关键词:

"> 光伏发电, 光伏功率预测, 层次聚类, 样本熵, 长序列预测, 倒置Transformer

Abstract: [Objectives] Accurate prediction of photovoltaic power is of great significance for the safe, stable and economic operation of power grid. In order to improve the accuracy of pv power prediction, this paper proposes a pv power prediction model based on sample entropy clustering decomposition-inverted Transformer. [Methods] A sample entropy clustering decomposition method is proposed to optimize the sample entropy reconstruction process by introducing a hierarchical clustering algorithm and contour coefficients to construct an adaptive assessment system; Secondly, the optimized variational modal decomposition algorithm is used to perform a targeted quadratic decomposition of the clustered clusters with noise interference; then, the decomposed components are predicted separately using the inverted Transformer model, to deeply mine the correlation between long time series across variables; finally, superimpose the prediction results of each component to get the final prediction results. [Results] Example analysis shows that the proposed method improves R² by 0.7%, 3.1% and 3.2% in sunny, cloudy and rainy days, respectively, compared with the benchmark iTransformer model; and the R² improves by 4.2%, 4.7% and 4.6% in different predicted sequence lengths, which fully verifies the superiority and feasibility of the proposed model. [Conclusions] The proposed method effectively solves the problem of low prediction accuracy caused by the weak characterization of highly fluctuating and intermittent photovoltaic power data in traditional models, as well as the insufficient ability of multivariate long-term time series modeling, and significantly improves the prediction accuracy.

Key words:

"> photovoltaic power generation, photovoltaic power prediction, hierarchical clustering, sample entropy, long sequence prediction, inverted transformer