Sparse Oblique Decision Tree for Power System Security Rules Extraction and Embedding

Increasing the penetration of variable generation has a substantial effect on operational reliability power systems. The higher level uncertainty that stems from this variability makes it more difficult to determine whether given operating condition will be secure or insecure. Data-driven techniques provide promising way identify security rules can embedded in economic dispatch model keep system states secure. This paper proposes using sparse weighted oblique decision tree learn accurate, understandable, and embeddable are linear extracted as matrices recursive algorithm. These matrix then easily constraints calculations Big-M method. Tests several large datasets with high renewable energy demonstrate effectiveness proposed In particular, outperforms state-of-art while keeping simple. When dispatch, these significantly increase percentage reduce average solution time.