Identification of wind turbine using fractional order dynamic neural network and optimization algorithm

Abstract

In this paper, an efficient technique is presented to identify a 2500 KW wind turbine operating in Kahak wind farm, Qazvin province, Iran. This complicated system dealing with wind behavior is identified by using a proposed fractional order dynamic neural network (FODNN) optimized with evolutionary computation. In the proposed method, some parameters of FODNN are unknown during the process of identification, so a particle swarm optimization (PSO) algorithm is employed to determine the optimal values by which a fractional order nonlinear system can be completely identified with a high degree of accuracy. These parameters are very effective to achieve high performance of FODNN identifier and they include fractional order, initial values of states and weights of FODNN, and numerical algorithm step size for solving FODNN equation. Simulation results confirm the efficiency of the proposed scheme in term of accuracy. Furthermore, comparison of the results achieved by the proposed method and those of the integer order dynamic neural network (IODNN) depicts higher accuracy of the proposed FODNN.