Wind power generation prediction during the COVID-19 epidemic based on novel hybrid deep learning techniques

Lingshu Zhong, Pan Wu and Mingyang Pei

Renewable Energy, 2024, vol. 222, issue C

Abstract: Wind power generation (WPG) has been expanding rapidly because wind energy is clean, sustainable, and environmentally friendly. Accurate forecasting of WPG is particularly important for maintaining a functioning electricity system in a secure and steady manner. However, WPG is affected by many factors, such as weather, and the accurate prediction of WPG is complex and difficult, especially under special circumstances (e.g., during epidemics, war, or severe weather). To accurately predict WPG under special conditions, a novel hybrid deep learning approach (MLP-LSTM) combined with the long short-term memory (LSTM) network and the multilayer perceptron (MLP) network with fully connected layers is proposed in this paper. The MLP-LSTM method exhibited excellent predictive performance in forecasting WPG. Specifically, considering the external environment, we investigated the influence of factors by forecasting the WPG difference between normal and special cases with statistical regression modeling. The identified determinant information regarding climate factors and epidemic response indices was gathered and matched to the WPG difference and input into the MLP models. The prediction result of the MLP model was further utilized to correct the prediction values of the LSTM network for predicting WPG to obtain precise and reliable prediction values. To further assess the predictive performance of the MLP-LSTM method, WPG data from seven Nordic countries were used in the prediction models. The outcomes demonstrated that the MLP-LSTM method had high accuracy and robustness in predicting WPG, and it outperformed benchmark methods. Moreover, the combined method's prediction error was much lower than that of the single method.

Keywords: Renewable energy; Hybrid deep learning; MLP-LSTM model; Multivariate time series; Wind power generation forecasting (search for similar items in EconPapers)
Date: 2024
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0960148123017780
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:renene:v:222:y:2024:i:c:s0960148123017780

DOI: 10.1016/j.renene.2023.119863

Access Statistics for this article

Renewable Energy is currently edited by Soteris A. Kalogirou and Paul Christodoulides

More articles in Renewable Energy from Elsevier
Bibliographic data for series maintained by Catherine Liu ().