谷歌的DeepMind AI項目可在渦輪開始旋轉之前36小時預測發(fā)電量，從而讓電廠能夠提前一天確定向電網(wǎng)提供的輸電量。

一年前，谷歌與DeepMind將機器學習算法應用于谷歌美國中部的一組風力發(fā)電廠。這些風力發(fā)電廠的風電容量達到了700兆瓦，能夠提供一座中型城市所需的電力。

通過研究風力發(fā)電廠、天氣預報以及渦輪的歷史數(shù)據(jù)，經(jīng)調試的DeepMind用于在實際發(fā)電之前預測風能發(fā)電量。此舉也為風力發(fā)電廠的容量帶來了更大的價值，因為發(fā)電廠可以提前對向電網(wǎng)的供電量進行規(guī)劃。

DeepMind在一份聲明中表示：“我們無法消除風力的波動性，但研究的早期結果顯示，我們能夠使用機器學習大大提升風力發(fā)電的可預測性和其價值。”

公司稱，DeepMind的預測將谷歌風能的價值提升了約20%。（財富中文網(wǎng)）

譯者：馮豐

審校：夏林

Google’s DeepMind AI program can predict wind power output 36 hours before the turbines start spinning, allowing one to make delivery commitments to the power grid up to a day in advance.

The news comes a year after Google and DeepMind applied machine learning algorithms to Google’s fleet of wind farms in central United States. With 700 megawatts of wind power capacity, these wind farms can generate as much power needed by a medium-sized city.

By studying the wind farms, weather forecasts, and historical turbine data, DeepMind was configured to be able to predict the wind power output ahead of actual generation. This brings greater value to wind farms’ capabilities, as power delivery to the grid can be scheduled in advance.

“We can’t eliminate the variability of the wind, but our early results suggest that we can use machine learning to make wind power sufficiently more predictable and valuable,” said DeepMind in a statement.

According to the company, DeepMind’s predictions have boosted the value of Google’s wind energy by roughly 20%.