IEEE Transactions on Mobile Computing最新文献_第4页

IRS Aided Federated Learning: Multiple Access and Fundamental Tradeoff IRS辅助联邦学习：多访问和基本权衡

IF 8.8 2区计算机科学

IEEE Transactions on Mobile Computing Pub Date : 2026-07-01 Epub Date: 2026-02-16 DOI: 10.1109/TMC.2026.3665183

Guangji Chen;Jun Li;Yuanhao Cui;Qingqing Wu;Yiyang Ni;Meng Hua;Shihang Lu

{"title":"IRS Aided Federated Learning: Multiple Access and Fundamental Tradeoff","authors":"Guangji Chen;Jun Li;Yuanhao Cui;Qingqing Wu;Yiyang Ni;Meng Hua;Shihang Lu","doi":"10.1109/TMC.2026.3665183","DOIUrl":"https://doi.org/10.1109/TMC.2026.3665183","url":null,"abstract":"This paper investigates an intelligent reflecting surface (IRS) aided wireless federated learning (FL) system, where an access point (AP) coordinates multiple edge devices to train a machine leaning model without sharing their own raw data. During the training process, we exploit the joint channel reconfiguration via IRS and resource allocation design to reduce the latency of a FL task. Particularly, we propose three transmission protocols for assisting the local model uploading from multiple devices to an AP, namely IRS aided time division multiple access (I-TDMA), IRS aided frequency division multiple access (I-FDMA), and IRS aided non-orthogonal multiple access (I-NOMA), to investigate the impact of IRS on the multiple access for FL. Under the three protocols, we minimize the per-round latency subject to a given training loss by jointly optimizing the device scheduling, IRS phase-shifts, and communication-computation resource allocation. For the associated problem under I-TDMA, an efficient algorithm is proposed to solve it optimally by exploiting its intrinsic structure, whereas the high-quality solutions of the problems under I-FDMA and I-NOMA are obtained by invoking a successive convex approximation (SCA) based approach. Then, we further develop a theoretical framework for the performance comparison of the proposed three transmission protocols. Sufficient conditions for ensuring that I-TDMA outperforms I-NOMA and those of its opposite are unveiled, which is fundamentally different from that NOMA always outperforms TDMA in the system without IRS. Simulation results validate our theoretical findings and also demonstrate the usefulness of IRS for enhancing the fundamental tradeoff between the learning latency and learning accuracy.","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":"25 7","pages":"10402-10419"},"PeriodicalIF":8.8,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148517469","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

Cooperative HAP-UAV Optimization for IoRT Data Collection: A Green Transmission Strategy for Maximizing Energy Efficiency 协同HAP-UAV优化IoRT数据收集：一种能源效率最大化的绿色传输策略

IF 8.8 2区计算机科学

IEEE Transactions on Mobile Computing Pub Date : 2026-07-01 Epub Date: 2026-02-16 DOI: 10.1109/TMC.2026.3664906

Yanbo Fan;Yuanguo Bi;Xingyu Ji;Dusit Niyato;Enchao Zhang;Liang Zhao;Qiang He

{"title":"Cooperative HAP-UAV Optimization for IoRT Data Collection: A Green Transmission Strategy for Maximizing Energy Efficiency","authors":"Yanbo Fan;Yuanguo Bi;Xingyu Ji;Dusit Niyato;Enchao Zhang;Liang Zhao;Qiang He","doi":"10.1109/TMC.2026.3664906","DOIUrl":"https://doi.org/10.1109/TMC.2026.3664906","url":null,"abstract":"Supported by space-air-ground integrated networks (SAGIN), Internet of Remote Things (IoRT) is regarded as a cornerstone for realizing global connectivity in 6G networks. The integration of high-altitude platforms (HAPs) and uncrewed aerial vehicles (UAVs), offering both wide coverage and agile data access, becomes a promising paradigm for IoRT data collection. However, sustaining reliable and efficient transmission is challenged by the mobility and constrained onboard energy of HAPs and UAVs, as well as atmospheric fading effects. To address these issues, we propose a green and efficient HAP-UAV collaborative design for IoRT data collection, which jointly considers both transmission performance and energy consumption. Firstly, we introduce a novel metric, Overall Energy Efficiency (OEE), to quantify the balance between cooperative transmission performance and the total energy cost under dynamic trajectory planning. Secondly, we formulate a joint optimization problem that simultaneously optimizes UAV/HAP trajectories, UAV power control, HAP selection, and bandwidth allocation. Thirdly, to address the formulated non-convex fractional problem, we develop an energy efficiency maximization strategy based on the successive convex approximation technique. Extensive simulation results demonstrate that the proposed strategy achieves significant gains in OEE, achieving superior trade-offs between energy consumption and transmission performance in HAP-UAV-assisted IoRT networks.","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":"25 7","pages":"10800-10817"},"PeriodicalIF":8.8,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148517942","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

An Ensemble MARL Approach for Heterogeneous UAV Swarm Target Search in 3D Space 三维空间异构无人机群目标搜索的集成MARL方法

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.2026.3656917

Xuan Zhang;Changxu Wei;Ziyuan Wang;Yixian Zhang;Wenbo Ding;Xiao-Ping Zhang

{"title":"An Ensemble MARL Approach for Heterogeneous UAV Swarm Target Search in 3D Space","authors":"Xuan Zhang;Changxu Wei;Ziyuan Wang;Yixian Zhang;Wenbo Ding;Xiao-Ping Zhang","doi":"10.1109/TMC.2026.3656917","DOIUrl":"https://doi.org/10.1109/TMC.2026.3656917","url":null,"abstract":"In recent years, unmanned aerial vehicles (UAVs) have become increasingly pivotal in cooperative searches.However, the performance of using a homogeneous UAV swarm for search is often limited because a single class of UAVs cannot guarantee accuracy and coverage simultaneously. This work tackles the challenge of target search in a large-scale three-dimensional (3D) environment using a heterogeneous UAV swarm. Specifically, we design a novel search scheme that leverages the complementary strengths of two UAV types: fixed-wing UAVs, which enable swift area coverage at high altitudes, and multi-rotor UAVs, which provide high-precision detection at low altitudes. To address the stochastic optimization problem posed by unknown targets, we develop a multi-agent reinforcement learning (MARL) scheme—where multiple agents learn to optimize their strategies through interactions with each other and the environment—for efficient target search. To ensure the safety of UAVs, an action masking scheme is integrated into the MARL framework to avoid collisions. Moreover, to further enhance decision robustness and search efficiency, we propose an Ensemble MARL framework that aggregates multiple independently trained networks via a majority voting mechanism, and further present our Ensemble QMIX (E-QMIX) algorithm. Furthermore, we provide a mathematical analysis showing that E-QMIX increases the probability that each agent selects its optimal action, thereby strengthening the robustness of joint decision-making. Simulation results demonstrate that our E-QMIX outperforms classic single-network MARL benchmarks in both search efficiency and coverage rate.","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":"25 7","pages":"10076-10093"},"PeriodicalIF":8.8,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148518093","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

SlimCaching: Edge Caching of Mixture-of-Experts for Distributed Inference SlimCaching：用于分布式推理的混合专家边缘缓存

IF 8.8 2区计算机科学

IEEE Transactions on Mobile Computing Pub Date : 2026-07-01 Epub Date: 2026-02-13 DOI: 10.1109/TMC.2026.3664415

Qian Chen;Xianhao Chen;Kaibin Huang

{"title":"SlimCaching: Edge Caching of Mixture-of-Experts for Distributed Inference","authors":"Qian Chen;Xianhao Chen;Kaibin Huang","doi":"10.1109/TMC.2026.3664415","DOIUrl":"https://doi.org/10.1109/TMC.2026.3664415","url":null,"abstract":"Mixture-of-Experts (MoE) models improve the scalability of large language models (LLMs) by activating only a small subset of relevant experts per input. However, the sheer number of expert networks in an MoE model introduces a significant storage/memory burden for an edge device. To address this challenge, we consider a scenario where experts are dispersed across an edge network for distributed inference. Based on the popular Top-<inline-formula><tex-math>$K$</tex-math></inline-formula> expert selection strategy, we formulate a latency minimization problem by optimizing expert caching on edge servers under storage constraints. When <inline-formula><tex-math>$K=1$</tex-math></inline-formula>, the problem reduces to a monotone submodular maximization problem with knapsack constraints, for which we design a greedy-based algorithm with a <inline-formula><tex-math>$(1 - 1/e)$</tex-math></inline-formula>-approximation guarantee. For the general case where <inline-formula><tex-math>$Kgeq 1$</tex-math></inline-formula>, expert co-activation within the same MoE layer introduces non-submodularity, which renders greedy methods ineffective. To tackle this issue, we propose a successive greedy decomposition method to decompose the original problem into a series of subproblems, with each being solved by a dynamic programming approach. Furthermore, we design an accelerated algorithm based on the max-convolution technique to obtain the approximate solution with a provable guarantee in polynomial time. Simulation results on various MoE models demonstrate that our method significantly reduces inference latency compared to existing baselines.","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":"25 7","pages":"10924-10938"},"PeriodicalIF":8.8,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148518216","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

UAV-Enabled Computing Power Networks: Design and Performance Analysis Under Energy Constraints 基于无人机的计算能力网络：能量约束下的设计与性能分析

IF 8.8 2区计算机科学

IEEE Transactions on Mobile Computing Pub Date : 2026-07-01 Epub Date: 2026-01-19 DOI: 10.1109/TMC.2026.3655118

Yiqin Deng;Zhengru Fang;Senkang Hu;Yanan Ma;Xiaoyu Guo;Haixia Zhang;Yuguang Fang

{"title":"UAV-Enabled Computing Power Networks: Design and Performance Analysis Under Energy Constraints","authors":"Yiqin Deng;Zhengru Fang;Senkang Hu;Yanan Ma;Xiaoyu Guo;Haixia Zhang;Yuguang Fang","doi":"10.1109/TMC.2026.3655118","DOIUrl":"https://doi.org/10.1109/TMC.2026.3655118","url":null,"abstract":"This paper presents an innovative framework that boosts computing power by utilizing <italic>ubiquitous computing power distribution and enabling higher <italic>computing node accessibility via adaptive UAV positioning, establishing a <italic>UAV-enabled Computing Power Network (UAV-CPN). In a UAV-CPN, a UAV functions as a dynamic relay, outsourcing computing tasks from the <italic>request zone to an expanded <italic>service zone with diverse computing nodes, including vehicle onboard units, edge servers, and dedicated powerful nodes. This approach has the potential to alleviate communication bottlenecks and overcome the “island effect” observed in multi-access edge computing. A significant challenge is to quantify computing power performance under complex dynamics of communication and computing. To address this challenge, we introduce <italic>task completion probability to capture the capability of UAV-CPNs for task computing. We further enhance UAV-CPN performance under a hybrid energy architecture by jointly optimizing UAV altitude and transmit power, where fuel cells and batteries collectively power both UAV propulsion and communication systems. Extensive evaluations show significant performance gains, highlighting the importance of balancing communication and computing capabilities, especially under dual-energy constraints. These findings underscore the potential of UAV-CPNs to significantly boost computing power.","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":"25 7","pages":"9563-9577"},"PeriodicalIF":8.8,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148518218","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

Traffic-Aware Asynchronous Trajectory Planning and Scheduling in UAV-Assisted Wireless Networks With Heterogeneous Traffic Demands 具有异构流量需求的无人机辅助无线网络中流量感知异步轨迹规划与调度

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.2026.3656507

Che Chen;Bo Gu;Bin Lyu;Shimin Gong;Zhi Liu;Yuming Fang

{"title":"Traffic-Aware Asynchronous Trajectory Planning and Scheduling in UAV-Assisted Wireless Networks With Heterogeneous Traffic Demands","authors":"Che Chen;Bo Gu;Bin Lyu;Shimin Gong;Zhi Liu;Yuming Fang","doi":"10.1109/TMC.2026.3656507","DOIUrl":"https://doi.org/10.1109/TMC.2026.3656507","url":null,"abstract":"In this paper, we consider an uncrewed aerial vehicle (UAV)-assisted wireless network, where UAVs serve as agile relays to capture traffic data from user devices (UDs) and transmit data to target UDs using non-orthogonal multiple access (NOMA) technique. However, the high traffic density exacerbates the complexity of managing UAV-assisted networks, particularly for machine-to-machine (M2M) data communications, where each UD generates traffic demands directed to different target UDs with heterogeneous traffic patterns. To maximize the uplink and downlink throughput among UDs, we first propose a spatial-temporal graph attention network (STGAN) to analyze the UDs’ historical traffic flows and then cluster different UDs according to their traffic features. As such, the UAVs can serve simultaneously the UDs with similar traffic patterns, thereby enhancing spectrum efficiency and reducing the system complexity. We further develop a traffic-aware asynchronous trajectory planning and scheduling approach that enables UAVs to independently optimize their trajectories, scheduling, and time allocation. Moreover, considering the complex and dynamic spatial-temporal relationships between UAVs and UDs’ clusters, we propose a graph neural network (GNN)-enhanced deep reinforcement learning (DRL) framework, which employs a graph neural network to enhance UAVs’ perception of the network state during model training. Simulation results demonstrate that our proposed method significantly improves traffic throughput compared to benchmark methods.","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":"25 7","pages":"9816-9832"},"PeriodicalIF":8.8,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148518190","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-Assisted Real-Time Motion Capture System 边缘辅助实时运动捕捉系统

IF 8.8 2区计算机科学

IEEE Transactions on Mobile Computing Pub Date : 2026-07-01 Epub Date: 2026-01-22 DOI: 10.1109/TMC.2026.3656822

Chen Qian;Danyang Li;Jingao Xu;Zheng Yang;Qiang Ma

{"title":"Edge-Assisted Real-Time Motion Capture System","authors":"Chen Qian;Danyang Li;Jingao Xu;Zheng Yang;Qiang Ma","doi":"10.1109/TMC.2026.3656822","DOIUrl":"https://doi.org/10.1109/TMC.2026.3656822","url":null,"abstract":"Real-time motion capture stands as a pivotal enabler for human-centric applications, such as AR interactions, VR live-streaming, and immersive gaming. Deploying motion capture models on edge/cloud server to provide scalable services is emerging as a promising trend. However, due to the computational burden of model inference and the inevitable network transmission delays, mainstream DNN-based systems struggle to deliver real-time motion capture services. In this paper, we propose edgeMoCap, the first edge-assisted real-time DNN-based motion capture system. At the heart of edgeMoCap is a motion capture-tracking architecture optimized for edge-client heterogeneous computing capabilities. We dig into the spatio-temporal correlation between human motions and body-attached markers to: <inline-formula><tex-math>$(i)$</tex-math></inline-formula> distill a lightweight tracker for real-time motion tracking on client devices, and <inline-formula><tex-math>$(ii)$</tex-math></inline-formula> efficiently partition functional modules and schedule motion data. Together, these efforts establish a parallel capture-tracking architecture that enhances edge-client collaboration, ensuring accurate and real-time motion capture. We fully implement edgeMoCap on devices with varying computational resources and network conditions, conducting extensive experiments with diverse users and motions. The results show that edgeMoCap achieves an average latency of 6 ms and an accuracy of 3.8 cm, outperforming comparative methods by 70%. Code and data will be made publicly available before publication.","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":"25 7","pages":"9521-9533"},"PeriodicalIF":8.8,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148518402","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

Spectral-Convergent Decentralized Machine Learning: Theory and Application in Space Networks 频谱收敛分散机器学习：空间网络中的理论与应用

IF 8.8 2区计算机科学

IEEE Transactions on Mobile Computing Pub Date : 2026-07-01 Epub Date: 2026-02-13 DOI: 10.1109/TMC.2026.3664367

Zhiyuan Zhai;Shuyan Hu;Wei Ni;Xiaojun Yuan;Xin Wang;Jie Wu

{"title":"Spectral-Convergent Decentralized Machine Learning: Theory and Application in Space Networks","authors":"Zhiyuan Zhai;Shuyan Hu;Wei Ni;Xiaojun Yuan;Xin Wang;Jie Wu","doi":"10.1109/TMC.2026.3664367","DOIUrl":"https://doi.org/10.1109/TMC.2026.3664367","url":null,"abstract":"Decentralized machine learning (DML) supports collaborative training in large-scale networks with no central server. It is sensitive to the quality and reliability of inter-device communications that result in time-varying and stochastic topologies. This paper studies the impact of unreliable communication on the convergence of DML and establishes a direct connection between the spectral properties of the mixing process and the global performance. We provide rigorous convergence guarantees under random topologies and derive bounds that characterize the impact of the expected mixing matrix's spectral properties on learning. We formulate a spectral optimization problem that minimizes the nontrivial spectral radius of the expected second-order mixing matrix to enhance the convergence rate under probabilistic link failures. To solve this non-smooth spectral problem in a fully decentralized manner, we design an efficient subgradient-based algorithm that integrates Chebyshev-accelerated eigenvector estimation with local update and aggregation weight adjustment, while ensuring symmetry and stochasticity constraints without central coordination. Experiments on a realistic low Earth orbit satellite constellation with time-varying inter-satellite link models and real-world remote sensing data demonstrate the feasibility and effectiveness of our method. The method significantly improves classification accuracy and convergence efficiency compared to existing baselines, validating its applicability in satellite and other decentralized systems.","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":"25 7","pages":"10788-10799"},"PeriodicalIF":8.8,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148519211","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

Federated Unlearning via Distilled Data 通过蒸馏数据联合学习

IF 8.8 2区计算机科学

IEEE Transactions on Mobile Computing Pub Date : 2026-07-01 Epub Date: 2026-02-19 DOI: 10.1109/TMC.2026.3666356

Alessio Mora;Lorenzo Valerio;Paolo Bellavista

{"title":"Federated Unlearning via Distilled Data","authors":"Alessio Mora;Lorenzo Valerio;Paolo Bellavista","doi":"10.1109/TMC.2026.3666356","DOIUrl":"https://doi.org/10.1109/TMC.2026.3666356","url":null,"abstract":"Federated Learning (FL) has emerged as a privacy-preserving paradigm that enables collaborative model training between distributed client devices without exchanging raw data. However, while FL mitigates direct data exposure, the influence of client data remains encoded in the trained model, raising concerns in scenarios where data deletion is legally or ethically required. Federated Unlearning (FU) aims to address this gap. Yet first existing FU solutions often rely on strong assumptions, such as maintaining complete histories of model updates or leveraging publicly available datasets that resemble private client data, or propose solutions which are not selective and coarsely reinitialize part of the learned model (with the associated non-negligible overhead). This work introduces a novel unlearning method based on distilled synthetic data, which clients can generate and transmit to the server; these compact and distilled samples are unrecognizable from the original data, but preserve most of their training influence, thus enabling targeted removal from the global model. The unlearning phase is executed on the server side, without requiring the target client to be online or maintaining any historical record of client participation. In the reported experimental results, we show that our method can achieve competitive or superior unlearning performance compared to state-of-the-art baselines, in particular in terms of more precise forgetting, using a very small distilled dataset (e.g., distilling only five data points per class).","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":"25 7","pages":"10607-10618"},"PeriodicalIF":8.8,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11399903","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148518193","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

QRPL: Q-Learning-Based Routing Protocol for Low-Power and Lossy IoT Networks QRPL：基于q学习的低功耗和有损物联网网络路由协议

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.2026.3657189

Badis Djamaa;Mustapha Reda Senouci;Issam Eddine Lakhlaf;Abbas Bradai;Walid Moussaoui;Yacine Moussaoui

{"title":"QRPL: Q-Learning-Based Routing Protocol for Low-Power and Lossy IoT Networks","authors":"Badis Djamaa;Mustapha Reda Senouci;Issam Eddine Lakhlaf;Abbas Bradai;Walid Moussaoui;Yacine Moussaoui","doi":"10.1109/TMC.2026.3657189","DOIUrl":"https://doi.org/10.1109/TMC.2026.3657189","url":null,"abstract":"The Internet of Things (IoT) refers to the interconnection of numerous computationally, memory, communication, and energy-constrained objects over the Internet and local communication technologies by leveraging unicast and multicast routing solutions. These device and network limitations have resulted in several challenges for IoT routing protocols, leading to the standardization of RPL; the Routing Protocol for Low-power and Lossy Networks (LLNs). Nonetheless, while RPL addresses some hardware and software limitations, its decisions still rely on basic hand-crafted algorithms. The recent success of machine learning in several domains has motivated us to consider intelligent algorithms based on Reinforcement Learning (RL) as a solution to this problem. Therefore, we contribute in this paper three Q-learning-based algorithms for intelligent information dissemination and routing in IoT networks, named SMART, TRAP, and TRAST. SMART focuses on the intelligent suppression of unnecessary messages, TRAP dynamically adapts communication intervals to the network’s needs, and TRAST combines the two. These proposals have been integrated into RPL, evaluated through extensive simulations on dedicated IoT platforms, and validated via real experiments on the publicly available large-scale IoT-Lab testbed. The obtained results demonstrate the performance of our solutions compared to the state of the art in terms of energy consumption, load balancing, and end-to-end delay.","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":"25 7","pages":"9437-9453"},"PeriodicalIF":8.8,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148518401","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