A multi-step probability density prediction model based on gaussian approximation of quantiles for offshore wind power br

With the increasing utilization of offshore wind power, accurate prediction of offshore wind power is crucialfor preventive control and scheduling. In this paper, a new hybrid probability density model is proposed formulti-step offshore wind power prediction, including time varying filter based empirical mode decomposition(TVFEMD), approximate entropy (AE), Yeo-Johnson transform quantile regression (YJQR) and gaussianapproximation of quantile (GAQ). Firstly, TVFEMD decomposition and AE theory are used to preprocess theoriginal data for reducing the complexity and modeling workload. Secondly, the 16-step ahead offshore windpower is predicted using YJQR, in which the model structures established for each component are selected bygrid search for comprehensive optimization to ensure the best prediction performance. Finally, the GAQ methodis adopted to construct probability density curves for the 16-step cumulative quantile prediction results. Thevariance of the probability density curves in each step is adjusted to optimize the interval prediction results,resulting in more robust and integrated prediction results. Taking the historical offshore wind power datacollected by German transmission system operator 50 Hertz as an example, the model has higher predictionaccuracy and stability on the basis of obtaining reasonable quantile estimation results in multi-step offshore wind power probabilistic prediction

Automated summary

A new hybrid probability density model is proposed for multi-step offshore wind power prediction in this paper, which includes TVFEMD, AE, YJQR, and GAQ. The model preprocesses the original data, predicts the offshore wind power using YJQR, and constructs probability density curves using GAQ. Experimental results on German 50 Hertz offshore wind power data show that the model has higher prediction accuracy and stability.