A CNN-LSTM-LightGBM based short-term wind power prediction method based on attention mechanism

This paper proposes a CNN-LSTM-LightGBM based short-term wind power prediction method based on the attention mechanism, which contains three main parts: data preprocessing, model training and model prediction. In the data preprocessing stage, the historical environment and historical wind power data are collected, then data cleaning and normalization and other preprocessing on the data are performed; in the model training stage, we first build a CNN-LSTM model (model 1) that includes an attention mechanism. CNN network includes the Conv1D layer, the MaxPooling1D layer and the LSTM network includes the basic LSTM layer, the attention layer, the Dropout layer and the final Dense layer. Secondly, we build the LightGBM model (model 2), using the training set and the validation set for the two models above separately. In the model prediction stage, the trained model 1 and model 2 are used to make parallel predictions on the test set, and the MAPE-RW algorithm is employed to linearly combine model 1 and model 2 to form the final combined prediction model. The proposed prediction method considers various environmental factors including weather, wind speed, wind direction, temperature, pressure, humidity, etc., effectively extracts the local characteristics and time series characteristics of the data, and allocates the feature weights reasonably, thus can realize the accurate prediction of wind power. (c) 2022 The Author(s). Published by Elsevier Ltd. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/). Peer-review under responsibility of the scientific committee of the 2021 The 2nd International Conference on Power Engineering, ICPE, 2021.