Adaptive VMD based optimized deep learning mixed kernel ELM autoencoder for single and multistep wind power forecasting

In this paper, an efficient new hybrid time series forecasting model combining variational mode decomposition (VMD) and Deep learning mixed Kernel ELM (MKELM) Autoencoder (AE) has been presented for precise prediction of wind power. It is well known that KELM-AE avoids manual tuning of weights of hi...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Energy (Oxford) Jg. 244; S. 122585
Hauptverfasser: Krishna Rayi, Vijaya, Mishra, S.P., Naik, Jyotirmayee, Dash, P.K.
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Oxford Elsevier Ltd 01.04.2022
Elsevier BV
Schlagworte:
Adaptive variational mode decomposition
Algorithms
Back propagation
Back propagation networks
California
Deep learning
Deep learning kernel ELM Autoencoder
energy
Exact solutions
Forecasting
Heuristic methods
Hydrologic cycle
Kernels
Machine learning
Mathematical models
Multistep prediction
Neural networks
Noise prediction
Optimization
Outliers (statistics)
Parameters
prediction
Sine cosine water cycle algorithm
Spain
time series analysis
Trigonometric functions
wind
Wind farms
Wind power
Wind power prediction
Wyoming
Wyoming
California
Spain
Multistep prediction
Deep learning kernel ELM Autoencoder
Adaptive variational mode decomposition
Wind power prediction
Sine cosine water cycle algorithm
ISSN:0360-5442, 1873-6785
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:In this paper, an efficient new hybrid time series forecasting model combining variational mode decomposition (VMD) and Deep learning mixed Kernel ELM (MKELM) Autoencoder (AE) has been presented for precise prediction of wind power. It is well known that KELM-AE avoids manual tuning of weights of hidden layer nodes, and exhibits superb model generalization property, reduces execution time, and produces exact solution of output weights by generalized least squares resulting in compact storage space, etc. This is in contrast to other deep learning neural network models with nonconvex optimization problems, time consuming training process and limitations of backpropagation learning algorithms. Further the VMD parameters (α, K) are optimized to yield suitable number of intrinsic modes (IMFs) using a newly presented meta-heuristic population based Sine Cosine integrated water cycle algorithm (SCWCA) algorithm. Further the mixed kernel parameters and their associated weights are optimized using the same SCWCA to improve the performance of the Deep MKELM predictor against any outliers or noise in the data. Wind power data of three wind farms located in Sotavento Spain, Wyoming, and California, USA are applied for short-term and multi-step prediction of wind power with significant accuracy. [Display omitted] •A new Deep learning mixed kernel ELM-AE is presented for wind power prediction.•Adaptive VMD is used to select suitable IMFs as inputs to Deep MKELM Autoencoder.•MKELM-AE parameters are optimized using a novel Sine Cosine Water Cycle Algorithm.•Multi step forecasting of wind power is achieved using the Robust MKELM-AE.•High prediction accuracy is achieved using data from three wind farms.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:0360-5442
1873-6785
DOI:10.1016/j.energy.2021.122585