2021 IEEE 4th 5G World Forum (5GWF)最新文献_第2页

A Taxonomy of Machine Learning Methodologies Used Against Physical Unclonable Functions 针对物理不可克隆函数的机器学习方法分类

2021 IEEE 4th 5G World Forum (5GWF) Pub Date : 2021-10-01 DOI: 10.1109/5GWF52925.2021.00043

Sean Donnelly, Liam Meany

引用次数: 0

An Ultra-Flexible Software Architecture Concept for 6G Core Networks 6G核心网超灵活软件架构概念

2021 IEEE 4th 5G World Forum (5GWF) Pub Date : 2021-10-01 DOI: 10.1109/5GWF52925.2021.00077

M. Corici, Eric Troudt, Pousali Chakraborty, T. Magedanz

引用次数: 11

Design of AoI-Aware 5G Uplink Scheduler Using Reinforcement Learning 基于强化学习的aoi感知5G上行调度设计

2021 IEEE 4th 5G World Forum (5GWF) Pub Date : 2021-10-01 DOI: 10.1109/5GWF52925.2021.00038

Chien-Cheng Wu, P. Popovski, Z. Tan, Č. Stefanović

引用次数: 3

NVIDIA Aerial GPU Hosted AI-on-5G NVIDIA空中GPU承载AI-on-5G

2021 IEEE 4th 5G World Forum (5GWF) Pub Date : 2021-10-01 DOI: 10.1109/5GWF52925.2021.00019

Anupa Kelkar, C. Dick

引用次数: 6

Method to Handle BWP Inactivity Timer to Reduce Latency and to Improve Throughput in 5G Devices 在5G设备中处理BWP非活动定时器以减少延迟和提高吞吐量的方法

2021 IEEE 4th 5G World Forum (5GWF) Pub Date : 2021-10-01 DOI: 10.1109/5GWF52925.2021.00062

Goutham Ponnamreddy, C. Dev, Pratibha Jiniwal

{"title":"Method to Handle BWP Inactivity Timer to Reduce Latency and to Improve Throughput in 5G Devices","authors":"Goutham Ponnamreddy, C. Dev, Pratibha Jiniwal","doi":"10.1109/5GWF52925.2021.00062","DOIUrl":"https://doi.org/10.1109/5GWF52925.2021.00062","url":null,"abstract":"Bandwidth Parts (BWPs) is a 5G New Radio (NR) Release 15 feature introduced for dynamically adapting the carrier bandwidth and numerology in which a User Equipment (UE) operates. In 4G/LTE, UEs support the maximum possible bandwidth of 20MHz. In 5G, the operating bandwidth can be as high as 800MHz per carrier. Each UE cannot support such a high bandwidth without high-power consumption. Therefore, a 5G UE has to communicate on a bandwidth smaller than the cell’s channel bandwidth. The smaller part is referred to as BWP. BWP enables higher spectrum flexibility with reduced baseband processing and power savings. BWP selection (or BWP switching) can be performed through several different methods. bwp-InactivityTimer is one of the methods or techniques to switch BWP. BWP switching is always associated with switch delay. Frequent BWP switching directly impacts latency and system throughput. In NR, new gap patterns with larger gap lengths of 40 ms and 66 ms features are implemented for accurate positioning measurements. The effect of bwp-InactivityTimer during larger measurement gaps and associated delays have not been studied and understood thoroughly for bursty traffic. Trade-offs must be carefully considered between energy efficiency and other performance aspects such as latency, throughput, and so on. In this paper, we propose an Efficient BWP Switch Method (EBSM) novel algorithm to handle bwp-InactivityTimer to reduce latency and thereby increase the system throughput during larger gap lengths configured for accurate positioning measurements. Simulation results show that the proposed EBSM algorithm is on average 29.8% more efficient in shortening latency and around 15-52% more efficient in avoiding unnecessary BWP switching in comparison with the specification-defined current legacy method.","PeriodicalId":226257,"journal":{"name":"2021 IEEE 4th 5G World Forum (5GWF)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125870837","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

A Survey of AI Enabled Edge Computing for Future Networks 面向未来网络的人工智能边缘计算研究

2021 IEEE 4th 5G World Forum (5GWF) Pub Date : 2021-10-01 DOI: 10.1109/5GWF52925.2021.00087

Prakash Ramachandran, Sunku Ranganath, Malini K. Bhandaru, Sujata Tibrewala

{"title":"A Survey of AI Enabled Edge Computing for Future Networks","authors":"Prakash Ramachandran, Sunku Ranganath, Malini K. Bhandaru, Sujata Tibrewala","doi":"10.1109/5GWF52925.2021.00087","DOIUrl":"https://doi.org/10.1109/5GWF52925.2021.00087","url":null,"abstract":"We have been talking about 5G and beyond (B5G) in IEEE future networks. The Exabyte of data moving from Cloud enabled edge to distributed edge has led to a push for local processing at the edge. We start with what is intelligence and how to distribute it in light of Edge resources. It started with a need for a nimble edge, essentially microdata centers to another extreme \"replace every O-RAN and BBUs with a Hyperscale DC\". We try to ascertain through this survey can Intelligent devices termed xPU (covering GPUs, FPGAs, SoCs and NVME and many more) provide functional baseline for lowering power consumption & performance, to support AI and ML to deliver edge native low latency & ultra-reliable functions beyond 5G as a better alternative? This is a survey of different industry parties to enable innovation and intelligent edge local processing, discovering challenges and trends to arrive at runtime baseline and abstractions. The survey covers the challenges of different evolving architectures x86, ARM, RISC-V with players like Intel, NVIDIA, Microsoft, IBM, Google & Amazon to name a few. The common theme turns out to be intelligent connected edge services on mini–Data Center as one option while the Edge focus to be Scalable, Secure, Reliable, Performant & Automated platform & Services. We have Reference, Glossary at the end for acronyms used.","PeriodicalId":226257,"journal":{"name":"2021 IEEE 4th 5G World Forum (5GWF)","volume":"46 2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125879044","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: 2

One Step Further: Tunable and Explainable Throughput Prediction based on Large-scale Commercial Networks 更进一步:基于大规模商业网络的可调可解释吞吐量预测

2021 IEEE 4th 5G World Forum (5GWF) Pub Date : 2021-10-01 DOI: 10.1109/5GWF52925.2021.00082

Roman Zhohov, Alexandros Palaios, Philipp Geuer

{"title":"One Step Further: Tunable and Explainable Throughput Prediction based on Large-scale Commercial Networks","authors":"Roman Zhohov, Alexandros Palaios, Philipp Geuer","doi":"10.1109/5GWF52925.2021.00082","DOIUrl":"https://doi.org/10.1109/5GWF52925.2021.00082","url":null,"abstract":"Throughput prediction remains a relevant and challenging problem in the area of wireless networking. Both users and service providers would benefit from the predictive Quality of Service (QoS) which has the potential to improve perceived service quality by users but also provide valuable insights for the network planning, optimization, and deployment. There are many factors that can hinder the adoption of Machine Learning (ML) models, such as the data collection overhead for the network operator, prediction uncertainties of an ML model and the lack of transparency in the ML inference process. In this paper, we provide results on the instantaneous throughput prediction using ML techniques. The data for the throughput prediction was collected in a live network of one of the biggest operators in Asia which improves confidence of the results. We also discuss how custom loss functions can extract value from prediction errors. Finally, we look at explainability methods providing more transparency on the predictions of ML algorithms. Various explainability methods prove that without being explicitly programmed, ML algorithms can exploit and learn from the underlying physical phenomena and operating principles of wireless networks.","PeriodicalId":226257,"journal":{"name":"2021 IEEE 4th 5G World Forum (5GWF)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130207146","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: 4

5G-IoT Architecture for Next Generation Smart Systems 下一代智能系统的5G-IoT架构

2021 IEEE 4th 5G World Forum (5GWF) Pub Date : 2021-10-01 DOI: 10.1109/5GWF52925.2021.00049

Snigdhaswin Kar, Prabodh Mishra, Kuang-Ching Wang

引用次数: 6

Utilizing Ground Nodes with Multi-Hop Capabilities to Extend the Range of UAV-BSs 利用具有多跳能力的地面节点扩展UAV-BSs的范围

2021 IEEE 4th 5G World Forum (5GWF) Pub Date : 2021-10-01 DOI: 10.1109/5GWF52925.2021.00029

Nadir H. Adam, C. Tapparello, W. Heinzelman, H. Yanikomeroglu

{"title":"Utilizing Ground Nodes with Multi-Hop Capabilities to Extend the Range of UAV-BSs","authors":"Nadir H. Adam, C. Tapparello, W. Heinzelman, H. Yanikomeroglu","doi":"10.1109/5GWF52925.2021.00029","DOIUrl":"https://doi.org/10.1109/5GWF52925.2021.00029","url":null,"abstract":"Due to recent technological advancements in the area of unmanned aerial systems, equipping an unmanned aerial vehicle (UAV) with a base station (BS) has been proposed to augment terrestrial base stations and to enhance the performance of 5G and beyond-5G networks. At the same time, advances in multi-hop ad hoc networks have made these networks feasible for supporting communications when fixed infrastructure is unavailable. In this paper, we examine the benefit of combining these two types of networks, utilizing multi-hop ad hoc networks to augment the coverage achievable by a UAV-BS. In particular, we explore the 3D placement problem for multiple UAV-BSs that maximize the number of covered ground nodes both with and without support of multi-hop ad hoc ground networks. First we present a mathematical formulation of the single UAV-BS placement problem, then we propose a heuristic algorithm that to the best of our knowledge is the first one in the literature to maximize the number of directly and indirectly covered ground nodes considering nodes with the same as well as with different quality of service (QoS) requirements. Simulation results show the merits of our proposed algorithm regarding utilizing the multi-hop capabilities of the ground nodes in terms of reducing the number of UAV-BSs required to cover the nodes compared to a benchmark algorithm that does not take into account the potential of covering nodes indirectly.","PeriodicalId":226257,"journal":{"name":"2021 IEEE 4th 5G World Forum (5GWF)","volume":"174 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126067366","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 a Threat Model and Privacy Analysis for V2P in 5G Networks 5G网络中V2P的威胁模型与隐私分析

2021 IEEE 4th 5G World Forum (5GWF) Pub Date : 2021-10-01 DOI: 10.1109/5GWF52925.2021.00074

Raiful Hasan, Ragib Hasan

引用次数: 4