ANFIS modeling and validation of a variable speed wind turbine based on actual data

Abstract

In this research paper, ANFIS modeling and validation of Vestas 660 kW wind turbine based on actual data obtained from Eoun-Ebn-Ali wind farm in Tabriz, Iran, and FAST is performed. The turbine modeling is performed by deriving the non-linear dynamic equations of different subsystems. Then, the model parameters are identified to match the actual response. ANFIS is an artificial intelligent technique which creates a fuzzy inference system based on input and output information of the model. In this research, the ANFIS algorithm combines neural network and fuzzy logic with 5 layers which utilize different node functions for learning and setting fuzzy inference system parameters. After learning, by assuming constant parameters, a hybrid method is used to update the results. Employing the proposed method, computation time and complexity are remarkably reduced. Results of the proposed method are then compared and validated with the actual data of Eoun-Ebn-Ali wind farm in Tabriz. It is shown and concluded that the proposed model matches favorably well with the actual data and FAST model.