Short-term PV power forecasting based on combined SOM-FCM and KELM method

A hybrid forecasting model was proposed to improve the accuracy of short-term photovoltaic (PV) power generation forecasting, which combined the clustering of trained self-organizing map(SOM) network and optimized kernel extreme learning machine(KELM) method. First, a pure SOM was employed to complete the initial partitions of the training data set. Then clustering was executed on the trained SOM network by fuzzy C-means(FCM). Meanwhile, the davies-bouldin index(DBI) was hired to determine the optimal size of clusters. Finally, in each data partition, the regional KELM model was built with the KELM optimized by differential evolution, or the regional linear regression(MR) model was built with the multiple MR using the least square method to complete the coefficient evaluation. In addition, varying local multiple regression model was also proposed based on SOM. The proposed model based on SOM-FCM and KELM was employed to one-hour-ahead PV power forecasting instances of three different solar power plants provided by the GEFCom2014. Compared with other control models, the mean absolute error (MAE) of plant 1 was reduced by 61.41%, that of plant 2 by 60.19%, and that of plant 3 by 58.92%. The root means square errors (RMSE) of plant 1 was reduced by 52.06%, that of plant 2 by 54.56%, and that of plant 3 by 51.43% on average. The forecasting accuracy was significantly improved with the proposed model.