Search

With the large-scale grid connected operation of new energy power plants, the safe operation of grid and new energy power plants has been faced with unprecedented challenges, especially the influence of meteorological conditions. Due to the inherent volatility of new energy, accurate prediction of generation power can effectively reduce the impact on the electricity grid system. In order to improve the prediction accuracy, a dynamic meteorological element correction method considering multiple meteorological elements is introduced, and a centralized power forecasting platform is established. At the same time, due to the frequent occurrence of extreme weather events in recent years, such as wind fan icing, lightning gale, hail, mountain torrents and so on, all of them have brought challenges to the safe operation of new energy power plants, so a fan icing warning model has been developed. Based on the Internet automatic published information plantform of meteorological disaster has established which greatly reduced the loss of power plants caused by the extreme weather.

In order to improve the prediction accuracy of the photovoltaic power prediction model, this paper presents a novel forecasting model, which is the combination between Principal Component Analysis (PCA) and Support Vector Machine (SVM) intelligent algorithm. PCA statistical method used to extract less principal components instead of the original meteorological factor. Then that is as the input of the SVM model. The proposed prediction model verify its validity by the data of a roof grid-connected PV system located at Huazhong University of Science and Technology. The results show that the forecasting model can not only improve the prediction accuracy of the photovoltaic power output also reduce the computational model to meet real-time requirements for forecasting. The prediction of the accuracy is better than that of the currently used photovoltaic power forecast by comparing other model.