Secondary Factor Induced Wind Speed Time-Series Prediction Using Self-Adaptive Interval Type-2 Fuzzy Sets with Error Correction

Abstract

Accurate wind speed forecasting is very crucial for wind power generation systems, but the inherent randomness of wind speeds makes wind speed forecasting challenging. There have been many studies on predicting wind speeds, but they ignored the influence factor of wind speed on its change over time with multiple factors, such as wind direction, temperature, humidity and atmospheric pressure. Therefore, a secondary factor induced wind speed time series prediction using self-adaptive interval type-2 fuzzy sets (IT2FS) with error correction was proposed. First, an IT2FS model is developed to induce secondary factors to predict wind speed and select the best prediction value. Specifically, the differential evolution (DE) algorithm is employed to optimize parameters of IT2FS model. Second, error correction strategy is adopted to correct the model error. Variational mode decomposition (VMD) is used to decompose the residual sequence and autoregressive integrated moving average model (ARIMA) is used to predict each decomposed mode signal. Finally, by predicting the wind speed of two wind farms in China, it is verified that the proposed hybrid system transcends the other compared single and traditional models and simultaneously realizes high accuracy and strong stability. Thus, employing a new strategy to conduct the main factor time series prediction using its secondary factors is extremely useful for enhancing the prediction precision.