arXiv - CS - Networking and Internet Architecture最新文献_第6页

Maximization of Communication Network Throughput using Dynamic Traffic Allocation Scheme 利用动态流量分配方案实现通信网络吞吐量最大化

arXiv - CS - Networking and Internet Architecture Pub Date : 2024-09-07 DOI: arxiv-2409.04724

Md. Arquam, Suchi Kumari

引用次数: 0

IPN-V: The Interplanetary Network Visualizer IPN-V：星际网络展示台

arXiv - CS - Networking and Internet Architecture Pub Date : 2024-09-07 DOI: arxiv-2409.04857

Alice Le Bihan, Juan A. Fraire, Pierre Francois, Felix Flentge

{"title":"IPN-V: The Interplanetary Network Visualizer","authors":"Alice Le Bihan, Juan A. Fraire, Pierre Francois, Felix Flentge","doi":"arxiv-2409.04857","DOIUrl":"https://doi.org/arxiv-2409.04857","url":null,"abstract":"The Interplanetary Network (IPN) emerges as the backbone for communication\u0000between various spacecraft and satellites orbiting distant celestial bodies.\u0000This paper introduces the Interplanetary Network Visualizer (IPN-V), a software\u0000platform that integrates interplanetary communications planning support,\u0000education, and outreach. IPN-V bridges the gap between the complexities of\u0000astrodynamics and network engineering by enabling the generation and assessment\u0000of dynamic, realistic network topologies that encapsulate the inherent\u0000challenges of space communication, such as time-evolving latencies and\u0000planetary occlusions. Leveraging the power of Unity 3D and C#, IPN-V provides a\u0000user-friendly 3D interface for the interactive visualization of interplanetary\u0000networks, incorporating contact tracing models to represent line-of-sight\u0000communication constraints accurately. IPN-V supports importing and exporting\u0000contact plans compatible with established space communication standards,\u0000including NASA's ION and HDTN formats. This paper delineates the conception,\u0000architecture, and operational framework of IPN-V while evaluating its\u0000performance metrics.","PeriodicalId":501280,"journal":{"name":"arXiv - CS - Networking and Internet Architecture","volume":"23 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142183732","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Digital Twin Enabled Data-Driven Approach for Traffic Efficiency and Software-Defined Vehicular Network Optimization 交通效率和软件定义车载网络优化的数字孪生数据驱动方法

arXiv - CS - Networking and Internet Architecture Pub Date : 2024-09-06 DOI: arxiv-2409.04622

Mohammad Sajid Shahriar, Suresh Subramaniam, Motoharu Matsuura, Hiroshi Hasegawa, Shih-Chun Lin

{"title":"Digital Twin Enabled Data-Driven Approach for Traffic Efficiency and Software-Defined Vehicular Network Optimization","authors":"Mohammad Sajid Shahriar, Suresh Subramaniam, Motoharu Matsuura, Hiroshi Hasegawa, Shih-Chun Lin","doi":"arxiv-2409.04622","DOIUrl":"https://doi.org/arxiv-2409.04622","url":null,"abstract":"In the realms of the internet of vehicles (IoV) and intelligent\u0000transportation systems (ITS), software defined vehicular networks (SDVN) and\u0000edge computing (EC) have emerged as promising technologies for enhancing road\u0000traffic efficiency. However, the increasing number of connected autonomous\u0000vehicles (CAVs) and EC-based applications presents multi-domain challenges such\u0000as inefficient traffic flow due to poor CAV coordination and flow-table\u0000overflow in SDVN from increased connectivity and limited ternary content\u0000addressable memory (TCAM) capacity. To address these, we focus on a data-driven\u0000approach using virtualization technologies like digital twin (DT) to leverage\u0000real-time data and simulations. We introduce a DT design and propose two\u0000data-driven solutions: a centralized decision support framework to improve\u0000traffic efficiency by reducing waiting times at roundabouts and an approach to\u0000minimize flow-table overflow and flow re-installation by optimizing flow-entry\u0000lifespan in SDVN. Simulation results show the decision support framework\u0000reduces average waiting times by 22% compared to human-driven vehicles, even\u0000with a CAV penetration rate of 40%. Additionally, the proposed optimization of\u0000flow-table space usage demonstrates a 50% reduction in flow-table space\u0000requirements, even with 100% penetration of connected vehicles.","PeriodicalId":501280,"journal":{"name":"arXiv - CS - Networking and Internet Architecture","volume":"21 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-09-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142183692","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Minimizing Power Consumption under SINR Constraints for Cell-Free Massive MIMO in O-RAN 在 SINR 约束条件下最大限度降低 O-RAN 中无蜂窝大规模多输入多输出的功耗

arXiv - CS - Networking and Internet Architecture Pub Date : 2024-09-06 DOI: arxiv-2409.04135

Vaishnavi Kasuluru, Luis Blanco, Miguel Angel Vazquez, Cristian J. Vaca-Rubio, Engin Zeydan

{"title":"Minimizing Power Consumption under SINR Constraints for Cell-Free Massive MIMO in O-RAN","authors":"Vaishnavi Kasuluru, Luis Blanco, Miguel Angel Vazquez, Cristian J. Vaca-Rubio, Engin Zeydan","doi":"arxiv-2409.04135","DOIUrl":"https://doi.org/arxiv-2409.04135","url":null,"abstract":"This paper deals with the problem of energy consumption minimization in Open\u0000RAN cell-free (CF) massive Multiple-Input Multiple-Output (mMIMO) systems under\u0000minimum per-user signal-to-noise-plus-interference ratio (SINR) constraints.\u0000Considering that several access points (APs) are deployed with multiple\u0000antennas, and they jointly serve multiple users on the same time-frequency\u0000resources, we design the precoding vectors that minimize the system power\u0000consumption, while preserving a minimum SINR for each user. We use a simple,\u0000yet representative, power consumption model, which consists of a fixed term\u0000that models the power consumption due to activation of the AP and a variable\u0000one that depends on the transmitted power. The mentioned problem boils down to\u0000a binary-constrained quadratic optimization problem, which is strongly\u0000non-convex. In order to solve this problem, we resort to a novel approach,\u0000which is based on the penalized convex-concave procedure. The proposed approach\u0000can be implemented in an O-RAN cell-free mMIMO system as an xApp in the\u0000near-real time RIC (RAN intelligent Controller). Numerical results show the\u0000potential of this approach for dealing with joint precoding optimization and AP\u0000selection.","PeriodicalId":501280,"journal":{"name":"arXiv - CS - Networking and Internet Architecture","volume":"59 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-09-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142183698","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

VQ-DeepVSC: A Dual-Stage Vector Quantization Framework for Video Semantic Communication VQ-DeepVSC：用于视频语义通信的双级矢量量化框架

arXiv - CS - Networking and Internet Architecture Pub Date : 2024-09-05 DOI: arxiv-2409.03393

Yongyi Miao, Zhongdang Li, Yang Wang, Die Hu, Jun Yan, Youfang Wang

{"title":"VQ-DeepVSC: A Dual-Stage Vector Quantization Framework for Video Semantic Communication","authors":"Yongyi Miao, Zhongdang Li, Yang Wang, Die Hu, Jun Yan, Youfang Wang","doi":"arxiv-2409.03393","DOIUrl":"https://doi.org/arxiv-2409.03393","url":null,"abstract":"In response to the rapid growth of global videomtraffic and the limitations\u0000of traditional wireless transmission systems, we propose a novel dual-stage\u0000vector quantization framework, VQ-DeepVSC, tailored to enhance video\u0000transmission over wireless channels. In the first stage, we design the adaptive\u0000keyframe extractor and interpolator, deployed respectively at the transmitter\u0000and receiver, which intelligently select key frames to minimize inter-frame\u0000redundancy and mitigate the cliff-effect under challenging channel conditions.\u0000In the second stage, we propose the semantic vector quantization encoder and\u0000decoder, placed respectively at the transmitter and receiver, which efficiently\u0000compress key frames using advanced indexing and spatial normalization modules\u0000to reduce redundancy. Additionally, we propose adjustable index selection and\u0000recovery modules, enhancing compression efficiency and enabling flexible\u0000compression ratio adjustment. Compared to the joint source-channel coding\u0000(JSCC) framework, the proposed framework exhibits superior compatibility with\u0000current digital communication systems. Experimental results demonstrate that\u0000VQ-DeepVSC achieves substantial improvements in both Multi-Scale Structural\u0000Similarity (MS-SSIM) and Learned Perceptual Image Patch Similarity (LPIPS)\u0000metrics than the H.265 standard, particularly under low channel signal-to-noise\u0000ratio (SNR) or multi-path channels, highlighting the significantly enhanced\u0000transmission capabilities of our approach.","PeriodicalId":501280,"journal":{"name":"arXiv - CS - Networking and Internet Architecture","volume":"22 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142183701","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Towards Autonomous Cybersecurity: An Intelligent AutoML Framework for Autonomous Intrusion Detection 迈向自主网络安全：用于自主入侵检测的智能 AutoML 框架

arXiv - CS - Networking and Internet Architecture Pub Date : 2024-09-05 DOI: arxiv-2409.03141

Li Yang, Abdallah Shami

{"title":"Towards Autonomous Cybersecurity: An Intelligent AutoML Framework for Autonomous Intrusion Detection","authors":"Li Yang, Abdallah Shami","doi":"arxiv-2409.03141","DOIUrl":"https://doi.org/arxiv-2409.03141","url":null,"abstract":"The rapid evolution of mobile networks from 5G to 6G has necessitated the\u0000development of autonomous network management systems, such as Zero-Touch\u0000Networks (ZTNs). However, the increased complexity and automation of these\u0000networks have also escalated cybersecurity risks. Existing Intrusion Detection\u0000Systems (IDSs) leveraging traditional Machine Learning (ML) techniques have\u0000shown effectiveness in mitigating these risks, but they often require extensive\u0000manual effort and expert knowledge. To address these challenges, this paper\u0000proposes an Automated Machine Learning (AutoML)-based autonomous IDS framework\u0000towards achieving autonomous cybersecurity for next-generation networks. To\u0000achieve autonomous intrusion detection, the proposed AutoML framework automates\u0000all critical procedures of the data analytics pipeline, including data\u0000pre-processing, feature engineering, model selection, hyperparameter tuning,\u0000and model ensemble. Specifically, it utilizes a Tabular Variational\u0000Auto-Encoder (TVAE) method for automated data balancing, tree-based ML models\u0000for automated feature selection and base model learning, Bayesian Optimization\u0000(BO) for hyperparameter optimization, and a novel Optimized Confidence-based\u0000Stacking Ensemble (OCSE) method for automated model ensemble. The proposed\u0000AutoML-based IDS was evaluated on two public benchmark network security\u0000datasets, CICIDS2017 and 5G-NIDD, and demonstrated improved performance\u0000compared to state-of-the-art cybersecurity methods. This research marks a\u0000significant step towards fully autonomous cybersecurity in next-generation\u0000networks, potentially revolutionizing network security applications.","PeriodicalId":501280,"journal":{"name":"arXiv - CS - Networking and Internet Architecture","volume":"67 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142183731","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Weather-Adaptive Multi-Step Forecasting of State of Polarization Changes in Aerial Fibers Using Wavelet Neural Networks 利用小波神经网络对航空光纤极化状态变化进行天气适应性多步骤预测

arXiv - CS - Networking and Internet Architecture Pub Date : 2024-09-05 DOI: arxiv-2409.03663

Khouloud Abdelli, Matteo Lonardi, Jurgen Gripp, Samuel Olsson Fabien Boitier, Patricia Layec

引用次数: 0

VECA: Reliable and Confidential Resource Clustering for Volunteer Edge-Cloud Computing VECA：面向志愿者边缘云计算的可靠保密资源集群

arXiv - CS - Networking and Internet Architecture Pub Date : 2024-09-04 DOI: arxiv-2409.03057

Hemanth Sai Yeddulapalli, Mauro Lemus Alarcon, Upasana Roy, Roshan Lal Neupane, Durbek Gafurov, Motahare Mounesan, Saptarshi Debroy, Prasad Calyam

{"title":"VECA: Reliable and Confidential Resource Clustering for Volunteer Edge-Cloud Computing","authors":"Hemanth Sai Yeddulapalli, Mauro Lemus Alarcon, Upasana Roy, Roshan Lal Neupane, Durbek Gafurov, Motahare Mounesan, Saptarshi Debroy, Prasad Calyam","doi":"arxiv-2409.03057","DOIUrl":"https://doi.org/arxiv-2409.03057","url":null,"abstract":"Volunteer Edge-Cloud (VEC) computing has a significant potential to support\u0000scientific workflows in user communities contributing volunteer edge nodes.\u0000However, managing heterogeneous and intermittent resources to support\u0000machine/deep learning (ML/DL) based workflows poses challenges in resource\u0000governance for reliability, and confidentiality for model/data privacy\u0000protection. There is a need for approaches to handle the volatility of\u0000volunteer edge node availability, and also to scale the confidential\u0000data-intensive workflow execution across a large number of VEC nodes. In this\u0000paper, we present VECA, a reliable and confidential VEC resource clustering\u0000solution featuring three-fold methods tailored for executing ML/DL-based\u0000scientific workflows on VEC resources. Firstly, a capacity-based clustering\u0000approach enhances system reliability and minimizes VEC node search latency.\u0000Secondly, a novel two-phase, globally distributed scheduling scheme optimizes\u0000job allocation based on node attributes and using time-series-based Recurrent\u0000Neural Networks. Lastly, the integration of confidential computing ensures\u0000privacy preservation of the scientific workflows, where model and data\u0000information are not shared with VEC resources providers. We evaluate VECA in a\u0000Function-as-a-Service (FaaS) cloud testbed that features OpenFaaS and MicroK8S\u0000to support two ML/DL-based scientific workflows viz., G2P-Deep (bioinformatics)\u0000and PAS-ML (health informatics). Results from tested experiments demonstrate\u0000that our proposed VECA approach outperforms state-of-the-art methods;\u0000especially VECA exhibits a two-fold reduction in VEC node search latency and\u0000over 20% improvement in productivity rates following execution failures\u0000compared to the next best method.","PeriodicalId":501280,"journal":{"name":"arXiv - CS - Networking and Internet Architecture","volume":"59 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142183702","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Enhancing 5G Performance: Reducing Service Time and Research Directions for 6G Standards 增强 5G 性能：缩短服务时间和 6G 标准的研究方向

arXiv - CS - Networking and Internet Architecture Pub Date : 2024-09-04 DOI: arxiv-2409.02788

Laura Landon, Vipindev Adat Vasudevan, Jaeweon Kim, Junmo Sung, Jeffery Tony Masters, Muriel Médard

引用次数: 0

Jäger: Automated Telephone Call Traceback Jäger：自动电话回溯

arXiv - CS - Networking and Internet Architecture Pub Date : 2024-09-04 DOI: arxiv-2409.02839

David Adei, Varun Madathil, Sathvik Prasad, Bradley Reaves, Alessandra Scafuro

{"title":"Jäger: Automated Telephone Call Traceback","authors":"David Adei, Varun Madathil, Sathvik Prasad, Bradley Reaves, Alessandra Scafuro","doi":"arxiv-2409.02839","DOIUrl":"https://doi.org/arxiv-2409.02839","url":null,"abstract":"Unsolicited telephone calls that facilitate fraud or unlawful telemarketing\u0000continue to overwhelm network users and the regulators who prosecute them. The\u0000first step in prosecuting phone abuse is traceback -- identifying the call\u0000originator. This fundamental investigative task currently requires hours of\u0000manual effort per call. In this paper, we introduce J\"ager, a distributed\u0000secure call traceback system. J\"ager can trace a call in a few seconds, even\u0000with partial deployment, while cryptographically preserving the privacy of call\u0000parties, carrier trade secrets like peers and call volume, and limiting the\u0000threat of bulk analysis. We establish definitions and requirements of secure\u0000traceback, then develop a suite of protocols that meet these requirements using\u0000witness encryption, oblivious pseudorandom functions, and group signatures. We\u0000prove these protocols secure in the universal composibility framework. We then\u0000demonstrate that J\"ager has low compute and bandwidth costs per call, and\u0000these costs scale linearly with call volume. J\"ager provides an efficient,\u0000secure, privacy-preserving system to revolutionize telephone abuse\u0000investigation with minimal costs to operators.","PeriodicalId":501280,"journal":{"name":"arXiv - CS - Networking and Internet Architecture","volume":"57 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142183739","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0