Hybrid power generation forecasting using CNN based BILSTM method for renewable energy systems

This paper presents the design of a grid-connected hybrid system using modified Z source converter, bidirectional converter and battery storage system. The input sources for proposed are fed from solar wind power systems. A high gain switched is designed supplying constant DC to DC-link inverter. deep learning (HDL) algorithm (CNN-BiLSTM) predicting output HDL method PI controller generate pulses closed loop control framework implemented grid integrated 1.5 Kw in MATLAB/SIMULINK software results validated. prototype developed laboratory experimental obtained it. From simulation results, it observed that ANN with SVPWM (Space vector Pulse width Modulation) gives THD (Total harmonic distortion) 2.2% which within IEEE 519 standard. Therefore, identified ANN-SVPWM injects less currents into than other two controllers.