IEEE Transactions on Machine Learning in Communications and Networking最新文献_第8页

NeIL: Intelligent Replica Selection for Distributed Applications NeIL：为分布式应用程序选择智能副本

IEEE Transactions on Machine Learning in Communications and Networking Pub Date : 2024-10-11 DOI: 10.1109/TMLCN.2024.3479109

Faraz Ahmed;Lianjie Cao;Ayush Goel;Puneet Sharma

{"title":"NeIL: Intelligent Replica Selection for Distributed Applications","authors":"Faraz Ahmed;Lianjie Cao;Ayush Goel;Puneet Sharma","doi":"10.1109/TMLCN.2024.3479109","DOIUrl":"https://doi.org/10.1109/TMLCN.2024.3479109","url":null,"abstract":"Distributed applications such as cloud gaming, streaming, etc., are increasingly using edge-to-cloud infrastructure for high availability and performance. While edge infrastructure brings services closer to the end-user, the number of sites on which the services need to be replicated has also increased. This makes replica selection challenging for clients of the replicated services. Traditional replica selection methods including anycast based methods and DNS re-directions are performance agnostic, and clients experience degraded network performance when network performance dynamics are not considered in replica selection. In this work, we present a client-side replica selection framework NeIL, that enables network performance aware replica selection. We propose to use bandits with experts based Multi-Armed Bandit (MAB) algorithms and adapt these algorithms for replica selection at individual clients without centralized coordination. We evaluate our approach using three different setups including a distributed Mininet setup where we use publicly available network performance data from the Measurement Lab (M-Lab) to emulate network conditions, a setup where we deploy replica servers on AWS, and finally we present results from a global enterprise deployment. Our experimental results show that in comparison to greedy selection, NeIL performs better than greedy for 45% of the time and better than or equal to greedy selection for 80% of the time resulting in a net gain in end-to-end network performance. On AWS, we see similar results where NeIL performs better than or equal to greedy for 75% of the time. We have successfully deployed NeIL in a global enterprise remote device management service with over 4000 client devices and our analysis shows that NeIL achieves significantly better tail service quality by cutting the \u0000<inline-formula> <tex-math>$99th$ </tex-math></inline-formula>\u0000 percentile tail latency from 5.6 seconds to 1.7 seconds.","PeriodicalId":100641,"journal":{"name":"IEEE Transactions on Machine Learning in Communications and Networking","volume":"2 ","pages":"1580-1594"},"PeriodicalIF":0.0,"publicationDate":"2024-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10714467","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142540425","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

An Intelligent and Programmable Data Plane for QoS-Aware Packet Processing 面向服务质量感知数据包处理的智能可编程数据平面

IEEE Transactions on Machine Learning in Communications and Networking Pub Date : 2024-10-07 DOI: 10.1109/TMLCN.2024.3475968

Muhammad Saqib;Halime Elbiaze;Roch H. Glitho;Yacine Ghamri-Doudane

{"title":"An Intelligent and Programmable Data Plane for QoS-Aware Packet Processing","authors":"Muhammad Saqib;Halime Elbiaze;Roch H. Glitho;Yacine Ghamri-Doudane","doi":"10.1109/TMLCN.2024.3475968","DOIUrl":"https://doi.org/10.1109/TMLCN.2024.3475968","url":null,"abstract":"One of the main features of data plane programmability is that it allows the easy deployment of a programmable network traffic management framework. One can build an early-stage Internet traffic classifier to facilitate effective Quality of Service (QoS) provisioning. However, maintaining accuracy and efficiency (i.e., processing delay/pipeline latency) in early-stage traffic classification is challenging due to memory and operational constraints in the network data plane. Additionally, deploying network-wide flow-specific rules for QoS leads to significant memory usage and overheads. To address these challenges, we propose new architectural components encompassing efficient processing logic into the programmable traffic management framework. In particular, we propose a single feature-based traffic classification algorithm and a stateless QoS-aware packet scheduling mechanism. Our approach first focuses on maintaining accuracy and processing efficiency in early-stage traffic classification by leveraging a single input feature - sequential packet size information. We then use the classifier to embed the Service Level Objective (SLO) into the header of the packets. Carrying SLOs inside the packet allows QoS-aware packet processing through admission control-enabled priority queuing. The results show that most flows are properly classified with the first four packets. Furthermore, using the SLO-enabled admission control mechanism on top of the priority queues enables stateless QoS provisioning. Our approach outperforms the classical and objective-based priority queuing in managing heterogeneous traffic demands by improving network resource utilization.","PeriodicalId":100641,"journal":{"name":"IEEE Transactions on Machine Learning in Communications and Networking","volume":"2 ","pages":"1540-1557"},"PeriodicalIF":0.0,"publicationDate":"2024-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10706883","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142443062","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

Learning Radio Environments by Differentiable Ray Tracing 通过可变光线跟踪学习无线电环境

IEEE Transactions on Machine Learning in Communications and Networking Pub Date : 2024-10-04 DOI: 10.1109/TMLCN.2024.3474639

Jakob Hoydis;Fayçal Aït Aoudia;Sebastian Cammerer;Florian Euchner;Merlin Nimier-David;Stephan Ten Brink;Alexander Keller

引用次数: 0

Smart Jamming Attack and Mitigation on Deep Transfer Reinforcement Learning Enabled Resource Allocation for Network Slicing 基于深度传输强化学习的网络切片资源分配的智能干扰攻击与缓解

IEEE Transactions on Machine Learning in Communications and Networking Pub Date : 2024-09-30 DOI: 10.1109/TMLCN.2024.3470760

Shavbo Salehi;Hao Zhou;Medhat Elsayed;Majid Bavand;Raimundas Gaigalas;Yigit Ozcan;Melike Erol-Kantarci

{"title":"Smart Jamming Attack and Mitigation on Deep Transfer Reinforcement Learning Enabled Resource Allocation for Network Slicing","authors":"Shavbo Salehi;Hao Zhou;Medhat Elsayed;Majid Bavand;Raimundas Gaigalas;Yigit Ozcan;Melike Erol-Kantarci","doi":"10.1109/TMLCN.2024.3470760","DOIUrl":"https://doi.org/10.1109/TMLCN.2024.3470760","url":null,"abstract":"Network slicing is a pivotal paradigm in wireless networks enabling customized services to users and applications. Yet, intelligent jamming attacks threaten the performance of network slicing. In this paper, we focus on the security aspect of network slicing over a deep transfer reinforcement learning (DTRL) enabled scenario. We first demonstrate how a deep reinforcement learning (DRL)-enabled jamming attack exposes potential risks. In particular, the attacker can intelligently jam resource blocks (RBs) reserved for slices by monitoring transmission signals and perturbing the assigned resources. Then, we propose a DRL-driven mitigation model to mitigate the intelligent attacker. Specifically, the defense mechanism generates interference on unallocated RBs where another antenna is used for transmitting powerful signals. This causes the jammer to consider these RBs as allocated RBs and generate interference for those instead of the allocated RBs. The analysis revealed that the intelligent DRL-enabled jamming attack caused a significant 50% degradation in network throughput and 60% increase in latency in comparison with the no-attack scenario. However, with the implemented mitigation measures, we observed 80% improvement in network throughput and 70% reduction in latency in comparison to the under-attack scenario.","PeriodicalId":100641,"journal":{"name":"IEEE Transactions on Machine Learning in Communications and Networking","volume":"2 ","pages":"1492-1508"},"PeriodicalIF":0.0,"publicationDate":"2024-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10699421","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142397284","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

Optimizing Resource Fragmentation in Virtual Network Function Placement Using Deep Reinforcement Learning 利用深度强化学习优化虚拟网络功能布局中的资源碎片

IEEE Transactions on Machine Learning in Communications and Networking Pub Date : 2024-09-26 DOI: 10.1109/TMLCN.2024.3469131

Ramy Mohamed;Marios Avgeris;Aris Leivadeas;Ioannis Lambadaris

{"title":"Optimizing Resource Fragmentation in Virtual Network Function Placement Using Deep Reinforcement Learning","authors":"Ramy Mohamed;Marios Avgeris;Aris Leivadeas;Ioannis Lambadaris","doi":"10.1109/TMLCN.2024.3469131","DOIUrl":"https://doi.org/10.1109/TMLCN.2024.3469131","url":null,"abstract":"In the 6G wireless era, the strategical deployment of Virtual Network Functions (VNFs) within a network infrastructure that optimizes resource utilization while fulfilling performance criteria is critical for successfully implementing the Network Function Virtualization (NFV) paradigm across the Edge-to-Cloud continuum. This is especially prominent when resource fragmentation –where available resources become isolated and underutilized– becomes an issue due to the frequent reallocations of VNFs. However, traditional optimization methods often struggle to deal with the dynamic and complex nature of the VNF placement problem when fragmentation is considered. This study proposes a novel online VNF placement approach for Edge/Cloud infrastructures that utilizes Deep Reinforcement Learning (DRL) and Reward Constrained Policy Optimization (RCPO) to address this problem. We combine DRL’s adaptability with RCPO’s constraint incorporation capabilities to ensure that the learned policies satisfy the performance and resource constraints while minimizing resource fragmentation. Specifically, the VNF placement problem is first formulated as an offline-constrained optimization problem, and then we devise an online solver using Neural Combinatorial Optimization (NCO). Our method incorporates a metric called Resource Fragmentation Degree (RFD) to quantify fragmentation in the network. Using this metric and RCPO, our NCO agent is trained to make intelligent placement decisions that reduce fragmentation and optimize resource utilization. An error correction heuristic complements the robustness of the proposed framework. Through extensive testing in a simulated environment, the proposed approach is shown to outperform state-of-the-art VNF placement techniques when it comes to minimizing resource fragmentation under constraint satisfaction guarantees.","PeriodicalId":100641,"journal":{"name":"IEEE Transactions on Machine Learning in Communications and Networking","volume":"2 ","pages":"1475-1491"},"PeriodicalIF":0.0,"publicationDate":"2024-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10695455","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142397282","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

Removing the Need for Ground Truth UWB Data Collection: Self-Supervised Ranging Error Correction Using Deep Reinforcement Learning 无需收集地面实况 UWB 数据：利用深度强化学习进行自监督测距纠错

IEEE Transactions on Machine Learning in Communications and Networking Pub Date : 2024-09-26 DOI: 10.1109/TMLCN.2024.3469128

Dieter Coppens;Ben van Herbruggen;Adnan Shahid;Eli de Poorter

{"title":"Removing the Need for Ground Truth UWB Data Collection: Self-Supervised Ranging Error Correction Using Deep Reinforcement Learning","authors":"Dieter Coppens;Ben van Herbruggen;Adnan Shahid;Eli de Poorter","doi":"10.1109/TMLCN.2024.3469128","DOIUrl":"https://doi.org/10.1109/TMLCN.2024.3469128","url":null,"abstract":"Indoor positioning using UWB technology has gained interest due to its centimeter-level accuracy potential. However, multipath effects and non-line-of-sight conditions cause ranging errors between anchors and tags. Existing approaches for mitigating these ranging errors rely on collecting large labeled datasets, making them impractical for real-world deployments. This paper proposes a novel self-supervised deep reinforcement learning approach that does not require labeled ground truth data. A reinforcement learning agent uses the channel impulse response as a state and predicts corrections to minimize the error between corrected and estimated ranges. The agent learns, self-supervised, by iteratively improving corrections that are generated by combining the predictability of trajectories with filtering and smoothening. Experiments on real-world UWB measurements demonstrate comparable performance to state-of-the-art supervised methods, overcoming data dependency and lack of generalizability limitations. This makes self-supervised deep reinforcement learning a promising solution for practical and scalable UWB-ranging error correction.","PeriodicalId":100641,"journal":{"name":"IEEE Transactions on Machine Learning in Communications and Networking","volume":"2 ","pages":"1615-1627"},"PeriodicalIF":0.0,"publicationDate":"2024-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10695458","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142565484","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

Decentralized Grant-Free mMTC Traffic Multiplexing With eMBB Data Through Deep Reinforcement Learning 通过深度强化学习利用 eMBB 数据实现分散式无补助 mMTC 流量复用

IEEE Transactions on Machine Learning in Communications and Networking Pub Date : 2024-09-24 DOI: 10.1109/TMLCN.2024.3467044

Giovanni Di Gennaro;Amedeo Buonanno;Gianmarco Romano;Stefano Buzzi;Francesco A. N. Palmieri

{"title":"Decentralized Grant-Free mMTC Traffic Multiplexing With eMBB Data Through Deep Reinforcement Learning","authors":"Giovanni Di Gennaro;Amedeo Buonanno;Gianmarco Romano;Stefano Buzzi;Francesco A. N. Palmieri","doi":"10.1109/TMLCN.2024.3467044","DOIUrl":"https://doi.org/10.1109/TMLCN.2024.3467044","url":null,"abstract":"This paper addresses the problem of joint multiplexing of enhanced Mobile Broadband (eMBB) and massive Machine-Type Communications (mMTC) traffic in the same uplink time-frequency RG. Given the challenge posed by a potentially large number of users, it is essential to focus on a multiple access strategy that leverages artificial intelligence to adapt to specific channel conditions. An mMTC agent is developed through a Deep Reinforcement Learning (DRL) methodology for generating grant-free frequency hopping traffic in a decentralized manner, assuming the presence of underlying eMBB traffic dynamics. Within this DRL framework, a methodical comparison between two possible deep neural networks is conducted, using different generative models employed to ascertain their intrinsic capabilities in various application scenarios. The analysis conducted reveals that the Long Short-Term Memory network is particularly suitable for the required task, demonstrating a robustness that is consistently very close to potential upper-bounds, despite the latter requiring complete knowledge of the underlying statistics.","PeriodicalId":100641,"journal":{"name":"IEEE Transactions on Machine Learning in Communications and Networking","volume":"2 ","pages":"1440-1455"},"PeriodicalIF":0.0,"publicationDate":"2024-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10689612","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142368315","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

Biased Backpressure Routing Using Link Features and Graph Neural Networks 利用链路特征和图神经网络进行有偏向的反压路由选择

IEEE Transactions on Machine Learning in Communications and Networking Pub Date : 2024-09-16 DOI: 10.1109/TMLCN.2024.3461711

Zhongyuan Zhao;Bojan Radojičić;Gunjan Verma;Ananthram Swami;Santiago Segarra

{"title":"Biased Backpressure Routing Using Link Features and Graph Neural Networks","authors":"Zhongyuan Zhao;Bojan Radojičić;Gunjan Verma;Ananthram Swami;Santiago Segarra","doi":"10.1109/TMLCN.2024.3461711","DOIUrl":"https://doi.org/10.1109/TMLCN.2024.3461711","url":null,"abstract":"To reduce the latency of Backpressure (BP) routing in wireless multi-hop networks, we propose to enhance the existing shortest path-biased BP (SP-BP) and sojourn time-based backlog metrics, since they introduce no additional time step-wise signaling overhead to the basic BP. Rather than relying on hop-distance, we introduce a new edge-weighted shortest path bias built on the scheduling duty cycle of wireless links, which can be predicted by a graph convolutional neural network based on the topology and traffic of wireless networks. Additionally, we tackle three long-standing challenges associated with SP-BP: optimal bias scaling, efficient bias maintenance, and integration of delay awareness. Our proposed solutions inherit the throughput optimality of the basic BP, as well as its practical advantages of low complexity and fully distributed implementation. Our approaches rely on common link features and introduces only a one-time constant overhead to previous SP-BP schemes, or a one-time overhead linear in the network size to the basic BP. Numerical experiments show that our solutions can effectively address the major drawbacks of slow startup, random walk, and the last packet problem in basic BP, improving the end-to-end delay of existing low-overhead BP algorithms under various settings of network traffic, interference, and mobility.","PeriodicalId":100641,"journal":{"name":"IEEE Transactions on Machine Learning in Communications and Networking","volume":"2 ","pages":"1424-1439"},"PeriodicalIF":0.0,"publicationDate":"2024-09-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10681132","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142368430","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

Anticipating Optical Availability in Hybrid RF/FSO Links Using RF Beacons and Deep Learning 利用射频信标和深度学习预测射频/FSO 混合链路中的光学可用性

IEEE Transactions on Machine Learning in Communications and Networking Pub Date : 2024-09-10 DOI: 10.1109/TMLCN.2024.3457490

Mostafa Ibrahim;Arsalan Ahmad;Sabit Ekin;Peter LoPresti;Serhat Altunc;Obadiah Kegege;John F. O'Hara

{"title":"Anticipating Optical Availability in Hybrid RF/FSO Links Using RF Beacons and Deep Learning","authors":"Mostafa Ibrahim;Arsalan Ahmad;Sabit Ekin;Peter LoPresti;Serhat Altunc;Obadiah Kegege;John F. O'Hara","doi":"10.1109/TMLCN.2024.3457490","DOIUrl":"https://doi.org/10.1109/TMLCN.2024.3457490","url":null,"abstract":"Radiofrequency (RF) communications offer reliable but low data rates and energy-inefficient satellite links, while free-space optical (FSO) promises high bandwidth but struggles with disturbances imposed by atmospheric effects. A hybrid RF/FSO architecture aims to achieve optimal reliability along with high data rates for space communications. Accurate prediction of dynamic ground-to-satellite FSO link availability is critical for routing decisions in low-earth orbit constellations. In this paper, we propose a system leveraging ubiquitous RF links to proactively forecast FSO link degradation prior to signal drops below threshold levels. This enables pre-calculation of rerouting to maximally maintain high data rate FSO links throughout the duration of weather effects. We implement a supervised learning model to anticipate FSO attenuation based on the analysis of RF patterns. Through the simulation of a dense lower earth orbit (LEO) satellite constellation, we demonstrate the efficacy of our approach in a simulated satellite network, highlighting the balance between predictive accuracy and prediction duration. An emulated cloud attenuation model is proposed to provide insight into the temporal profiles of RF signals and their correlation to FSO channel dynamics. Our investigation sheds light on the trade-offs between prediction horizon and accuracy arising from RF beacon numbers and proximity.","PeriodicalId":100641,"journal":{"name":"IEEE Transactions on Machine Learning in Communications and Networking","volume":"2 ","pages":"1369-1388"},"PeriodicalIF":0.0,"publicationDate":"2024-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10672517","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142246523","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

RSMA-Enabled Interference Management for Industrial Internet of Things Networks With Finite Blocklength Coding and Hardware Impairments 利用有限块长编码和硬件损伤为工业物联网网络提供 RSMA 支持的干扰管理

IEEE Transactions on Machine Learning in Communications and Networking Pub Date : 2024-09-05 DOI: 10.1109/TMLCN.2024.3455268

Nahed Belhadj Mohamed;Md. Zoheb Hassan;Georges Kaddoum

{"title":"RSMA-Enabled Interference Management for Industrial Internet of Things Networks With Finite Blocklength Coding and Hardware Impairments","authors":"Nahed Belhadj Mohamed;Md. Zoheb Hassan;Georges Kaddoum","doi":"10.1109/TMLCN.2024.3455268","DOIUrl":"https://doi.org/10.1109/TMLCN.2024.3455268","url":null,"abstract":"The increasing proliferation of industrial internet of things (IIoT) devices requires the development of efficient radio resource allocation techniques to optimize spectrum utilization. In densely populated IIoT networks, the interference that results from simultaneously scheduling multiple IIoT devices over the same radio resource blocks (RRBs) severely degrades a network’s achievable capacity. This paper investigates an interference management problem for IIoT networks that considers both finite blocklength (FBL)-coded transmission and signal distortions induced by hardware impairments (HWIs) arising from practical, low-complexity radio-frequency front ends. We use the rate-splitting multiple access (RSMA) scheme to effectively schedule multiple IIoT devices in a cluster over the same RRB(s). To enhance the system’s achievable capacity, a joint clustering and transmit power allocation (PA) problem is formulated. To tackle the optimization problem’s inherent computational intractability due to its non-convex structure, a two-step distributed clustering and power management (DCPM) framework is proposed. First, the DCPM framework obtains a set of clustered devices for each access point by employing a greedy clustering algorithm while maximizing the clustered devices’ signal-to-interference-plus-noise ratio. Then, the DCPM framework employs a multi-agent deep reinforcement learning (DRL) framework to optimize transmit PA among the clustered devices. The proposed DRL algorithm learns a suitable transmit PA policy that does not require precise information about instantaneous signal distortions. Our simulation results demonstrate that our proposed DCPM framework adapts seamlessly to varying channel conditions and outperforms several benchmark schemes with and without HWI-induced signal distortions.","PeriodicalId":100641,"journal":{"name":"IEEE Transactions on Machine Learning in Communications and Networking","volume":"2 ","pages":"1319-1340"},"PeriodicalIF":0.0,"publicationDate":"2024-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10666756","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142246544","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