Researchers at MIT found a new method of predicting wind speed for future wind farm siting that takes only 3 months of data to calculate instead of the typical 12.
Before a large investment in a wind farm, developers usually hire a third party company like a consultant to take wind speed measurements at a proposed site, over a period of 9-12 months. These new measurements are correlated with previous measurements from a nearby weather station and used to determine the attractiveness of the proposed location for wind energy production. Now, MIT researchers are able to take 3 months’ worth of existing data from various nearby weather stations and even more accurately predict the proposed site’s wind speed for future projects.
A research scientist at MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL) and first author on the new paper, Kalyan Veeramachaneni said, “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 (Gaussian).”
According to their press release, the main advantage of this new way of calculating wind speed “is that it’s not restricted to Gaussian probability distributions. Moreover, it can use different types of distributions to characterize 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.”
Veeramachaneni and his research colleagues, Una-May O’Reilly, a principal research scientist at CSAIL, and Alfredo Cuesta-Infante of the Universidad Rey Juan Carlos in Madrid originally applied their new method to the data collected from the MIT Museum anemometer. When they determined how accurate their measurements were, they applied the same methodology to data provided by other consultants in the wind energy industry with great success.
Later this month, the research team will be presenting their new technique in more detail at the International Joint Conference on Artificial Intelligence.
Their new method of statistical analysis could save developers a lot of time and money especially on large-scale offshore wind farm projects.