Ultra-short-term wind speed and wind power forecast via selective Hankelization and low-rank tensor learning-based predictor. (September 2022)

• Record Type: Journal Article
• Authors: Ji, Tianyao; Jiang, Yuzi; Li, Mengshi; Wu, Qinghua
• Is Part Of: International journal of electrical power & energy systems. Volume 140(2022)
• Publication Date: 2022-09
• Subjects: Wind power forecasting -- Wind speed forecasting -- Tensor forecasting -- Feature selection -- Hankelization -- Tucker decomposition; Electrical engineering -- Periodicals; Electric power systems -- Periodicals; Électrotechnique -- Périodiques; Réseaux électriques (Énergie) -- Périodiques; Electric power systems; Electrical engineering; Periodicals; 621.3
• DOI: 10.1016/j.ijepes.2022.107994
• Languages: English
• ISSNs: 0142-0615

Abstract

Abstract: Accurate wind power or wind speed point forecast (WPF/WSF) can provide useful information for decision-makers to achieve a better energy management. This paper proposes an efficient univariate forecasting framework with a selective Hankelization (SH) technique and a low-rank tensor learning-based predictor (LRP). SH is applied to transform the original time series (e.g., wind data × time point) into a high-order tensor structure (e.g., wind data × similarity × time point). In SH, Hankelization introduces the additional dimension; similarity search (SS) collects the training samples sharing most similar features to the test sample; similarity rearranger (SR) reorders the fibres/vectors in tensors. The above three steps construct the translation invariance features in tensors' 2D slices. With the tensor structure, the forecasting task is transferred to a higher dimension, where the proposed LRP performs efficiently. It applies Tucker decomposition (TD) for low-rank approximation and extracts low-rank core tensors for regression, which reduces information redundancy and computational cost. Then the low-rank tensor learning network (LRN), which implements a long short-term memory network (LSTM) with attention as an encoder and a multilayer perceptron (MLP) as a decoder, is designed for tensors regression in LRP. Such encoder–decoder network is used as the tensor-to-tensor learning network and can fit the correlation between slices well. Finally, experiments are carried out using wind speed/power data obtained from two datasets. The results demonstrate that the proposed method, compared to the mainstream global forecasting methods, improves the NMAE, NRMSE, and MAPE criteria by 22%, 25%, and 19% for WPF and by 9%, 11%, and 8% for WSF. It also outperforms some state-of-the-art local forecasting methods in terms of accuracy, which improves the three criteria by 8%, 11%, and 7% for WPF and by 3%, 7%, and 3% for WSF. In this process, the mapping to high dimension, the use of SS, the strategy of multi-step sampling and the architecture of the LRN all play positive and effective roles in improving the accuracy. Highlights: A novel SH-LRP method has been constructed for ultra-short term wind speed/wind power forecasting, where Selective Hankelization (SH) is proposed to fold the univariate wind data into 3D space to depict the temporal autocorrelation features of the time series in higher dimensions. In data pre-process, we creatively propose the method of assembling fibres to make image-like 2D slices with similarity search, where the similarity of external environment can be transformed into translation-invariant features. A reorganized network-LRN (sequence-to-sequence LSTM with attention as encoder and MLP as decoder) is proposed as a tensor-to-tensor learning network to improve the prediction accuracy of post-processing tensor-to-tensor predictors. Experiments have demonstrated the advantage of the proposed method, and comparison studies have shown that it outperforms some main-stream global forecasting methods and state of-the-art local forecasting methods.