An isolated wind hydro hybrid system with two back-to-back power converters and a battery energy storage system using neural network compensator

This paper presents the improved model of wind hydro hybrid generation system involving an Artificial Intelligence control technique (ANN) in which three phase four wire local loads fed with two squirrel cage induction generators, one driven by a variable speed wind turbine and another driven by a constant power hydro turbine. The proposed system has a battery at the middle of two back-to-back connected pulse width modulation (PWM) controlled insulated-gate-bipolar - transistor (IGBT) based voltage source converters (VSCs). The main objectives of the control algorithm for the VSCs are to achieve the maximum power tracking (MPT) through rotor speed control of a wind turbine driven SCIG under varying wind speeds at machine side and to control the magnitude and frequency of the load voltage at load side. In this paper back-propagation neural network trained model is employed to simulate and predict the maximum power point of a wind turbine using a set of data collected from the characteristics of wind turbine. The random performance of the proposed system is presented to demonstrate its capability of MPT, voltage and frequency control (VFC) under various load conditions at different wind speeds. The proposed wind-hydro hybrid power generation is modeled and simulated in Matlab/simulink GUI environment.