IEEE Transactions on Machine Learning in Communications and Networking最新文献_第5页

Objective-Driven Differentiable Optimization of Traffic Prediction and Resource Allocation for Split AI Inference Edge Networks 目标驱动的分体式人工智能推理边缘网络流量预测和资源分配差异化优化

IEEE Transactions on Machine Learning in Communications and Networking Pub Date : 2024-08-26 DOI: 10.1109/TMLCN.2024.3449831

Xinchen Lyu;Yuewei Li;Ying He;Chenshan Ren;Wei Ni;Ren Ping Liu;Pengcheng Zhu;Qimei Cui

{"title":"Objective-Driven Differentiable Optimization of Traffic Prediction and Resource Allocation for Split AI Inference Edge Networks","authors":"Xinchen Lyu;Yuewei Li;Ying He;Chenshan Ren;Wei Ni;Ren Ping Liu;Pengcheng Zhu;Qimei Cui","doi":"10.1109/TMLCN.2024.3449831","DOIUrl":"https://doi.org/10.1109/TMLCN.2024.3449831","url":null,"abstract":"Split AI inference partitions an artificial intelligence (AI) model into multiple parts, enabling the offloading of computation-intensive AI services. Resource allocation is critical for the performance of split AI inference. The challenge arises from the time-sensitivity of many services versus time-varying traffic arrivals and network conditions. The conventional prediction-based resource allocation frameworks have adopted separate traffic prediction and resource optimization modules, which may be inefficient due to discrepancies between the traffic prediction accuracy and resource optimization objective. This paper proposes a new, objective-driven, differentiable optimization framework that integrates traffic prediction and resource allocation for split AI inference. The resource optimization problem (aimed to maximize network revenue while adhering to service and network constraints) is designed to be embedded as the output layer following the traffic prediction module. As such, the traffic prediction module can be trained directly based on the network revenue instead of the prediction accuracy, significantly outperforming the conventional prediction-based separate design. Employing the Lagrange duality and Karush-Kuhn-Tucker (KKT) conditions, we achieve efficient forward pass (obtaining resource allocation decisions) and backpropagation (deriving the objective-driven gradients for joint model training) of the output layer. Extensive experiments on different traffic datasets validate the superiority of the proposed approach, achieving up to 38.85% higher network revenue than the conventional predictive baselines.","PeriodicalId":100641,"journal":{"name":"IEEE Transactions on Machine Learning in Communications and Networking","volume":"2 ","pages":"1178-1192"},"PeriodicalIF":0.0,"publicationDate":"2024-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10646623","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142123023","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Deep Reinforcement Learning-Based mmWave Beam Alignment for V2I Communications 基于深度强化学习的毫米波波束对准，实现 V2I 通信

IEEE Transactions on Machine Learning in Communications and Networking Pub Date : 2024-08-22 DOI: 10.1109/TMLCN.2024.3447634

Yuanyuan Qiao;Yong Niu;Lan Su;Shiwen Mao;Ning Wang;Zhangdui Zhong;BO Ai

{"title":"Deep Reinforcement Learning-Based mmWave Beam Alignment for V2I Communications","authors":"Yuanyuan Qiao;Yong Niu;Lan Su;Shiwen Mao;Ning Wang;Zhangdui Zhong;BO Ai","doi":"10.1109/TMLCN.2024.3447634","DOIUrl":"https://doi.org/10.1109/TMLCN.2024.3447634","url":null,"abstract":"Millimeter wave (mmWave) communication can meet the requirements of vehicle-to-infrastructure (V2I) systems, for high throughput and ultra-low latency. However, searching for the optimal beamforming vectors in highly dynamic environments, incurs considerable training overhead. And it is a huge challenge to achieve beam alignment between receivers and transmitters. This paper proposes a beam alignment algorithm based on vehicle position information, to achieve fast beam alignment in the V2I network. In the proposed algorithm, a roadside unit (RSU) obtains a set of candidate beams by the vehicle position information and the double deep Q network (DDQN) algorithm. Then, according to the criterion of maximizing the system spectral efficiency, the optimal beam of the candidate beam set is obtained by the exhaustive search, to achieve fast beam alignment. In this paper, the DeepMIMO dataset is utilized to fully consider the actual scene of V2I, and the effect of Doppler expansion is taken into account in the mathematical model. The simulation results show that the received signal-noise ratio (SNR) of vehicle at different positions is greater than the SNR threshold, which avoids communication interruption and improves the reliability of V2I communications. Meanwhile, we also evaluates the effect of vehicle speed. Compared with other search schemes, the proposed scheme attains higher transmission rates, effectively balances the training overhead and achievable rate, and is suitable for mmWave V2I networks.","PeriodicalId":100641,"journal":{"name":"IEEE Transactions on Machine Learning in Communications and Networking","volume":"2 ","pages":"1216-1228"},"PeriodicalIF":0.0,"publicationDate":"2024-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10643601","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142152133","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Calibrating Wireless Ray Tracing for Digital Twinning Using Local Phase Error Estimates 利用局部相位误差估算校准数字孪生的无线光线跟踪

IEEE Transactions on Machine Learning in Communications and Networking Pub Date : 2024-08-22 DOI: 10.1109/TMLCN.2024.3448391

Clement Ruah;Osvaldo Simeone;Jakob Hoydis;Bashir Al-Hashimi

{"title":"Calibrating Wireless Ray Tracing for Digital Twinning Using Local Phase Error Estimates","authors":"Clement Ruah;Osvaldo Simeone;Jakob Hoydis;Bashir Al-Hashimi","doi":"10.1109/TMLCN.2024.3448391","DOIUrl":"https://doi.org/10.1109/TMLCN.2024.3448391","url":null,"abstract":"Embodying the principle of simulation intelligence, digital twin (DT) systems construct and maintain a high-fidelity virtual model of a physical system. This paper focuses on ray tracing (RT), which is widely seen as an enabling technology for DTs of the radio access network (RAN) segment of next-generation disaggregated wireless systems. RT makes it possible to simulate channel conditions, enabling data augmentation and prediction-based transmission. However, the effectiveness of RT hinges on the adaptation of the electromagnetic properties assumed by the RT to actual channel conditions, a process known as calibration. The main challenge of RT calibration is the fact that small discrepancies in the geometric model fed to the RT software hinder the accuracy of the predicted phases of the simulated propagation paths. Existing solutions to this problem either rely on the channel power profile, hence disregarding phase information, or they operate on the channel responses by assuming the simulated phases to be sufficiently accurate for calibration. This paper proposes a novel channel response-based scheme that, unlike the state of the art, estimates and compensates for the phase errors in the RT-generated channel responses. The proposed approach builds on the variational expectation maximization algorithm with a flexible choice of the prior phase-error distribution that bridges between a deterministic model with no phase errors and a stochastic model with uniform phase errors. The algorithm is computationally efficient, and is demonstrated, by leveraging the open-source differentiable RT software available within the Sionna library, to outperform existing methods in terms of the accuracy of RT predictions.","PeriodicalId":100641,"journal":{"name":"IEEE Transactions on Machine Learning in Communications and Networking","volume":"2 ","pages":"1193-1215"},"PeriodicalIF":0.0,"publicationDate":"2024-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10643616","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142123043","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Mobility-Aware Federated Learning-Based Proactive UAVs Placement in Emerging Cellular Networks 新兴蜂窝网络中基于移动感知联合学习的主动式无人机部署

IEEE Transactions on Machine Learning in Communications and Networking Pub Date : 2024-08-21 DOI: 10.1109/TMLCN.2024.3439289

Sanaullah Manzoor;Muhammad Zeeshan Shakir;Mazen O. Hasna;Khalid A. Qaraqe

{"title":"Mobility-Aware Federated Learning-Based Proactive UAVs Placement in Emerging Cellular Networks","authors":"Sanaullah Manzoor;Muhammad Zeeshan Shakir;Mazen O. Hasna;Khalid A. Qaraqe","doi":"10.1109/TMLCN.2024.3439289","DOIUrl":"https://doi.org/10.1109/TMLCN.2024.3439289","url":null,"abstract":"With the vast proliferation of smart mobile devices, there is an ever-increasing demand for higher data rates and seamless connectivity throughout. Current 5th generation and beyond (B5G) cellular networks struggle to eradicate outage zones and ensure seamless connectivity. One promising solution to this problem is the use of unmanned aerial vehicles (UAVs) to assist the traditional ground network and provide connectivity in places where there are no small base stations or faulty ones as a result of some natural disasters such as flooding. In this paper, we propose a novel users’ mobility-aware & users’ demand-aware federated learning-based proactive UAV placement (MFPUP) framework to assist the existing ground communication network and minimise overall network outages. Our MFPUP framework utilises the federated learning-based mobility prediction model that recommends the potential outage areas to deploy UAVs using user-UAV association techniques such as the optimum association approach (OAP) and the greedy association approach (GAP). In order to validate the performance of the proposed MFPUP scheme we carried out extensive simulations. The proposed LSTM-based mobility model outperforms the DNN model with 92.88% prediction accuracy. Further, our results show that the proposed MFPUP framework associates the optimal number of users to UAVs while also improving 1.25 times users’ downlink rates as compared other UAVs placement schemes.","PeriodicalId":100641,"journal":{"name":"IEEE Transactions on Machine Learning in Communications and Networking","volume":"2 ","pages":"1305-1318"},"PeriodicalIF":0.0,"publicationDate":"2024-08-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10643371","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142246438","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Distinguishable IQ Feature Representation for Domain-Adaptation Learning of WiFi Device Fingerprints 用于 WiFi 设备指纹领域适应性学习的可区分 IQ 特征表示法

IEEE Transactions on Machine Learning in Communications and Networking Pub Date : 2024-08-20 DOI: 10.1109/TMLCN.2024.3446743

Abdurrahman Elmaghbub;Bechir Hamdaoui

{"title":"Distinguishable IQ Feature Representation for Domain-Adaptation Learning of WiFi Device Fingerprints","authors":"Abdurrahman Elmaghbub;Bechir Hamdaoui","doi":"10.1109/TMLCN.2024.3446743","DOIUrl":"https://doi.org/10.1109/TMLCN.2024.3446743","url":null,"abstract":"Deep learning (DL)-based RF fingerprinting (RFFP) technology has emerged as a powerful physical-layer security mechanism, enabling device identification and authentication based on unique device-specific signatures that can be extracted from the received RF signals. However, DL-based RFFP methods face major challenges concerning their ability to adapt to domain (e.g., day/time, location, channel, etc.) changes and variability. This work proposes a novel IQ data representation and feature design, termed Double-Sided Envelope Power Spectrum or \u0000<monospace>EPS</monospace>\u0000, that is proven to significantly overcome the domain adaptation challenges associated with WiFi transmitter fingerprinting. By accurately capturing device hardware impairments while suppressing irrelevant domain information, \u0000<monospace>EPS</monospace>\u0000 offers improved feature selection for DL models in RFFP. Our experimental evaluation demonstrates the effectiveness of the integration of \u0000<monospace>EPS</monospace>\u0000 representation with a Convolution Neural Network (CNN) model, termed \u0000<monospace>EPS-CNN</monospace>\u0000, achieving over 99% testing accuracy in same-day/channel/location evaluations and 93% accuracy in cross-day evaluations, outperforming the traditional IQ representation. Additionally, \u0000<monospace>EPS-CNN</monospace>\u0000 excels in cross-location evaluations, achieving a 95% accuracy. The proposed representation significantly enhances the robustness and generalizability of DL-based RFFP methods, thereby presenting a transformative solution to IQ data-based device fingerprinting.","PeriodicalId":100641,"journal":{"name":"IEEE Transactions on Machine Learning in Communications and Networking","volume":"2 ","pages":"1404-1423"},"PeriodicalIF":0.0,"publicationDate":"2024-08-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10640139","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142320477","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

5G Network on Wings: A Deep Reinforcement Learning Approach to the UAV-Based Integrated Access and Backhaul 插上翅膀的 5G 网络：基于无人机的综合接入和回程的深度强化学习方法

IEEE Transactions on Machine Learning in Communications and Networking Pub Date : 2024-08-13 DOI: 10.1109/TMLCN.2024.3442771

Hongyi Zhang;Zhiqiang Qi;Jingya Li;Anders Aronsson;Jan Bosch;Helena Holmström Olsson

{"title":"5G Network on Wings: A Deep Reinforcement Learning Approach to the UAV-Based Integrated Access and Backhaul","authors":"Hongyi Zhang;Zhiqiang Qi;Jingya Li;Anders Aronsson;Jan Bosch;Helena Holmström Olsson","doi":"10.1109/TMLCN.2024.3442771","DOIUrl":"https://doi.org/10.1109/TMLCN.2024.3442771","url":null,"abstract":"Fast and reliable wireless communication has become a critical demand in human life. In the case of mission-critical (MC) scenarios, for instance, when natural disasters strike, providing ubiquitous connectivity becomes challenging by using traditional wireless networks. In this context, unmanned aerial vehicle (UAV) based aerial networks offer a promising alternative for fast, flexible, and reliable wireless communications. Due to unique characteristics such as mobility, flexible deployment, and rapid reconfiguration, drones can readily change location dynamically to provide on-demand communications to users on the ground in emergency scenarios. As a result, the usage of UAV base stations (UAV-BSs) has been considered an appropriate approach for providing rapid connection in MC scenarios. In this paper, we study how to control multiple UAV-BSs in both static and dynamic environments. We use a system-level simulator to model an MC scenario in which a macro-BS of a cellular network is out of service and multiple UAV-BSs are deployed using integrated access and backhaul (IAB) technology to provide coverage for users in the disaster area. With the data collected from the system-level simulation, a deep reinforcement learning algorithm is developed to jointly optimize the three-dimensional placement of these multiple UAV-BSs, which adapt their 3-D locations to the on-ground user movement. The evaluation results show that the proposed algorithm can support the autonomous navigation of the UAV-BSs to meet the MC service requirements in terms of user throughput and drop rate.","PeriodicalId":100641,"journal":{"name":"IEEE Transactions on Machine Learning in Communications and Networking","volume":"2 ","pages":"1109-1126"},"PeriodicalIF":0.0,"publicationDate":"2024-08-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10634545","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142044355","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Deep Learning-Based Positioning With Multi-Task Learning and Uncertainty-Based Fusion 基于多任务学习和不确定性融合的深度学习定位技术

IEEE Transactions on Machine Learning in Communications and Networking Pub Date : 2024-08-09 DOI: 10.1109/TMLCN.2024.3441521

Anastasios Foliadis;Mario H. Castañeda Garcia;Richard A. Stirling-Gallacher;Reiner S. Thomä

{"title":"Deep Learning-Based Positioning With Multi-Task Learning and Uncertainty-Based Fusion","authors":"Anastasios Foliadis;Mario H. Castañeda Garcia;Richard A. Stirling-Gallacher;Reiner S. Thomä","doi":"10.1109/TMLCN.2024.3441521","DOIUrl":"https://doi.org/10.1109/TMLCN.2024.3441521","url":null,"abstract":"Deep learning (DL) methods have been shown to improve the performance of several use cases for the fifth-generation (5G) New radio (NR) air interface. In this paper we investigate user equipment (UE) positioning using the channel state information (CSI) fingerprints between a UE and multiple base stations (BSs). In such a setup, we consider two different fusion techniques: early and late fusion. With early fusion, a single DL model can be trained for UE positioning by combining the CSI fingerprints of the multiple BSs as input. With late fusion, a separate DL model is trained at each BS using the CSI specific to that BS and the outputs of these individual models are then combined to determine the UE’s position. In this work we compare these different fusion techniques and show that fusing the outputs of separate models achieves higher positioning accuracy, especially in a dynamic scenario. We also show that the combination of multiple outputs further benefits from considering the uncertainty of the output of the DL model at each BS. For a more efficient training of the DL model across BSs, we additionally propose a multi-task learning (MTL) scheme by sharing some parameters across the models while jointly training all models. This method, not only improves the accuracy of the individual models, but also of the final combined estimate. Lastly, we evaluate the reliability of the uncertainty estimation to determine which of the fusion methods provides the highest quality of uncertainty estimates.","PeriodicalId":100641,"journal":{"name":"IEEE Transactions on Machine Learning in Communications and Networking","volume":"2 ","pages":"1127-1141"},"PeriodicalIF":0.0,"publicationDate":"2024-08-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10632202","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142083901","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Deep Reinforcement Learning for Uplink Scheduling in NOMA-URLLC Networks 针对 NOMA-URLLC 网络中上行链路调度的深度强化学习

IEEE Transactions on Machine Learning in Communications and Networking Pub Date : 2024-08-02 DOI: 10.1109/TMLCN.2024.3437351

Benoît-Marie Robaglia;Marceau Coupechoux;Dimitrios Tsilimantos

{"title":"Deep Reinforcement Learning for Uplink Scheduling in NOMA-URLLC Networks","authors":"Benoît-Marie Robaglia;Marceau Coupechoux;Dimitrios Tsilimantos","doi":"10.1109/TMLCN.2024.3437351","DOIUrl":"https://doi.org/10.1109/TMLCN.2024.3437351","url":null,"abstract":"This article addresses the problem of Ultra Reliable Low Latency Communications (URLLC) in wireless networks, a framework with particularly stringent constraints imposed by many Internet of Things (IoT) applications from diverse sectors. We propose a novel Deep Reinforcement Learning (DRL) scheduling algorithm, named NOMA-PPO, to solve the Non-Orthogonal Multiple Access (NOMA) uplink URLLC scheduling problem involving strict deadlines. The challenge of addressing uplink URLLC requirements in NOMA systems is related to the combinatorial complexity of the action space due to the possibility to schedule multiple devices, and to the partial observability constraint that we impose to our algorithm in order to meet the IoT communication constraints and be scalable. Our approach involves 1) formulating the NOMA-URLLC problem as a Partially Observable Markov Decision Process (POMDP) and the introduction of an agent state, serving as a sufficient statistic of past observations and actions, enabling a transformation of the POMDP into a Markov Decision Process (MDP); 2) adapting the Proximal Policy Optimization (PPO) algorithm to handle the combinatorial action space; 3) incorporating prior knowledge into the learning agent with the introduction of a Bayesian policy. Numerical results reveal that not only does our approach outperform traditional multiple access protocols and DRL benchmarks on 3GPP scenarios, but also proves to be robust under various channel and traffic configurations, efficiently exploiting inherent time correlations.","PeriodicalId":100641,"journal":{"name":"IEEE Transactions on Machine Learning in Communications and Networking","volume":"2 ","pages":"1142-1158"},"PeriodicalIF":0.0,"publicationDate":"2024-08-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10621640","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142099787","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

On Learning Suitable Caching Policies for In-Network Caching 论学习适合网络内缓存的缓存策略

IEEE Transactions on Machine Learning in Communications and Networking Pub Date : 2024-07-31 DOI: 10.1109/TMLCN.2024.3436472

Stéfani Pires;Adriana Ribeiro;Leobino N. Sampaio

{"title":"On Learning Suitable Caching Policies for In-Network Caching","authors":"Stéfani Pires;Adriana Ribeiro;Leobino N. Sampaio","doi":"10.1109/TMLCN.2024.3436472","DOIUrl":"https://doi.org/10.1109/TMLCN.2024.3436472","url":null,"abstract":"In-network cache architectures, such as Information-centric networks (ICNs), have proven to be an efficient alternative to deal with the growing content consumption on networks. In caching networks, any device can potentially act as a caching node. In practice, real cache networks may employ different caching replacement policies by a node. The reason is that the policies may vary in efficiency according to unbounded context factors, such as cache size, content request pattern, content distribution popularity, and the relative cache location. The lack of suitable policies for all nodes and scenarios undermines the efficient use of available cache resources. Therefore, a new model for choosing caching policies appropriately to cache contexts on-demand and over time becomes necessary. In this direction, we propose a new caching meta-policy strategy capable of learning the most appropriate policy for cache online and dynamically adapting to context variations that leads to changes in which policy is best. The meta-policy decouples the eviction strategy from managing the context information used by the policy, and models the choice of suitable policies as online learning with a bandit feedback problem. The meta-policy supports deploying a diverse set of self-contained caching policies in different scenarios, including adaptive policies. Experimental results with single and multiple caches have shown the meta-policy effectiveness and adaptability to different content request models in synthetic and trace-driven simulations. Moreover, we compared the meta-policy adaptive behavior with the Adaptive Replacement Policy (ARC) behavior.","PeriodicalId":100641,"journal":{"name":"IEEE Transactions on Machine Learning in Communications and Networking","volume":"2 ","pages":"1076-1092"},"PeriodicalIF":0.0,"publicationDate":"2024-07-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10616152","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141965679","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Ensemble-Based Reliability Enhancement for Edge-Deployed CNNs in Few-Shot Scenarios 以集合为基础增强边缘部署的 CNN 在少镜头场景中的可靠性

IEEE Transactions on Machine Learning in Communications and Networking Pub Date : 2024-07-29 DOI: 10.1109/TMLCN.2024.3435168

Zhen Gao;Shuang Liu;Junbo Zhao;Xiaofei Wang;Yu Wang;Zhu Han

{"title":"Ensemble-Based Reliability Enhancement for Edge-Deployed CNNs in Few-Shot Scenarios","authors":"Zhen Gao;Shuang Liu;Junbo Zhao;Xiaofei Wang;Yu Wang;Zhu Han","doi":"10.1109/TMLCN.2024.3435168","DOIUrl":"https://doi.org/10.1109/TMLCN.2024.3435168","url":null,"abstract":"Convolutional Neural Networks (CNNs) have been applied in wide areas of computer vision, and edge intelligence is expected to provide instant AI service with the support of broadband mobile networks. However, the deployment of CNNs on network edge faces severe challenges. First, edge or embedded devices are usually not reliable, and hardware failures can corrupt the CNN system, which is unacceptable for critical applications, such as autonomous driving and object detection on space platforms. Second, edge or embedded devices are usually resource-limited, and therefore traditional redundancy-based protection methods are not applicable due to huge overhead. Although network pruning is effective to reduce the complexity of CNNs, we cannot have sufficient data for performance recovery in many scenarios due to privacy and security concerns. To enhance the reliability of CNNs on resource-limited devices with the few-shot constraint, we propose to construct an ensemble system with weak base CNNs pruned from the original strong CNN. To improve the ensemble performance with diverse base CNNs, we first propose a novel filter importance evaluation method by combining the amplitude and gradient information of the filter. Since the gradient part is related to the input data, different subsets of data are used for layer sensitivity analysis for different base CNNs, so that the different pruning configurations can be obtained for each base CNN. On this basis, a modified ReLU function is proposed to determine the final pruning rate of each layer in each base CNN. Extensive experiments prove that the proposed solution can effectively improve the reliability of CNNs with much less resource requirement for each edge server.","PeriodicalId":100641,"journal":{"name":"IEEE Transactions on Machine Learning in Communications and Networking","volume":"2 ","pages":"1062-1075"},"PeriodicalIF":0.0,"publicationDate":"2024-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10614218","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141965372","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0