Multi-step wind speed forecasting based on hybrid multi-stage decomposition model and long short-term memory neural network

Moreno, Sinvaldo Rodrigues; Silva, Ramon Gomes da; Mariani, Viviana Cocco; Coelho, Leandro dos Santos

doi:10.1016/j.enconman.2020.112869

Cited by 113 publications

(27 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There are three main concepts related to VMD, which are Wiener filtering, Hilbert transform and analytic signal, and frequency mixing and heterodyne demodulation. Sparsity prior of each mode is chosen as bandwidth in the spectral domain and can be accessed by the following scheme for each model: (i) compute associated analytic signal utilizing the Hilbert transform to obtain a unilateral frequency spectrum; (ii) shift frequency spectrum of mode to baseband by mixing the exponential tune to the respective estimated center frequency; and (iii) the bandwidth estimated through the Gaussian smoothness of the demodulated signal [21].…”

Section: Methodologiesmentioning

confidence: 99%

“…By the coupling of some methods, it is possible to use the specialty of each one to deal with different characteristics and therefore building an effective model. In context of the preprocessing techniques, especially signal decomposition methods, the variational mode decomposition (VMD) [20] is an effective approach to decompose a dimensional signal into an ensemble of band-limited modes with specific bandwidth in a spectral domain applied in several fields [21,22,23], once can deal with nonlinearities, and non-stationarity inherent to time series. Considering the intrinsic mode function (IMF) obtained through VMD, it is hard to choose AI models to train and forecasting the VMD components.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Forecasting Brazilian and American COVID-19 cases based on artificial intelligence coupled with climatic exogenous variables

Silva

Ribeiro

Mariani

et al. 2020

Chaos, Solitons & Fractals

Self Cite

114

View full text Add to dashboard Cite

The novel coronavirus disease (COVID-19) is a public health problem once according to the World Health Organization up to June 10th, 2020, more than 7.1 million people were infected, and more than 400 thousand have died worldwide. In the current scenario, the Brazil and the United States of America present a high daily incidence of new cases and deaths. Therefore, it is important to forecast the number of new cases in a time window of one week, once this can help the public health system developing strategic planning to deals with the COVID-19. The application of the forecasting artificial intelligence (AI) models has the potential of deal with difficult dynamical behavior of time-series like of COVID-19. In this paper, Bayesian regression neural network, cubist regression, k-nearest neighbors, quantile random forest, and support vector regression, are used stand-alone, and coupled with the recent preprocessing variational mode decomposition (VMD) employed to decompose the time series into several intrinsic mode functions. All AI techniques are evaluated in the task of timeseries forecasting with one, three, and six-days-ahead the cumulative COVID-19 cases in five Brazilian and American states, with a high number of cases up to April 28th, 2020. Previous cumulative COVID-19 cases and exogenous variables as daily temperature and precipitation were employed as inputs for all forecasting models. The models' effectiveness are evaluated based on the performance criteria. In general, the hybridization of VMD outperformed single forecasting models regarding the accuracy, specifically when the horizon is six-days-ahead, the hybrid VMD-single models achieved better accuracy in 70% of the cases. Regarding the exogenous variables, the importance ranking as predictor variables is, from the upper to the lower, past cases, temperature, and precipitation. Therefore, due to the efficiency of evaluated models to forecasting cumulative COVID-19 cases up to six-days-ahead, the

show abstract

Section: Methodologiesmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Forecasting Brazilian and American COVID-19 cases based on artificial intelligence coupled with climatic exogenous variables

Silva

Ribeiro

Mariani

et al. 2020

Chaos, Solitons & Fractals

Self Cite

114

View full text Add to dashboard Cite

show abstract

“…The training data are centered by its mean value and divided by its standard deviation. To develops multi-days-ahead COVID-19 cases forecasting, recursive strategy is employed [24] . In this aspect, one model is fitted for one-day-ahead forecasting.…”

Section: Proposed Forecasting Frameworkmentioning

confidence: 99%

Short-term forecasting COVID-19 cumulative confirmed cases: Perspectives for Brazil

Ribeiro

Silva

Mariani

et al. 2020

Chaos, Solitons & Fractals

431

313

View full text Add to dashboard Cite

Elsevier has created a COVID-19 resource centre with free information in English and Mandarin on the novel coronavirus COVID-19. The COVID-19 resource centre is hosted on Elsevier Connect, the company's public news and information website. Elsevier hereby grants permission to make all its COVID-19-related research that is available on the COVID-19 resource centre-including this research content-immediately available in PubMed Central and other publicly funded repositories, such as the WHO COVID database with rights for unrestricted research re-use and analyses in any form or by any means with acknowledgement of the original source. These permissions are granted for free by Elsevier for as long as the COVID-19 resource centre remains active.

show abstract

“…PLS is a straightforward dimensionality reduction technique that maps the variables in a new feature space with lower dimensions. The Variable Importance of load Patterns (VIP) for 32 features is shown in Regarding Figure 9, the most important features are hour, workday, temperature and lagged load (t − x) with x ∈ [1,2,3,4,5,6,7,11,12,13,17,18,19,20,21,22,23]. Thus, the selected threshold is VIP = 0.5.…”

Section: Data Pre-processing and Feature Engineeringmentioning

confidence: 99%

“…This gives more information about the samples periodicity [15]. To improve cognition for time series data, the authors in [17] coupled LSTM with Singular Spectral analysis and variational mode decomposition. However, most of CNN and LSTM deployment is applied to classification problems such as natural language recognition and image classification.…”

Section: Introductionmentioning

confidence: 99%

PLS-CNN-BiLSTM: An End-to-End Algorithm-Based Savitzky–Golay Smoothing and Evolution Strategy for Load Forecasting

et al. 2020

View full text Add to dashboard Cite

This paper proposes an effective deep learning framework for Short-Term Load Forecasting (STLF) of multivariate time series. The proposed model consists of a hybrid Convolutional neural network-Bidirectional Long Short-Term Memory (CBiLSTM) based on the Evolution Strategy (ES) method and the Savitzky–Golay (SG) filter (SG-CBiLSTM). The adopted methodology incorporates the virtue of different prepossessing blocks to enhance the performance of the CBiLSTM model. In particular, a data-augmentation strategy is employed to synthetically improve the feature representation of the CBiLSTM model. The augmented data is forwarded to the Partial Least Square (PLS) method to select the most informative features above the predefined threshold. Next, the SG algorithm is computed for smoothing the load to enhance the learning capabilities of the underlying system. The structure of the SG-CBiLSTM for the ISO New England dataset is optimized using the ES technique. Finally, the CBiLSTM model generates output forecasts. The proposed approach demonstrates a remarkable improvement in the performance of the original CBiLSTM model. Furthermore, the experimental results strongly confirm the high effectiveness of the proposed SG-CBiLSTM model compared to the state-of-the-art techniques.

show abstract

Multi-step wind speed forecasting based on hybrid multi-stage decomposition model and long short-term memory neural network

Cited by 113 publications

References 40 publications

Forecasting Brazilian and American COVID-19 cases based on artificial intelligence coupled with climatic exogenous variables

Forecasting Brazilian and American COVID-19 cases based on artificial intelligence coupled with climatic exogenous variables

Short-term forecasting COVID-19 cumulative confirmed cases: Perspectives for Brazil

PLS-CNN-BiLSTM: An End-to-End Algorithm-Based Savitzky–Golay Smoothing and Evolution Strategy for Load Forecasting

Contact Info

Product

Resources

About