Wind Turbine Layout Optimisation

{access view=!registered}Only logged in users can view the full text of the article.{/access}{access view=registered}The layout of turbines in large wind farms is challenging because of the larger farm and the additional turbines, feasibility constraints and wake model complexity. Due to the inherent complexity, bio-inspired algorithms such as evolutionary strategies (ES), genetic algorithms (GAs) and particle swarm optimisation (PSO) have been used for layout optimisation. Evolutionary algorithms (EAs) perform stochastic sampling optimisation by mimicking fundamental aspects of the neo-Darwinian evolutionary process. They simultaneously search with a ‘population’ of candidate solutions and associate an objective score as a fitness value for each one. They then select among the population to favour those solutions that are more ‘fit’. The next generation (i.e. a new population) consists of replicates of the fitter solutions which have been ‘genetically mutated and/or crossed over’ in a biological metaphor: the decision variables were perturbed such that they inherit some characters of their ‘parents’ as well as change in random ways.