Decision tree based online stability assessment scheme for power systems with renewable generations

Abstract

The stochastic fluctuation of renewable energy resources has significant impact on the stability of the power system with renewable generations and results in change in stability. Therefore, it is necessary to track the changing stability of the power system with renewable generations, a task that can be performed online. This paper details the use of decision trees to predict multi-mode damping of power system integrating renewable generations with the help of wide-area measurements system (WAMS). Power systems with renewable source generation are complex with vast amounts of data being collected from WAMS. Decision trees (DTs) are employed as a means to handle vast quantities of wide-area information, which involves the mode damping information indicating the stability. A 16-generator, 68- bus system with photovoltaic power generation and wind power generation is used as the test system. Remote signals obtained from phasor measurement units (PMUs) are employed as the input variables of DTs for predicting purposes. The simulation results demonstrate that the proposed predicting scheme is able to suggest the optimal course of action to remedy any near instability or unstable electromechanical oscillations even without prior knowledge of the varying output of the renewable source power.