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

TL;DR

This paper introduces a power-efficient chirp-based over-the-air computation scheme for long-range federated edge learning, improving energy efficiency and accuracy without requiring channel state information.

Contribution

It proposes a novel circularly-shifted chirp scheme for over-the-air computation that reduces power back-off and enhances test accuracy in federated learning.

Findings

Lower output-power back-off requirement compared to OBDA.

Outperforms OBDA in test accuracy under PA non-linearity.

No need for channel state information at devices or server.

Abstract

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.