A novel non-iterative correction method for short-term photovoltaic power forecasting

By Wansi Yin, Yutong Han, H. Zhou, Ming Ma, L. Li, Honglu Zhu. 2020

69 citations recorded by the source corpus.

Abstract Short-term photovoltaic (PV) power forecasting is of great significance for the real-time dispatching of power systems, but the accuracy of short-term forecasting of PV power is not satisfactory. Mastering the distribution characteristics of forecasting error and correcting the forecasting results are effective ways to improve the short-term forecasting accuracy. In this paper, the error distribution characteristics of short-term prediction results of PV power are studied, and then a non-iterative correction method for PV power short-term forecasting is proposed. The statistical result show that the error distribution is different in different seasons, the power forecasted error is strongly similar to the irradiance error distribution in numerical weather prediction (NWP). Therefore, this paper calculates the short-term forecasting results through seasonal models and uses non-iterative method to correct forecasting results, which can effective avoids the influence of accumulation errors. Compared with other methods, the root mean square error (RMSE) of this method is reduced by about 4.5%, and the mean absolute error (MAE) is reduced by about 2.6%, it shows the method can effectively improve the short-term forecasting accuracy of PV power.

Subfields: Artificial Intelligence, Electrical and Electronic Engineering, Renewable Energy, Sustainability and the Environment

View Paper: https://www.semanticscholar.org/paper/73c28fe7cdf82c4c314401cb0a2baf2f892ce1df