Long-Term Wind Power Forecasting Using Variational Mode Decomposition and Convolutional Neural Netwrok

Danya Al-Hindawi, Maher Al-Greer, Gobind Pillai

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This research paper presents a two-step wind power forecasting in wind turbine applications. The proposed approach incorporates Variational Mode Decomposition (VMD) as a feature extraction method, followed by Convolutional Neural Network (CNN) model. The effectiveness of this method is evaluated using real wind power data, results demonstrate the accuracy and reliability of the proposed technique. Specifically, the VMD-CNN model trained with a 90% training and 10% testing split achieves the highest accuracy, yielding an RMSE value of 0.1307. The comparative analysis with previous architectures that do not employ decomposition reveals the superior performance of the proposed method. Moreover, it exhibits promising potential for long-term wind power forecasting, outperforming recently proposed methods.

Original languageEnglish
Title of host publication58th International Universities Power Engineering Conference, UPEC 2023
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1-5
Number of pages5
ISBN (Electronic)9798350316834
DOIs
Publication statusPublished - 1 Nov 2023
Event58th International Universities Power Engineering Conference - Technological University , Dublin, Ireland
Duration: 30 Aug 20231 Sept 2023
https://upec2023.com/

Conference

Conference58th International Universities Power Engineering Conference
Abbreviated titleUPEC 2023
Country/TerritoryIreland
CityDublin
Period30/08/231/09/23
Internet address

Bibliographical note

Publisher Copyright:
© 2023 IEEE.

Fingerprint

Dive into the research topics of 'Long-Term Wind Power Forecasting Using Variational Mode Decomposition and Convolutional Neural Netwrok'. Together they form a unique fingerprint.

Cite this