SVR-based flicker estimation for wind power systems

This paper presents a simulation model based on support vector regression (SVR) for flicker estimation emitted from wind turbines. Training patterns are developed by applying the moving window method to estimate the voltage flicker. A comparison is done for the fixed speed wind turbine (WT), which leads to a conclusion that the SVR based flicker measurement is effective and not limited by processing time and memory size. The simulation results have shown that the flicker estimation is performed accurately.