Adaptive wind generation modeling by fuzzy clustering of experimental data

The massive penetration of wind generators in existing electrical grids is causing several critical issues, which are pushing system operators to enhance their operation functions in order to mitigate the effects produced by the intermittent and non-programmable generation profiles. In this context, the integration of wind forecasting and reliability models based on experimental data represents a strategic tool for assessing the impact of generators and grid operation state on the available power profiles. Unfortunately, field data acquired by Supervisory Control and Data Acquisition systems can be characterized by outliers and incoherent data, which need to be properly detected and filtered in order to avoid large modeling errors. To deal with this challenging issue, in this paper a novel methodology fusing Fuzzy clustering techniques, and probabilistic-based anomaly detection algorithms are proposed for wind data filtering and data-driven generator modeling.