Fast dynamic voltage security marginestimation: concept and development

Artikel i vetenskaplig tidskrift, 2020

This study develops a machine learning-based method for a fast estimation of the dynamic voltage security margin(DVSM). The DVSM can incorporate the dynamic system response following a disturbance and it generally provides a bettermeasure of security than the more commonly used static voltage security margin (VSM). Using the concept of transient P - Vcurves, this study first establishes and visualises the circumstances when the DVSM is to prefer the static VSM. To overcomethe computational difficulties in estimating the DVSM, this study proposes a method based on training two separate neuralnetworks on a data set composed of combinations of different operating conditions and contingency scenarios generated usingtime-domain simulations. The trained neural networks are used to improve the search algorithm and significantly increase thecomputational efficiency in estimating the DVSM. The machine learning-based approach is thus applied to support theestimation of the DVSM, while the actual margin is validated using time-domain simulations. The proposed method was testedon the Nordic32 test system and the number of time-domain simulations was possible to reduce with ∼70%, allowing systemoperators to perform the estimations in near real-time.