Retracted: Using Fuzzy Uncertainty Quantization and Hybrid RNN-LSTM Deep Learning Model for Wind Turbine Power

Abstract

Along with the many benefits, which the high penetration of wind turbine has brought to the smart grids, the issues arising due to the uncertainty effect is an inevitable phenomenon, which needs to be controlled. The high uncertainty effects can cause unstable operation and management scheduling plans, which can cause severe problems for both the operator and customers. This paper proposes a new quantization approach based on hybrid deep learning to capture the forecast error in the wind turbine output power. The proposed method is equipped with a long-short term memory (LSTM) model and recurrent neural network (RNN) to learn the most effective spatial-temporal features in wind turbine output power. Due to the high complexity of the data, a new optimization method based on a modified sine cos algorithm is proposed to help more stable training of the model. The feasibility and appropriate performance of the model is assessed through experimental analysis on two datasets in the Australia wind farms.