Classification of operating states for decision making in power systems control with feature selection based on mutual information

Abstract

The classification of power systems operating states plays an important role in power systems control and operation. Determining the state of a power system is crucial and requirements for real-time decision making in power systems security assessment demand low dimensionality and low computational time. This paper investigates the performances of feature extraction based on mutual information in power system state classification with machine learning. The AdaBoost algorithm is used for classification based on large training databases and feature extraction is applied in order to reduce their dimensionality.

New signal subspace approach to estimate the inter‐area oscillatory modes in power system using TLS‐ESPRIT algorithm

“…As the state of the WAMS is continuously changing over time, so its continuous monitoring is required. There are certain good estimation processes to collect data on-line [11]. Furthermore, a power system signal consists of both analogue and digital signals.…”

“…. Compute the matrix Ψ of right singular vectors of (11). (22) and (23) gives the frequency estimates using (27).…”