数据驱动的电力系统动态安全评估研究综述OA

The integration of large-scale new energy and flexible loads increases the uncertainty of power grid operating conditions,and the operating status of the power grid frequently approaches the stability limit,highlighting various dynamic security risks.As an efficient assessment method,data-driven dynamic security assessment(DSA)can directly obtain the mapping relationship between input features and dynamic security output,which can timely discover various dynamic security risks.It is an important means to improve the intelligent defense level of the power system.With the development of power big data and artificial intelligence techniques,various cutting-edge machine learning methods are explored and applied to the DSA.According to the procedure of data-driven DSA,the current research status was reviewed in terms of four perspectives:feature selection,model training,model updating,and online assessment.Moreover,five major challenges were summarized.