Harmonics Forecasting of Wind and Solar Hybrid Model Driven by DFIG and PMSG Using ANN and ANFIS

Grid integration of Renewable Energy Systems (RES) involves various types power electronics-based converters and inverters. The use these electronic-based devices results in inducing both current voltage harmonics to the grid. In order reduce harmonics, especially for large-scale RES, harmonic forecasting is one many techniques used design mitigation devices. core objective this work develop a novel model accurate reliable estimation RES. To achieve two hybrid generator models are used. First consists wind turbine coupled with Doubly Fed Induction Generator (DFIG) combined Solar Photo Voltaic (PV) based which connected common second uses Permanent Magnet Synchronous (PMSG) conjunction Solar-PV generator. With real world meteorological data (wind speed solar irradiation) as inputs, generators simulate produce output waveforms. Harmonics extracted from waveforms record, analyze, arrange forecast future harmonics. Three parameters namely, Total Distortion (THD) dominant individual contents, 11 th (h11) 13 (h13) forecasted Artificial Neural Networks (ANN) Adaptive Neuro Fuzzy Inference (ANFIS) prominent methods forecasting. three-layered ANN structures namely Cascaded Network Recurrent Local feedback (3LCRNNL), Global (3LCRNNG) (CRNNGL) have been proposed utilized hyperbolic tangent transfer function adjust weights scaled conjugate gradient method optimizer training error. ANFIS also employed subtractive clustering improve adaptability accuracy forecasts. compared presented shows that recorded best performance THDV h13 3LCRNNGL h11 Wind DFIG-PV forecast. For forecasts performed THDI h11, whereas h13. PMSG-PV model, yields every scenario involving