A Non-stationary Transformer model for power forecasting with dynamic data distillation and wake effect correction suitable for large wind farms

Abstract

Listen

Translate article

Reliable, high-precision short-term power forecasting is crucial for ensuring power safety and improving wind energy utilization. However, the randomness and non-stationary features of wind present significant challenges in enhancing the precision and efficiency of power forecasts in large-scale wind farm (WF). Previous research often fails to adaptively enhance the original data’s features and neglects the impact of wake effects between wind turbines (WTs), leading to reduced forecasting accuracy. In this paper, a novel method is proposed for power forecasting based on non-stationary Transformer model, which also incorporates dynamic data distillation and wake effect correction to improve forecasting performance. In this proposed method, a non-stationary Transformer model is proposed for extracting features from supervisory control and data acquisition (SCADA) data, which significantly improved the feature extraction capability for non-stationary SCADA data. A dynamic data distillation technique is proposed to remove redundant data and enhance dataset quality, and the wake effect is developed to correct forecasting results and reducing error sources. Dynamic data distillation addresses the loss of data features caused by dataset preprocessing, while wake correction reduces the forecasting errors caused by the wake effect between WTs. The SCADA datasets are used from northwest and northeast China WFs, and the forecasting results demonstrate the effectiveness and superiority of the proposed method. Ablation experiments further confirm that dynamic data distillation and wake effect effectively enhance wind power forecasting accuracy.