Research on MPPT of the Photovoltaic System Based on the PSO-BP Neural Network

Maximum power point tracking (MPPT) technique is an effective way to boost the utilization rate of solar energy in photovoltaic (PV) systems. Aiming at the problem of slow response and large fluctuations in MPPT for the PV system, this paper proposes an MPPT method with BP neural network based on the particle swarm optimization (PSO-BP), the PSO-BP neural network has strong nonlinear input and output capabilities, which can greatly improve the tracking of the photovoltaic maximum power point in terms of real-time control, stability and control accuracy. The PSO method is used to increase the convergence speed and lower the prediction error of the BP neural network by optimizing the starting weight and threshold, thereby improving the tracking speed and accuracy of MPPT. For the MPPT control of PV systems, a simulation model based on the PSO-BP neural network algorithm is developed. The PSO-optimized BP neural network has a quick convergence speed and smaller prediction error, according to the test and simulation findings. When compared to the BP neural network that has not been optimized, the PSO-BP neural network MPPT strategy can quickly and accurately track the maximum power point and significantly suppress power fluctuations under steady-state conditions, with good steady-state accuracy and dynamic characteristics.