Metodologia de apoio à operação de sistemas elétricos de potência baseada em identificação de sistemas com aprendizado de máquina

Recent advances on synchro phasor measurement along with its regulation by the Operador Nacional do Sistema – ONS brought access to high resolution data rates up one sample per cycle. Electrical power system current, voltage, phase and frequency are collected through Phasor Measurement Units-PMUs stored in Data Concentrators PDCs. Such high-resolution favours new algorithms applications towards electrical systems dynamic behaviour, once unattainable due supervisory control acquisition limitations. Implementations regarding real time operations help room operators’ awareness reactions under disturbances malfunctions. System identification methods, together artificial intelligence tools such machine learning, contribute research development control. In this study a classic algorithm is implemented process find model representing behaviour PMU data. A stabilization diagram applied as post processing method results used build histogram underlining electromechanical modes.