Machine Learning for Smart Meter Data

A Structured Path from Meter Signal to Business Insight

A structured, project-based path through smart meter data: ML foundations, disaggregation, grid-edge value, and forecasting, from raw signal to business insight.
Author

Anthony Faustine

Published

July 24, 2026

A practical book for energy analytics and ML practitioners

Machine Learning for Smart Meter Data

From raw meter signal to business decision, through the ML foundations, disaggregation, and grid-edge value that make the closing forecast worth trusting, built to be run, not just read.

342Real households
16Appliance types
19Chapters live

By Anthony Faustine    

The book, in eight parts

Signal Foundations

ML Foundations

Part 1 · Signal Foundations

Reading a meter signal, general event and change detection, and feature-engineering concepts every later part reuses.

  • 01Reading a meter signalSoon

Chapters land after Part 8 ships.

Part 2 · ML Foundations

The mathematical and statistical theory behind every model this book uses as a tool: learning theory, optimization, tree ensembles, deep architectures, and the uncertainty-quantification foundations Part 8’s own forecasts depend on.

  • 01What is machine learning, preciselySoon

Chapters land after Part 8 ships.

Part 3 · Disaggregation

Non-intrusive load monitoring: from the aggregate signal to appliance-level insight.

Part 4 · LV Network and Topology Foundations

Modeling the low-voltage network, simulating DER time series on it, and identifying phase from smart-meter data alone, all with open-source power-flow simulation the rest of the book reuses.

Part 5 · Clustering

Theoretical foundations of clustering under DER, a settled methodology validated across three real utilities, then applying it to real customers across those utilities and to real feeders at scale.

Part 6 · Ranking and Recommendation

Retrieval, ranking, and case-based recommendation for LV management under DER, checked against real, OpenDSS-simulated per-customer outcomes.

Part 7 · Anomaly Detection

Voltage-violation and power-quality anomaly detection combining smart-meter data and LV topology, beyond what a single meter can see alone.

Part 8 · Forecasting

Household-scale load, PV, and EV forecastability and uncertainty, built on Twiga. The book’s closing part, feeding its own forecasts back into Part 4’s LV network model.

20 chapters shipped so far, each with a runnable notebook. Follow progress on GitHub.