Over-the-Air Federated Edge Learning with Integrated Sensing, Communication, and Computation

Dingzhu Wen1; Sijing Xie1; Xiaowen Cao2; Yuanhao Cui3; Weijie Yuan3; Zhaohui Yang4; Jie Xu5; Yuanming Shi1; Shuguang Cui5

10.1109/ICCC62479.2024.10681942

2024-08-09

2377-8644

979-8-3503-7842-9

2024 IEEE/CIC International Conference on Communications in China (ICCC)

7-9 Aug. 2024

Hangzhou, China

This paper studies an over-the-air federated edge learning (Air-FEEL) system with integrated sensing, communication, and computation (ISCC), in which one edge server coordinates multiple edge devices to wirelessly sense the objects and use the sensing data to collaboratively train a machine learning model for conducting tasks like human motion recognition. In this system, over-the-air computation (AirComp) is employed for edge devices to efficiently aggregate their local models. Under this setup, we analyze the convergence of the ISCC-enabled Air-FEEL, by particularly taking into account the wireless sensing noise and AirComp distortions. It is shown that a higher convergence rate is achieved with higher sensing and AirComp signal-to-noise ratios (SNRs), and a larger sum batch size of all devices. Particularly, a larger sum batch size can enhance the benefit of high sensing SNR as well as suppressing the stochastic gradient variance. Based on the convergence analysis, we design the ISCC parameters via jointly optimizing batch size control and resource allocation to maximize the loss function degradation while ensuring the latency in each round. Experimental simulations are conducted based on human motion recognition to evaluate the performance.

其他

1.School of Information Science and Technology, ShanghaiTech University, Shanghai, China
2.Shenzhen University, Shenzhen, China
3.Southern University of Science and Technology, Shenzhen, China
4.College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou, China
5.SSE and FNii, The Chinese University of Hong Kong (Shenzhen), Shenzhen, China

Dingzhu Wen,Sijing Xie,Xiaowen Cao,et al. Over-the-Air Federated Edge Learning with Integrated Sensing, Communication, and Computation[C],2024.