arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2206.10784eess.SP
收藏

基于Chirp的空中计算用于远程联邦边缘学习

Chirp-Based Over-the-Air Computation for Long-Range Federated Edge Learning

Safi Shams Muhtasimul Hoque, Mohammad Hassan Adeli, Alphan Sahin

摘要:

在这项研究中,我们提出了基于循环移位线性调频(CSC)的多数表决(MV)(CSC-MV),一种节能的空中计算(OAC)方案,以实现远程联邦边缘学习(FEEL)。所提出的方法映射投票(即,局部梯度的符号)到用离散傅里叶变换-扩展正交频分复用(DFT-s-OFDM)发射机构造的线性CSC。在边缘服务器(ES)处,使用能量检测器来计算MV。我们比较我们提出的方案与一位宽带数字聚合(OBDA),并表明,输出功率回退(OBO)的发射机与相邻信道泄漏比(ACLR)约束CSC-MV的要求是低于一个与OBDA。例如,在ACLR约束为-22 dB的情况下,CSC-MV可以具有比OBDA低6-7 dB的OBO要求。当功率放大器(PA)的非线性被认为是,我们表明,CSC-MV优于OBDA的测试精度方面的同质和异构的数据分布,而不使用信道状态信息(CSI)在ES和ED。

英文摘要:

In this study, we propose circularly-shifted chirp (CSC)-based majority vote (MV) (CSC-MV), a power-efficient over-the-air computation (OAC) scheme, to achieve long-range federated edge learning (FEEL). The proposed approach maps the votes (i.e., the sign of the local gradients) from the edge devices (EDs) to the linear CSCs constructed with a discrete Fourier transform-spread orthogonal frequency division multiplexing (DFT-s-OFDM) transmitter. At the edge server (ES), the MV is calculated with an energy detector. We compare our proposed scheme with one-bit broadband digital aggregation (OBDA) and show that the output-power back-off (OBO) requirement of the transmitters with an adjacent-channel-leakage ratio (ACLR) constraint for CSC-MV is lower than the one with OBDA. For example, with an ACLR constraint of -22 dB, CSC-MV can have an OBO requirement of 6-7 dB less than the one with OBDA. When the power amplifier (PA) non-linearity is considered, we demonstrate that CSC-MV outperforms OBDA in terms of test accuracy for both homogeneous and heterogeneous data distributions, without using channel state information (CSI) at the ES and EDs.

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。

↑