Short-term prediction of the output power of PV system based on improved grey prediction model

In connection with the random fluctuation and the intermittent problems of output power of photovoltaic (PV) power station and the gray prediction had a less effective on the strong volatility sequence, exponential smoothing was proposed to improve gray prediction model to predict the PV power generation. The gray prediction model is improved by using exponential smoothing method since the exponential smoothing method had smoothing effect on the strong volatility sequence. There is no denying that it can increase the prediction accuracy. Builds the hourly power grey prediction models by choosing proper samples and gray prediction model and improved gray prediction model were used to predict the short-term PV power. Using practical output power data of PV to evaluate the gray prediction and improved gray prediction model. The evaluation results not only show that the improved gray forecasting model has higher prediction accuracy, and the predicted results are closer to the actual value of the PV power, but also proved that the improved gray prediction method is effective and accurate and providing a simple and reliable method for the prediction of PV power generation.