2020 IEEE 17th Annual Consumer Communications & Networking Conference (CCNC)最新文献_第6页

Training Task Allocation in Federated Edge Learning: A Matching-Theoretic Approach 联邦边缘学习中的训练任务分配:一种匹配理论方法

2020 IEEE 17th Annual Consumer Communications & Networking Conference (CCNC) Pub Date : 2020-01-01 DOI: 10.1109/CCNC46108.2020.9045112

Jiawen Kang, Zehui Xiong, D. Niyato, Zhiguang Cao, Amir Leshem

{"title":"Training Task Allocation in Federated Edge Learning: A Matching-Theoretic Approach","authors":"Jiawen Kang, Zehui Xiong, D. Niyato, Zhiguang Cao, Amir Leshem","doi":"10.1109/CCNC46108.2020.9045112","DOIUrl":"https://doi.org/10.1109/CCNC46108.2020.9045112","url":null,"abstract":"Federated edge learning has emerged as a promising technique to enable distributed machine learning using local datasets from large-scale edge devices, e.g., mobile phones or parked vehicles, that share only model updates without uploading raw training data. This technique not only preserves data privacy of edge devices but also simultaneously ensures high learning performance. However, the emerging federated edge learning still confronts serious challenges, such as the lack of efficient training task assignment schemes with reliable edge devices acting as workers. To address this challenge, we utilize a many-to-one matching model to solve the training task assignment problem between the workers and multiple task publishers. In the matching model, we minimize not only the overall training time of the task publishers but also the energy consumption of the workers. To define against malicious model updates from unreliable workers, we present reputation as a metric to evaluate the reliability and trustworthiness of the edge devices, and also take the reputation into consideration when assigning training tasks. The numerical results indicate that the proposed schemes can efficiently improve the performance of federated edge learning.","PeriodicalId":443862,"journal":{"name":"2020 IEEE 17th Annual Consumer Communications & Networking Conference (CCNC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130134174","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: 8

An Energy-Efficient Collaborative Scheme for UAVs and VANETs for Dissemination of Real-Time Surveillance Data on Highways 高速公路实时监控数据分发的无人机和vanet节能协同方案

2020 IEEE 17th Annual Consumer Communications & Networking Conference (CCNC) Pub Date : 2020-01-01 DOI: 10.1109/CCNC46108.2020.9045425

Nouman Bashir, S. Boudjit

{"title":"An Energy-Efficient Collaborative Scheme for UAVs and VANETs for Dissemination of Real-Time Surveillance Data on Highways","authors":"Nouman Bashir, S. Boudjit","doi":"10.1109/CCNC46108.2020.9045425","DOIUrl":"https://doi.org/10.1109/CCNC46108.2020.9045425","url":null,"abstract":"In addition to military applications, Unmanned Aerial Vehicles (UAVs) are now finding their ways in civilian and public domains. Surveillance of highways with the use of a helicopter is a costly option that could be replaced with a more economical option of UAVs. Unlike MANETs in general and VANETs in particular, UAV networks have unique characteristics due to the association of factors like dynamic topology, high mobility, and limited energy. Keeping in view the real-time aspect of road surveillance, the use of UAVs with the existing routing protocols is not a straight forward option. A fleet of drones en route to surveillance on the highways may face frequent link failures due to its dynamical sparse linear architecture. To compensate for the sparse topology, a collaboration of UAVs with VANETs might be a good choice but as such integration of the two networks could create too much overhead. In this article, a proactive energy-efficient and reliable Collaborative scheme between UAVs and VANETs, termed as CUV, is presented. To avoid flooding in the entire network, Base station Association Messages (BAM), in a unicast manner, are forwarded till the end-nodes. Although BAM is received by each node which ensures connectivity with the BS but only certain nodes are allowed to retransmit. Furthermore, to take care of the loss of BAM messages due to the presence of hidden nodes, a novel mechanism for link repair inside a BAM interval is introduced. The proposed scheme is simulated in Network-Simulator-2 and compared with the well known proactive OLSR and reactive AODV protocols.","PeriodicalId":443862,"journal":{"name":"2020 IEEE 17th Annual Consumer Communications & Networking Conference (CCNC)","volume":"80 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121164240","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: 6

Multi-AP Multi-Link Aggregation for High Data Rate Real-Time Applications 用于高数据速率实时应用的多ap多链路聚合

2020 IEEE 17th Annual Consumer Communications & Networking Conference (CCNC) Pub Date : 2020-01-01 DOI: 10.1109/CCNC46108.2020.9045205

Yoshihisa Kondo, H. Yomo, H. Yokoyama

引用次数: 1

Performance Evaluation of Machine Learning Based Channel Selection Algorithm Implemented on IoT Sensor Devices in Coexisting IoT Networks 共存物联网网络中基于机器学习的物联网传感器设备信道选择算法性能评价

2020 IEEE 17th Annual Consumer Communications & Networking Conference (CCNC) Pub Date : 2020-01-01 DOI: 10.1109/CCNC46108.2020.9045712

So Hasegawa, Song-Ju Kim, Y. Shoji, M. Hasegawa

引用次数: 6

Fast Reroute in Hybrid Segment Routing Network 混合网段路由网络中的快速重路由

2020 IEEE 17th Annual Consumer Communications & Networking Conference (CCNC) Pub Date : 2020-01-01 DOI: 10.1109/CCNC46108.2020.9045129

Xiaoqian Li, K. Yeung

引用次数: 2

Blockchain-based Mobility Verification of Connected Cars 基于区块链的互联汽车移动性验证

2020 IEEE 17th Annual Consumer Communications & Networking Conference (CCNC) Pub Date : 2020-01-01 DOI: 10.1109/CCNC46108.2020.9045104

C. Chiasserini, Paolo Giaccone, Giovanni Malnati, Michele Macagno, G. Sviridov

引用次数: 4

Distributed Wireless Network Optimization With Stochastic Local Search 基于随机局部搜索的分布式无线网络优化

2020 IEEE 17th Annual Consumer Communications & Networking Conference (CCNC) Pub Date : 2020-01-01 DOI: 10.1109/CCNC46108.2020.9045189

T. Lee, Georgios Exarchakos, S. Groot

引用次数: 0

Co-simulation of an electrical distribution network and its supervision communication network 配电网与监控通信网络的联合仿真

2020 IEEE 17th Annual Consumer Communications & Networking Conference (CCNC) Pub Date : 2020-01-01 DOI: 10.1109/CCNC46108.2020.9045183

Benjamin Camus, A. Blavette, Anne-Cécile Orgerie, Jean-Baptiste Blanc-Rouchossé

引用次数: 1

A Sequential WLAN Channel Selection Adaptive to Factors Outside the System 自适应系统外部因素的连续无线局域网信道选择

2020 IEEE 17th Annual Consumer Communications & Networking Conference (CCNC) Pub Date : 2020-01-01 DOI: 10.1109/CCNC46108.2020.9045313

K. Ohtsu, Shotaro Kamiya, Koji Yamamoto, T. Nishio, M. Morikura, Noriyasu Kato

引用次数: 0

Evaluation of CSL-based Low Power MAC Protocol for Wireless Smart Metering Networks 基于csl的无线智能计量网络低功耗MAC协议评估

2020 IEEE 17th Annual Consumer Communications & Networking Conference (CCNC) Pub Date : 2020-01-01 DOI: 10.1109/CCNC46108.2020.9045549

Kai Samejima, Ryota Okumura, K. Mizutani, H. Harada

{"title":"Evaluation of CSL-based Low Power MAC Protocol for Wireless Smart Metering Networks","authors":"Kai Samejima, Ryota Okumura, K. Mizutani, H. Harada","doi":"10.1109/CCNC46108.2020.9045549","DOIUrl":"https://doi.org/10.1109/CCNC46108.2020.9045549","url":null,"abstract":"The wireless smart utility network (Wi-SUN) gets attention as one of the promising wireless networks for the machine-to-machine (M2M) and Internet of Things (IoT) systems. The resource-limited monitoring and management (RLMM) is a profile of the Wi-SUN for the non-Internet protocol (non-IP)-based networks in resource-poor environments. The coordinated sampled listening (CSL) is one of the IEEE 802.15.4e-based low-power media access control (MAC) protocols, and it is a candidate protocol for the RLMM systems. To construct the CSL-based RLMM systems in a variable environment, the communication characteristics should be evaluated theoretically and experimentally. In this paper, we designed a practical CSL protocol for the implementation, and a theoretical analysis scheme to evaluate communication characteristics of the practical CSL is proposed considering with the effect of Acknowledgement (ACK) frames. Furthermore, the practical CSL protocol is demonstrated experimentally using 30 actual Wi-SUN dongles in a radio anechoic chamber. The proposed theoretical analysis results agree well with not only computer simulation results but also experimental results. It means that the proposed theoretical analysis scheme has high practicality and reliability under actual environments. The experimental and theoretical results show that a high communication success rate of over 90 % can be achieved when the data generation rate is lower than 5.0 × 10−3s−1.","PeriodicalId":443862,"journal":{"name":"2020 IEEE 17th Annual Consumer Communications & Networking Conference (CCNC)","volume":"411 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123048072","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: 3