Optimized Power Control for Multi-User Integrated Sensing and Edge AI

TL;DR

This paper develops optimal power control strategies for multi-user integrated sensing and edge AI systems, balancing AirComp accuracy and inference quality through novel proxies and closed-form solutions.

Contribution

It introduces two proxies for AirComp error and inference performance, deriving closed-form power allocation schemes for TDM and FDM settings.

Findings

Optimal power allocation schemes are derived for TDM and FDM.

Proxies effectively characterize the relationship between AirComp error and inference performance.

Experimental results validate the theoretical power control strategies.

Abstract

This work investigates an integrated sensing and edge artificial intelligence (ISEA) system, where multiple devices first transmit probing signals for target sensing and then offload locally extracted features to the access point (AP) via analog over-the-air computation (AirComp) for collaborative inference. To characterize the relationship between AirComp error and inference performance, two proxies are established: the \emph{computation-optimal} proxy that minimizes the aggregation distortion, and the \emph{decision-optimal} proxy that maximizes the inter-class separability, respectively. Optimal transceiver designs in terms of closed-form power allocation are derived for both time-division multiplexing (TDM) and frequency-division multiplexing (FDM) settings, revealing threshold-based and dual-decomposition structures, respectively. Experimental results validate the theoretical findings.