Growth of wind farm layouts
This project proposes a novel approach to generate wind farm layouts. Their design is a complex process that involves many stakeholders and combines intensive computer simulation, optimization techniques and manual iterations.
We propose a novel approach based on a bio-inspired artificial-cell-based developmental model. The simulated environment is inoculated with a virtual cell. This cell can divide in order to populate the environment. When the development of the virtual organism is finished, all the cells are assumed to represent turbines to generate the final wind farm layout. The behavior of the cells is optimized by an evolutionary algorithm to generate an optimal layout. A fundamental advantage of this approach is that it scales up easily: once learned, the cell’s behavior can be reused in various environments without further learning.
The video hereafter shows an example of a wind farm layout growth after the optimization of the cell behavior. The following images show the resulting farms with the same cell, with no re-optimization, in different conditions (farm size and obstacles). The duration of the optimization of these farms are close to the minutes in comparison to days for the other approaches (genetic algorithm, swarm particle optimization or CMA-ES).
Sylvain Cussat-Blanc (Université Toulouse 1 Capitole - IRIT)
Hervé Luga (Université Toulouse Le Mirail - IRIT)
Dennis Wilson (MIT - CSAIL)
Kalyan Veeramachaneni (MIT - CSAIL)
Una-May O'Reilly (MIT - CSAIL)
Dennis Wilson, Sylvain Cussat-Blanc, Kalyan Veeramachaneni, Una-May O'Reilly, Hervﾃ Luga. A continuous developmental model for wind farm layout optimization. Genetic and Evolutionary Computation COnference (GECCO 2014), Vancouver, ACM, 2014. PDF
Dennis Wilson, Emmanuel Awa, Sylvain Cussat-Blanc, Kalyan Veeramachaneni, Una-May O'Reilly. On Learning to Generate Wind Farm Layouts (regular paper). In Genetic and Evolutionary Computation COnference (GECCO 2013), Amsterdam, 06/07/2013-10/07/2013, ACM, july 2013. PDF