Energy-Efficient Classification at the Wireless Edge with Reliability Guarantees

TL;DR

This paper introduces an adaptive algorithm for energy-efficient classification at the wireless edge, balancing energy consumption, delay, and reliability without prior statistical knowledge.

Contribution

It presents a novel dynamic resource allocation method that optimizes classification performance and energy use in real-time without needing prior data statistics.

Findings

Reduces end devices' energy consumption while maintaining delay and reliability constraints.

Effective in real-time adaptive resource management for edge classification tasks.

Demonstrates superior trade-offs between energy, delay, and accuracy in CNN-based image classification.

Abstract

Learning at the edge is a challenging task from several perspectives, since data must be collected by end devices (e.g. sensors), possibly pre-processed (e.g. data compression), and finally processed remotely to output the result of training and/or inference phases. This involves heterogeneous resources, such as radio, computing and learning related parameters. In this context, we propose an algorithm that dynamically selects data encoding scheme, local computing resources, uplink radio parameters, and remote computing resources, to perform a classification task with the minimum average end devices' energy consumption, under E2E delay and inference reliability constraints. Our method does not assume any prior knowledge of the statistics of time varying context parameters, while it only requires the solution of low complexity per-slot deterministic optimization problems, based on instantaneous observations of these parameters and that of properly defined state variables. Numerical results on convolutional neural network based image classification illustrate the effectiveness of our method in striking the best trade-off between energy, delay and inference reliability.