Intelligent control of photovoltaic system using BPSO-GSA-optimized neural network and fuzzy-based PID for maximum power point tracking

摘要: The maximum power point tracking (MPPT) technique is applied in the photovoltaic (PV) systems to achieve from a PV panel different atmospheric conditions and optimize efficiency of panel. A proportional-integral-derivative (PID) controller was used this study for (MPP). fuzzy gain scheduling system with optimized rules by subtractive clustering algorithm employed tuning PID parameters based on error error-difference an online mode. In addition, Elman-type recurrent neural network (RNN) inverse identification estimating solar radiation intensity determine MPP voltage. optimum number neurons single hidden-layer RNN determined binary particle swarm optimization algorithm. weights were also using hybrid method Levenberg-Marquardt gravitational search (GSA). proposed fitness function optimization, both size its convergence accuracy considered. Thus, attempts minimize structural complexity mean square error. Simulation results revealed superior performance GSA comparison swarm, cuckoo, grey wolf algorithms. MPPT evaluated under four ambient conditions. Our experimental show that more efficient than three competitive methods presented recent years.