Short-Term Forecasting of Wind Power Using CEEMDAN-ICOA-GRU Model

Accurate wind power prediction plays a vital role in ensuring the safe operation of wind power connected to the grid. To improve the prediction accuracy of wind power, a short-term wind power prediction model (CEEMDAN-ICOA-GRU) based on a Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) combined with improved Coati Optimization Algorithm(ICOA) to optimize Gated Recurrent Unit (GRU) is proposed in this paper. First, CEEMDAN was used to decompose the original wind power data, reduce its volatility, and reduce the lag of the forecast curve. Then, to solve the problem that the traditional Coati Optimization Algorithm(COA) is prone to locally optimal solutions, chaotic sequences are added to improve the initial population distribution to be more uniform. Finally, ICOA is used to optimize the hyperparameters of GRU to obtain the optimal prediction model, which is used to predict different sub-sequences, and the prediction results are superimposed to obtain the final prediction results. To verify the validity of the model, a large number of experiments were conducted using the data set of a wind power plant in Turkey in 2022. The results show that CEEMDAN-ICOA-GRU can effectively improve the accuracy of wind power prediction.