A short-term wind speed prediction method utilizing rolling decomposition and time-series extension to avoid information leakage

ABSTRACT

The accuracy of wind speed prediction is crucial for the efficient operation and scheduling of power grids. In recent years, many wind speed prediction methods have been proposed, but the results have always been unsatisfactory, and the model accuracy in experimental testing has always been overestimated. This study focuses on the problem of information leakage caused by the decomposition of the test and general training sets in traditional wind speed prediction methods. Using the original model without decomposition as the standard and the mean average (P_MAE) and mean squared (P_MSE) errors as evaluation metrics, the overestimation degree of information leakage on the model accuracy was quantified. The results show that when the test set is decomposed together, the accuracy of the model is significantly overestimated. Specifically, the overestimation of P_MAE ranges from 40% to 55%, and that of P_MSE is from 65% to 85%. In addition, a singular spectrum analysis (SSA) – rolling decomposition (RD) – convolutional neural network (CNN) – bidirectional gated recurrent unit (BiGRU) – attention mechanism (AM) model based on the RD method was proposed. First, SSA was used to denoise the wind speed sequence, and then RD was performed on the original sequence to provide input vectors for the neural network model. Then, the CNN – BiGRU – AM hybrid neural network module predicted the wind speed sequence. Finally, to suppress the impact of boundary effects on the model accuracy, a time-series extension strategy based on neural networks was incorporated into the model. An example analysis indicates that the SSA – RD – CNN – BiGRU – AM model can avoid information leakage compared with other traditional models.

KEYWORDS:

• Short-term wind speed prediction
• rolling decomposition
• time-series extension
• information leakage
• wind energy

Disclosure statement

No potential conflict of interest was reported by the author(s).

Additional information

Funding

The work was supported by the National Natural Science Foundation of China [52178452]; the Science Research Foundation of Hunan Provincial Department of Education [22A0595]; Hunan Provincial Talent Recruitment Project Fund [2023TJ-N17]; the Practical Innovation and the Entrepreneurship Ability Improvement Plan of Changsha University of Science and Technology [CLSJCX23040]; Training Program for Excellent Young Innovators of Changsha [kq1905004]

Notes on contributors

Pinhan Zhou

Pinhan Zhou, Conceptualization, study design, execution, and analysis.

Lian Shen

Lian Shen, Conceptualization, methodology, and validation.

Yan Han

Yan Han, Project administration, writing-review.

Lihua Mi

Lihua Mi, Validation, writing-review.

Guoji Xu

Guoji Xu, Methodology and writing-review.