arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2201.08270cs.LGcs.DCcs.NI
收藏

面向6 G网络的节能分布式联邦学习

Towards Energy Efficient Distributed Federated Learning for 6G Networks

University of Sindh, Jamshoro(信德大学);Korea Polytechnic University(韩国理工大学);University of Johannesburg(约翰内斯堡大学);University of Bologna(博洛尼亚大学)

Sunder Ali Khowaja, Kapal Dev, Parus Khuwaja, Paolo Bellavista

摘要:

通过便携式和移动设备(如空中基站)提供通信服务是5G/6 G网络中要实现的关键概念。传统上,物联网/边缘设备需要将数据直接传输到基站,以便使用机器学习技术训练模型。数据传输引入了可能导致安全问题和金钱损失的隐私问题。最近,联邦学习被提出来通过与基站的模型共享来部分地解决隐私问题。然而,联邦学习的集中式本质仅允许基站附近的设备共享训练模型。此外,长距离通信迫使设备增加传输功率,这引起了能量效率问题。在这项工作中,我们提出了分布式联邦学习(DBFL)框架,克服了连接和能源效率的问题,为远程设备。DBFL框架与移动边缘计算架构兼容,该架构使用集群协议以分布式方式连接设备。实验结果表明,与传统的联邦学习相比,该框架在降低能耗的同时,分类性能提高了7.4%.

英文摘要:

The provision of communication services via portable and mobile devices, such as aerial base stations, is a crucial concept to be realized in 5G/6G networks. Conventionally, IoT/edge devices need to transmit the data directly to the base station for training the model using machine learning techniques. The data transmission introduces privacy issues that might lead to security concerns and monetary losses. Recently, Federated learning was proposed to partially solve privacy issues via model-sharing with base station. However, the centralized nature of federated learning only allow the devices within the vicinity of base stations to share the trained models. Furthermore, the long-range communication compels the devices to increase transmission power, which raises the energy efficiency concerns. In this work, we propose distributed federated learning (DBFL) framework that overcomes the connectivity and energy efficiency issues for distant devices. The DBFL framework is compatible with mobile edge computing architecture that connects the devices in a distributed manner using clustering protocols. Experimental results show that the framework increases the classification performance by 7.4\% in comparison to conventional federated learning while reducing the energy consumption.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑