• 文献检索
  • 文档翻译
  • 深度研究
  • 学术资讯
  • Suppr Zotero 插件Zotero 插件
  • 邀请有礼
  • 套餐&价格
  • 历史记录
应用&插件
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
定价
高级版会员购买积分包购买API积分包
服务
文献检索文档翻译深度研究API 文档MCP 服务
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利：CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2026

文献检索

告别复杂PubMed语法，用中文像聊天一样搜索，搜遍4000万医学文献。AI智能推荐，让科研检索更轻松。

立即免费搜索

文件翻译

保留排版，准确专业，支持PDF/Word/PPT等文件格式，支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述，25分钟生成高质量综述，智能提取关键信息，辅助科研写作。

立即免费体验

通过深度学习和软件定义网络管理具有多连接性的设备的能源消耗

Managing Energy Consumption of Devices with Multiconnectivity by Deep Learning and Software-Defined Networking.

作者信息

Shams Ramiza, Abdrabou Atef, Al Bataineh Mohammad, Noordin Kamarul Ariffin

机构信息

Department of Electrical and Communication Engineering, College of Engineering, United Arab Emirates University, Al-Ain P.O. Box 15551, Abu Dhabi, United Arab Emirates.

Telecommunications Engineering Department, Yarmouk University, Irbid 21163, Jordan.

出版信息

Sensors (Basel). 2023 Sep 6;23(18):7699. doi: 10.3390/s23187699.

DOI:10.3390/s23187699
PMID:37765757
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC10535206/
Abstract

Multiconnectivity allows user equipment/devices to connect to multiple radio access technologies simultaneously, including 5G, 4G (LTE), and WiFi. It is a necessity in meeting the increasing demand for mobile network services for the 5G and beyond wireless networks, while ensuring that mobile operators can still reap the benefits of their present investments. Multipath TCP (MPTCP) has been introduced to allow uninterrupted reliable data transmission over multiconnectivity links. However, energy consumption is a significant issue for multihomed wireless devices since most of them are battery-powered. This paper employs software-defined networking (SDN) and deep neural networks (DNNs) to manage the energy consumption of devices with multiconnectivity running MPTCP. The proposed method involves two lightweight algorithms implemented on an SDN controller, using a real hardware testbed of dual-homed wireless nodes connected to WiFi and cellular networks. The first algorithm determines whether a node should connect to a specific network or both networks. The second algorithm improves the selection made by the first by using a DNN trained on different scenarios, such as various network sizes and MPTCP congestion control algorithms. The results of our extensive experimentation show that this approach effectively reduces energy consumption while providing better network throughput performance compared to using single-path TCP or MPTCP Cubic or BALIA for all nodes.

摘要

多连接允许用户设备同时连接到多种无线接入技术，包括5G、4G（LTE）和WiFi。这对于满足5G及以后无线网络对移动网络服务日益增长的需求是必要的，同时确保移动运营商仍能从其现有投资中获益。多路径TCP（MPTCP）已被引入，以允许在多连接链路上进行不间断的可靠数据传输。然而，能耗对于多归属无线设备来说是一个重要问题，因为它们中的大多数由电池供电。本文采用软件定义网络（SDN）和深度神经网络（DNN）来管理运行MPTCP的多连接设备的能耗。所提出的方法涉及在SDN控制器上实现的两种轻量级算法，使用连接到WiFi和蜂窝网络的双归属无线节点的真实硬件测试平台。第一种算法确定节点是应连接到特定网络还是两个网络。第二种算法通过使用在不同场景（如各种网络规模和MPTCP拥塞控制算法）上训练的DNN来改进第一种算法所做的选择。我们广泛实验的结果表明，与对所有节点使用单路径TCP或MPTCP Cubic或BALIA相比，这种方法在有效降低能耗的同时提供了更好的网络吞吐量性能。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7fd2/10535206/a734e6770849/sensors-23-07699-g015.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7fd2/10535206/57842fb28cf9/sensors-23-07699-g001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7fd2/10535206/54bea91f3f91/sensors-23-07699-g002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7fd2/10535206/a93da2f8ae5e/sensors-23-07699-g003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7fd2/10535206/5e4c95705c74/sensors-23-07699-g004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7fd2/10535206/da47a24c3ed1/sensors-23-07699-g005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7fd2/10535206/680583a185dc/sensors-23-07699-g006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7fd2/10535206/1b3b692260fc/sensors-23-07699-g007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7fd2/10535206/ebf3f32d1fd2/sensors-23-07699-g008.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7fd2/10535206/2859921689cf/sensors-23-07699-g009.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7fd2/10535206/164c6c3e6fc5/sensors-23-07699-g010.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7fd2/10535206/afb5d2d1de99/sensors-23-07699-g011.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7fd2/10535206/979e6c828803/sensors-23-07699-g012.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7fd2/10535206/5905d03a492e/sensors-23-07699-g013.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7fd2/10535206/a166d256334f/sensors-23-07699-g014.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7fd2/10535206/a734e6770849/sensors-23-07699-g015.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7fd2/10535206/57842fb28cf9/sensors-23-07699-g001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7fd2/10535206/54bea91f3f91/sensors-23-07699-g002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7fd2/10535206/a93da2f8ae5e/sensors-23-07699-g003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7fd2/10535206/5e4c95705c74/sensors-23-07699-g004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7fd2/10535206/da47a24c3ed1/sensors-23-07699-g005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7fd2/10535206/680583a185dc/sensors-23-07699-g006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7fd2/10535206/1b3b692260fc/sensors-23-07699-g007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7fd2/10535206/ebf3f32d1fd2/sensors-23-07699-g008.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7fd2/10535206/2859921689cf/sensors-23-07699-g009.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7fd2/10535206/164c6c3e6fc5/sensors-23-07699-g010.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7fd2/10535206/afb5d2d1de99/sensors-23-07699-g011.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7fd2/10535206/979e6c828803/sensors-23-07699-g012.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7fd2/10535206/5905d03a492e/sensors-23-07699-g013.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7fd2/10535206/a166d256334f/sensors-23-07699-g014.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7fd2/10535206/a734e6770849/sensors-23-07699-g015.jpg

相似文献

1
Managing Energy Consumption of Devices with Multiconnectivity by Deep Learning and Software-Defined Networking.通过深度学习和软件定义网络管理具有多连接性的设备的能源消耗
Sensors (Basel). 2023 Sep 6;23(18):7699. doi: 10.3390/s23187699.
2
Performance Evaluation of MPTCP on Simultaneous Use of 5G and 4G Networks.MPTCP 在 5G 和 4G 网络同时使用中的性能评估。
Sensors (Basel). 2022 Oct 3;22(19):7509. doi: 10.3390/s22197509.
3
On the Fidelity of NS-3 Simulations of Wireless Multipath TCP Connections.关于无线多路径TCP连接的NS-3模拟的保真度
Sensors (Basel). 2020 Dec 18;20(24):7289. doi: 10.3390/s20247289.
4
An Approach to Reinforce Multipath TCP with Path-Aware Information.利用路径感知信息增强多路径 TCP 的方法。
Sensors (Basel). 2019 Jan 24;19(3):476. doi: 10.3390/s19030476.
5
Multipath TCP-Based IoT Communication Evaluation: From the Perspective of Multipath Management with Machine Learning.基于多路径TCP的物联网通信评估：从机器学习多路径管理的视角
Sensors (Basel). 2020 Nov 18;20(22):6573. doi: 10.3390/s20226573.
6
Combining 5G New Radio, Wi-Fi, and LiFi for Industry 4.0: Performance Evaluation.将5G新无线电、Wi-Fi和LiFi结合用于工业4.0：性能评估
Sensors (Basel). 2024 Sep 18;24(18):6022. doi: 10.3390/s24186022.
7
BA-MPCUBIC: Bottleneck-Aware Multipath CUBIC for Multipath-TCP.瓶颈感知多路径 CUBIC 算法（BA-MPCUBIC）：一种用于多路径 TCP 的算法。
Sensors (Basel). 2021 Sep 19;21(18):6289. doi: 10.3390/s21186289.
8
Research on the control strategies of data flow transmission paths for MPTCP-based communication networks.基于多路径传输控制协议（MPTCP）的通信网络数据流传输路径控制策略研究
PeerJ Comput Sci. 2023 Dec 6;9:e1716. doi: 10.7717/peerj-cs.1716. eCollection 2023.
9
Solving the multicommodity flow problem using an evolutionary routing algorithm in a computer network environment.在计算机网络环境中使用进化路由算法解决多商品流问题。
PLoS One. 2023 Apr 19;18(4):e0278317. doi: 10.1371/journal.pone.0278317. eCollection 2023.
10
An implementation and evaluation of MPTCP-based IoT router.基于多路径传输控制协议（MPTCP）的物联网路由器的实现与评估
Multimed Tools Appl. 2023 Mar 3:1-16. doi: 10.1007/s11042-023-14781-8.