Deep Learning-Based FOPID Controller for Cascaded DC-DC Converters

Smart grids and their technologies transform the traditional electric to assure safe, secure, cost-effective, reliable power transmission. Non-linear phenomena in systems, such as voltage collapse oscillatory phenomena, can be investigated by chaos theory. Recently, renewable energy resources, wind turbines, solar photovoltaic (PV) arrays, have been widely used for generation. The design of controller direct Current (DC) converter a PV system is performed based on linearized model at an appropriate operating point. However, these points are ever-changing system, usually accomplished low irradiance level. This study designs fractional-order proportional-integrated-derivative (FOPID) using deep learning (DL) with quasi-oppositional Archimedes Optimization algorithm (FOPID-QOAOA) cascaded DC-DC converters micro-grid applications. presented FOPID-QOAOA designed enhance overall efficiency boost converter. In addition, proposed develops FOPID stacked sparse autoencoder (SSAE) regulate output voltage. To tune hyper-parameters related SSAE model, QOAOA derived including (QOBL) AOA. Moreover, objective function integral time multiplied squared error (ITSE) considered this study. For validating method, sequence simulations was under distinct aspects. A comparative buck carried out authenticate effectiveness performance techniques.