Patent Application: Video Encoding Energy and Greenhouse Gas Emission Prediction

ChangeBridge: Patent Apps - Business Methods (G06Q)

Published September 24th, 2025

Detected March 26th, 2026

Summary

The USPTO has published a patent application (US20260087505A1) for techniques related to video encoding energy and greenhouse gas emission prediction. The application, filed by Bitmovin GmbH, details a system using machine learning to predict energy consumption and calculate emissions based on video complexity and carbon intensity data.

View original document View source feed page

What changed

This document is a patent application (US20260087505A1) filed with the USPTO by Bitmovin GmbH. It discloses techniques for predicting energy consumption and greenhouse gas emissions associated with video encoding. The proposed system utilizes a video analyzer, an energy predictor module with machine learning models (ensemble-based and linear regression), a carbon data source, and a carbon emissions calculator to estimate CO2 emissions based on predicted energy use and regional carbon intensity data, accounting for both fossil fuel and renewable energy sources.

As this is a patent application, it does not impose direct regulatory obligations or compliance deadlines on entities. However, it signals potential future technological developments and intellectual property in the area of sustainable video encoding. Companies involved in video encoding, cloud computing, and environmental impact assessment may wish to monitor this patent's progress and consider its implications for their operations and potential licensing requirements.

Source document (simplified)

← USPTO Patent Applications

Video Encoding Energy and Greenhouse Gas Emission Prediction

Application US20260087505A1 Kind: A1 Mar 26, 2026

Assignee

Bitmovin GmbH

Inventors

Christian Timmerer, Samira Afzal, Manuel Hoi, Armin Lachini, Farzad Tashtarian, Radu Prodan

Abstract

Techniques relating to video encoding energy and greenhouse gas emission prediction are disclosed. A system for video encoding energy and greenhouse gas emission prediction includes a video analyzer, an energy predictor module, a carbon data source, and a carbon emissions calculator. The system may be configured to carry out a method that includes extracting complexity features from a video segment, predicting energy consumption for video encoding the video segment on a cloud instance using a machine learning (ML) model, receiving carbon intensity data, cloud instance type data, and region (i.e., country or set of countries) data, and calculating greenhouse gas (e.g., CO2) emissions based on predicted energy consumption and carbon intensity data. Both fossil fuel and renewable energy sources may be accounted for, along with power imports and exports using a peer-reviewed flow-tracing methodology. The ML model may use one or both of ensemble-based and linear regression methods.