Distributed solar photovoltaic power prediction algorithm based on deep neural network

Solar photovoltaic (PV) power prediction is easily affected by weather factors. In order to reduce the solar photovoltaic (PV) power prediction deviation and improve the prediction accuracy, a distributed solar photovoltaic (PV) power prediction algorithm based on deep neural network is proposed. By deeply exploring the working principle of photovoltaic power generation, constructing a photovoltaic power generation system model, and systematically analyzing various factors that affect photovoltaic power generation, detailed classification of weather types can be achieved. On this basis, outlier detection, standardization processing, and normalization techniques are used to deeply clean and optimize the raw data, effectively avoiding the problem of neuron saturation. The use of wavelet packet decomposition method to decompose the photovoltaic power generation sequence into multiple sub sequences significantly reduces the difficulty of prediction. The effective fusion of LSTM (Long Short-Term Memory) and BPNN (Back Propagation Neural Network), and the fine adjustment of the fusion ratio parameter through genetic algorithm, ultimately achieved high-precision prediction of distributed photovoltaic power under complex and variable weather conditions. The experimental results show that the proposed method can accurately predict photovoltaic power under different weather conditions, and the prediction results are reliable.