IBM's big data helps Vestas wind turbines crank
IBM Firestorm supercomputer will analyze petabytes of weather-related data to optimize placement of Vestas wind turbines and maximize performance over time.
A wind farm in North Dakota
(Credit: Google )In a classic pairing of IT and renewable energy, an IBM supercomputer will optimize placement of wind turbines to improve performance.
IBM and Danish wind turbine manufacturer Vestas yesterday announced that the Firestorm supercomputer will analyze petabytes of data to maximize energy output of Vestas turbines.
The supercomputer crunches through weather reports, moon and tidal phase, sensor data, satellite images, and deforestation maps to generate the best placement of turbines, IBM said. Once installed, Vestas engineers will use the software to predict future performance and figure out the best time to do maintenance.
Predicting energy output of turbines is vitally important to project developers who put up money for wind farms with an expectation of selling a certain amount of energy to the grid. Although wind power is growing in many places around the world, project developers are seeking better methods, including better wind speed measurement, to better match expected and actual performance.
• Wind Pole Ventures tackles faulty wind data
• Second Wind crunches data for wind turbines
• Good data needed for small-wind turbines to spin
The turbines themselves are high-tech devices, equipped with processors to track wind direction and control the pitch of the blade.
IBM said the software took four years to develop and will run on the Apache Hadoop software for parallel processing of very large data sets. This sort of analysis used to take weeks, but can be done in under an hour, IBM said.
