A multimodal approach to chaotic renewable energy prediction using meteorological and historical information

Wind energy, which exhibits non-stationarity, randomness, and intermittency, is inextricably linked to meteorological data. The wind power series can be broken down into several subsequences using data decomposition techniques to make forecasting simpler and more accurate. Because of this, a single prediction model does not perform well in extracting hidden information from each subsequence. To predict different frequency series, this research employed shallow and deep learning models and proposed an improved hybrid wind power prediction model based on secondary decomposition, extreme learning machines (ELM), convolutional neural networks (CNN), and bidirectional long short-term memory (BiLSTM). To begin, secondary decomposition was employed to break down the wind power series into several components. The ELM was used to forecast the low-frequency components. Following that, CNN was utilized to reintegrate the input characteristics of the high-frequency components, followed by BiLSTM prediction. Finally, the forecasting values for each component were added to generate the final prediction results.

Requirements:
Python 3.6.x
TensorFlow 1.19.0
Numpy 1.19.5
Pandas 1.0.5
Keras 2.2.5
scikit-learn 0.23.1
Matplotlib 3.2.2

Reference:
The detailed information of CEEMDAN and VMD are shown in:
https://github.com/vrcarva/vmdpy
https://github.com/laszukdawid/PyEMD

Data availability:
Supplementary data to this research can be found online at https://opendata-renewables.engie.com

风力能源，其特征为非平稳性、随机性和间歇性，与气象数据密切相关。通过数据分解技术，可将风力发电量序列分解为若干个子序列，以简化并提高预测的精确度。鉴于单一预测模型在从每个子序列中提取隐含信息方面表现不佳，本研究采用了浅层和深度学习模型，并基于二次分解、极限学习机（ELM）、卷积神经网络（CNN）和双向长短期记忆（BiLSTM）提出了改进的混合风力发电量预测模型。首先，采用二次分解将风力发电量序列分解为多个组成部分。利用ELM对低频分量进行预测。随后，运用CNN重新整合高频分量的输入特征，并随后进行BiLSTM预测。最终，将各分量的预测值相加，以生成最终的预测结果。

技术要求：
Python 3.6.x
TensorFlow 1.19.0
Numpy 1.19.5
Pandas 1.0.5
Keras 2.2.5
scikit-learn 0.23.1
Matplotlib 3.2.2

参考信息：
CEEMDAN和VMD的详细信息请参阅：
https://github.com/vrcarva/vmdpy
https://github.com/laszukdawid/PyEMD

数据可用性：
本研究的相关补充数据可在以下网址获取：https://opendata-renewables.engie.com