Research Article
Differential Evolution Based IDWNN Controller for Fault Ride-Through of Grid-Connected Doubly Fed Induction Wind Generators
Pseudocode 2
Pseudocode for DE-IDWNN controller.
Start | Phase I: | Initialize the IDWNN weights, learning rate and inertia factor. | Randomly generate weight values. | Present the input samples to the network model. | Compute net input of the network considered. | Apply activations to compute output of calculated net input. | Perform the above process for hidden layer to hidden layer and hidden layer to output layer. | Finally compute the output from the output layer. | Perform weight updation till stopping condition met. | Phase II: | Present the computed outputs from IDWNN model into DE. | Invoke DE | Perform Mutation | Perform Crossover | Perform Selection | Do carry out generations until fitness criteria met. | Note the points at which best fitness is achieved. | Present the points of best fitness back to IDWNN. | Phase III: | Invoke IDWNN with the inputs from the output of Phase II | Tune the weights to this IDWNN employing DE | Invoke DE | Perform Phase I process for tuned weights of DE. | Continue Phase II. | Repeat until stopping condition met (Stopping conditions can be number of iterations/generations or | reaching the optimal fitness value) | Stop |
|