To Compute or not to Compute? Adaptive Smart Sensing in Resource-Constrained Edge Computing

TL;DR

This paper introduces an adaptive sensing framework for resource-constrained edge networks, balancing latency and accuracy through reinforcement learning to optimize sensor data transmission and processing.

Contribution

It presents an estimation-theoretic optimization model incorporating latency and proposes a reinforcement learning method for dynamic resource allocation at sensors.

Findings

Reinforcement learning improves sensor data transmission decisions.

Sensor selection enhances monitoring performance under resource constraints.

The approach is validated in scenarios like drones and autonomous vehicles.

Abstract

We consider a network of smart sensors for an edge computing application that sample a time-varying signal and send updates to a base station for remote global monitoring. Sensors are equipped with sensing and compute, and can either send raw data or process them on-board before transmission. Limited hardware resources at the edge generate a fundamental latency-accuracy trade-off: raw measurements are inaccurate but timely, whereas accurate processed updates are available after processing delay. Hence, one needs to decide when sensors should transmit raw measurements or rely on local processing to maximize network monitoring performance. To tackle this sensing design problem, we model an estimation-theoretic optimization framework that embeds both computation and communication latency, and propose a Reinforcement Learning-based approach that dynamically allocates computational resources at each sensor. Effectiveness of our proposed approach is validated through numerical experiments motivated by smart sensing for the Internet of Drones and self-driving vehicles. In particular, we show that, under constrained computation at the base station, monitoring performance can be further improved by an online sensor selection.