Hybrid model based on K-means++ algorithm, optimal similar day approach, and long short-term memory neural network for short-term photovoltaic power prediction

Abstract

Photovoltaic (PV) power generation is characterized by randomness and intermittency due to weather changes. Consequently, large-scale PV power connections to the grid can threaten the stable operation of the power system. An effective method to resolve this problem is to accurately predict PV power. In this study, an innovative short-term hybrid prediction model (i.e., HKSL) of PV power is established. The model combines K-means++, optimal similar day approach, and long short-term memory (LSTM) network. Historical power data and meteorological factors are utilized. This model searches for the best similar day based on the results of classifying weather types. Then, the data of similar day are inputted into the LSTM network to predict PV power. The validity of the hybrid model is verified based on the datasets from a PV power station in Shandong Province, China. Four evaluation indices, mean absolute error, root mean square error (RMSE), normalized RMSE, and mean absolute deviation, are employed to assess the performance of the HKSL model. The RMSE of the proposed model compared with those of Elman, LSTM, HSE (hybrid model combining similar day approach and Elman), HSL (hybrid model combining similar day approach and LSTM), and HKSE (hybrid model combining K-means++, similar day approach, and LSTM) decreases by 66.73%, 70.22%, 65.59%, 70.51%, and 18.40%, respectively. This proves the reliability and excellent performance of the proposed hybrid model in predicting power.