Additional Algorithm Problems

[donghyeoncheon]

I'm trying to add a Bayesian algorithm in addition to scipy, serial refine, and geometrics, which can be tested with Floris this time. I'm encountering an error 'axis 2 is out of bounds for an array of dimension 2' when using the 'fi.calculate_wake(yaw_angles=yaw_agnles_array)' syntax. When using '.list', I get a 'dimension 1' error. Is there a good alternative? I apologize for asking what may seem like silly questions.

def calculate_efficiency(yaw_angles, wind_direction, wind_speed):
   # Calculate the efficiency based on yaw angles, wind direction, and wind speed
   total_efficiency = 1.0
   for yaw_angle in yaw_angles:
       angle_diff = min(abs(wind_direction - yaw_angle), 360 - abs(wind_direction - yaw_angle))
       eff = max(0, np.cos(np.radians(angle_diff)))  # Efficiency based on the cosine of the angle difference
       total_efficiency += eff
   average_efficiency = total_efficiency / len(yaw_angles)  # Average efficiency per turbine
   return average_efficiency


 def calculate_AEP(efficiency, wind_speed):
   # Calculate the Annual Energy Production (AEP)
   Air_Density = 1.0  # Air density (kg/m^3)
   power_output = Air_Density * efficiency * (wind_speed ** 3)
   hours_per_year = 8760  # Operating hours per year
   AEP = power_output * hours_per_year  # Annual energy production (MWh)
   return AEP / 1000  # Convert to GWh

 def optimize_yaw_angles():
   # Initialize the Floris Interface
   fi = wfct.floris_interface.FlorisInterface("examples/inputs/gch.yaml")

   # Reinitialize the Floris Interface with a new layout, wind directions, and wind speeds
   D = 40.0
   F = D * 3
   fi.reinitialize(
       layout_x=[882.51*F, 883.71*F, 884.82*F, 886.34*F, 888.48*F, 888.07*F, 886.76*F, 885.32*F, 887.92*F, 889.53*F, 890.96*F, 892.56*F, 890.73*F], 
       layout_y=[1758.3*F, 1755.87*F, 1753.26*F, 1751.23*F, 1752.14*F, 1755.57*F, 1758.35*F, 1760.55*F, 1761.95*F, 1759.4*F, 1757.2*F, 1754.7*F, 1753.35*F],
       wind_directions=np.arange(260.0, 280.0, 2.0),
       wind_speeds=[7.0]
   )

   def yaw_angles_efficiency(wind_direction, wind_speed, **yaw_angles):
       # Convert 1D array of yaw_angles to a 2D array
       yaw_angles_list = [yaw_angles[f'yaw_angle_{i}'] for i in range(len(fi.floris.farm.layout_x))]
       yaw_angles_array = np.array([yaw_angles_list])

       # Set wind direction, wind speed, and yaw angles in FLORIS
       fi.reinitialize(wind_directions=np.array([wind_direction]), wind_speeds=np.array([wind_speed]))
       fi.calculate_wake(yaw_angles=yaw_angles_array)

       # Calculate AEP
       power_output = fi.get_farm_power()
       efficiency = calculate_efficiency(yaw_angles_list, wind_direction, wind_speed)
       hours_per_year = 8760
       AEP = power_output * hours_per_year / 1000  # Convert to GWh
       return AEP

   # Set up Bayesian Optimization
   pbounds = {f'yaw_angle_{i}': (-25, 25) for i in range(len(fi.floris.farm.layout_x))}
   pbounds['wind_direction'] = (260, 280)
   pbounds['wind_speed'] = (7, 7)

   optimizer = BayesianOptimization(
       f=yaw_angles_efficiency,
       pbounds=pbounds,
       random_state=2048,
       verbose=2
   )
   optimizer.maximize(init_points=13, n_iter=500)

   # Print the optimized results
   optimized_parameters = optimizer.max['params']
   print("\nOptimized Yaw Angles and Estimated AEP:")
   for i in range(len(fi.floris.farm.layout_x)):
       angle = optimized_parameters[f'yaw_angle_{i}']
       print(f"Turbine {i+1}: Yaw Angle = {angle:.2f} degrees")
  total_AEP = calculate_AEP(fi.get_farm_power(), optimized_parameters['wind_speed'])
   print(f"Estimated Total AEP: {total_AEP:.2f} GWh")

if __name__ == "__main__":
   optimize_yaw_angles() ''