Evolutionary lessons for wind farm efficiency

May 4, 2011, University of Adelaide
A wind farm in South Australia

Evolution is providing the inspiration for University of Adelaide computer science research to find the best placement of turbines to increase wind farm productivity.

Senior Lecturer Dr Frank Neumann, from the School of Computer Science, is using a "selection of the fittest" step-by-step approach called "evolutionary algorithms" to optimise wind turbine placement. This takes into account wake effects, the minimum amount of land needed, wind factors and the complex aerodynamics of wind turbines.

"Renewable energy is playing an increasing role in the supply of energy worldwide and will help mitigate ," says Dr Neumann. "To further increase the productivity of wind farms, we need to exploit methods that help to optimise their performance."

Dr Neumann says the question of exactly where should be placed to gain is highly complex. "An evolutionary algorithm is a mathematical process where potential solutions keep being improved a step at a time until the optimum is reached," he says.

"You can think of it like parents producing a number of offspring, each with differing characteristics," he says. "As with evolution, each population or `set of solutions' from a new generation should get better. These solutions can be evaluated in parallel to speed up the computation."

Other biology-inspired algorithms to solve complex problems are based on .

"Ant colony optimisation" uses the principle of ants finding the shortest way to a source of food from their nest.

"You can observe them in nature, they do it very efficiently communicating between each other using pheromone trails," says Dr Neumann. "After a certain amount of time, they will have found the best route to the food - problem solved. We can also solve human problems using the same principles through ."

Dr Neumann has come to the University of Adelaide this year from Germany where he worked at the Max Planck Institute. He is working on wind turbine placement optimisation in collaboration with researchers at the Massachusetts Institute of Technology.

"Current approaches to solving this placement optimisation can only deal with a small number of turbines," Dr Neumann says. "We have demonstrated an accurate and efficient algorithm for as many as 1000 turbines."

The researchers are now looking to fine-tune the algorithms even further using different models of wake effect and complex aerodynamic factors.

Explore further: Recycling wind turbines

Related Stories

Recycling wind turbines

September 21, 2007

The development of wind power promises much in terms of providing us with renewable energy for the future and wind turbines could be the most effective way to harness that power. Danish researchers now suggest that in order ...

Smart wind turbines can predict the wind

January 5, 2010

Risø DTU researchers have recently completed the world’s first successful test on a wind turbine with a laser-based anemometer built into the spinner in order to increase electricity generation.

Optimizing large wind farms

November 23, 2010

Wind farms around the world are large and getting larger. Arranging thousands of wind turbines across many miles of land requires new tools that can balance cost and efficiency to provide the most energy for the buck.

Recommended for you


Adjust slider to filter visible comments by rank

Display comments: newest first

not rated yet May 04, 2011
It's an exciting approach with some interesting applications but I think it's success will depend upon how easy it is to apply a variety of fitness criteria. Applying it in the offshore environment, the only place in Europe where you're likely to get 1000 turbine farms, would demand the ability to input from a variety of GIS sources for things such as shipping lanes, migratory routes and UXO.
not rated yet May 04, 2011
I want more info on how they're doing it before I pass judgement on this. I'm not sure that windfarms are a good application of evolutionary algorithms.

Making a slight change to one turbine can affect every other turbine in the array. One change might be a negative impact, but it you do the same change, but push the turbing slightly farther, it could hit an airflow just right to have a positive impact. Are they going to throw out a perfectly good change because the positive version of it is too far outside their parameters?

It's like chess, where there are almost infinite possibilities. To have an effective algorithm in a case like this, it seems that you would have to put so many constraints on it that you could hardly call it an evolutionary algorithm.
not rated yet May 05, 2011
The constraints emerge as a consequence of the fitness function, which is used to guide evolution. Our own evolution has progressed quite well without explicit knowledge of protein expression and dna modification.

Please sign in to add a comment. Registration is free, and takes less than a minute. Read more

Click here to reset your password.
Sign in to get notified via email when new comments are made.