With the continuous expansion of the power system scale and extensive application of phasor measurement units (PMUs), the secure operation of power systems has been increasingly concerned. In this paper, an integrated scheme for online dynamic security assessment (DSA) based on feature selection and regression prediction is proposed. First, partial mutual information (PMI) and the Pearson correlation coefficient (PCC) are used to select the key variables in the feature selection process. Second, an iterated random forest (IRF) is applied to predict the transient stability margin (TSM) based on the selected variables. Combining the feature selection process and regression prediction, a DSA model is constructed. Finally, a spatial-temporal dynamic visualization approach is proposed, which can intuitively provide real-time dynamic security information of power systems. The integrated scheme, which is tested on the IEEE 39-bus system and a practical 1648-bus system provided by the software PSS/E, exhibits desirable assessment accuracy and is suitable for online application. In the robustness test, some impact factors for power system operation are considered, such as topology change, variation of generator/load power distribution and variation of load characteristics. Moreover, the impacts of missing data and measurement noise are studied.

中文翻译：

---

基于部分互信息和迭代随机森林的在线动态安全评估集成方案

随着电力系统规模的不断扩大和相量测量单元（PMU）的广泛应用，电力系统的安全运行越来越受到关注。提出了一种基于特征选择和回归预测的在线动态安全评估（DSA）集成方案。首先，在特征选择过程中，使用部分互信息（PMI）和Pearson相关系数（PCC）选择关键变量。其次，基于所选变量，应用迭代随机森林（IRF）来预测暂态稳定裕度（TSM）。结合特征选择过程和回归预测，构建了DSA模型。最后，提出了一种时空动态可视化方法，可以直观地提供电力系统的实时动态安全信息。该集成方案在IEEE 39总线系统和PSS / E软件提供的实用1648总线系统上进行了测试，显示出理想的评估准确性，适合在线应用。在鲁棒性测试中，考虑了一些影响电力系统运行的因素，例如拓扑变化，发电机/负载功率分布的变化以及负载特性的变化。此外，还研究了丢失数据和测量噪声的影响。考虑了电力系统运行的一些影响因素，例如拓扑变化，发电机/负载功率分布的变化以及负载特性的变化。此外，还研究了丢失数据和测量噪声的影响。考虑了电力系统运行的一些影响因素，例如拓扑变化，发电机/负载功率分布的变化以及负载特性的变化。此外，还研究了丢失数据和测量噪声的影响。