Pub Date : 2024-10-18DOI: 10.1109/TMC.2024.3476340
Jialiang Zhu;Hao Zheng;Wenchao Xu;Haozhao Wang;Zhiming He;Yuxuan Liu;Shuang Wang;Qi Sun
Federated Learning (FL) is to collaboratively train a global model among distributed clients by iteratively aggregating their local updates without sharing their raw data, whereby the global modal can approximately converge to the centralized training way over a global dataset that composed of all local datasets (i.e., union of all users’ local data). However, in real-world scenarios, the distributions of the data classes are often imbalanced not only locally, but also in the global dataset, which severely deteriorate the FL performance due to the conflicting knowledge aggregation. Existing solutions for FL class imbalance either focus on the local data to regulate the training process or purely aim at the global datasets, which often fail to alleviate the class imbalance problem if there is mismatch between the local and global imbalance. Considering these limitations, this paper proposes a Global-Local Joint Learning method, namely GLJL, which simultaneously harmonizes the global and local class imbalance issue by jointly embedding the local and the global factors into each client’s loss function. Through extensive experiments over popular datasets with various class imbalance settings, we show that the proposed method can significantly improve the model accuracy over minority classes without sacrificing the accuracy of other classes.
{"title":"Harmonizing Global and Local Class Imbalance for Federated Learning","authors":"Jialiang Zhu;Hao Zheng;Wenchao Xu;Haozhao Wang;Zhiming He;Yuxuan Liu;Shuang Wang;Qi Sun","doi":"10.1109/TMC.2024.3476340","DOIUrl":"https://doi.org/10.1109/TMC.2024.3476340","url":null,"abstract":"Federated Learning (FL) is to collaboratively train a global model among distributed clients by iteratively aggregating their local updates without sharing their raw data, whereby the global modal can approximately converge to the centralized training way over a global dataset that composed of all local datasets (i.e., union of all users’ local data). However, in real-world scenarios, the distributions of the data classes are often imbalanced not only locally, but also in the global dataset, which severely deteriorate the FL performance due to the conflicting knowledge aggregation. Existing solutions for FL class imbalance either focus on the local data to regulate the training process or purely aim at the global datasets, which often fail to alleviate the class imbalance problem if there is mismatch between the local and global imbalance. Considering these limitations, this paper proposes a Global-Local Joint Learning method, namely GLJL, which simultaneously harmonizes the global and local class imbalance issue by jointly embedding the local and the global factors into each client’s loss function. Through extensive experiments over popular datasets with various class imbalance settings, we show that the proposed method can significantly improve the model accuracy over minority classes without sacrificing the accuracy of other classes.","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":"24 2","pages":"1120-1131"},"PeriodicalIF":7.7,"publicationDate":"2024-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142938402","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 : 2024-10-17DOI: 10.1109/TMC.2024.3476338
Jiongyu Dai;Lianjun Li;Ramin Safavinejad;Shadab Mahboob;Hao Chen;Vishnu V Ratnam;Haining Wang;Jianzhong Zhang;Lingjia Liu
Network slicing plays a critical role in enabling multiple virtualized and independent network services to be created on top of a common physical network infrastructure. In this paper, we introduce a deep reinforcement learning (DRL)-based radio resource management (RRM) solution for radio access network (RAN) slicing under service-level agreement (SLA) guarantees. The objective of this solution is to minimize the SLA violation. Our method is designed with a two-level scheduling structure that works seamlessly under Open Radio Access Network (O-RAN) architecture. Specifically, at an upper level, a DRL-based inter-slice scheduler is working on a coarse time granularity to allocate resources to network slices. And at a lower level, an existing intra-slice scheduler such as proportional fair (PF) is working on a fine time granularity to allocate slice dedicated resources to slice users. This setting makes our solution O-RAN compliant and ready to be deployed as an ‘xApp’ on the RAN Intelligent Controller (RIC). For performance evaluation and proof of concept purposes, we develop two platforms, one industry-level simulator and one O-RAN compliant testbed; evaluation on both platforms demonstrates our solution’s superior performance over conventional methods.
{"title":"O-RAN-Enabled Intelligent Network Slicing to Meet Service-Level Agreement (SLA)","authors":"Jiongyu Dai;Lianjun Li;Ramin Safavinejad;Shadab Mahboob;Hao Chen;Vishnu V Ratnam;Haining Wang;Jianzhong Zhang;Lingjia Liu","doi":"10.1109/TMC.2024.3476338","DOIUrl":"https://doi.org/10.1109/TMC.2024.3476338","url":null,"abstract":"Network slicing plays a critical role in enabling multiple virtualized and independent network services to be created on top of a common physical network infrastructure. In this paper, we introduce a deep reinforcement learning (DRL)-based radio resource management (RRM) solution for radio access network (RAN) slicing under service-level agreement (SLA) guarantees. The objective of this solution is to minimize the SLA violation. Our method is designed with a two-level scheduling structure that works seamlessly under Open Radio Access Network (O-RAN) architecture. Specifically, at an upper level, a DRL-based inter-slice scheduler is working on a coarse time granularity to allocate resources to network slices. And at a lower level, an existing intra-slice scheduler such as proportional fair (PF) is working on a fine time granularity to allocate slice dedicated resources to slice users. This setting makes our solution O-RAN compliant and ready to be deployed as an ‘xApp’ on the RAN Intelligent Controller (RIC). For performance evaluation and proof of concept purposes, we develop two platforms, one industry-level simulator and one O-RAN compliant testbed; evaluation on both platforms demonstrates our solution’s superior performance over conventional methods.","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":"24 2","pages":"890-906"},"PeriodicalIF":7.7,"publicationDate":"2024-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142938371","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 : 2024-10-15DOI: 10.1109/TMC.2024.3478048
Jakub Žádník;Michel Kieffer;Anthony Trioux;Markku Mäkitalo;Pekka Jääskeläinen
Remote inference allows lightweight edge devices, such as autonomous drones, to perform vision tasks exceeding their computational, energy, or processing delay budget. In such applications, reliable transmission of information is challenging due to high variations of channel quality. Traditional approaches involving spatio-temporal transforms, quantization, and entropy coding followed by digital transmission may be affected by a sudden decrease in quality (the digital cliff ) when the channel quality is less than expected during design. This problem can be addressed by using Linear Coding and Transmission (LCT), a joint source and channel coding scheme relying on linear operators only, allowing to achieve reconstructed per-pixel error commensurate with the wireless channel quality. In this paper, we propose CV-Cast: the first LCT scheme optimized for computer vision task accuracy instead of per-pixel distortion. Using this approach, for instance at 10 dB channel signal-to-noise ratio, CV-Cast requires transmitting 28% less symbols than a baseline LCT scheme in semantic segmentation and 15% in object detection tasks. Simulations involving a realistic 5G channel model confirm the smooth decrease in accuracy achieved with CV-Cast, while images encoded by JPEG or learned image coding (LIC) and transmitted using classical schemes at low Eb/N0 are subject to digital cliff.
{"title":"CV-Cast: Computer Vision–Oriented Linear Coding and Transmission","authors":"Jakub Žádník;Michel Kieffer;Anthony Trioux;Markku Mäkitalo;Pekka Jääskeläinen","doi":"10.1109/TMC.2024.3478048","DOIUrl":"https://doi.org/10.1109/TMC.2024.3478048","url":null,"abstract":"Remote inference allows lightweight edge devices, such as autonomous drones, to perform vision tasks exceeding their computational, energy, or processing delay budget. In such applications, reliable transmission of information is challenging due to high variations of channel quality. Traditional approaches involving spatio-temporal transforms, quantization, and entropy coding followed by digital transmission may be affected by a sudden decrease in quality (the \u0000<italic>digital cliff</i>\u0000) when the channel quality is less than expected during design. This problem can be addressed by using Linear Coding and Transmission (LCT), a joint source and channel coding scheme relying on linear operators only, allowing to achieve reconstructed per-pixel error commensurate with the wireless channel quality. In this paper, we propose CV-Cast: the first LCT scheme optimized for computer vision task accuracy instead of per-pixel distortion. Using this approach, for instance at 10 dB channel signal-to-noise ratio, CV-Cast requires transmitting 28% less symbols than a baseline LCT scheme in semantic segmentation and 15% in object detection tasks. Simulations involving a realistic 5G channel model confirm the smooth decrease in accuracy achieved with CV-Cast, while images encoded by JPEG or learned image coding (LIC) and transmitted using classical schemes at low Eb/N0 are subject to digital cliff.","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":"24 2","pages":"1149-1162"},"PeriodicalIF":7.7,"publicationDate":"2024-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10719663","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142938440","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}
Deep learning (DL) based Wi-Fi sensing has witnessed great development in recent years. Although decent results have been achieved in certain scenarios, Wi-Fi based activity recognition is still difficult to deploy in real smart homes due to the limited cross-environment adaptability, i.e. a well-trained Wi-Fi sensing neural network in one environment is hard to adapt to other environments. To address this challenge, we propose AdaWiFi , a DL-based Wi-Fi sensing framework that allows multiple Internet-of-Things (IoT) devices to collaborate and adapt to various environments effectively. The key innovation of AdaWiFi includes a collective sensing model architecture that utilizes complementary information between distinct devices and avoids the biased perception of individual sensors and an accompanying model adaptation technique that can transfer the sensing model to new environments with limited data. We evaluate our system on a public dataset and a custom dataset collected from three complex sensing environments. The results demonstrate that AdaWiFi is able to achieve significantly better sensing adaptation effectiveness (e.g. 30% higher accuracy with one-shot adaptation) as compared with state-of-the-art baselines.
{"title":"AdaWiFi, Collaborative WiFi Sensing for Cross-Environment Adaptation","authors":"Naiyu Zheng;Yuanchun Li;Shiqi Jiang;Yuanzhe Li;Rongchun Yao;Chuchu Dong;Ting Chen;Yubo Yang;Zhimeng Yin;Yunxin Liu","doi":"10.1109/TMC.2024.3474853","DOIUrl":"https://doi.org/10.1109/TMC.2024.3474853","url":null,"abstract":"Deep learning (DL) based Wi-Fi sensing has witnessed great development in recent years. Although decent results have been achieved in certain scenarios, Wi-Fi based activity recognition is still difficult to deploy in real smart homes due to the limited cross-environment adaptability, i.e. a well-trained Wi-Fi sensing neural network in one environment is hard to adapt to other environments. To address this challenge, we propose \u0000<sc>AdaWiFi</small>\u0000, a DL-based Wi-Fi sensing framework that allows multiple Internet-of-Things (IoT) devices to collaborate and adapt to various environments effectively. The key innovation of \u0000<sc>AdaWiFi</small>\u0000 includes a collective sensing model architecture that utilizes complementary information between distinct devices and avoids the biased perception of individual sensors and an accompanying model adaptation technique that can transfer the sensing model to new environments with limited data. We evaluate our system on a public dataset and a custom dataset collected from three complex sensing environments. The results demonstrate that \u0000<sc>AdaWiFi</small>\u0000 is able to achieve significantly better sensing adaptation effectiveness (e.g. 30% higher accuracy with one-shot adaptation) as compared with state-of-the-art baselines.","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":"24 2","pages":"845-858"},"PeriodicalIF":7.7,"publicationDate":"2024-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142938476","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 : 2024-10-10DOI: 10.1109/TMC.2024.3477462
Yanbing Liu;Chunyi Peng
In this work, we conduct a measurement study with three US operators to reveal three types of problematic failure handling on secondary radio access which have not been reported before. Compared to primary radio access failures, secondary radio access failures do not hurt radio access availability but significantly impact data performance, particularly when 5G is used as secondary radio access to boost throughput. Improper failure handling results in significant throughput loss, which is unnecessary in most instances. We then pinpoint the root causes behind these three types of problematic failure handling. When 5G provides higher throughput, failures are more likely to be falsely triggered by a specific event, causing the User Equipment (UE) to unnecessarily lose well-performing 5G connections. Moreover, after failures, the recovery of secondary radio access may fail due to inconsistent parameter settings or be delayed due to missing specific signaling fields. To address these issues, we propose SCGFailure Manager ( SFM ), a solution to optimize the detection and recovery of secondary radio access failures. Our evaluation results demonstrate that SFM can effectively avoid 60%-80% of problematic failure handling and double throughput in more than half of failure instances.
{"title":"Handling Failures in Secondary Radio Access Failure Handling in Operational 5G Networks","authors":"Yanbing Liu;Chunyi Peng","doi":"10.1109/TMC.2024.3477462","DOIUrl":"https://doi.org/10.1109/TMC.2024.3477462","url":null,"abstract":"In this work, we conduct a measurement study with three US operators to reveal three types of problematic failure handling on secondary radio access which have not been reported before. Compared to primary radio access failures, secondary radio access failures do not hurt radio access availability but significantly impact data performance, particularly when 5G is used as secondary radio access to boost throughput. Improper failure handling results in significant throughput loss, which is unnecessary in most instances. We then pinpoint the root causes behind these three types of problematic failure handling. When 5G provides higher throughput, failures are more likely to be falsely triggered by a specific event, causing the User Equipment (UE) to unnecessarily lose well-performing 5G connections. Moreover, after failures, the recovery of secondary radio access may fail due to inconsistent parameter settings or be delayed due to missing specific signaling fields. To address these issues, we propose SCGFailure Manager (\u0000<sc>SFM</small>\u0000), a solution to optimize the detection and recovery of secondary radio access failures. Our evaluation results demonstrate that \u0000<sc>SFM</small>\u0000 can effectively avoid 60%-80% of problematic failure handling and double throughput in more than half of failure instances.","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":"24 2","pages":"956-969"},"PeriodicalIF":7.7,"publicationDate":"2024-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142938589","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 : 2024-10-10DOI: 10.1109/TMC.2024.3477616
Chenhao Ying;Fuyuan Xia;David S. L. Wei;Xinchun Yu;Yibin Xu;Weiting Zhang;Xikun Jiang;Haiming Jin;Yuan Luo;Tao Zhang;Dacheng Tao
Harnessing the benefits of blockchain, such as decentralization, immutability, and transparency, to bolster the credibility and security attributes of federated learning (FL) has garnered increasing attention. However, blockchain-enabled FL (BFL) still faces several challenges. The primary and most significant issue arises from its essential but slow validation procedure, which selects high-quality local models by recruiting distributed validators. The second issue stems from its incentive mechanism under the transparent nature of blockchain, increasing the risk of privacy breaches regarding workers’ cost information. The final challenge involves data eavesdropping from shared local models. To address these significant obstacles, this paper proposes a Blockchain-enabled Incentivized and Secure Federated Learning (BIT-FL) framework. BIT-FL leverages a novel loop-based sharded consensus algorithm to accelerate the validation procedure, ensuring the same security as non-sharded consensus protocols. It consistently outputs the correct local model selection when the fraction of adversaries among validators is less than $1/2$ with synchronous communication. Furthermore, BIT-FL integrates a randomized incentive procedure, attracting more participants while guaranteeing the privacy of their cost information through meticulous worker selection probability design. Finally, by adding artificial Gaussian noise to local models, it ensures the privacy of trainers’ local models. With the careful design of Gaussian noise, the excess empirical risk of BIT-FL is upper-bounded by $mathcal {O}(frac{ln n_{min}}{ n_{min}^{3/2}}+frac{ln n}{n})$ , where $n$ represents the size of the union dataset, and $n_{{min}}$ represents the size of the smallest dataset. Our extensive experiments demonstrate that BIT-FL exhibits efficiency, robustness, and high accuracy for both classification and regression tasks.
{"title":"BIT-FL: Blockchain-Enabled Incentivized and Secure Federated Learning Framework","authors":"Chenhao Ying;Fuyuan Xia;David S. L. Wei;Xinchun Yu;Yibin Xu;Weiting Zhang;Xikun Jiang;Haiming Jin;Yuan Luo;Tao Zhang;Dacheng Tao","doi":"10.1109/TMC.2024.3477616","DOIUrl":"https://doi.org/10.1109/TMC.2024.3477616","url":null,"abstract":"Harnessing the benefits of blockchain, such as decentralization, immutability, and transparency, to bolster the credibility and security attributes of federated learning (FL) has garnered increasing attention. However, blockchain-enabled FL (BFL) still faces several challenges. The primary and most significant issue arises from its essential but slow validation procedure, which selects high-quality local models by recruiting distributed validators. The second issue stems from its incentive mechanism under the transparent nature of blockchain, increasing the risk of privacy breaches regarding workers’ cost information. The final challenge involves data eavesdropping from shared local models. To address these significant obstacles, this paper proposes a Blockchain-enabled Incentivized and Secure Federated Learning (BIT-FL) framework. BIT-FL leverages a novel loop-based sharded consensus algorithm to accelerate the validation procedure, ensuring the same security as non-sharded consensus protocols. It consistently outputs the correct local model selection when the fraction of adversaries among validators is less than \u0000<inline-formula><tex-math>$1/2$</tex-math></inline-formula>\u0000 with synchronous communication. Furthermore, BIT-FL integrates a randomized incentive procedure, attracting more participants while guaranteeing the privacy of their cost information through meticulous worker selection probability design. Finally, by adding artificial Gaussian noise to local models, it ensures the privacy of trainers’ local models. With the careful design of Gaussian noise, the excess empirical risk of BIT-FL is upper-bounded by \u0000<inline-formula><tex-math>$mathcal {O}(frac{ln n_{min}}{ n_{min}^{3/2}}+frac{ln n}{n})$</tex-math></inline-formula>\u0000, where \u0000<inline-formula><tex-math>$n$</tex-math></inline-formula>\u0000 represents the size of the union dataset, and \u0000<inline-formula><tex-math>$n_{{min}}$</tex-math></inline-formula>\u0000 represents the size of the smallest dataset. Our extensive experiments demonstrate that BIT-FL exhibits efficiency, robustness, and high accuracy for both classification and regression tasks.","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":"24 2","pages":"1212-1229"},"PeriodicalIF":7.7,"publicationDate":"2024-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142938417","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 : 2024-10-09DOI: 10.1109/TMC.2024.3472081
Zhen Li;Chunxiao Jiang;Jiachen Sun;Jianhua Lu
The integrated satellite-terrestrial network with cascaded downlinks from satellites to wide-area mobile base stations and subsequently to terrestrial users enables global communication for terrestrial 4G/5G cellular users and is widely used in emergency rescue scenarios. However, in this network, satellites and wide-area mobile base stations are controlled by distinct resource scheduling systems with disparate packet queues, which means resources allocated by the satellite to the wide-area mobile base stations may not match the resources allocated by the wide-area mobile base stations to the terrestrial users, leading to coordination inefficiencies and resource wastage. To tackle this challenge, a resource collaborative scheduling mechanism based on cooperative game theory for cascaded downlinks is established, which effectively adapts to distinct resource scheduling systems with various QoS constraints. Then, the utility function of the Nash product is converted into a max-min problem, and a convex transformation method is proposed for the non-convex optimization problem. Simulation results demonstrate that the proposed collaborative scheduling mechanism effectively improves resource utilization and the transmission rate of cascaded downlinks.
{"title":"Resource Collaboration Between Satellite and Wide-Area Mobile Base Stations in Integrated Satellite-Terrestrial Network","authors":"Zhen Li;Chunxiao Jiang;Jiachen Sun;Jianhua Lu","doi":"10.1109/TMC.2024.3472081","DOIUrl":"https://doi.org/10.1109/TMC.2024.3472081","url":null,"abstract":"The integrated satellite-terrestrial network with cascaded downlinks from satellites to wide-area mobile base stations and subsequently to terrestrial users enables global communication for terrestrial 4G/5G cellular users and is widely used in emergency rescue scenarios. However, in this network, satellites and wide-area mobile base stations are controlled by distinct resource scheduling systems with disparate packet queues, which means resources allocated by the satellite to the wide-area mobile base stations may not match the resources allocated by the wide-area mobile base stations to the terrestrial users, leading to coordination inefficiencies and resource wastage. To tackle this challenge, a resource collaborative scheduling mechanism based on cooperative game theory for cascaded downlinks is established, which effectively adapts to distinct resource scheduling systems with various QoS constraints. Then, the utility function of the Nash product is converted into a max-min problem, and a convex transformation method is proposed for the non-convex optimization problem. Simulation results demonstrate that the proposed collaborative scheduling mechanism effectively improves resource utilization and the transmission rate of cascaded downlinks.","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":"24 2","pages":"875-889"},"PeriodicalIF":7.7,"publicationDate":"2024-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142938372","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 : 2024-10-07DOI: 10.1109/TMC.2024.3475428
Jiani Guo;Shanshan Song;Jun Liu;Miao Pan;Jun-Hong Cui;GuangJie Han
Autonomous Underwater Vehicle (AUV)-assisted Underwater Acoustic Networks (UANs) are promising for complex ocean applications. In essence, an AUV-assisted UAN is still dominated by fixed nodes, and Time Division Multiple Access (TDMA)-based Medium Access Control (MAC) protocols have undisputed practicability in such fixed nodes-dominated UANs since they are simple and easy to deploy. However, AUV-assisted UANs may exist dynamic bidirectional data streams, while most existing protocols assume UANs have a unidirectional data stream, and their fixed scheduling sequence results in the long end-to-end delay in AUV-assisted UANs. In this paper, we first reveal a phenomenon between the data stream and the scheduling sequence, derived from real-world experiments: their consistent direction decreases the packet waiting delay but increases the slot length, and vice versa. To optimize the end-to-end delay, UANs with dynamic bidirectional data streams expect the MAC protocol to provide a flexible scheduling sequence. To this end, we propose a low-delay Adaptive Scheduling MAC protocol (AS-MAC) based on TDMA for AUV-assisted UANs. In AS-MAC, we analyze the relationship between scheduling sequence and data stream, extracting two significant factors: slot length and packet delay. Afterwards, we design Slot Length Model (SLM) and Packet Delay Model (PDM) to analyze the end-to-end delay of different data streams. Based on these two models, we present a Scheduling Sequence and Slot Length allocation Algorithm (SSSLA) to adaptively provide the minimum end-to-end delay for current bidirectional data streams. Extensive simulation results show that AS-MAC efficiently addresses severe queue congestion of the state-of-the-art protocols and reduces the end-to-end delay of different dynamic streams in various scenarios.
{"title":"AS-MAC: An Adaptive Scheduling MAC Protocol for Reducing the End-to-End Delay in AUV-Assisted Underwater Acoustic Networks","authors":"Jiani Guo;Shanshan Song;Jun Liu;Miao Pan;Jun-Hong Cui;GuangJie Han","doi":"10.1109/TMC.2024.3475428","DOIUrl":"https://doi.org/10.1109/TMC.2024.3475428","url":null,"abstract":"Autonomous Underwater Vehicle (AUV)-assisted Underwater Acoustic Networks (UANs) are promising for complex ocean applications. In essence, an AUV-assisted UAN is still dominated by fixed nodes, and Time Division Multiple Access (TDMA)-based Medium Access Control (MAC) protocols have undisputed practicability in such fixed nodes-dominated UANs since they are simple and easy to deploy. However, AUV-assisted UANs may exist dynamic bidirectional data streams, while most existing protocols assume UANs have a unidirectional data stream, and their fixed scheduling sequence results in the long end-to-end delay in AUV-assisted UANs. In this paper, we first reveal a phenomenon between the data stream and the scheduling sequence, derived from real-world experiments: their consistent direction decreases the packet waiting delay but increases the slot length, and vice versa. To optimize the end-to-end delay, UANs with dynamic bidirectional data streams expect the MAC protocol to provide a flexible scheduling sequence. To this end, we propose a low-delay Adaptive Scheduling MAC protocol (AS-MAC) based on TDMA for AUV-assisted UANs. In AS-MAC, we analyze the relationship between scheduling sequence and data stream, extracting two significant factors: slot length and packet delay. Afterwards, we design Slot Length Model (SLM) and Packet Delay Model (PDM) to analyze the end-to-end delay of different data streams. Based on these two models, we present a Scheduling Sequence and Slot Length allocation Algorithm (SSSLA) to adaptively provide the minimum end-to-end delay for current bidirectional data streams. Extensive simulation results show that AS-MAC efficiently addresses severe queue congestion of the state-of-the-art protocols and reduces the end-to-end delay of different dynamic streams in various scenarios.","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":"24 2","pages":"1197-1211"},"PeriodicalIF":7.7,"publicationDate":"2024-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142938413","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 dairy industry is experiencing a surge in data from Edge devices, using spectroscopic techniques for milk quality assessment. Milk spectral data can help understand the species of milk producer and detect inter-species adulteration. Transmitting raw milk spectral data to the cloud for processing faces challenges due to limited network resources such as bandwidth, computational memory, and energy availability. Edge processing offers a solution by training data closer to the source, enhancing efficiency and real-time analysis by providing reduced latency, improved accuracy, resource-aware computation, and real-time customization. However, traditional Deep Learning (DL) methods such as Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) struggle on resource-constrained Edge devices due to complexity. To address this, we propose an Edge-Centric Application-Adaptive Light-Weight DL approach (AppAdapt-LWDL) for milk species identification and adulteration detection. Our method optimizes DL models via double model optimization, involving low-magnitude pruning and post-training quantization. Our novel application-adaptive algorithm balances speed and accuracy by determining the pruning ratio automatically for the specific application. The chosen model is then quantized for smaller databases, ideal for embedded devices. The AppAdapt-LWDL framework significantly accelerates training, speeds up inferencing, enhances energy efficiency, and maintains accuracy based on application needs.
{"title":"Application Adaptive Light-Weight Deep Learning (AppAdapt-LWDL) Framework for Enabling Edge Intelligence in Dairy Processing","authors":"Rahul Umesh Mhapsekar;Lizy Abraham;Steven Davy;Indrakshi Dey","doi":"10.1109/TMC.2024.3475634","DOIUrl":"https://doi.org/10.1109/TMC.2024.3475634","url":null,"abstract":"The dairy industry is experiencing a surge in data from Edge devices, using spectroscopic techniques for milk quality assessment. Milk spectral data can help understand the species of milk producer and detect inter-species adulteration. Transmitting raw milk spectral data to the cloud for processing faces challenges due to limited network resources such as bandwidth, computational memory, and energy availability. Edge processing offers a solution by training data closer to the source, enhancing efficiency and real-time analysis by providing reduced latency, improved accuracy, resource-aware computation, and real-time customization. However, traditional Deep Learning (DL) methods such as Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) struggle on resource-constrained Edge devices due to complexity. To address this, we propose an Edge-Centric Application-Adaptive Light-Weight DL approach (AppAdapt-LWDL) for milk species identification and adulteration detection. Our method optimizes DL models via double model optimization, involving low-magnitude pruning and post-training quantization. Our novel application-adaptive algorithm balances speed and accuracy by determining the pruning ratio automatically for the specific application. The chosen model is then quantized for smaller databases, ideal for embedded devices. The AppAdapt-LWDL framework significantly accelerates training, speeds up inferencing, enhances energy efficiency, and maintains accuracy based on application needs.","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":"24 2","pages":"1105-1119"},"PeriodicalIF":7.7,"publicationDate":"2024-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142938401","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 : 2024-10-07DOI: 10.1109/TMC.2024.3475481
Yang Xu;Shanshan Zhang;Chen Lyu;Jia Liu;Tarik Taleb;Shiratori Norio
Distributed Vehicle Sharing System (DVSS) leverages emerging technologies such as blockchain to create a secure, transparent, and efficient platform for sharing vehicles. In such a system, both efficient matching of users with available vehicles and optimal pricing mechanisms play crucial roles in maximizing system revenue. However, most existing schemes utilize user-to-vehicle (two-sided) matching and pricing, which are unrealistic for DVSS due to the lack of participation of service providers. To address this issue, we propose in this paper a novel Three-sided stable Matching with an optimal Pricing (TRIMP) scheme. First, to achieve maximum utilities for all three parties simultaneously, we formulate the optimal policy and pricing problem as a three-stage Stackelberg game and derive its equilibrium points accordingly. Second, relying on these solutions from the Stackelberg game, we construct a three-sided cyclic matching for DVSS. Third, as the existence of such a matching is NP-complete, we design a specific vehicle sharing algorithm to realize stable matching. Extensive experiments demonstrate the effectiveness of our TRIMP scheme, which optimizes the matching process and ensures efficient resource allocation, leading to a more stable and well-functioning decentralized vehicle sharing ecosystem.
{"title":"TRIMP: Three-Sided Stable Matching for Distributed Vehicle Sharing System Using Stackelberg Game","authors":"Yang Xu;Shanshan Zhang;Chen Lyu;Jia Liu;Tarik Taleb;Shiratori Norio","doi":"10.1109/TMC.2024.3475481","DOIUrl":"https://doi.org/10.1109/TMC.2024.3475481","url":null,"abstract":"Distributed Vehicle Sharing System (DVSS) leverages emerging technologies such as blockchain to create a secure, transparent, and efficient platform for sharing vehicles. In such a system, both efficient matching of users with available vehicles and optimal pricing mechanisms play crucial roles in maximizing system revenue. However, most existing schemes utilize user-to-vehicle (two-sided) matching and pricing, which are unrealistic for DVSS due to the lack of participation of service providers. To address this issue, we propose in this paper a novel Three-sided stable Matching with an optimal Pricing (TRIMP) scheme. First, to achieve maximum utilities for all three parties simultaneously, we formulate the optimal policy and pricing problem as a three-stage Stackelberg game and derive its equilibrium points accordingly. Second, relying on these solutions from the Stackelberg game, we construct a three-sided cyclic matching for DVSS. Third, as the existence of such a matching is NP-complete, we design a specific vehicle sharing algorithm to realize stable matching. Extensive experiments demonstrate the effectiveness of our TRIMP scheme, which optimizes the matching process and ensures efficient resource allocation, leading to a more stable and well-functioning decentralized vehicle sharing ecosystem.","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":"24 2","pages":"1132-1148"},"PeriodicalIF":7.7,"publicationDate":"2024-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142938439","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：