Artificial Neural Network Control of Hybrid Renewable Energy System Connected to Ac Grid

This paper discusses the development of new control method using artificial neural network model for the optimum operation of hybrid renewable energy system (HRES) connected to AC grid. The hybrid system consists of wind generator (WG), diesel generator (DG), and flywheel energy storage system (FESS). The system is based on permanent magnet synchronous machines (PMSM) which are controlled by sliding mode control, according to type of subsystems. An artificial neural networking supervisor control is designed to determine the energy transfer type of flywheel energy storage system (charging / discharging / no transfer of energy), and to take decision on diesel generators ON/OFF status, these two parameters are used to simplify the control mode of these subsystems. The supervisor inputs are the difference between the reference power of hybrid renewable energy system and the power generated by wind generator, and the energy stored in flywheel. The objectives of the supervisor are to satisfy the hybrid system reference power (power requested by AC network), to manage the energy transfer between hybrid system and AC grid, to optimize the use of wind energy, and to reduce fuel of diesel generator. The ANN testing and the system simulation give encouraging results such as power requested is satisfied.