Chapter 09 · Sustainability & AISustainability & AI

Energy disaggregation

Meaning statusEstablishedSource recordDirect document linkedWhy these are different

Definition

Inferring the consumption of individual appliances from a building's aggregate meter signal, using signal processing or machine learning — also called non-intrusive load monitoring.

References

Proceedings of the IEEE 1992Hart — Nonintrusive appliance load monitoring

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

ACMNILMTK: An Open Source Toolkit for Non-intrusive Load Monitoring (2014)

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

Overview

What it means

The technique dates to Hart's foundational 1992 paper on non-intrusive appliance load monitoring, which showed that device 'signatures' could be separated from a single measurement point. Modern implementations apply machine learning to smart-meter data.

How it is used

Utilities and efficiency programmes use disaggregation to give households and facility managers appliance-level feedback without installing sub-meters, targeting the largest loads and verifying savings from retrofits and behaviour programmes.

Why it matters

Feedback is among the cheapest efficiency interventions, and disaggregation makes it scalable. It also raises the privacy side of the sustainability bargain: fine-grained consumption data reveals household behaviour, requiring careful governance.

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

Meaning status
Established
Verification date
Not recorded
Last updated
21 Aug 2026
What the classifications mean

Meaning status: Established

EstablishedCurrentMultiple definitionsContestedEmergingIndexed