Photovoltaic Super-Short Term Power Prediction Based on BP-ANN Generalization Neural Network Technology Research

The research is mainly based on BP-ANN neural network method, through direct and indirect data collection to predict the photovoltaic super-short term power generation, discussed the influence and effection about the generalization of the BP-ANN neural network model ,which is used to predict the photovoltaic super-short term power generation. Combined with the actual operation situation, analyzed and compared the system operation results. The actual results show that measured data has the same trend with the super-short term prediction results, the root mean square error and mean absolute error are small, the prediction accuracy reached 96.71% and has high application value.