/Patent Tracker
GooglePatent applicationBatteries & energyInterest 3/10

Google patents method to tune grid energy models without sharing private data

This filing describes a way to improve how computers predict electricity usage on the power grid. It uses a two-step process where a local system adjusts a prediction model based on local data and sends only the adjustments back to a central server, rather than sending the raw usage data itself.

Why it mattersIt offers a technical approach to balancing accurate energy forecasting with user privacy, which is a growing concern for smart grid systems.

In the filing’s own words

Methods, systems, and apparatus, including medium-encoded computer program products, for configuring location-specific electrical load models while preserving privacy. A first machine learning model configured to predict electrical load curves of an electrical utility grid can be obtained from a server. Load values associated with a particular region of the electrical utility grid can be obtained. The load values can be applied as calibration input to the first machine learning model to produce first adjustment parameters for the first machine learning model. The first adjustment parameters can be provided to the server.

What exactly they claim (claim 1)

1. (canceled)

Facts

Company
Google (X Development LLC)
Official title
PRIVACY-PRESERVING CONFIGURATION OF LOCATION-SPECIFIC ELECTRICAL LOAD MODELS
Publication number
US20260291277A1
Application number
19440261
Filed
Jan 5, 2026
Published
Sep 24, 2026
Inventors
4
Claims
21

Classified under

H02J 13/12 Electricity & electronicsG05B 13/0265 Physics & computingG05B 13/042 Physics & computingH02J 2103/30 Electricity & electronics

More from Google in Batteries & energy

Summaries are simplified from the filing’s own abstract and first claim. A patent filing is not a product announcement.
Patent data and drawings: U.S. Patent and Trademark Office (USPTO). Nebula is not affiliated with or endorsed by the USPTO.