Ultra‐Short‐Term Wind Speed Prediction Based on Information Aggregation With Spatial Decoupling in Turbine Cluster Space

ABSTRACT Accurate wind speed prediction is essential for the safe and stable operation of the power system. Thus, an ultra‐short‐term prediction model of a convolutional memory network is proposed based on information aggregation of cluster space decoupling in this paper. Firstly, the influence of the wake effect of the cluster is analysed and the wake effect impact factor is embedded into cluster analysis to realise the space decoupling based on the wake correlation of the wind turbines. Then, the spatial correlation index is constructed. The representative wind turbine is selected from each decoupling cluster. And the spatial information domain is extended by combining temporal information similarity. Based on the aggregation information of the high‐order spatial domain, the convolutional memory network is constructed to enhance the spatial characteristics and carry out ultra‐short‐term prediction of wind speed. Finally, the proposed model is applied to the wind speed prediction of an actual wind farm and the effectiveness and applicability of the model are verified through comparative analysis.