基于6G In-X子网络的联邦学习自适应传感器
首发时间:2023-03-13
摘要:6G 时代,拥有数据和计算资源的各类终端设备可以通过联邦学习(Federated Learning, FL)进行协作,以实现泛在智能。然而,在任何这些\'X\'(即实体)设备内部,将训练数据从 机载传感器无线上传到嵌入式接入点(Access Point,AP)的 6G in-X 子网络可能成为FL过程 中的通信瓶颈。为了支持 in-X 子网的通信效率,本文提出了一种自适应传感器调度算法,该 算法基于李亚普诺夫优化和最大比率调度方法,共同解决了队列稳定性问题和信息年龄(Age of Information,AoI)优化问题。仿真实验结果表明,所提出的算法实现了更高的联邦学习精 度,同时保证了 AP 的队列稳定性和更好的数据新鲜度(质量),以便通过 in-X 子网进行数据上传。
For information in English, please click here
Adaptive Sensor Scheduling for Federated Learning over 6G In-X Subnetworks
Abstract:In the upcoming 6G era, various end devices with data and computing resources can collaborate through federated learning (FL) to achieve the goal of ubiquitous intelligence. Inside any of those \'X\' (i.e. everything) devices, however, a 6G in-X subnetwork that wire lessly uploads training data from onboard sensors to an embedded access point (AP) may be come a communication bottleneck during the process of FL. To support communication-efficient FL over in-X subnetworks, this paper proposes an adaptive sensor scheduling algorithm that jointly solves a queue stability problem and an age of information (AoI) optimization problem, based on Lyapunov optimization and Max-Ratio scheduling methods. Our simulations show that the proposed algorithm achieves higher FL accuracy, while guaranteeing queue stability at APs and better data freshness (quality) for data uploading over in-X subnetworks.
Keywords: Federated Learning AoI in-X subnetwork Sensor Scheduling
引用
No.****
同行评议
共计0人参与
勘误表
基于6G In-X子网络的联邦学习自适应传感器
评论
全部评论