Study on the accuracy and stability of distributed photovoltaic customer load forecasting based on hybrid modeling

In this paper, a simplified mathematical model of distributed PV grid-connection is constructed under two control strategies based on the basic principles of distributed generation system. After that, the mapping relationship between the input data and the output predicted value is obtained by the time series prediction method, on the basis of which the distributed PV prediction model with hybrid model (CNN-LSTM) is established. Finally, the stability of customer load voltage is analyzed using the continuous tidal current method. The results show that the hybrid model constructed in this paper has high accuracy for predicting the load of distributed PV customers. Without affecting user satisfaction, the control strategy regulates each controllable load on the user side separately and transfers the load to the user side. The quantitative analysis of the static voltage stability of the distribution network before and after DC access confirms that the access to DC can effectively improve the static voltage stability of the distribution network, and the larger the access capacity is within the allowed range of the system, the better the static voltage stability is.