提出的NoSR方案有效地减少了切片的惩罚,保证了城域光网络的高QoS。
{"title":"Node-Oriented Slice Reconfiguration Based on Spatial and Temporal Traffic Prediction in Metro Optical Networks","authors":"Bowen Bao;Hui Yang;Qiuyan Yao;Jie Zhang;Bijoy Chand Chatterjee;Eiji Oki","doi":"10.1109/TNSM.2024.3453381","DOIUrl":"10.1109/TNSM.2024.3453381","url":null,"abstract":"Given the spring-up of diverse new applications with different requirements in metro optical networks, network slicing provides a virtual end-to-end resource connection with customized service provision. To improve the quality-of-service (QoS) of slices with long-term operation in networks, it is beneficial to reconfigure the slice adaptively, referring to the future traffic state. Considering the busy-hour Internet traffic with daily human mobility, the tidal pattern of traffic flow occurs in metro optical networks, expressing both temporal and spatial features. To achieve high QoS of slices, this paper proposes a node-oriented slice reconfiguration (NoSR) scheme to reduce the penalty of slices, where a gradient-based priority strategy is designed to reduce the penalties of slices overall penalties in reconfiguration. Besides, given that a precise traffic prediction model is essential for efficient slice reconfiguration with future traffic state, this paper presents the model combining the graph convolutional network (GCN) and gated recurrent unit (GRU) to extract the traffic features in space and time dimensions. Simulation results show that the presented GCN-GRU traffic prediction model achieves a high forecasting accuracy, and the proposed NoSR scheme efficiently reduces the penalty of slices to guarantee a high QoS in metro optical networks.","PeriodicalId":13423,"journal":{"name":"IEEE Transactions on Network and Service Management","volume":"21 6","pages":"6731-6743"},"PeriodicalIF":4.7,"publicationDate":"2024-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142187120","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Energy-Efficient and Latency-Aware Data Routing in Small-World Internet of Drone Networks 小型世界无人机互联网络中的高能效和延迟感知数据路由选择
IF 4.7 2区 计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS Pub Date : 2024-08-30 DOI: 10.1109/TNSM.2024.3452414
Sreenivasa Reddy Yeduri;Sindhusha Jeeru;Om Jee Pandey;Linga Reddy Cenkeramaddi
Recently, drones have attracted considerable attention for sensing hostile areas. Multiple drones are deployed to communicate and coordinate sensing and data transfer in the Internet of Drones (IoD) network. Traditionally, multi-hop routing is employed for communication over long distances to increase the network’s lifetime. However, multi-hop routing over large-scale networks leads to energy imbalance and higher data latency. Motivated by this, in this paper, a novel framework of energy-efficient and latency-aware data routing is proposed for Small-World (SW)-IoD networks. We started with an optimization problem formulation in terms of network delay, energy consumption, and reliability. Then, the formulated mixed integer problem is solved by introducing the Small-World Characters (SWC) into the conventional IoD network to form the SW-IoD network. Here, the proposed framework introduces SWC by removing a few existing edges with the least edge weight from the traditional network and introducing the same number of long-range edges with the highest edge weight. We present the simulation results corresponding to packet delivery ratio, network lifetime, and network delay for the performance comparison of the proposed framework with state-of-the-art approaches such as the conventional SWC method, LEACH, Modified LEACH, Canonical Particle Multi-Swarm (PMS) method, and conventional shortest path routing algorithm. We also analyze the effect of the location of the ground control station, the velocity of the drones, and the different heights of layers on the performance of the proposed framework. Through experiments, the superiority of the proposed method is proven to be better when compared to other methods. Finally, the performance evaluation of the proposed model is tested on a network simulator (NS3).
最近,无人机因探测敌对地区而备受关注。在无人机互联网(Internet of drones, IoD)网络中,部署多架无人机进行通信和协调传感和数据传输。传统上,多跳路由用于长距离通信,以增加网络的生命周期。但是,在大规模网络中,多跳路由会导致能量不平衡和数据延迟。基于此,本文提出了一种适用于小世界(SW)-IoD网络的节能和延迟感知数据路由的新框架。我们从网络延迟、能耗和可靠性方面的优化问题开始。然后,将小世界字符(Small-World Characters, SWC)引入到传统的IoD网络中,形成SW-IoD网络,解决了公式化的混合整数问题。在这里,提出的框架通过从传统网络中去除一些边缘权值最小的现有边缘,并引入相同数量的边缘权值最高的远程边缘来引入SWC。我们给出了相应的数据包传送率、网络寿命和网络延迟的仿真结果,以将所提出的框架与最先进的方法(如传统的SWC方法、LEACH、改进的LEACH、规范粒子多群(PMS)方法和传统的最短路径路由算法)进行性能比较。我们还分析了地面控制站的位置、无人机的速度和不同层的高度对所提出框架性能的影响。通过实验证明,与其他方法相比,该方法具有更好的优越性。最后,在网络模拟器(NS3)上对该模型进行了性能评估。
{"title":"Energy-Efficient and Latency-Aware Data Routing in Small-World Internet of Drone Networks","authors":"Sreenivasa Reddy Yeduri;Sindhusha Jeeru;Om Jee Pandey;Linga Reddy Cenkeramaddi","doi":"10.1109/TNSM.2024.3452414","DOIUrl":"10.1109/TNSM.2024.3452414","url":null,"abstract":"Recently, drones have attracted considerable attention for sensing hostile areas. Multiple drones are deployed to communicate and coordinate sensing and data transfer in the Internet of Drones (IoD) network. Traditionally, multi-hop routing is employed for communication over long distances to increase the network’s lifetime. However, multi-hop routing over large-scale networks leads to energy imbalance and higher data latency. Motivated by this, in this paper, a novel framework of energy-efficient and latency-aware data routing is proposed for Small-World (SW)-IoD networks. We started with an optimization problem formulation in terms of network delay, energy consumption, and reliability. Then, the formulated mixed integer problem is solved by introducing the Small-World Characters (SWC) into the conventional IoD network to form the SW-IoD network. Here, the proposed framework introduces SWC by removing a few existing edges with the least edge weight from the traditional network and introducing the same number of long-range edges with the highest edge weight. We present the simulation results corresponding to packet delivery ratio, network lifetime, and network delay for the performance comparison of the proposed framework with state-of-the-art approaches such as the conventional SWC method, LEACH, Modified LEACH, Canonical Particle Multi-Swarm (PMS) method, and conventional shortest path routing algorithm. We also analyze the effect of the location of the ground control station, the velocity of the drones, and the different heights of layers on the performance of the proposed framework. Through experiments, the superiority of the proposed method is proven to be better when compared to other methods. Finally, the performance evaluation of the proposed model is tested on a network simulator (NS3).","PeriodicalId":13423,"journal":{"name":"IEEE Transactions on Network and Service Management","volume":"21 6","pages":"6555-6565"},"PeriodicalIF":4.7,"publicationDate":"2024-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142187265","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Edge Computing and Few-Shot Learning Featured Intelligent Framework in Digital Twin Empowered Mobile Networks 数字孪生移动网络中的边缘计算和快速学习特色智能框架
IF 4.7 2区 计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS Pub Date : 2024-08-30 DOI: 10.1109/TNSM.2024.3450993
Yirui Wu;Hao Cao;Yong Lai;Liang Zhao;Xiaoheng Deng;Shaohua Wan
Digital twins (DT) and mobile networks have evolved forms of intelligence in Internet of Things (IoT). In this work, we consider a Digital Twin Mobile Network (DTMN) scenario with few multimedia samples. Facing challenges of knowledge extraction with few samples, stable interaction with dynamic changes of multimedia data, time and privacy saving in low-resource mobile network, we propose an edge computing and few-shot learning featured intelligent framework. Considering time-sensitive property of transmission and privacy risks of directly uploads in mobile network, we deploy edge computing to locally run networks for analysis, thus saving time to offload computing request and enhancing privacy by encrypting original data. Inspired by remarkable relationship representation of graphs, we build Graph Neural Network (GNN) in cloud to map physical mobile systems to virtual entities with DT, thus performing semantic inferences in cloud with few samples uploaded by edges. Occasionally, node features in GNN could converge to similar, non-discriminative embeddings, causing catastrophic unstable phenomena. An iterative reweight and drop structure (IRDS) is thus constructed in cloud, which nonetheless contributes stability with respect to edge uncertainty. As part of IRDS, a drop Edge&Node scheme is proposed to randomly remove certain nodes and edges, which not only enhances distinguished capability of graph neighbor patterns, but also offers data encryption with random strategy. We show one implementation case of image classification in social network, where experiments on public datasets show that our framework is effective with user-friendly advantages and significant intelligence.
数字孪生体(DT)和移动网络已经在物联网(IoT)中进化出智能形式。在这项工作中,我们考虑了一个数字孪生移动网络(DTMN)的场景,只有很少的多媒体样本。面对低资源移动网络环境下的少样本知识提取、与多媒体数据动态变化的稳定交互、节省时间和隐私等挑战,提出了一种边缘计算和少镜头学习的智能框架。考虑到传输的时效性和在移动网络中直接上传的隐私风险,我们将边缘计算部署到本地运行的网络中进行分析,从而节省了卸载计算请求的时间,并通过对原始数据进行加密来增强隐私性。受图出色的关系表示的启发,我们在云中构建了图神经网络(GNN),利用DT将物理移动系统映射到虚拟实体,从而在边缘上传少量样本的云中进行语义推理。偶尔,GNN中的节点特征可能收敛到相似的非判别嵌入,从而导致灾难性的不稳定现象。因此,在云中构建了迭代重权重和丢弃结构(IRDS),尽管如此,它仍然有助于相对于边缘不确定性的稳定性。作为IRDS的一部分,提出了一种drop Edge&Node方案,随机删除部分节点和边,既增强了图邻居模式的识别能力,又为数据加密提供了随机策略。我们展示了一个社交网络图像分类的实现案例,在公共数据集上的实验表明,我们的框架是有效的,具有用户友好的优势和显著的智能。
{"title":"Edge Computing and Few-Shot Learning Featured Intelligent Framework in Digital Twin Empowered Mobile Networks","authors":"Yirui Wu;Hao Cao;Yong Lai;Liang Zhao;Xiaoheng Deng;Shaohua Wan","doi":"10.1109/TNSM.2024.3450993","DOIUrl":"10.1109/TNSM.2024.3450993","url":null,"abstract":"Digital twins (DT) and mobile networks have evolved forms of intelligence in Internet of Things (IoT). In this work, we consider a Digital Twin Mobile Network (DTMN) scenario with few multimedia samples. Facing challenges of knowledge extraction with few samples, stable interaction with dynamic changes of multimedia data, time and privacy saving in low-resource mobile network, we propose an edge computing and few-shot learning featured intelligent framework. Considering time-sensitive property of transmission and privacy risks of directly uploads in mobile network, we deploy edge computing to locally run networks for analysis, thus saving time to offload computing request and enhancing privacy by encrypting original data. Inspired by remarkable relationship representation of graphs, we build Graph Neural Network (GNN) in cloud to map physical mobile systems to virtual entities with DT, thus performing semantic inferences in cloud with few samples uploaded by edges. Occasionally, node features in GNN could converge to similar, non-discriminative embeddings, causing catastrophic unstable phenomena. An iterative reweight and drop structure (IRDS) is thus constructed in cloud, which nonetheless contributes stability with respect to edge uncertainty. As part of IRDS, a drop Edge&Node scheme is proposed to randomly remove certain nodes and edges, which not only enhances distinguished capability of graph neighbor patterns, but also offers data encryption with random strategy. We show one implementation case of image classification in social network, where experiments on public datasets show that our framework is effective with user-friendly advantages and significant intelligence.","PeriodicalId":13423,"journal":{"name":"IEEE Transactions on Network and Service Management","volume":"21 6","pages":"6505-6514"},"PeriodicalIF":4.7,"publicationDate":"2024-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142187267","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
期刊
IEEE Transactions on Network and Service Management
全部 Acc. Chem. Res. ACS Applied Bio Materials ACS Appl. Electron. Mater. ACS Appl. Energy Mater. ACS Appl. Mater. Interfaces ACS Appl. Nano Mater. ACS Appl. Polym. Mater. ACS BIOMATER-SCI ENG ACS Catal. ACS Cent. Sci. ACS Chem. Biol. ACS Chemical Health & Safety ACS Chem. Neurosci. ACS Comb. Sci. ACS Earth Space Chem. ACS Energy Lett. ACS Infect. Dis. ACS Macro Lett. ACS Mater. Lett. ACS Med. Chem. Lett. ACS Nano ACS Omega ACS Photonics ACS Sens. ACS Sustainable Chem. Eng. ACS Synth. Biol. Anal. Chem. BIOCHEMISTRY-US Bioconjugate Chem. BIOMACROMOLECULES Chem. Res. Toxicol. Chem. Rev. Chem. Mater. CRYST GROWTH DES ENERG FUEL Environ. Sci. Technol. Environ. Sci. Technol. Lett. Eur. J. Inorg. Chem. IND ENG CHEM RES Inorg. Chem. J. Agric. Food. Chem. J. Chem. Eng. Data J. Chem. Educ. J. Chem. Inf. Model. J. Chem. Theory Comput. J. Med. Chem. J. Nat. Prod. J PROTEOME RES J. Am. Chem. Soc. LANGMUIR MACROMOLECULES Mol. Pharmaceutics Nano Lett. Org. Lett. ORG PROCESS RES DEV ORGANOMETALLICS J. Org. Chem. J. Phys. Chem. J. Phys. Chem. A J. Phys. Chem. B J. Phys. Chem. C J. Phys. Chem. Lett. Analyst Anal. Methods Biomater. Sci. Catal. Sci. Technol. Chem. Commun. Chem. Soc. Rev. CHEM EDUC RES PRACT CRYSTENGCOMM Dalton Trans. Energy Environ. Sci. ENVIRON SCI-NANO ENVIRON SCI-PROC IMP ENVIRON SCI-WAT RES Faraday Discuss. Food Funct. Green Chem. Inorg. Chem. Front. Integr. Biol. J. Anal. At. Spectrom. J. Mater. Chem. A J. Mater. Chem. B J. Mater. Chem. C Lab Chip Mater. Chem. Front. Mater. Horiz. MEDCHEMCOMM Metallomics Mol. Biosyst. Mol. Syst. Des. Eng. Nanoscale Nanoscale Horiz. Nat. Prod. Rep. New J. Chem. Org. Biomol. Chem. Org. Chem. Front. PHOTOCH PHOTOBIO SCI PCCP Polym. Chem.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1