Recent studies highlighted the advantages of Visible Light Communication (VLC) over radio technology for future 6G networks. Thanks to the use of Reflective Intelligent Surfaces (RISs), researchers showed that is possible to guarantee communication secrecy in a VLC network where the adversary location is unknown. However, the problem of authenticating the transmitter with a low-complexity physical layer solution while guaranteeing communication secrecy is still open. This paper proposes a novel multi-RIS architecture to guarantee source authentication, communication secrecy, and integrity in a VLC scenario. We leverage the intuition that a signal transmitted by users located in different positions will undergo a different propagation path to discriminate between the legitimate intended transmitter and an attacker. To increase the channel's variability and reduce the chances that an adversary might be able to replicate it, we leverage the reconfiguration capabilities of RIS. We derive a statistical characterization of the non-line-of-sight VLC channel, representing the light reflected by RIS elements. Via numerical simulations, we show that the channel variability combined with the configurability capabilities of RISs provide sufficient statistics to authenticate the legitimate transmitter at the physical layer.
{"title":"Multi-RIS Aided VLC Physical Layer Security for 6G Wireless Networks","authors":"Simone Soderi;Alessandro Brighente;Saiqin Xu;Mauro Conti","doi":"10.1109/TMC.2024.3452963","DOIUrl":"10.1109/TMC.2024.3452963","url":null,"abstract":"Recent studies highlighted the advantages of Visible Light Communication (VLC) over radio technology for future 6G networks. Thanks to the use of Reflective Intelligent Surfaces (RISs), researchers showed that is possible to guarantee communication secrecy in a VLC network where the adversary location is unknown. However, the problem of authenticating the transmitter with a low-complexity physical layer solution while guaranteeing communication secrecy is still open. This paper proposes a novel multi-RIS architecture to guarantee source authentication, communication secrecy, and integrity in a VLC scenario. We leverage the intuition that a signal transmitted by users located in different positions will undergo a different propagation path to discriminate between the legitimate intended transmitter and an attacker. To increase the channel's variability and reduce the chances that an adversary might be able to replicate it, we leverage the reconfiguration capabilities of RIS. We derive a statistical characterization of the non-line-of-sight VLC channel, representing the light reflected by RIS elements. Via numerical simulations, we show that the channel variability combined with the configurability capabilities of RISs provide sufficient statistics to authenticate the legitimate transmitter at the physical layer.","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":null,"pages":null},"PeriodicalIF":7.7,"publicationDate":"2024-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142180558","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}
Communication plays a vital role in multi-agent systems, fostering collaboration and coordination. However, in real-world scenarios where communication is bandwidth-limited, existing multi-agent reinforcement learning (MARL) algorithms often provide agents with a binary choice: either transmitting a fixed amount of data or no information at all. This rigid communication strategy hinders the ability to effectively utilize bandwidth. To overcome this challenge, we present the Dynamic Size Message Scheduling (DSMS) method, which introduces finer-grained communication scheduling by considering the actual size of the information being exchanged. Our approach lies in adapting message sizes using Fourier transform-based compression techniques with clipping, enabling agents to tailor their messages to match the allocated bandwidth according to importance weights. This method realizes a balance between information loss and bandwidth utilization. Receiving agents reliably decompress the messages using the inverse Fourier transform. We evaluate DSMS in cooperative tasks where the agent has partial observability. Experimental results demonstrate that DSMS significantly improves performance by optimizing the utilization of bandwidth and effectively balancing information importance.
{"title":"Dynamic Size Message Scheduling for Multi-Agent Communication Under Limited Bandwidth","authors":"Qingshuang Sun;Denis Steckelmacher;Yuan Yao;Ann Nowé;Raphaël Avalos","doi":"10.1109/TMC.2024.3452986","DOIUrl":"10.1109/TMC.2024.3452986","url":null,"abstract":"Communication plays a vital role in multi-agent systems, fostering collaboration and coordination. However, in real-world scenarios where communication is bandwidth-limited, existing multi-agent reinforcement learning (MARL) algorithms often provide agents with a binary choice: either transmitting a fixed amount of data or no information at all. This rigid communication strategy hinders the ability to effectively utilize bandwidth. To overcome this challenge, we present the Dynamic Size Message Scheduling (DSMS) method, which introduces finer-grained communication scheduling by considering the actual size of the information being exchanged. Our approach lies in adapting message sizes using Fourier transform-based compression techniques with clipping, enabling agents to tailor their messages to match the allocated bandwidth according to importance weights. This method realizes a balance between information loss and bandwidth utilization. Receiving agents reliably decompress the messages using the inverse Fourier transform. We evaluate DSMS in cooperative tasks where the agent has partial observability. Experimental results demonstrate that DSMS significantly improves performance by optimizing the utilization of bandwidth and effectively balancing information importance.","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":null,"pages":null},"PeriodicalIF":7.7,"publicationDate":"2024-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142180594","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}
Deep learning (DL) powered real-time applications usually need continuous training using data streams generated over time and across different geographical locations. Enabling data offloading among computation nodes through model training is promising to mitigate the problem that devices generating large datasets may have low computation capability. However, offloading can compromise model convergence and incur communication costs, which must be balanced with the long-term cost spent on computation and model synchronization. Therefore, this paper proposes EdgeC3, a novel framework that can optimize the frequency of model aggregation and dynamic offloading for continuously generated data streams, navigating the trade-off between long-term accuracy and cost. We first provide a new error bound to capture the impacts of data dynamics that are varying over time and heterogeneous across devices, as well as quantifying varied data heterogeneity between local models and the global one. Based on the bound, we design a two-timescale online optimization framework. We periodically learn the synchronization frequency to adapt with uncertain future offloading and network changes. In the finer timescale, we manage online offloading by extending Lyapunov optimization techniques to handle an unconventional setting, where our long-term global constraint can have abruptly changed aggregation frequencies that are decided in the longer timescale. Finally, we theoretically prove the convergence of EdgeC3 by integrating the coupled effects of our two-timescale decisions, and we demonstrate its advantage through extensive experiments performing distributed DL training for different domains.
{"title":"Online Management for Edge-Cloud Collaborative Continuous Learning: A Two-Timescale Approach","authors":"Shaohui Lin;Xiaoxi Zhang;Yupeng Li;Carlee Joe-Wong;Jingpu Duan;Dongxiao Yu;Yu Wu;Xu Chen","doi":"10.1109/TMC.2024.3451715","DOIUrl":"10.1109/TMC.2024.3451715","url":null,"abstract":"Deep learning (DL) powered real-time applications usually need continuous training using data streams generated over time and across different geographical locations. Enabling data offloading among computation nodes through model training is promising to mitigate the problem that devices generating large datasets may have low computation capability. However, offloading can compromise model convergence and incur communication costs, which must be balanced with the long-term cost spent on computation and model synchronization. Therefore, this paper proposes EdgeC3, a novel framework that can optimize the frequency of model aggregation and dynamic offloading for continuously generated data streams, navigating the trade-off between long-term accuracy and cost. We first provide a new error bound to capture the impacts of data dynamics that are varying over time and heterogeneous across devices, as well as quantifying varied data heterogeneity between local models and the global one. Based on the bound, we design a two-timescale online optimization framework. We periodically learn the synchronization frequency to adapt with uncertain future offloading and network changes. In the finer timescale, we manage online offloading by extending Lyapunov optimization techniques to handle an unconventional setting, where our long-term global constraint can have abruptly changed aggregation frequencies that are decided in the longer timescale. Finally, we theoretically prove the convergence of EdgeC3 by integrating the coupled effects of our two-timescale decisions, and we demonstrate its advantage through extensive experiments performing distributed DL training for different domains.","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":null,"pages":null},"PeriodicalIF":7.7,"publicationDate":"2024-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142180560","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}
{"title":"MagWear: Vital Sign Monitoring based on Biomagnetism Sensing","authors":"Xiuzhen Guo, Long Tan, Chaojie Gu, Yuanchao Shu, Shibo He, Jiming Chen","doi":"10.1109/tmc.2024.3452499","DOIUrl":"https://doi.org/10.1109/tmc.2024.3452499","url":null,"abstract":"","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":null,"pages":null},"PeriodicalIF":7.9,"publicationDate":"2024-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142180564","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}
As a promising approach, Clustered Federated Learning (CFL) enables personalized model aggregation for heterogeneous clients. However, facing dynamic and open edge networks, previous CFL rarely considers the impact of dynamic client data on clustering validity, or sensitively identifies low-quality parameters from highly heterogeneous client models. Moreover, the device heterogeneity in each cluster leads to unbalanced model transmission delay, thus reducing the system efficiency. To tackle the above issues, this paper proposes a Robust and Efficient Clustered Federated System (REC-Fed). First, a Hierarchical Attention based Robust Aggregation (HARA) method is designed to realize layer-wise model customization for clients, meanwhile keeping the clustering validity under dynamic client data distribution. In addition, the fine-grained parameter detection in HARA provides a natural advantage to detect low-quality parameters, which improves the robustness of CFL systems. Second, to realize efficient synchronous model transmission, an Adaptive Model Transmission Optimization (AMTO) is proposed to jointly optimize the model compression and bandwidth allocation for heterogenous clients. Finally, we theoretically analyze the convergence of REC-Fed and conduct experiments on several personalization tasks, which demonstrate that our REC-Fed has significant improvement on flexibility, robustness and efficiency.
{"title":"REC-Fed: A Robust and Efficient Clustered Federated System for Dynamic Edge Networks","authors":"Jialin Guo;Zhetao Li;Anfeng Liu;Xiong Li;Ting Chen","doi":"10.1109/TMC.2024.3452312","DOIUrl":"10.1109/TMC.2024.3452312","url":null,"abstract":"As a promising approach, Clustered Federated Learning (CFL) enables personalized model aggregation for heterogeneous clients. However, facing dynamic and open edge networks, previous CFL rarely considers the impact of dynamic client data on clustering validity, or sensitively identifies low-quality parameters from highly heterogeneous client models. Moreover, the device heterogeneity in each cluster leads to unbalanced model transmission delay, thus reducing the system efficiency. To tackle the above issues, this paper proposes a Robust and Efficient Clustered Federated System (REC-Fed). First, a Hierarchical Attention based Robust Aggregation (HARA) method is designed to realize layer-wise model customization for clients, meanwhile keeping the clustering validity under dynamic client data distribution. In addition, the fine-grained parameter detection in HARA provides a natural advantage to detect low-quality parameters, which improves the robustness of CFL systems. Second, to realize efficient synchronous model transmission, an Adaptive Model Transmission Optimization (AMTO) is proposed to jointly optimize the model compression and bandwidth allocation for heterogenous clients. Finally, we theoretically analyze the convergence of REC-Fed and conduct experiments on several personalization tasks, which demonstrate that our REC-Fed has significant improvement on flexibility, robustness and efficiency.","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":null,"pages":null},"PeriodicalIF":7.7,"publicationDate":"2024-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142180565","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 : 2024-08-30DOI: 10.1109/TMC.2024.3449039
En Wang;Dongming Luan;Yuanbo Xu;Yongjian Yang;Jie Wu
Mobile CrowdSensing (MCS) is a promising sensing paradigm that leverages users’ mobile devices to collect and share data for various applications. A key challenge in MCS is task allocation, which aims to assign sensing tasks to suitable users efficiently and effectively. Existing task allocation approaches are mostly centralized, requiring users to disclose their private information and facing high computational complexity. Moreover, centralized approaches may not satisfy users’ preferences or incentives. To address these issues, we propose a novel distributed task allocation scheme based on route navigation systems. We consider two scenarios: time-tolerant tasks and time-sensitive tasks, and formulate them as potential games. We design distributed algorithms to achieve Nash equilibria while considering users’ individual preferences and the platform’s task allocation objectives. We also analyze the convergence and performance of our algorithm theoretically. In the time-sensitive task scenario, the problem becomes even more intricate due to temporal conflicts among tasks. We prove the task selection problem is NP-hard and propose a distributed task selection algorithm. In contrast to existing distributed approaches that require users to deviate from their regular routes, our method ensures task completion while minimizing disruption to users. Trace-based simulation results validate that the proposed algorithm attains a Nash equilibrium and offers a total user profit performance closely aligned with that of the optimal solution.
{"title":"Distributed Task Selection for Crowdsensing: A Game-Theoretical Approach","authors":"En Wang;Dongming Luan;Yuanbo Xu;Yongjian Yang;Jie Wu","doi":"10.1109/TMC.2024.3449039","DOIUrl":"10.1109/TMC.2024.3449039","url":null,"abstract":"Mobile CrowdSensing (MCS) is a promising sensing paradigm that leverages users’ mobile devices to collect and share data for various applications. A key challenge in MCS is task allocation, which aims to assign sensing tasks to suitable users efficiently and effectively. Existing task allocation approaches are mostly centralized, requiring users to disclose their private information and facing high computational complexity. Moreover, centralized approaches may not satisfy users’ preferences or incentives. To address these issues, we propose a novel distributed task allocation scheme based on route navigation systems. We consider two scenarios: time-tolerant tasks and time-sensitive tasks, and formulate them as potential games. We design distributed algorithms to achieve Nash equilibria while considering users’ individual preferences and the platform’s task allocation objectives. We also analyze the convergence and performance of our algorithm theoretically. In the time-sensitive task scenario, the problem becomes even more intricate due to temporal conflicts among tasks. We prove the task selection problem is NP-hard and propose a distributed task selection algorithm. In contrast to existing distributed approaches that require users to deviate from their regular routes, our method ensures task completion while minimizing disruption to users. Trace-based simulation results validate that the proposed algorithm attains a Nash equilibrium and offers a total user profit performance closely aligned with that of the optimal solution.","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":null,"pages":null},"PeriodicalIF":7.7,"publicationDate":"2024-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142180569","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}
In the Industrial Internet of Things (IIoT), Multi-access Edge Computing (MEC) emerges as a transformative paradigm for managing computation-intensive tasks, where task offloading plays an important role. However, due to the complex environment of IIoT, existing deep reinforcement learning-based schemes suffer from significant shortcomings in accuracy and convergence speed during model training when addressing the issue of task offloading. In this paper, to solve this problem, we propose an online task offloading scheme based on reinforcement learning, leveraging the double deep Q network (DQN) and dueling DQN with a prioritized experience replay mechanism, called the P rioritized experience-based D ouble D ueling DQN task offloading scheme (P-D3QN). P-D3QN enhances action selection accuracy using double DQN and mitigates Q-value overestimation by decomposing state and advantage using dueling DQN. Additionally, we adopt the prioritized experience replay mechanism to enhance the convergence speed of model training by selecting transitions that induce a higher training error between the evaluation network and the target network. Experimental results demonstrate that P-D3QN outperforms several state-of-the-art schemes, achieving a reduction of 21.0% in the average cost of the task and improving the completion rate of the task by 19.5%.
{"title":"Task Offloading via Prioritized Experience-Based Double Dueling DQN in Edge-Assisted IIoT","authors":"Jiancheng Chi;Xiaobo Zhou;Fu Xiao;Yuto Lim;Tie Qiu","doi":"10.1109/TMC.2024.3452502","DOIUrl":"10.1109/TMC.2024.3452502","url":null,"abstract":"In the Industrial Internet of Things (IIoT), Multi-access Edge Computing (MEC) emerges as a transformative paradigm for managing computation-intensive tasks, where task offloading plays an important role. However, due to the complex environment of IIoT, existing deep reinforcement learning-based schemes suffer from significant shortcomings in accuracy and convergence speed during model training when addressing the issue of task offloading. In this paper, to solve this problem, we propose an online task offloading scheme based on reinforcement learning, leveraging the double deep Q network (DQN) and dueling DQN with a prioritized experience replay mechanism, called the \u0000<bold>P</b>\u0000rioritized experience-based \u0000<bold>D</b>\u0000ouble \u0000<bold>D</b>\u0000ueling \u0000<bold>DQN</b>\u0000 task offloading scheme (P-D3QN). P-D3QN enhances action selection accuracy using double DQN and mitigates Q-value overestimation by decomposing state and advantage using dueling DQN. Additionally, we adopt the prioritized experience replay mechanism to enhance the convergence speed of model training by selecting transitions that induce a higher training error between the evaluation network and the target network. Experimental results demonstrate that P-D3QN outperforms several state-of-the-art schemes, achieving a reduction of 21.0% in the average cost of the task and improving the completion rate of the task by 19.5%.","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":null,"pages":null},"PeriodicalIF":7.7,"publicationDate":"2024-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142180566","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 : 2024-08-30DOI: 10.1109/TMC.2024.3452510
Yili Jin;Wenyi Zhang;Zihan Xu;Fangxin Wang;Xue Liu
Immersive videos, also known as 360 $^{circ }$ videos, have gained significant attention in recent years due to their ability to provide an interactive and engaging experience. However, the development of immersive video streaming faces several challenges, including privacy concerns, the need for accurate viewport prediction, and efficient bandwidth allocation. In this paper, we propose a comprehensive system that integrates three specialized modules: the Privacy Protection module, the Viewport Prediction module, and the Bitrate Allocation module. The Privacy Protection module introduces a novel approach to differential privacy tailored for immersive video environments, considering the spatial and temporal correlations in viewport and gaze motion data. The Viewport Prediction module leverages a crossmodal attention mechanism based on the transformer to predict user viewport movements by analyzing the complex interactions between historical data, video content, and gaze patterns. The Bitrate Allocation module employs an adaptive tile-based bitrate allocation strategy using an exponential decay function to optimize video quality and maximize user quality of experience. Experimental results demonstrate that our proposed framework outperforms three state-of-the-art integrated frameworks, achieving an average QoE improvement of 21.61%. This paper offers substantial novelty in addressing privacy concerns, leveraging gaze information for viewport prediction, and utilizing underlying correlations between different features.
{"title":"Privacy-Preserving Gaze-Assisted Immersive Video Streaming","authors":"Yili Jin;Wenyi Zhang;Zihan Xu;Fangxin Wang;Xue Liu","doi":"10.1109/TMC.2024.3452510","DOIUrl":"10.1109/TMC.2024.3452510","url":null,"abstract":"Immersive videos, also known as 360\u0000<inline-formula><tex-math>$^{circ }$</tex-math></inline-formula>\u0000 videos, have gained significant attention in recent years due to their ability to provide an interactive and engaging experience. However, the development of immersive video streaming faces several challenges, including privacy concerns, the need for accurate viewport prediction, and efficient bandwidth allocation. In this paper, we propose a comprehensive system that integrates three specialized modules: the Privacy Protection module, the Viewport Prediction module, and the Bitrate Allocation module. The Privacy Protection module introduces a novel approach to differential privacy tailored for immersive video environments, considering the spatial and temporal correlations in viewport and gaze motion data. The Viewport Prediction module leverages a crossmodal attention mechanism based on the transformer to predict user viewport movements by analyzing the complex interactions between historical data, video content, and gaze patterns. The Bitrate Allocation module employs an adaptive tile-based bitrate allocation strategy using an exponential decay function to optimize video quality and maximize user quality of experience. Experimental results demonstrate that our proposed framework outperforms three state-of-the-art integrated frameworks, achieving an average QoE improvement of 21.61%. This paper offers substantial novelty in addressing privacy concerns, leveraging gaze information for viewport prediction, and utilizing underlying correlations between different features.","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":null,"pages":null},"PeriodicalIF":7.7,"publicationDate":"2024-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142180623","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 : 2024-08-30DOI: 10.1109/TMC.2024.3452101
Rong Cong;Zhiwei Zhao;Linyuanqi Zhang;Geyong Min
Vision-based real-time object detection has become a key fundamental service for smart-city applications such as auto-drive and digital twins. Due to the limited resource available at camera devices, edge-assisted object detection has attracted increasing research attention. The existing edge-assisted schemes often assume stable or averaged wireless links during the frame offloading process. However, the assumption does not hold in real-world dynamic edge networks and will lead to significant performance degradation in terms of both detection latency and accuracy. In this paper, we propose $Kite$ , a link-adaptive scheme for real-time object detection. Based on measurement studies and systematic analysis, we devise a lightweight yet representative performance indicator – “frame-anchor” distance, to incorporate the immeasurable impact of wireless dynamics into a measurable metric. Based on this performance indicator, we model the offloading process as an integer nonlinear programming problem, and propose an online link-adaptive algorithm for frame offloading decisions. We implement $Kite$ in a neuro-enhanced live streaming application and conduct comparative experiments with four different datasets in WiFi/LTE based edge networks. The results show that Kite can improve the detection accuracy by 40.53% in highly dynamic networks, compared to the state-of-the-art works.
{"title":"Kite: Link-Adaptive and Real-Time Object Detection in Dynamic Edge Networks","authors":"Rong Cong;Zhiwei Zhao;Linyuanqi Zhang;Geyong Min","doi":"10.1109/TMC.2024.3452101","DOIUrl":"10.1109/TMC.2024.3452101","url":null,"abstract":"Vision-based real-time object detection has become a key fundamental service for smart-city applications such as auto-drive and digital twins. Due to the limited resource available at camera devices, edge-assisted object detection has attracted increasing research attention. The existing edge-assisted schemes often assume stable or averaged wireless links during the frame offloading process. However, the assumption does not hold in real-world dynamic edge networks and will lead to significant performance degradation in terms of both detection latency and accuracy. In this paper, we propose \u0000<inline-formula><tex-math>$Kite$</tex-math></inline-formula>\u0000, a link-adaptive scheme for real-time object detection. Based on measurement studies and systematic analysis, we devise a lightweight yet representative performance indicator – “frame-anchor” distance, to incorporate the immeasurable impact of wireless dynamics into a measurable metric. Based on this performance indicator, we model the offloading process as an integer nonlinear programming problem, and propose an online link-adaptive algorithm for frame offloading decisions. We implement \u0000<inline-formula><tex-math>$Kite$</tex-math></inline-formula>\u0000 in a neuro-enhanced live streaming application and conduct comparative experiments with four different datasets in WiFi/LTE based edge networks. The results show that \u0000<i>Kite</i>\u0000 can improve the detection accuracy by 40.53% in highly dynamic networks, compared to the state-of-the-art works.","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":null,"pages":null},"PeriodicalIF":7.7,"publicationDate":"2024-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142180567","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}
This two-part paper focuses on the system design and performance analysis for a point-to-point resonant beam communication (RBCom) system under both the quasi-static and mobile scenarios. Part I of this paper proposes a synchronization-based information transmission scheme and derives the capacity upper and lower bounds for the quasi-static channel case. In Part II, we address the mobile scenario, where the receiver is in relative motion to the transmitter, and derive a mobile RBCom channel model that jointly considers the Doppler effect, channel variation, and echo interference. With the obtained channel model, we prove that the channel gain of the mobile RBCom decreases as the number of transmitted frames increases, and thus show that the considered mobile RBCom terminates after the transmitter sends a certain number of frames without frequency compensation. By deriving an upper bound on the number of successfully transmitted frames, we formulate the throughput maximization problem for the considered mobile RBCom system, and solve it via a sequential parametric convex approximation (SPCA) method. Finally, simulation results validate the analysis of our proposed method in some typical scenarios.
{"title":"Design and Performance of Resonant Beam Communications—Part II: Mobile Scenario","authors":"Dongxu Li;Yuanming Tian;Chuan Huang;Qingwen Liu;Shengli Zhou","doi":"10.1109/TMC.2024.3451657","DOIUrl":"10.1109/TMC.2024.3451657","url":null,"abstract":"This two-part paper focuses on the system design and performance analysis for a point-to-point resonant beam communication (RBCom) system under both the quasi-static and mobile scenarios. Part I of this paper proposes a synchronization-based information transmission scheme and derives the capacity upper and lower bounds for the quasi-static channel case. In Part II, we address the mobile scenario, where the receiver is in relative motion to the transmitter, and derive a mobile RBCom channel model that jointly considers the Doppler effect, channel variation, and echo interference. With the obtained channel model, we prove that the channel gain of the mobile RBCom decreases as the number of transmitted frames increases, and thus show that the considered mobile RBCom terminates after the transmitter sends a certain number of frames without frequency compensation. By deriving an upper bound on the number of successfully transmitted frames, we formulate the throughput maximization problem for the considered mobile RBCom system, and solve it via a sequential parametric convex approximation (SPCA) method. Finally, simulation results validate the analysis of our proposed method in some typical scenarios.","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":null,"pages":null},"PeriodicalIF":7.7,"publicationDate":"2024-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142180624","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：