Optimizing a Straight‐Bladed Vertical Axis Wind Turbine With Computational Fluid Dynamics (CFD), Artificial Neural Network (ANN), and Genetic Algorithm (GA)

Vertical axis wind turbine (VAWT) is a suitable renewable power generation tool for use in urban areas, especially at low wind speeds and with low noise level. However, an approach with accurate results, acceptable time consumption, and cost for optimizing this turbine is not reported in the literature. The aim of this study is to propose an approach for optimizing a VAWT with three straight blades. In the first step, the air forces acting on the turbine blades are estimated by computational fluid dynamics (CFD). Three effective parameters, that is, turbine diameter, tip speed ratio, and airfoil chord length, were changed, and 180 CFD runs were performed. In the second step, to save running time and cost, an artificial neural network (ANN) method was used, and the turbine power coefficient, which was the ANN output, was predicted just by specifying the above three effective parameters. In the third step, the Genetic Algorithm optimization technique was used to find the maximum value of the power coefficient of the vertical axis wind turbine () as the objective function and the above three effective parameters as design variables in the specified range. The optimum value of power coefficient for the optimized VAWT by the use of the procedure proposed here was 0.319 (15.16% increase in comparison with 0.277 for the existing VAWT). The optimum values of design variables were also obtained: 2.5 m for diameter (instead of 1.7 m), 0.213 m (instead of 0.246 m) for the airfoil chord length, and 2.3 for the blade tip speed ratio (instead of 2.23).