65,000 wind turbines installed in the US will generate 400 GWh in 2021
400,000 wind turbines installed worldwide
$100B annual US and $600B world annual wind industry with 20% annual growth
Accelerating national attention to green energy.
Meanwhile 2018 US average wind PPAs were below 2¢/kWh - squeezing margins
Small production increases have huge impacts on margins
Turbine size and cost keeps growing - going to 6 MW onshore
Hundreds of thousands of dollars to replace a gearbox
The vast majority of wind turbines today adjust after winds arrive causing lost energy production and exposure to damaging gusts. Available methods for providing wind event alerts are very expensive, and not widely deployed.
Windscape.ai will be a 10x breakthrough in cost and effectiveness in generating 10-60 second alerts of wind changes and gusts. This will allow operators to increase wind farm energy production and turbine life by optimizing pitch and yaw settings for energy capture and protecting gearboxes and blades from damaging gusts.
Windscape.ai uses a low-cost wifi mesh network of sensors across and surrounding the wind farm that feed into AI data correlation. This approach is 10x cheaper than any alternative. It is patented and made possible now through advances in edge AI and sensor-on-a-chip tech.
$100M addressable US market; $600M worldwide
Enabling wind turbine pitch and yaw ahead of wind events with 10 to 45 seconds lead time alerts
AI pattern recognition of telltale atmospheric signals
Ultra-low cost, robust hardware
Increased annual energy
The goal is to predict wind events to adjust pitch and yaw to optimize energy capture and reduce gearbox stress.
Wind changes aloft are caused by and produce pressure changes due to conservation of energy.
Pressure changes near ground and well upstream and downstream from wind farms are related to wind changes at the wind farm.
New highly sensitive, low-cost pressure sensors will be placed on short posts in an array around wind farms and extending out up to 500m.
Data from these sensors and wind farm anemometers will be collected on a wireless mesh network.
The AI model will be trained over time (some months) in supervised learning on pressure sensor array and wind data.
The edge AI model will compute real time inference on live pressure data to give wind change alerts to the owner’s SCADA.
The 10-45 second alerts will allow proactive adjustments to pitch, yaw and other systems.
Expected but still to be demonstrated:
- Pressure drops downwind creating high p to low p movement.
- Intersection of two moving air masses.
- Partial heating from partial cloud cover.
Our June 2021 field tests are starting to answer these questions.
Wind farm size: 50 MW
Annual output*: 153,300 MWh/yr
(Based on 35% CF - average for US fleet)
Annual revenue*: $6,132,000
(Based on $40 PPA - low range)
Output improvement with windscape.ai: 1%
(Anticipate 2%-3%. Using lowest estimate here.)
Annual energy production (AEP) only. Turbine life improvements not included.
Increased wind farm annual revenue: $61,320
Richard D. Ely, Ph.D., Inventor, Advisor
- Davis Wind, Founder
- Davis Hydro, Founder
- Massachusetts Institute of Technology
- UC Berkeley
- University of Rhode Island
- University of Connecticut
Eric Thompson, CEO
- Extensive leadership in wind and renewable energy
- Ensemble Energy (AI for wind farm O&M)
Chief Business Development Officer
- Nordic Windpower (Utility-scale WTG OEM)
- Strategy and Bizdev Consultant with multiple wind, solar and hydro technology companies
- Cornell University
Layne Williams, Chief Engineer
- 30+ years experience in Test, Network Design, System Development and Performance testing.
- Telkonet Inc. - Sr. System Test Engineer
- Uptime Network Inc. - Network Engineer
- Broadsoft Inc. - Test Engineer
- Implementing on Win10 / Win7, Linux RedHat Fedora Debian and Raspbian on RPi2/3/4/Arduino; working in Perl, C / C++, VBScript, Visual Basic, HTML, XML, Java and SQL scripting.
Matthew A. Wright, Ph.D., AI/ML Lead
- Extensive controls, AI and traffic nodes modeling experience
- UC Berkeley
- UT Austin
Nathan Sackheim, Analytics Developer
- Experienced in programming and data management with Python and PyTorch
- University of California, Santa Barbara
Nick Werhren, Full Stack Software Engineer
- Experienced with MVC web architecture
- Relational Database Expertise
- University Nevada Reno
Pilot 1 started in June with the helpful assistance of the UC Davis Atmospheric Science group at their test site.
AI analysis of data
Phase 2 testing