Calendar An icon of a desk calendar. Cancel An icon of a circle with a diagonal line across. Caret An icon of a block arrow pointing to the right. Email An icon of a paper envelope. Facebook An icon of the Facebook "f" mark. Google An icon of the Google "G" mark. Linked In An icon of the Linked In "in" mark. Logout An icon representing logout. Profile An icon that resembles human head and shoulders. Telephone An icon of a traditional telephone receiver. Tick An icon of a tick mark. Is Public An icon of a human eye and eyelashes. Is Not Public An icon of a human eye and eyelashes with a diagonal line through it. Pause Icon A two-lined pause icon for stopping interactions. Quote Mark A opening quote mark. Quote Mark A closing quote mark. Arrow An icon of an arrow. Folder An icon of a paper folder. Breaking An icon of an exclamation mark on a circular background. Camera An icon of a digital camera. Caret An icon of a caret arrow. Clock An icon of a clock face. Close An icon of the an X shape. Close Icon An icon used to represent where to interact to collapse or dismiss a component Comment An icon of a speech bubble. Comments An icon of a speech bubble, denoting user comments. Ellipsis An icon of 3 horizontal dots. Envelope An icon of a paper envelope. Facebook An icon of a facebook f logo. Camera An icon of a digital camera. Home An icon of a house. Instagram An icon of the Instagram logo. LinkedIn An icon of the LinkedIn logo. Magnifying Glass An icon of a magnifying glass. Search Icon A magnifying glass icon that is used to represent the function of searching. Menu An icon of 3 horizontal lines. Hamburger Menu Icon An icon used to represent a collapsed menu. Next An icon of an arrow pointing to the right. Notice An explanation mark centred inside a circle. Previous An icon of an arrow pointing to the left. Rating An icon of a star. Tag An icon of a tag. Twitter An icon of the Twitter logo. Video Camera An icon of a video camera shape. Speech Bubble Icon A icon displaying a speech bubble WhatsApp An icon of the WhatsApp logo. Information An icon of an information logo. Plus A mathematical 'plus' symbol. Duration An icon indicating Time. Success Tick An icon of a green tick. Success Tick Timeout An icon of a greyed out success tick. Loading Spinner An icon of a loading spinner.

MIT devises more effective way to measure wind resources

Renewables news
Renewables news

When a power company wants to build a new windfarm, it generally hires a consultant to make wind speed measurements at the proposed site for a period of time.

Those measurements are correlated with historical data and used to assess the site’s power-generation capacity potential.

At the International Joint Conference on Artificial Intelligence last month, researchers at the world renowned Massachusetts Institute of Technology (MIT) presented a new statistical technique that yields better wind-speed predictions than existing techniques do – even when it uses only three months’ worth of data.

According to MIT, that could save power companies time and money, particularly in the evaluation of sites for offshore windfarms, where maintaining measurement stations is particularly costly and is a significant issue in the North Sea, which leads the world in terms of wind turbine population.

“We talked with people in the wind industry, and we found that they were using a very, very simplistic mechanism to estimate the wind resource at a site,” says Kalyan Veeramachaneni, a research scientist at MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL) and first author of the paper delivered.

In particular, Veeramachaneni says, standard practice in the industry is to assume that wind-speed data follows a so-called Gaussian distribution – the “bell curve” familiar from basic statistics.

“The data here is non-Gaussian; we all know that,” Veeramachaneni says. “You can fit a bell curve to it, but that’s not an accurate representation of the data.”

Typically, a wind energy consultant will find correlations between wind speed measurements at a proposed site and those made, during the same period, at a nearby weather station where records stretch back for decades.

On the basis of those correlations, the consultant will adjust the weather station’s historical data to provide an approximation of wind speeds at the new site.

The correlation model is what’s known in statistics as a joint distribution. That means that it represents the probability not only of a particular measurement at one site, but of that measurement’s coincidence with a particular measurement at the other.

Wind-industry consultants, Veeramachaneni says, usually characterise that joint distribution as a Gaussian distribution.

The first novelty of the model that Veeramachaneni developed with his colleagues – Una-May O’Reilly, a principal research scientist at CSAIL, and Alfredo Cuesta-Infante of the Universidad Rey Juan Carlos in Madrid – is that it can factor in data from more than one weather station. In some of their analyses, the researchers used data from 15 or more other sites.

But its main advantage is that it’s not restricted to Gaussian probability distributions.

Moreover, it can use different types of distributions to characterise data from different sites, and it can combine them in different ways. It can even use so-called nonparametric distributions, in which the data are described not by a mathematical function, but by a collection of samples, much the way a digital music file consists of discrete samples of a continuous sound wave.

Another aspect of the model is that it can find nonlinear correlations between data sets.

Standard regression analysis, of the type commonly used in the wind industry, identifies the straight line that best approximates a scattering of data points, according to some distance measure. But often, a curved line would offer a better approximation. The researchers’ model allows for that possibility.

The researchers first applied their technique to data collected from an anemometer on top of the MIT Museum in Cambridge, Mass, which was looking to install a wind turbine on its roof.

Once they had evidence of their model’s accuracy, they applied it to data provided to them by a major consultant in the wind industry.

With only three months of the company’s historical data for a particular windfarm site, Veeramachaneni and his colleagues were able to predict wind speeds over the next two years three times as accurately as existing models could with eight months of data.

Since then, the team has improved their model by evaluating alternative ways of calculating joint distributions.

According to additional analysis of the data from the Museum of Science, which is reported in the new paper, their revised approach could double the accuracy of their predictions.

Recommended for you


More from Energy Voice

Latest Posts