Wind speed forecasting based on variational mode decomposition and improved echo state network

Hu, Huanling; Wang, Lin; Tao, Rui

doi:10.1016/j.renene.2020.09.109

Cited by 142 publications

(60 citation statements)

References 52 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…8,9 Statistical methods are artificial intelligencebased methods to find the hidden relationship between past power data and weather forecast data. In this field, artificial neural networks-based, [11][12][13] support vector machines-based, 14,15 and linear regression-based 16,17 models are frequently used for accurate estimation of wind speed and power. Physical methods generally use characteristics of power plant area such as roughness, height, and slope of the area as the inputs of the models.…”

Section: Introductionmentioning

confidence: 99%

Reducing the cost of wind resource assessment: using a regional wind power forecasting method for assessment

Özkan

Karagöz

2021

Int J Energy Res

View full text Add to dashboard Cite

Wind energy, with its high potential, has an important place among renewable energy sources. Therefore, the number of investments on wind energy is increasing with new turbine technologies and solutions. For the investors of these technologies, how to determine the location of wind turbines for such investments is a challenging and critical problem. Wind maps of the country are a useful resource to determine high potential locations. However, such maps often present an overview to provide the general picture, and there is a need for a more detailed analysis, specifically on the potential plant area. In this paper, we investigate the use of a recent regional wind power forecast method to determine the wind power potential. By applying the RegionalSHWIP on a potential plant area, investors can obtain the preliminary power prediction, hence the wind potential of the area, without any financial cost recurring for measurements and with negligible manhour for computation. The wind resource assessments of the RegionalSHWIP have been analyzed in comparison to the wind maps of four provinces from different regions of Turkey. In all of these test provinces, it has been observed that the model produces results compatible with the values in the wind potential atlas. In

show abstract

Section: Introductionmentioning

confidence: 99%

Reducing the cost of wind resource assessment: using a regional wind power forecasting method for assessment

Özkan

Karagöz

2021

Int J Energy Res

View full text Add to dashboard Cite

show abstract

“…Besides traditional AI/ML models, deep learning and extreme learning machines are also commonly applied in wind speed forecasting. Notable architectures include Kernel Extreme Learning Machine (KELM) [13,14], Long Short-Term Memory (LSTM) [15,16], Echo State Network [17], Deep Belief Network (DBN) [18,19], and Convolutional Neural Network (CNN) [20,21].…”

Section: Introductionmentioning

confidence: 99%

“…Considering the intrinsic weaknesses of all models, it is difficult for a single forecasting model to adequately capture the complex relationships of wind speed time series [22,23]. Therefore, a better approach is to use hybrid methods where every model utilizes its individual capability.…”

Section: Introductionmentioning

confidence: 99%

“…Aggregating all the individual predictions results in the final forecast [1]. Commonly used decomposition approaches are Wavelet Transformation [37], Empirical Mode Decomposition [38], Variational Mode Decomposition [17], and their variants [39]. The individual prediction models can either be statistical, artificial intelligence, or bothfor instance, WT-ARIMA [7], EMD-PE-ANN [38], VMD-PRBF-ARMA-E [40], EEMD-PSF-ARIMA [39], WT-VMD-DLSTM-AT [41], EWT-BiDLSTM [42].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Short-Term Wind Speed Forecasting Based on Hybrid MODWT-ARIMA-Markov Model

2021

View full text Add to dashboard Cite

Markov chains (MC) are statistical models used to predict very short to short-term wind speed accurately. Such models are generally trained with a single moving window. However, wind speed time series do not possess an equal length of behavior for all horizons. Therefore, a single moving window can provide reasonable estimates but is not an optimal choice. In this study, a forecasting model is proposed that integrates MCs with an adjusting dynamic moving window. The model selects the optimal size of the window based on a similar approach to the leave-one-out method. The traditional model is further optimized by introducing a self-adaptive state categorization algorithm. Instead of synthetically generating time series, the modified model directly predicts one-step ahead wind speed. Initial results indicate that adjusting the moving window MC prediction model improved the forecasting performance of a single moving window approach by 50%. Based on preliminary findings, a novel hybrid model is proposed integrating maximal overlap discrete wavelet transform (MODWT) with auto-regressive integrated moving average (ARIMA) and adjusting moving window MC. It is evident from the literature that MC models are suitable for predicting residual sequences. However, MCs were not considered as a primary forecasting model for the decomposition-based hybrid approach in any wind forecasting studies. The improvement of the novel model is, on average, 55% for single deep learning models and 30% for decomposition-based hybrid models.

show abstract

“…Machine learning models are the third class of forecasting algorithms. They have been widely applied in predicting wind speed with good learning ability and nonlinear mapping ability [15]. Examples of these methods include neural networks, fuzzy-based systems, and decision trees.…”

Section: Introductionmentioning

confidence: 99%

Wind Speed Forecasting Using the Stationary Wavelet Transform and Quaternion Adaptive-Gradient Methods

2021

View full text Add to dashboard Cite

Accurate wind speed forecasting is a fundamental requirement for advanced and economically viable large-scale wind power integration. The hybridization of the quaternion-valued neural networks and stationary wavelet transform has not been proposed before. In this paper, we propose a novel wind-speed forecasting model that combines the stationary wavelet transform with quaternion-valued neural networks. The proposed forecasting model represents wavelet subbands in quaternion vectors, which avoid separating the naturally correlated subbands. The forecasting model consists of three main steps. In the first step, the wind speed signal is decomposed using the stationary wavelet transform into sublevels. In the second step, a quaternion-valued neural network is used to forecast wind speed components in the stationary wavelet domain. Finally, the inverse stationary wavelet transform is applied to estimate the predicted wind speed. In addition, a softplus quaternion variant of the RMSProp learning algorithm is developed and used to improve the performance and convergence speed of the proposed model. The proposed model is tested on wind speed data collected from different sites in China and the United States, and the results demonstrate that it consistently outperforms similar models based on real-valued neural networks, complex-valued neural networks, or LSTM units. In the meteorological terminal aviation routine (METAR) dataset experiment, the proposed wind speed forecasting model reduces the mean absolute error, and root mean squared error of predicted wind speed values by 26.5% and 33%, respectively, in comparison to a number of existing approaches INDEX TERMS Wind Speed Forecasting, Stationary Wavelet Transform, Quaternion Valued Neural Network, RMSProp learning algorithm.

show abstract

Wind speed forecasting based on variational mode decomposition and improved echo state network

Cited by 142 publications

References 52 publications

Reducing the cost of wind resource assessment: using a regional wind power forecasting method for assessment

Reducing the cost of wind resource assessment: using a regional wind power forecasting method for assessment

Short-Term Wind Speed Forecasting Based on Hybrid MODWT-ARIMA-Markov Model

Wind Speed Forecasting Using the Stationary Wavelet Transform and Quaternion Adaptive-Gradient Methods

Contact Info

Product

Resources

About