Photovoltaic (PV) Power Prediction Based on ABC - SVM

Abstract

Photovoltaic(PV) generation forecasting technology is an important part of the development of PV grid-connected system, which has a great impact on the reliability, stability and economy of the grid. Due to uncertain meteorological factors such as light intensity, temperature, humidity and wind speed, the output of PV system is random, intermittent and uncontrollable, which makes the prediction accuracy of PV power generation not high. In order to improve the accuracy of PV power generation forecasting, artificial bee colony (ABC) algorithm is used to optimize the support vector machine (SVM) model and predict the PV power generation: Firstly, the ABC algorithm is used to optimize the penalty factor C and the kernel function g of the SVM prediction model. Secondly, the optimized SVM algorithm is trained and tested. Finally, the ABC-SVM algorithm is used to predict the PV generation. The simulation results show that compared with the traditional SVM algorithm, the ABC-SVM algorithm has less control parameters, strong optimization ability, higher prediction accuracy and more stable system, which provides a certain scientific research value for PV power generation forecasting.