IEEE Transactions on Mobile Computing最新文献

FL in Motion: Accelerating FL via Mobility-Aware Vehicle Selection and Sparse Training 运动中的FL：通过机动感知车辆选择和稀疏训练加速FL

IF 8.8 2区计算机科学

IEEE Transactions on Mobile Computing Pub Date : 2026-07-01 Epub Date: 2026-01-16 DOI: 10.1109/TMC.2026.3654937

Haoyu Tu;Wen Wu;Lin Chen;Liang Li;Xu Chen;Xuemin Shen

{"title":"FL in Motion: Accelerating FL via Mobility-Aware Vehicle Selection and Sparse Training","authors":"Haoyu Tu;Wen Wu;Lin Chen;Liang Li;Xu Chen;Xuemin Shen","doi":"10.1109/TMC.2026.3654937","DOIUrl":"https://doi.org/10.1109/TMC.2026.3654937","url":null,"abstract":"Although federated learning (FL) can enable advanced autonomous driving via leveraging massive distributed data in vehicular networks, vehicle mobility causes frequent connection interruptions, hindering the FL process. In this paper, we propose a novel <underline>Mobility-<underline>Aware <underline>Vehicular <underline>FL (MAVFL) scheme, which can accelerate the training process in dynamic vehicular networks via adaptive vehicle selection and sparse training. Specifically, the MAVFL dynamically selects participating vehicles based on their locations and training loss. By incorporating adaptive model sparsification, the proposed scheme dynamically proceeds with sparse masks during vehicle local training, thereby reducing communication overhead while preserving model accuracy. We conduct a rigorous convergence analysis to uncover how vehicle mobility and model sparsification affect convergence rate. Furthermore, we formulate an optimization problem to accelerate the training process, which jointly optimizes vehicle selection, sparsification ratio, and bandwidth allocation to minimize training delay. To solve the problem, we employ the Lyapunov optimization method to decouple the long-term problem into a series of instantaneous subproblems. Next, a generalized Benders decomposition method structures the original problem into a master subproblem for vehicle selection and a primal subproblem for bandwidth allocation and sparsification ratio selection. The optimal solutions are derived via alternating iterations between these problems. Extensive simulation results based on the SUMO simulator demonstrate that the MAVFL accelerates model convergence by up to 14% and reduces communication overhead by up to 26% while preserving model accuracy, as compared to the state-of-the-art benchmarks.","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":"25 7","pages":"9801-9815"},"PeriodicalIF":8.8,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148517938","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

AutoRAN: Automated and Zero-Touch Open RAN Systems AutoRAN：自动化和零接触开放式RAN系统

IF 8.8 2区计算机科学

IEEE Transactions on Mobile Computing Pub Date : 2026-07-01 Epub Date: 2026-01-20 DOI: 10.1109/TMC.2026.3656056

Stefano Maxenti;Ravis Shirkhani;Maxime Elkael;Leonardo Bonati;Salvatore D’Oro;Tommaso Melodia;Michele Polese

{"title":"AutoRAN: Automated and Zero-Touch Open RAN Systems","authors":"Stefano Maxenti;Ravis Shirkhani;Maxime Elkael;Leonardo Bonati;Salvatore D’Oro;Tommaso Melodia;Michele Polese","doi":"10.1109/TMC.2026.3656056","DOIUrl":"https://doi.org/10.1109/TMC.2026.3656056","url":null,"abstract":"Modern cellular networks adopt a software-based and disaggregated approach to support diverse requirements and mission-critical reliability needs. While softwarization introduces flexibility, it also increases the complexity of the network architectures, which calls for robust automation frameworks that can deliver efficient and fully-autonomous configuration, scalability, and multi-vendor integration. This paper presents AutoRAN, an automated, intent-driven framework for zero-touch provisioning of open, programmable cellular networks. Leveraging cloud-native principles, AutoRAN employs virtualization, declarative infrastructure-as-code templates, and disaggregated micro-services to abstract physical resources and protocol stacks. Its orchestration engine integrates Large Language Models (LLMs) to translate high-level intents into machine-readable configurations, enabling closed-loop control via telemetry-driven observability. Implemented on a multi-architecture OpenShift cluster with heterogeneous compute (x86/ARM CPUs, NVIDIA GPUs) and multi-vendor Radio Access Network (RAN) hardware (Foxconn, NI), AutoRAN automates deployment of O-RAN-compliant stacks—including OpenAirInterface, NVIDIA ARC RAN, Open5GS core, and O-RAN Software Community (OSC) RIC components—using Continuous Integration and Continuous Delivery/Deployment (CI/CD) pipelines. Experimental results demonstrate that AutoRAN is capable of deploying an end-to-end Private 5G network in less than 60 seconds with 1.6 Gbps throughput, validating its ability to streamline configuration, accelerate testing, and reduce manual intervention with similar performance to non cloud-based implementations. With its novel LLM-assisted intent translation mechanism, and performance-optimized automation workflow for multi-vendor environments, AutoRAN has the potential of advancing the robustness of next-generation cellular supply chains through reproducible, intent-based provisioning across public and private deployments.","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":"25 7","pages":"10112-10129"},"PeriodicalIF":8.8,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148518095","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

Toward Sustainable Edge Computing Infrastructures: A VEC-MEC-Cloud Collaborative Framework for Adaptive Resource Distribution 面向可持续边缘计算基础设施：一种用于自适应资源分配的vec - mec -云协作框架

IF 8.8 2区计算机科学

IEEE Transactions on Mobile Computing Pub Date : 2026-07-01 Epub Date: 2026-01-16 DOI: 10.1109/TMC.2026.3654928

Dapeng Dong

{"title":"Toward Sustainable Edge Computing Infrastructures: A VEC-MEC-Cloud Collaborative Framework for Adaptive Resource Distribution","authors":"Dapeng Dong","doi":"10.1109/TMC.2026.3654928","DOIUrl":"https://doi.org/10.1109/TMC.2026.3654928","url":null,"abstract":"Edge computing systems experience significant challenges in dynamically adapting to unpredictable user mobility and fluctuating service demands, particularly in smart city scenarios where latency-sensitive applications are predominant. This paper addresses this critical gap by proposing a collaborative framework integrating vehicular edge computing (VEC), mobile edge computing (MEC), and cloud computing to achieve adaptive edge resource distribution. The system comprises core components including a network latency model, resource allocation model, deployment location identification model, and dispatch scheduling model. We evaluate our approach using real-world city maps and base station deployment information, demonstrating the effectiveness and robustness of the proposed methods. Results show an average error rate of approximately 0.02% in meeting time-sensitive applications’ resource requirements and delay constraints, and a conservative 8.1% improvement in service availability compared to static deployment strategies, validating the framework’s adaptability in dynamic environments. By enabling adaptive resource distribution, this approach offers a sustainable and cost-efficient solution for edge computing infrastructure, addressing the evolving demands of urban digital ecosystems.","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":"25 7","pages":"9910-9927"},"PeriodicalIF":8.8,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148518214","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 Offloading Policies in Multi-Access Edge Computing Systems With Task Handover 具有任务切换的多访问边缘计算系统节能卸载策略

IF 8.8 2区计算机科学

IEEE Transactions on Mobile Computing Pub Date : 2026-07-01 Epub Date: 2026-01-19 DOI: 10.1109/TMC.2026.3655433

Ling Hou;Shi Li;Zhishu Shen;Jing Fu;Jingjin Wu;Jiong Jin

{"title":"Energy Efficient Offloading Policies in Multi-Access Edge Computing Systems With Task Handover","authors":"Ling Hou;Shi Li;Zhishu Shen;Jing Fu;Jingjin Wu;Jiong Jin","doi":"10.1109/TMC.2026.3655433","DOIUrl":"https://doi.org/10.1109/TMC.2026.3655433","url":null,"abstract":"The rapid growth of mobile devices and the increasing complexity of tasks have made energy efficiency a critical challenge in Multi-Access Edge Computing (MEC) systems. This paper explores energy-efficient offloading strategies in large-scale MEC systems with heterogeneous mobile users, diverse network components, and frequent task handovers to capture user mobility. The problem is inherently complex due to the system’s scale, task and resource diversity, and the need to maintain real-time performance. Traditional optimization approaches are often computationally infeasible for large-scale MEC environments with dynamic task arrivals, unpredictable user mobility, and time-varying resource availability. To improve energy efficiency, we model the offloading problem using the restless multi-armed bandit (RMAB) framework, which enables scalable and adaptive decision-making in uncertain environments. We propose two offloading policies: Highest Energy Efficiency with Adjusted Capacity Coefficients Zero (HEE-ACC-zero), which prioritizes resource allocation based on predefined marginal cost indices, and HEE-ACC with Online Learning (HEE-ALRN), which dynamically refines the marginal cost indices using real-time feedback. The proposed policies dynamically adapt to the system’s heterogeneity and mobility while ensuring near-optimal energy efficiency. Through extensive numerical simulations, we demonstrate that the policies achieve over 15% power conservation compared to baseline methods and up to 30% improvement in throughput per unit power, while maintaining comparable average delay. The performance also remains robust under non-exponentially distributed task lifespans, with deviations within <inline-formula><tex-math>$pm 2%$</tex-math></inline-formula>. These results highlight the practical applicability and scalability of our approach in dynamic MEC environments.","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":"25 7","pages":"9419-9436"},"PeriodicalIF":8.8,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148518400","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

Model-Free Adaptive Sampling for Multi-Model Sensing Systems With Heterogeneous Age-of-Information Requirements 具有异构信息年龄要求的多模型传感系统的无模型自适应采样

IF 8.8 2区计算机科学

IEEE Transactions on Mobile Computing Pub Date : 2026-07-01 Epub Date: 2026-03-09 DOI: 10.1109/TMC.2026.3665767

Yifan Gu;Jianhua Li;Suzhi Bi;Zhi Quan

{"title":"Model-Free Adaptive Sampling for Multi-Model Sensing Systems With Heterogeneous Age-of-Information Requirements","authors":"Yifan Gu;Jianhua Li;Suzhi Bi;Zhi Quan","doi":"10.1109/TMC.2026.3665767","DOIUrl":"https://doi.org/10.1109/TMC.2026.3665767","url":null,"abstract":"Multi-modal sensing communication systems face significant challenges in guaranteeing the Age-of-Information (AoI) of multiple sensors with a shared transmission queue. First, sensors may have dramatically different AoI requirements and the AoIs of various sensors are heavily entangled. Second, the transmission delay and packet error rate are often unknown and non-stationary in practical connections. Existing studies on sampling schemes either assume stationary transmission delay statistics or fail to address heterogeneous AoI requirements across multiple sensors. This paper proposes a Differentiated AoI Guaranteed Sampling (DAGS) scheme that minimizes the short-term AoI (ST-AoI) violation probability based on different sensors’ requirements under non-stationary transmission delay. To deal with network dynamics, the ST-AoI is defined as the average AoI over recently received packets, not over the entire horizon. To solve such a problem, a dynamic linearization data model with a Pseudo-Jacobian Matrix (PJM) is introduced to capture the sampling-AoI coupling without prior knowledge or assumption of transmission delay statistics. To ensure system stability and convergence, the upper bound on the sampling rate for each sensor is derived. Based on the data model and the upper bound, we reformulate the original problem into a tractable mean squared error problem to achieve differentiated AoI guarantees. Both simulations and real-world experiments demonstrate that the DAGS scheme reduces the ST-AoI violation probability significantly compared to the state-of-the-art schemes under unknown and non-stationary transmission delay.","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":"25 7","pages":"10542-10556"},"PeriodicalIF":8.8,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148518406","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

ReparoV2: QoE-Aware Live Video Streaming Under Low-Bandwidth Networks 低带宽网络下基于qos的实时视频流

IF 8.8 2区计算机科学

IEEE Transactions on Mobile Computing Pub Date : 2026-07-01 Epub Date: 2026-02-17 DOI: 10.1109/TMC.2026.3665225

Fulin Wang;Qing Li;Wanxin Shi;Qian Yu;Gareth Tyson;Yong Jiang;Jianhui Lv;Zhenhui Yuan

{"title":"ReparoV2: QoE-Aware Live Video Streaming Under Low-Bandwidth Networks","authors":"Fulin Wang;Qing Li;Wanxin Shi;Qian Yu;Gareth Tyson;Yong Jiang;Jianhui Lv;Zhenhui Yuan","doi":"10.1109/TMC.2026.3665225","DOIUrl":"https://doi.org/10.1109/TMC.2026.3665225","url":null,"abstract":"Live video streaming has grown significantly, especially on networks with limited bandwidth. Traditional video streaming methods, which drop less important frames, often struggle with high latency. We propose ReparoV2, a novel approach designed specifically for live streaming environments. On the client side, ReparoV2 selectively omits video frames at the source, which substantially reduces bandwidth usage without significantly degrading the QoE. ReparoV2 implements a real-time Video Frame Discarding (VFD) algorithm, which categorizes even-indexed frames into three types: preserving, recovering using neural networks and substituting with the previous frame, which is corresponding to the high, medium and low degree of difference between two adjacent frames. Additionally, to gain a better QoE, ReparoV2 integrates an adaptive bitrate strategy and introduces multiple discrete low-frame-rate encoding modes, balancing video quality and bandwidth reduction when the network bandwidth is limited. On the server side, ReparoV2 uses a Video Frame Interpolation Deep Neural Network (VFI-DNN) and frame-copying to reconstruct dropped frames, ensuring a smooth viewing experience. It updates the VFD model based on received video chunks and sends the updated model back to the client. ReparoV2 outperforms conventional Dynamic Adaptive Streaming over HTTP (DASH), achieving higher Structural Similarity Index Measure (SSIM) (+0.024), lower bandwidth usage (−23.19% ), and improved QoE (+26.66% ) on 25fps videos under 0.974 Mbps average bandwidth.","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":"25 7","pages":"10182-10199"},"PeriodicalIF":8.8,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148518841","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

Open RAN-Based Mixed-Timescale and Robust Task Offloading in Vehicular Edge Computing 基于开放ran的混合时间尺度车辆边缘计算鲁棒任务卸载

IF 8.8 2区计算机科学

IEEE Transactions on Mobile Computing Pub Date : 2026-07-01 Epub Date: 2026-01-23 DOI: 10.1109/TMC.2026.3657303

Mohsen Tajallifar;Nizar Zorba;Nader Mokari;Hamid Saeedi

{"title":"Open RAN-Based Mixed-Timescale and Robust Task Offloading in Vehicular Edge Computing","authors":"Mohsen Tajallifar;Nizar Zorba;Nader Mokari;Hamid Saeedi","doi":"10.1109/TMC.2026.3657303","DOIUrl":"https://doi.org/10.1109/TMC.2026.3657303","url":null,"abstract":"Vehicular. edge computing (VEC) emerges as a critical enabler of low-latency and computation-intensive vehicular applications by offloading tasks from vehicles to edge servers. However, the dynamic nature of vehicular networks introduces significant uncertainty in task characteristics and network conditions, posing challenges for efficient resource allocation. This paper proposes a robust task offloading scheme for VEC within the open radio access network (O-RAN) architecture. Leveraging mixed-timescale optimization, the proposed approach integrates large-timescale computational resource allocation (CRA), moderate-timescale task partitioning, and small-timescale radio resource allocation (RRA) using O-RAN’s hierarchical control framework. The robust optimization model minimizes the network-wide resources while meeting the deadline of individual task execution latencies under demand uncertainty. We employ the cutting-set method to address the demand uncertainty in the large-timescale CRA. We obtain a closed-form solution to the optimal task partitioning problem. We adopt both the Lyapunov optimization and a heuristic approach for the small-timescale RRA, wherein we adopt the concave-convex procedure to resolve the non-convexity of the data rate expression. The efficiency of the proposed method is shown through extensive simulations. The results show that the small-timescale RRA succeeds to counteract the demand uncertainty at the large-timescale CRA, that is, no outage occurs when demands are in the assumed uncertainty set, whereas the non-robust scheme exhibits as high as <inline-formula><tex-math>$50 %$</tex-math></inline-formula> outage probability. Moreover, our heuristic scheme is less conservative and consumes less resources than the Lyapunov optimization, and it consumes about <inline-formula><tex-math>$40 %$</tex-math></inline-formula> less bandwidth than the conventional non-slotted robust solution","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":"25 7","pages":"10148-10165"},"PeriodicalIF":8.8,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148518842","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

Generative Radio Map-Assisted Channel Estimation in Low-Altitude Economy 低空经济下生成无线电地图辅助信道估计

IF 8.8 2区计算机科学

IEEE Transactions on Mobile Computing Pub Date : 2026-07-01 Epub Date: 2026-02-17 DOI: 10.1109/TMC.2026.3665545

Bin Yang;Wei Wang;Weizheng Zhang;Wei Zhang

{"title":"Generative Radio Map-Assisted Channel Estimation in Low-Altitude Economy","authors":"Bin Yang;Wei Wang;Weizheng Zhang;Wei Zhang","doi":"10.1109/TMC.2026.3665545","DOIUrl":"https://doi.org/10.1109/TMC.2026.3665545","url":null,"abstract":"The low-altitude economy (LAE) is inherently dependent on unmanned aerial vehicles (UAVs) as its core operational infrastructure, with applications spanning logistics, surveillance, and smart city development. Despite growing attention, LAE’s practical deployment faces substantial obstacles, particularly in maintaining reliable UAV operations. These UAVs require secure and efficient wireless communication services delivered by base stations (BSs), yet their high mobility, combined with multipath effects, creates significant channel estimation challenges that threaten the seamless connectivity. According to the fixed airspace and planned routes characteristics of LAE scenarios, in this paper we construct the radio map to assist channel estimation using sensing information. First, a grid-based UAV channel measurement scheme is proposed to collect CSI data labeled with discrete locations and velocities. Then, a new generative adversarial network (GAN)-based model named continuous vector-conditioned GAN (CVCGAN) is developed to complete the discrete map by establishing the mapping from continuous sensing information to their channel space. After that, an integrator is designed to fuse the channel state information (CSI) provided by radio map with that estimated by pilots. Simulation results validate the superiority of the proposed method, which outperforms state-of-the-art (SOTA) approaches including ChannelNet, conditional GAN (CGAN), RadioUNet and long short-term memory (LSTM).","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":"25 7","pages":"10724-10739"},"PeriodicalIF":8.8,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148519147","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

Beamforming in Dense Wi-Fi Networks: Beam Management and Throughput Analysis 密集Wi-Fi网络中的波束形成：波束管理和吞吐量分析

IF 8.8 2区计算机科学

IEEE Transactions on Mobile Computing Pub Date : 2026-07-01 Epub Date: 2026-01-21 DOI: 10.1109/TMC.2026.3656734

Hsin-Li Chiu;Sau-Hsuan Wu

{"title":"Beamforming in Dense Wi-Fi Networks: Beam Management and Throughput Analysis","authors":"Hsin-Li Chiu;Sau-Hsuan Wu","doi":"10.1109/TMC.2026.3656734","DOIUrl":"https://doi.org/10.1109/TMC.2026.3656734","url":null,"abstract":"Facing the strong demands for high speed Wi-Fi access in the already crowded unlicensed spectrum, enabling beamforming at Wi-Fi access points (APs) can be an efficient way to improve the network throughput with its compelling advantages in beamforming gain and spatial reuse factor. However, how much beamforming Wi-Fi can benefit in an environment populated with legacy Wi-Fi stations remains an open problem. After all, it could be incompatible with the legacy Wi-Fi protocol or causing unbalanced downlink (DL) and uplink (UL) channel access opportunities due to improper beam switching mechanisms. As an effort to explore the potential of beamforming Wi-Fi, we present a novel Markov model to analyze its throughput in randomly deployed Wi-Fi networks, and propose a beam switching mechanism which is backward compatible with the legacy Wi-Fi and able to adjust the DL and UL access probabilities between beamforming Wi-Fi APs and typical users. Analysis shows that the proposed scheme significantly improves DL throughput while maintaining balanced DL/UL throughput over a wide range of user densities, particularly in dense deployments. This encourages future study of beamforming for more advanced Wi-Fi technologies.","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":"25 7","pages":"9721-9736"},"PeriodicalIF":8.8,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148519250","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

HyperWay: Proactively Mitigating Transient Congestion With Edge Capsule Tunnel in Massive IoT HyperWay：利用边缘胶囊隧道主动缓解大规模物联网中的瞬态拥塞

IF 8.8 2区计算机科学

IEEE Transactions on Mobile Computing Pub Date : 2026-07-01 Epub Date: 2026-01-21 DOI: 10.1109/TMC.2026.3656275

Bo He;Haoran Zhao;Jinsheng Zhang;Jingyu Wang;Qi Qi;Haifeng Sun;Zirui Zhuang;Yuhan Jing;Jing Shang;Jianxin Liao

{"title":"HyperWay: Proactively Mitigating Transient Congestion With Edge Capsule Tunnel in Massive IoT","authors":"Bo He;Haoran Zhao;Jinsheng Zhang;Jingyu Wang;Qi Qi;Haifeng Sun;Zirui Zhuang;Yuhan Jing;Jing Shang;Jianxin Liao","doi":"10.1109/TMC.2026.3656275","DOIUrl":"https://doi.org/10.1109/TMC.2026.3656275","url":null,"abstract":"Massive Internet of Things (IoT) devices facilitate real-time monitoring and precise decision-making through the unceasing transmission of status update flows. Nevertheless, when multiple new devices access and compete, the CPU and bandwidth resources allocated to existing traffic by the User Plane Function (UPF) are significantly reduced. Such a sudden reduction causes the queue length in the UPF to spike, resulting in packets not being forwarded timely, a phenomenon known as transient congestion. Consequently, tail latency experiences a substantial increase, and the update process is significantly disrupted. However, constrained by the substantial proliferation of interconnected IoT devices and the inflated congestion control loop, existing solutions are unable to adequately address transient congestion in the UPF. In this paper, we propose <italic>HyperWay, a tunnel-based solution that provides stable UPF service for IoT applications by synergizing <italic>compressing and scheduling capsules. To timely forward a maximum number of packets within the constrained resources, <italic>HyperWay establishes QUIC-enabled tunnels that support the compression of packets into capsules. Meanwhile, <italic>HyperWay schedules capsules with more urgent status updates for priority forwarding through low-complexity computing, based on the results of mathematical analysis. We have implemented and evaluated <italic>HyperWay in both a software-defined platform and a real-world 5G network, while results show that <italic>HyperWay significantly reduces latency spikes and status update performance degradation by 12% to 89%.","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":"25 7","pages":"9578-9593"},"PeriodicalIF":8.8,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148519205","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