---
title: 'Google and Google DeepMind: ML-recommended hourly wind-energy delivery commitments'
slug: google-wind-commitment-optimization
stable_id: 63b51d1a931c9f58
company: Google and Google DeepMind
function_code: logistics
pattern_codes:
  - continuous_decisioning
  - step_before_decision
evidence_strength: mixed
publication_tier: showcase
freshness: current
reviewed_at: '2026-08-23'
updated_at: '2026-08-22'
source_quality_summary: 1 independent, 1 primary; publication outcomes are verified and reported.
caveat_summary: >-
  Google-reported value metric; monetary definition, forecast error distribution, and
  independent audit were not published.
collections: []
bundle_version: 1.0.0
bundle_fingerprint: sha256:c23c6cc2b88153d008ea8fda928f632ce0011fc2d4c5036672a16e5d895bab93
canonical_url: https://brianletort.ai/transformations/google-wind-commitment-optimization
---

# Google and Google DeepMind: ML-recommended hourly wind-energy delivery commitments

That variable wind generation cannot be committed to the grid on a useful day-ahead schedule.

Function: Logistics. Patterns: Continuous decisioning; AI prepares, human decides. Evidence: mixed.

Freshness: current. Reviewed: 2026-08-23. Updated: 2026-08-22.


Source quality: 1 independent, 1 primary; publication outcomes are verified and reported.

## Before

1. **Wind operator** — Estimate uncertain output without the ML forecast and avoid firm hourly commitments. (control: No time-based commitment baseline)
2. **Grid** — Treat wind as less schedulable and therefore less valuable. (control: Grid balancing rules)

## After

1. **Neural forecasting model** — Predicts wind output 36 hours ahead from weather forecasts and turbine history. (control: Forecast uncertainty)
2. **Optimization system and operator** — Recommend and submit hourly delivery commitments a day ahead. (control: Operator and market rules govern commitments)

## Decision rights

The model recommends commitments; accountable operators and market processes determine submitted schedules.

## Exception path

Operators update positions and manage imbalance when weather or turbine availability diverges from forecast.

## Outcomes

- **Value of wind energy versus no time-based commitments** (reported): No time-based delivery commitments to the grid → Roughly 20% higher value. Google-reported value metric; monetary definition, forecast error distribution, and independent audit were not published.

## Executive lesson

Prediction mattered because it was connected to a changed commitment decision; forecast accuracy alone would not create grid value.

## Anti-pattern

Reporting 20% more energy generated; the source says value, not production.

## Questions for leaders

- Which forecast changes a binding operating commitment?
- How is imbalance risk allocated?

## Sources

- [Machine learning can boost the value of wind energy](https://blog.google/innovation-and-ai/products/machine-learning-can-boost-value-wind-energy/) — Google
- [DeepMind's AI is predicting how much energy Google's wind turbines will produce](https://www.technologyreview.com/2019/02/27/239459/deepmind-creates-algorithm-to-squeeze-more-out-of-wind-power/) — MIT Technology Review