Sustainability & AI

Edge AI

Running AI models on local devices rather than in data centres, reducing data transmission and enabling low-power monitoring.

Established · Editorial draft · Last reviewed 21 Aug 2026

Definition

The deployment of AI models directly on local devices — sensors, cameras, phones, microcontrollers — rather than in centralised data centres.

Quick reference

At a glance

Subject
Sustainability & AI
Editorial status
Editorial draft
Definition status
Established
Last updated
21 August 2026
Also known as
edge computing AI · on-device AI

References

tinyML FoundationtinyML community and foundation

This source provides part of the technical or institutional basis for the definition.

AISTATS 2017 / arXivMcMahan et al. — Communication-Efficient Learning from Decentralized Data

This source supports the explanation of how the term is applied, measured or governed in practice.

Overview

What it means

Running inference at the edge reduces the need to transmit raw data, cuts latency and allows systems to work where connectivity is poor or power is scarce. It relies on compact, efficient models; quantisation and distillation are typical enablers.

How it is used

Edge AI suits distributed environmental monitoring: acoustic sensors identifying species in forests, camera traps filtering images on-device, smart meters analysing consumption locally, and buoys or field stations operating off-grid.

Why it matters

Conservation and agriculture often happen far from reliable networks and power. Edge AI extends automated observation into exactly those places — while its efficiency constraints align with the frugal-AI agenda of doing more with less compute.

Review

Help keep this definition useful and accurate.

0
No editor-accepted reviews yet

Submitted reviews stay private until an editor decides whether to accept and attribute them.

Endorse this definition

Confirm what works

Endorse the current wording when it is accurate and useful. Suggested changes use the separate editorial form below.

Have evidence, context, or a correction to share? Every suggestion is considered by an editor before publication.

Classification
Established
Review stage
Editorial draft
What the classifications mean

This term is classified as Established

EstablishedCurrentMultiple definitionsContestedEmergingIndexed