A data-driven approach for online dynamic security assessment with spatial-temporal dynamic visualization using random bits forest

Abstract

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. To construct an efficient dynamic security assessment (DSA) model and make it convenient for practical applications, an integrated framework for online DSA with spatial-temporal dynamic visualization is proposed in this paper. The proposed framework consists of DSA model based on random bits forest (RBF) and spatial-temporal dynamic visualization. By using a feature selection process based on the bagging nearest-neighbor prediction independence test (BNNPT) and Pearson correlation coefficient (PCC), the key features are selected for model training. Once the real-time PMU data from the wide area measurement system (WAMS) are received, the trained DSA model can rapidly provide the corresponding transient stability margin (TSM). Particularly, the spatial-temporal dynamic visualization is presented to describe the quickly captured dynamic security information. The encouraging performance of the framework is demonstrated by tests on a 23-bus test system and a practical 1648-bus system. Especially, some impact factors that influence the practical operation of power systems are considered in the robustness examination, including variations of the topology, power distribution among generators/loads, peak/minimum load and load characteristics.