Short-term PV power forecasting based on time series expansion and high-order fuzzy cognitive maps.

Achieving short-term accurate photovoltaic power forecasting is of great significance to improve the efficiency of grid operation, especially in power stations where historical values of meteorological parameters are lagged or not recorded. Therefore, numerous studies have been presented to predict the intricate stochastic properties of photovoltaic power sequence in recent years. However, due to the limitation of algorithm performance and the effect of noise in the time series, previously proposed methods may not extract effective features from power data. Furthermore, most studies have only focused on point prediction, which ignores the uncertain information and unavoidable forecast bias. In this study, a hybrid framework based on fuzzy information granulation algorithm, improved variational mode decomposition technique, and high-order fuzzy cognitive maps is proposed to fill these gaps. Comparison experiments were set up using 5-minute photovoltaic power data from Alice Springs, Australia. The computational results not only demonstrate that the proposed framework significantly improves forecast accuracy of short-term photovoltaic power, but also achieves effective interval prediction by fuzzy information. • A novel hybrid PV power forecasting framework is established. • IVMD is proposed to decompose modes and reduce noise in original datasets. • FIG algorithm is designed to analyze the uncertainty of PV power load forecasting. • Bayesian ridge regression is developed to compute the model's structure and weights. [ABSTRACT FROM AUTHOR]