Wind power fluctuation characteristics of Three North regions based on clustering algorithm

Limited by some restricted conditions, such as the grid structure and the power source type, the security of the grid and the consumption of the clean energy have faced the challenge from the random and intermittent characteristics of wind power. Firstly, an analyzing method to divide and express different types of wind power fluctuation process is proposed by utilizing the self‐organizing map clustering algorithm in this paper. The research framework of wind power fluctuations characteristics considering multiple space and time scales is also proposed. Furthermore, on the basis of the actual operation data of the north, northeast and northwest parts of China (Three North regions for short), and different time characteristics of the wind power fluctuations have been researched from three different spatial scales such as the wind power plant, the provincial grid and the regional grid. From the actual data analysis results, it can be seen that the wind power fluctuations categories can be efficiently identified by the self‐organizing map clustering algorithm. The results also show that, the time and spatial scale analysis of wind power fluctuations characteristics can support the quantitative evidences for the scheduling decision of the wind power enrichment regions.