Pub Date : 2025-09-23DOI: 10.1109/TMC.2025.3613450
Xinyu Lu;Zhanbo Feng;Jiong Lou;Chentao Wu;Guangtao Xue;Wei Zhao;Jie Li
In recent years, gig platforms have emerged as a new paradigm, seamlessly connecting workers and tasks while leveraging workers’ collective intelligence, participation, and shared resources. Traditionally, platforms have operated under the assumption of worker homogeneity, where service capabilities and associated service costs are similar. However, in mobile computing scenarios, such as mobile crowdsensing, the diversity in worker capabilities and costs renders the supply and demand matching into a complex problem characterized by multiple layers of workers possessing distinct attributes. The dynamic nature of incoming task requests requires the continual reallocation of these workers, thereby introducing a time-dependent overhead. In this paper, we introduce a framework, called the Generative Diffusion Model with Duality Guidance, termed Guid, to address the intricate multi-layer scheduling problem. We formalize a time-slotted long-term optimization problem that captures the spatiotemporal dynamics of task requests and worker services, as well as the intricate time-coupled overhead. Our framework employs a generative diffusion model to explore the complex solution space of the problem and generate superior solutions. To effectively manage time coupling, we utilize dual optimization theory to generate time slot-aware information, guiding the generative diffusion model towards solutions that assure long-term performance. We provide a rigorous theoretical analysis demonstrating that our guidance solution ensures a parameterized competitive ratio guarantee relative to the theoretically optimal solution. Our comprehensive experiments further illustrate that the proposed method outperforms benchmark techniques, achieving reduced overhead compared to seven baseline methods.
{"title":"Multi-Layer Scheduling in Gig Platforms Using a Generative Diffusion Model With Duality Guidance","authors":"Xinyu Lu;Zhanbo Feng;Jiong Lou;Chentao Wu;Guangtao Xue;Wei Zhao;Jie Li","doi":"10.1109/TMC.2025.3613450","DOIUrl":"https://doi.org/10.1109/TMC.2025.3613450","url":null,"abstract":"In recent years, gig platforms have emerged as a new paradigm, seamlessly connecting workers and tasks while leveraging workers’ collective intelligence, participation, and shared resources. Traditionally, platforms have operated under the assumption of worker homogeneity, where service capabilities and associated service costs are similar. However, in mobile computing scenarios, such as mobile crowdsensing, the diversity in worker capabilities and costs renders the supply and demand matching into a complex problem characterized by multiple layers of workers possessing distinct attributes. The dynamic nature of incoming task requests requires the continual reallocation of these workers, thereby introducing a time-dependent overhead. In this paper, we introduce a framework, called the <italic><u>G</u>enerative Diffusion Model with Duality G<u>uid</u>ance</i>, termed <italic>Guid</i>, to address the intricate multi-layer scheduling problem. We formalize a time-slotted long-term optimization problem that captures the spatiotemporal dynamics of task requests and worker services, as well as the intricate time-coupled overhead. Our framework employs a generative diffusion model to explore the complex solution space of the problem and generate superior solutions. To effectively manage time coupling, we utilize dual optimization theory to generate time slot-aware information, guiding the generative diffusion model towards solutions that assure long-term performance. We provide a rigorous theoretical analysis demonstrating that our guidance solution ensures a parameterized competitive ratio guarantee relative to the theoretically optimal solution. Our comprehensive experiments further illustrate that the proposed method outperforms benchmark techniques, achieving reduced overhead compared to seven baseline methods.","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":"25 2","pages":"2927-2940"},"PeriodicalIF":9.2,"publicationDate":"2025-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145929416","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}
Pub Date : 2025-09-22DOI: 10.1109/TMC.2025.3612469
Jiaqi Wu;Shihao Zhang;Simin Chen;Lixu Wang;Zehua Wang;Wei Chen;Fangyuan He;Zijian Tian;F. Richard Yu;Victor C. M. Leung
The paradigm of edge computing is pivotal for deploying deep learning object detectors in time-sensitive applications. Nevertheless, practical efficacy is often impeded by critical impediments: 1) the inherent trade-off between detection precision and model lightweightness; 2) the inflexibility of generalized deployment frameworks for task-specific object detection; and 3) the scarcity of validation in real world operational environments. To address these challenges, we propose the Edge Detection Toolbox (ED-TOOLBOX), which leverages generalizable plug-and-play components to enable edge-site adaptation of object detection models. Specifically, we propose a lightweight Reparameterized Dynamic Convolutional Network (Rep-DConvNet) that employs a weighted multi-shape convolutional branch structure to enhance detection performance. Furthermore, ED-TOOLBOX includes a Sparse Cross-Attention (SC-A) network that adopts a localized-mapping-assisted self-attention mechanism to facilitate a well-crafted Joint Module in adaptively transferring features for further performance improvement. Moreover, we propose an Efficient Head for the classification and location modules to achieve more efficient prediction. Furthermore, we address a critical oversight in industrial safety: conventional helmet detection’s neglect of band fastening. To bridge this gap, we construct the Helmet Band Detection Dataset (HBDD) and deploy our ED-TOOLBOX-optimized model on this practical challenge. Extensive experiments validate the efficacy of our components. In surveillance simulations, our model surpasses six state-of-the-art methods, achieving both real-time performance and high accuracy. These results establish our approach as a superior solution for edge object detection.
{"title":"Efficient Detection Framework Adaptation for Edge Computing: A Plug-and-Play Neural Network Toolbox Enabling Edge Deployment","authors":"Jiaqi Wu;Shihao Zhang;Simin Chen;Lixu Wang;Zehua Wang;Wei Chen;Fangyuan He;Zijian Tian;F. Richard Yu;Victor C. M. Leung","doi":"10.1109/TMC.2025.3612469","DOIUrl":"https://doi.org/10.1109/TMC.2025.3612469","url":null,"abstract":"The paradigm of edge computing is pivotal for deploying deep learning object detectors in time-sensitive applications. Nevertheless, practical efficacy is often impeded by critical impediments: 1) the inherent trade-off between detection precision and model lightweightness; 2) the inflexibility of generalized deployment frameworks for task-specific object detection; and 3) the scarcity of validation in real world operational environments. To address these challenges, we propose the <italic><u>E</u>dge <u>D</u>etection <u>Toolbox</u></i> (ED-TOOLBOX), which leverages generalizable plug-and-play components to enable edge-site adaptation of object detection models. Specifically, we propose a lightweight <italic>Reparameterized Dynamic Convolutional Network</i> (Rep-DConvNet) that employs a weighted multi-shape convolutional branch structure to enhance detection performance. Furthermore, ED-TOOLBOX includes a <italic>Sparse Cross-Attention</i> (SC-A) network that adopts a localized-mapping-assisted self-attention mechanism to facilitate a well-crafted <italic>Joint Module</i> in adaptively transferring features for further performance improvement. Moreover, we propose an <italic>Efficient Head</i> for the classification and location modules to achieve more efficient prediction. Furthermore, we address a critical oversight in industrial safety: conventional helmet detection’s neglect of band fastening. To bridge this gap, we construct the Helmet Band Detection Dataset (HBDD) and deploy our ED-TOOLBOX-optimized model on this practical challenge. Extensive experiments validate the efficacy of our components. In surveillance simulations, our model surpasses six state-of-the-art methods, achieving both real-time performance and high accuracy. These results establish our approach as a superior solution for edge object detection.","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":"25 2","pages":"2793-2810"},"PeriodicalIF":9.2,"publicationDate":"2025-09-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145929417","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}
Pub Date : 2025-09-18DOI: 10.1109/TMC.2025.3611963
Duong Thuy Anh Nguyen;Jiaming Cheng;Ni Trieu;Duong Tung Nguyen;Angelia Nedić
Mobile edge computing (MEC) is a promising solution for enhancing user experience, minimizing content delivery expenses, and reducing backhaul traffic. This paper presents a game-theoretic framework to address the edge resource crowdsourcing problem, where mobile edge devices (MEDs) provide idle storage for content caching in exchange for rewards from a content provider (CP). We model the interaction between the CP and MEDs as a Stackelberg game, with the CP as the leader setting the reward structure and the MEDs as followers competing in a non-cooperative game for these rewards. We propose a novel privacy-preserving method to derive the Stackelberg equilibrium of the game. Notably, our algorithm is designed to operate effectively in time-varying communication networks, addressing the high mobility inherent in MEC environments. This contrasts with state-of-the-art algorithms, which assume a static communication network among MEDs–an impractical condition that does not account for the mobility of MEDs during algorithm execution. Specifically, our approach employs consensus-based algorithms to compute the Nash equilibrium (NE) for MEDs, with MEDs exchanging NE profile estimates with neighbors via row-stochastic mixing matrices and performing gradient steps to optimize their utility in a fully decentralized manner. Based on the computed NE strategies, we propose a zeroth-order reward search algorithm for the CP to determine the optimal strategy for profit maximization. Our comprehensive analysis details the properties of the equilibrium and establishes the geometric convergence of the proposed algorithms to the NE. We also derive explicit bounds for the stepsizes based on the game’s properties and the graphs’ connectivity structure. Extensive numerical results validate the efficacy of our proposed approach.
{"title":"Bi-CrowdCache: A Decentralized Game-Theoretic Model for Edge Content Sharing Over Time-Varying Communication Networks","authors":"Duong Thuy Anh Nguyen;Jiaming Cheng;Ni Trieu;Duong Tung Nguyen;Angelia Nedić","doi":"10.1109/TMC.2025.3611963","DOIUrl":"https://doi.org/10.1109/TMC.2025.3611963","url":null,"abstract":"Mobile edge computing (MEC) is a promising solution for enhancing user experience, minimizing content delivery expenses, and reducing backhaul traffic. This paper presents a game-theoretic framework to address the edge resource crowdsourcing problem, where mobile edge devices (MEDs) provide idle storage for content caching in exchange for rewards from a content provider (CP). We model the interaction between the CP and MEDs as a Stackelberg game, with the CP as the leader setting the reward structure and the MEDs as followers competing in a non-cooperative game for these rewards. We propose a novel privacy-preserving method to derive the Stackelberg equilibrium of the game. Notably, our algorithm is designed to operate effectively in time-varying communication networks, addressing the high mobility inherent in MEC environments. This contrasts with state-of-the-art algorithms, which assume a static communication network among MEDs–an impractical condition that does not account for the mobility of MEDs during algorithm execution. Specifically, our approach employs consensus-based algorithms to compute the Nash equilibrium (NE) for MEDs, with MEDs exchanging NE profile estimates with neighbors via row-stochastic mixing matrices and performing gradient steps to optimize their utility in a fully decentralized manner. Based on the computed NE strategies, we propose a zeroth-order reward search algorithm for the CP to determine the optimal strategy for profit maximization. Our comprehensive analysis details the properties of the equilibrium and establishes the geometric convergence of the proposed algorithms to the NE. We also derive explicit bounds for the stepsizes based on the game’s properties and the graphs’ connectivity structure. Extensive numerical results validate the efficacy of our proposed approach.","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":"25 2","pages":"2895-2907"},"PeriodicalIF":9.2,"publicationDate":"2025-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145929587","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}
Pub Date : 2025-09-17DOI: 10.1109/TMC.2025.3611075
Zhigang Yan;Dong Li;Qiang Sun;Dusit Niyato;Tony Q. S. Quek
In Federated Learning (FL), with parameter aggregated by a central node, the communication overhead is a substantial concern. To circumvent this limitation and alleviate the single point of failure within the FL framework, recent studies have introduced Decentralized Federated Learning (DFL) as a viable alternative. Considering the device heterogeneity, and energy cost associated with parameter aggregation, in this paper, the problem on how to efficiently leverage the limited resources available to enhance the model performance is investigated. Specifically, we formulate a problem that minimizes the loss function of DFL while considering energy and latency constraints. The proposed solution involves optimizing the number of local training rounds across diverse devices with varying resource budgets. To make this problem tractable, we first analyze the convergence of DFL with edge devices with different rounds of local training. The derived convergence bound reveals the impact of the rounds of local training on the model performance. Then, based on the derived bound, the closed-form solutions of rounds of local training in different devices are obtained. Meanwhile, since the solutions require the energy cost of aggregation as low as possible, we modify different graph-based aggregation schemes to solve this energy consumption minimization problem, which can be applied to different communication scenarios. Finally, a DFL framework which jointly considers the optimized rounds of local training and the energy-saving aggregation scheme is proposed. Simulation results show that, the proposed algorithm achieves a better performance than the conventional schemes and consumes less energy than other traditional aggregation schemes.
{"title":"Adaptive Decentralized Federated Learning in Energy and Latency Constrained Wireless Networks","authors":"Zhigang Yan;Dong Li;Qiang Sun;Dusit Niyato;Tony Q. S. Quek","doi":"10.1109/TMC.2025.3611075","DOIUrl":"https://doi.org/10.1109/TMC.2025.3611075","url":null,"abstract":"In Federated Learning (FL), with parameter aggregated by a central node, the communication overhead is a substantial concern. To circumvent this limitation and alleviate the single point of failure within the FL framework, recent studies have introduced Decentralized Federated Learning (DFL) as a viable alternative. Considering the device heterogeneity, and energy cost associated with parameter aggregation, in this paper, the problem on how to efficiently leverage the limited resources available to enhance the model performance is investigated. Specifically, we formulate a problem that minimizes the loss function of DFL while considering energy and latency constraints. The proposed solution involves optimizing the number of local training rounds across diverse devices with varying resource budgets. To make this problem tractable, we first analyze the convergence of DFL with edge devices with different rounds of local training. The derived convergence bound reveals the impact of the rounds of local training on the model performance. Then, based on the derived bound, the closed-form solutions of rounds of local training in different devices are obtained. Meanwhile, since the solutions require the energy cost of aggregation as low as possible, we modify different graph-based aggregation schemes to solve this energy consumption minimization problem, which can be applied to different communication scenarios. Finally, a DFL framework which jointly considers the optimized rounds of local training and the energy-saving aggregation scheme is proposed. Simulation results show that, the proposed algorithm achieves a better performance than the conventional schemes and consumes less energy than other traditional aggregation schemes.","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":"25 2","pages":"2908-2926"},"PeriodicalIF":9.2,"publicationDate":"2025-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145929396","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}
Pub Date : 2025-09-17DOI: 10.1109/TMC.2025.3611135
Jian Yang;Jiadi Bao;Luyao Zhang;Yatong Wang;Fang Yang;Shafei Wang
Radio frequency fingerprint identification (RFFI) aims to identify subtle impairments in hardware devices, which play an important role in the mobile environment security community. To identify various mobile devices in the complex electromagnetic environment, deep learning methods such as convolutional neural networks (CNN) and recurrent neural networks (RNN) have been adopted to extract device hardware-related features. However, the single network structure has difficulty in comprehensive feature extraction, as many factors can introduce hardware impairments. In this paper, we propose a hybrid model termed switching dynamical deep network (SDDN) for RFFI tasks, which can jointly extract both coarse-grained radio frequency fingerprints (RFFs) and fine-grained RFFs. Additionally, the proposed hybrid model consists of a probabilistic part and a deterministic part. Specifically, in the probabilistic part, the switching linear dynamical systems (SLDS) are incorporated to establish the correspondence between the signal slice and the feature extraction network (FEN). In the deterministic part, multiple independent FENs are established to extract the RFFs. Moreover, to automatically determine the suitable number of FENs, a Bayesian nonparametric prior distribution is placed over the probabilistic part. Finally, an end-to-end parameter optimization method that is based on variational inference and stochastic gradient descent is proposed. Experiments on a real-life Wi-Fi dataset demonstrate the superiority of the proposed method over existing methods.
{"title":"A Hybrid Model With Bayesian Nonparametric Inference for RF Fingerprint Identification","authors":"Jian Yang;Jiadi Bao;Luyao Zhang;Yatong Wang;Fang Yang;Shafei Wang","doi":"10.1109/TMC.2025.3611135","DOIUrl":"https://doi.org/10.1109/TMC.2025.3611135","url":null,"abstract":"Radio frequency fingerprint identification (RFFI) aims to identify subtle impairments in hardware devices, which play an important role in the mobile environment security community. To identify various mobile devices in the complex electromagnetic environment, deep learning methods such as convolutional neural networks (CNN) and recurrent neural networks (RNN) have been adopted to extract device hardware-related features. However, the single network structure has difficulty in comprehensive feature extraction, as many factors can introduce hardware impairments. In this paper, we propose a hybrid model termed switching dynamical deep network (SDDN) for RFFI tasks, which can jointly extract both coarse-grained radio frequency fingerprints (RFFs) and fine-grained RFFs. Additionally, the proposed hybrid model consists of a probabilistic part and a deterministic part. Specifically, in the probabilistic part, the switching linear dynamical systems (SLDS) are incorporated to establish the correspondence between the signal slice and the feature extraction network (FEN). In the deterministic part, multiple independent FENs are established to extract the RFFs. Moreover, to automatically determine the suitable number of FENs, a Bayesian nonparametric prior distribution is placed over the probabilistic part. Finally, an end-to-end parameter optimization method that is based on variational inference and stochastic gradient descent is proposed. Experiments on a real-life Wi-Fi dataset demonstrate the superiority of the proposed method over existing methods.","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":"25 2","pages":"2941-2955"},"PeriodicalIF":9.2,"publicationDate":"2025-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145929588","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}
Pub Date : 2025-09-16DOI: 10.1109/TMC.2025.3610648
Yunshu Liu;Man Hon Cheung;Jianwei Huang
Blockchain-based energy trading (BBET) systems depend on prosumers to allocate energy between trading activities and blockchain mining operations. However, inadequate incentive structures lead prosumers to under-contribute to mining, creating throughput bottlenecks and system performance degradation. This paper introduces the Fee and Two-Piece Compensation (FTPC) mechanism to optimize energy allocation and enhance system throughput. We formulate the interaction between the system designer and prosumers as a three-stage Stackelberg game where the system designer establishes the incentive framework in Stage I, while prosumers determine energy allocation in Stage II and set transaction fees in Stage III. Our analysis demonstrates that prosumers’ failure to internalize mining’s positive externality results in suboptimal throughput investment. Counterintuitively, we show that impatient prosumers may exploit others’ mining contributions as free riders. The FTPC mechanism resolves these issues by jointly optimizing transaction fees and compensation structures to align individual incentives with social welfare. We prove that FTPC achieves socially optimal outcomes through fully decentralized decision-making. Numerical evaluation shows FTPC improves social welfare and prosumer payoffs by 88.1% and 87.8%, respectively. Ethereum testbed implementation validates equilibrium convergence through iterative best-response dynamics.
{"title":"Incentivizing Throughput Enhancement in Blockchain-Based Energy Trading System","authors":"Yunshu Liu;Man Hon Cheung;Jianwei Huang","doi":"10.1109/TMC.2025.3610648","DOIUrl":"https://doi.org/10.1109/TMC.2025.3610648","url":null,"abstract":"Blockchain-based energy trading (BBET) systems depend on prosumers to allocate energy between <italic>trading</i> activities and <italic>blockchain mining</i> operations. However, inadequate incentive structures lead prosumers to under-contribute to mining, creating throughput bottlenecks and system performance degradation. This paper introduces the Fee and Two-Piece Compensation (FTPC) mechanism to optimize energy allocation and enhance system throughput. We formulate the interaction between the system designer and prosumers as a three-stage Stackelberg game where the system designer establishes the incentive framework in Stage I, while prosumers determine energy allocation in Stage II and set transaction fees in Stage III. Our analysis demonstrates that prosumers’ failure to internalize mining’s positive externality results in suboptimal throughput investment. Counterintuitively, we show that impatient prosumers may exploit others’ mining contributions as free riders. The FTPC mechanism resolves these issues by jointly optimizing transaction fees and compensation structures to align individual incentives with social welfare. We prove that FTPC achieves socially optimal outcomes through fully decentralized decision-making. Numerical evaluation shows FTPC improves social welfare and prosumer payoffs by 88.1% and 87.8%, respectively. Ethereum testbed implementation validates equilibrium convergence through iterative best-response dynamics.","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":"25 2","pages":"2860-2877"},"PeriodicalIF":9.2,"publicationDate":"2025-09-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145929337","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}
The rapid expansion of cloud applications has led to unprecedented increases in network traffic volume, diversity, and complexity. As Cloud Service Providers (CSPs) adopt decentralized, geographically distributed data centers, effective traffic management across these environments has become critical. Distributed Rate Limiting (DRL) has emerged as an essential tool to manage the complex traffic dynamics of decentralized networks, yet traditional centralized rate limiting methods fall short, facing limitations in scalability, adaptability to bursty traffic, and efficiency. This paper presents C3PDAR (Cloud Control with Constant Probabilities and Dynamic Adjustment Range), a novel DRL algorithm tailored for decentralized cloud infrastructures. C3PDAR introduces three key innovations: (1) CPS-BPS Dual-Point Rate Limiting and Parent-Child Token Bucket mechanisms, which effectively mitigate burst traffic and short-lived connections while improving bandwidth fairness and inter-tenant isolation; (2) A vSwitch-CGW Cascade Rate Limiting architecture, which reduces CPU overhead in CGW clusters and accelerates convergence by 42% –78%; (3) Virtual Extensible Local Area Network (VXLAN) Padding scheme, which embeds rate-limiting information in existing traffic instead of transmitting new data packets, reducing the communication overhead of the C3PDAR algorithm by over 40%. By integrating these advancements, C3PDAR delivers a scalable, robust solution that outperforms traditional DRL approaches in performance, fault tolerance, and resource efficiency. C3PDAR uniquely empowers CSPs to manage complex, high-volume traffic dynamics in decentralized cloud environments, offering both theoretical insights and practical optimizations for next-generation network control.
云应用程序的快速扩展导致了网络流量、多样性和复杂性的空前增加。随着云服务提供商（csp）采用分散的、地理上分布的数据中心，跨这些环境的有效流量管理变得至关重要。分布式速率限制（DRL）已成为管理分散网络中复杂流量动态的重要工具，但传统的集中式速率限制方法在可扩展性、对突发流量的适应性和效率方面存在不足。C3PDAR （Cloud Control with Constant Probabilities and Dynamic Adjustment Range）是一种为去中心化云基础设施量身定制的新型DRL算法。C3PDAR引入了三个关键创新：(1)CPS-BPS双点速率限制和父子令牌桶机制，有效缓解突发流量和短时间连接，同时提高带宽公平性和租户间隔离；(2) vSwitch-CGW级联限速架构，降低了CGW集群的CPU开销，收敛速度提高42% ~ 78%；(3) VXLAN （Virtual Extensible Local Area Network）填充方案，该方案在现有流量中嵌入限速信息，而不传输新的数据包，使C3PDAR算法的通信开销降低40%以上。通过集成这些进步，C3PDAR提供了一个可扩展的、健壮的解决方案，在性能、容错性和资源效率方面优于传统的DRL方法。C3PDAR使csp能够在分散的云环境中管理复杂的、大容量的流量动态，为下一代网络控制提供理论见解和实践优化。
{"title":"Distributed Rate Limiting Under Decentralized Cloud Networks","authors":"Xiang Hu;Tianyu Xu;Lilong Chen;Xiaochong Jiang;Ye Yang;Liming Ye;Xu Wang;Yilong Lv;Chenhao Jia;Yongwang Wu;Zhigang Zong;Xing Li;Bingqian Lu;Shunmin Zhu;Chengkun Wei;Wenzhi Chen","doi":"10.1109/TMC.2025.3610314","DOIUrl":"https://doi.org/10.1109/TMC.2025.3610314","url":null,"abstract":"The rapid expansion of cloud applications has led to unprecedented increases in network traffic volume, diversity, and complexity. As Cloud Service Providers (CSPs) adopt decentralized, geographically distributed data centers, effective traffic management across these environments has become critical. Distributed Rate Limiting (DRL) has emerged as an essential tool to manage the complex traffic dynamics of decentralized networks, yet traditional centralized rate limiting methods fall short, facing limitations in scalability, adaptability to bursty traffic, and efficiency. This paper presents C3PDAR (Cloud Control with Constant Probabilities and Dynamic Adjustment Range), a novel DRL algorithm tailored for decentralized cloud infrastructures. C3PDAR introduces three key innovations: (1) CPS-BPS Dual-Point Rate Limiting and Parent-Child Token Bucket mechanisms, which effectively mitigate burst traffic and short-lived connections while improving bandwidth fairness and inter-tenant isolation; (2) A vSwitch-CGW Cascade Rate Limiting architecture, which reduces CPU overhead in CGW clusters and accelerates convergence by 42% –78%; (3) Virtual Extensible Local Area Network (VXLAN) Padding scheme, which embeds rate-limiting information in existing traffic instead of transmitting new data packets, reducing the communication overhead of the C3PDAR algorithm by over 40%. By integrating these advancements, C3PDAR delivers a scalable, robust solution that outperforms traditional DRL approaches in performance, fault tolerance, and resource efficiency. C3PDAR uniquely empowers CSPs to manage complex, high-volume traffic dynamics in decentralized cloud environments, offering both theoretical insights and practical optimizations for next-generation network control.","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":"25 2","pages":"2774-2792"},"PeriodicalIF":9.2,"publicationDate":"2025-09-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145929338","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}
Designing effective incentive mechanisms in mobile crowdsensing (MCS) networks is crucial for engaging distributed mobile users (workers) to contribute heterogeneous data for various applications (tasks). In this paper, we propose a novel stagewise trading framework to achieve efficient and stable task-worker matching, explicitly accounting for task diversity (e.g., spatio-temporal limitations) and network dynamics inherent in MCS environments. This framework integrates both futures and spot trading stages. In the former, we introduce the futures trading-driven stable matching and pre-path-planning mechanism (FT-SMP$^{3}$), which enables long-term task-worker assignment and pre-planning of workers’ trajectories based on historical statistics and risk-aware analysis. In the latter, we develop the spot trading-driven DQN-based path planning and onsite worker recruitment mechanism (ST-DP$^{2}$WR), which dynamically improves the practical utilities of tasks and workers by supporting real-time recruitment and path adjustment. We rigorously prove that the proposed mechanisms satisfy key economic and algorithmic properties, including stability, individual rationality, competitive equilibrium, and weak Pareto optimality. Extensive experiements further validate the effectiveness of our framework in realistic network settings, demonstrating superior performance in terms of service quality, computational efficiency, and decision-making overhead.
{"title":"Accelerating Stable Matching Between Workers and Spatial-Temporal Tasks for Dynamic MCS: A Stagewise Service Trading Approach","authors":"Houyi Qi;Minghui Liwang;Xianbin Wang;Liqun Fu;Yiguang Hong;Li Li;Zhipeng Cheng","doi":"10.1109/TMC.2025.3610915","DOIUrl":"https://doi.org/10.1109/TMC.2025.3610915","url":null,"abstract":"Designing effective incentive mechanisms in mobile crowdsensing (MCS) networks is crucial for engaging distributed mobile users (workers) to contribute heterogeneous data for various applications (tasks). In this paper, we propose a novel stagewise trading framework to achieve efficient and stable task-worker matching, explicitly accounting for task diversity (e.g., spatio-temporal limitations) and network dynamics inherent in MCS environments. This framework integrates both futures and spot trading stages. In the former, we introduce the <b>f</b>utures <b>t</b>rading-driven <b>s</b>table <b>m</b>atching and <b>p</b>re-<b>p</b>ath-<b>p</b>lanning mechanism (FT-SMP<inline-formula><tex-math>$^{3}$</tex-math></inline-formula>), which enables long-term task-worker assignment and pre-planning of workers’ trajectories based on historical statistics and risk-aware analysis. In the latter, we develop the <b>s</b>pot <b>t</b>rading-driven <b>D</b>QN-based <b>p</b>ath <b>p</b>lanning and onsite <b>w</b>orker <b>r</b>ecruitment mechanism (ST-DP<inline-formula><tex-math>$^{2}$</tex-math></inline-formula>WR), which dynamically improves the practical utilities of tasks and workers by supporting real-time recruitment and path adjustment. We rigorously prove that the proposed mechanisms satisfy key economic and algorithmic properties, including stability, individual rationality, competitive equilibrium, and weak Pareto optimality. Extensive experiements further validate the effectiveness of our framework in realistic network settings, demonstrating superior performance in terms of service quality, computational efficiency, and decision-making overhead.","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":"25 2","pages":"2878-2894"},"PeriodicalIF":9.2,"publicationDate":"2025-09-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145929573","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}
Pub Date : 2025-09-16DOI: 10.1109/TMC.2025.3610887
Yehui Wang;Baoxian Zhang;Jinkai Zhang;Cheng Li
Federated Learning (FL) enables collaborative model training across devices, but data exchanges pose privacy risks. Homomorphic Encryption (HE) is widely used to enhances privacy in FL but incurs significant communication and computation latency. Prior work reduced this latency using compressions, but sacrificed learning accuracy and overlooked the impact of the number of participating devices on latency. Over-the-air computation (AirComp) leverages wireless channels’ superposition property to achieve high spectral efficiency and efficient aggregation irrespective of device number. In this paper, we propose HEAirFed, integrating AirComp with the state-of-the-art HE scheme CKKS for efficient privacy-preserving FL. In HEAirFed, we develop a ciphertext-oriented wireless communication module to ensure homomorphic operations leverage AirComp’s superposition property, enabling correct decryption. We further build a rigorous error analysis model, derive the worst-case upper bound of approximation error, and characterize this bound’s impact on the convergence guarantee of HEAirFed, measured by the optimality gap with bounded approximation error. Then, we minimize this gap and derive a near-optimal solution in semi-closed form. Extensive experimental results on real-world datasets validate the ciphertext-oriented design’s necessity, the error analysis’s correctness, and demonstrate that HEAirFed achieves a substantial reduction in communication and aggregation latency compared to baseline, with minimal learning accuracy loss.
{"title":"Efficient Privacy-Preserving Federated Learning via Homomorphic Encryption-Enabled Over-the-Air Computation","authors":"Yehui Wang;Baoxian Zhang;Jinkai Zhang;Cheng Li","doi":"10.1109/TMC.2025.3610887","DOIUrl":"https://doi.org/10.1109/TMC.2025.3610887","url":null,"abstract":"Federated Learning (FL) enables collaborative model training across devices, but data exchanges pose privacy risks. Homomorphic Encryption (HE) is widely used to enhances privacy in FL but incurs significant communication and computation latency. Prior work reduced this latency using compressions, but sacrificed learning accuracy and overlooked the impact of the number of participating devices on latency. Over-the-air computation (AirComp) leverages wireless channels’ superposition property to achieve high spectral efficiency and efficient aggregation irrespective of device number. In this paper, we propose HEAirFed, integrating AirComp with the state-of-the-art HE scheme CKKS for efficient privacy-preserving FL. In HEAirFed, we develop a ciphertext-oriented wireless communication module to ensure homomorphic operations leverage AirComp’s superposition property, enabling correct decryption. We further build a rigorous error analysis model, derive the worst-case upper bound of approximation error, and characterize this bound’s impact on the convergence guarantee of HEAirFed, measured by the optimality gap with bounded approximation error. Then, we minimize this gap and derive a near-optimal solution in semi-closed form. Extensive experimental results on real-world datasets validate the ciphertext-oriented design’s necessity, the error analysis’s correctness, and demonstrate that HEAirFed achieves a substantial reduction in communication and aggregation latency compared to baseline, with minimal learning accuracy loss.","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":"24 12","pages":"13743-13759"},"PeriodicalIF":9.2,"publicationDate":"2025-09-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145442723","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}
Pub Date : 2025-09-16DOI: 10.1109/TMC.2025.3610501
Xuedou Xiao;Mingxuan Yan;Yingying Zuo;Boxi Liu;Paul Ruan;Yang Cao;Yue Cao;Wei Wang
Enhancing the quality of experience (QoE) in interactive video streaming (IVS) remains a persistent challenge due to the need for ultra-low latency and rising bandwidth demands. Conventional algorithms, whether rule-based or learning-based, are obsessed with achieving tight coupling between encoding and sending bitrate adaptations for low-latency guarantee. However, our measurement studies reveal alarming harms of tight coupling in suppressing throughput, encoding bitrates and smoothness, as application- and transport-layer bitrate adaptations inherently have different mechanisms and goals. To tackle this problem, we propose Octopus, the first loosely coupled cross-layer bitrate adaptation algorithm for IVS to maximize QoE. Instead of blind synchronization, Octopus promotes mutual cooperation and independence between encoding and sending bitrate adaptations by integrating a multi-head network with shortcut connections and auto-regressive action modules. Additionally, based on meta-imitation reinforcement learning, we design a network condition-aware online adaptation scheme that enables the loosely coupled policy to swiftly adapt to diverse and dynamic wireless networks. We implement Octopus on a testbed, a microcosm of real-world deployment, with transceiver pairs running WebRTC on the WeChat for Business dataset. Results show that Octopus outperforms state-of-the-art algorithms, either improving bitrates by 37.1%, or optimizing stalling rate and smoothness by 54.1% and 9.2%, or achieving all-around improvements.
{"title":"Octopus: Optimizing Interactive Video QoE via Loosely Coupled Codec-Transport Adaptation","authors":"Xuedou Xiao;Mingxuan Yan;Yingying Zuo;Boxi Liu;Paul Ruan;Yang Cao;Yue Cao;Wei Wang","doi":"10.1109/TMC.2025.3610501","DOIUrl":"https://doi.org/10.1109/TMC.2025.3610501","url":null,"abstract":"Enhancing the quality of experience (QoE) in interactive video streaming (IVS) remains a persistent challenge due to the need for ultra-low latency and rising bandwidth demands. Conventional algorithms, whether rule-based or learning-based, are obsessed with achieving tight coupling between encoding and sending bitrate adaptations for low-latency guarantee. However, our measurement studies reveal alarming harms of tight coupling in suppressing throughput, encoding bitrates and smoothness, as application- and transport-layer bitrate adaptations inherently have different mechanisms and goals. To tackle this problem, we propose Octopus, the first loosely coupled cross-layer bitrate adaptation algorithm for IVS to maximize QoE. Instead of blind synchronization, Octopus promotes mutual cooperation and independence between encoding and sending bitrate adaptations by integrating a multi-head network with shortcut connections and auto-regressive action modules. Additionally, based on meta-imitation reinforcement learning, we design a network condition-aware online adaptation scheme that enables the loosely coupled policy to swiftly adapt to diverse and dynamic wireless networks. We implement Octopus on a testbed, a microcosm of real-world deployment, with transceiver pairs running WebRTC on the WeChat for Business dataset. Results show that Octopus outperforms state-of-the-art algorithms, either improving bitrates by 37.1%, or optimizing stalling rate and smoothness by 54.1% and 9.2%, or achieving all-around improvements.","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":"25 2","pages":"2707-2724"},"PeriodicalIF":9.2,"publicationDate":"2025-09-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145929571","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：