Wind Speed Prediction Based on VMD-BLS and Error Compensation

As one of the fastest-growing new energy sources, wind power technology has attracted widespread attention from all over world. In order to improve quality generation, speed prediction is an indispensable task. this paper, error correction-based Variational Mode Decomposition and Broad Learning System (VMD-BLS) hybrid model proposed for prediction. First, decomposed into multiple components by VMD algorithm, then ARMA established each component find optimal number sequence divisions. Second, BLS used predict component, results are summed obtain forecast value. However, in some traditional methods, there always time lag, which will reduce accuracy. To deal with this, a novel correction technique developed utilizing BLS. Through verification experiment actual data, it proves that method can phenomenon achieve higher accuracy than approaches, shows our method’s effectiveness practice.