Imputation based wind speed forecasting technique during abrupt changes in short term scenario

Abstract

It is tough and complex to forecast wind speed due to its intermittent and stochastic nature as well as sudden and abrupt variations in the wind speed. Further, it is required to handle the variety of scenarios e.g. cyber-attacks, unexpected power device malfunction, communication/sensor outages etc. that can cause the missing data.This paper proposes and employs a de-noising autoencoder algorithm for wind speed forecasting to ensure the handling of missing data information. At the next step, the data is processed via variational mode decomposition technique to mitigate the noise and improves the model's prediction accuracy. Furthermore, the bi-directional long-short term memory deep learning approach is tied with convolution neural network to increase prediction accuracy and anticipating the sudden/abrupt changes in wind speed accurately. Finally, actual wind speed related data is examined to scrutinize meticulousness of projected forecast methodology particularly during sudden/abrupt changes in the wind speed. The parameter indicators of the wind speed forecasting technique exhibit the capability of improved predictions under the diversified conditions.