Wavelet based feature extraction of voltage profile for online voltage stability assessment using RBF neural network

Online voltage stability assessment is one of the vital requirements for intricate electric power systems. Due to the restructuring and liberalization, modern power systems tend to operate close to their stability limits with small security margin. In such environment, online voltage stability evaluation plays a significant role in secure operation of power systems. This paper presents a new approach for estimating voltage stability margin VSM, based on application of wavelet feature extraction method to network voltage profile. Voltage profile is adopted as the original input data for VSM estimation, because it contains sufficient information concerning network topology, load level, load-generation patterns and all system controllers. In this approach, in order to provide high discrimination between network voltage profiles, Multi-Resolution Wavelet Transform (MRWT) is utilized to extract the features of voltage profiles. Also, in order to eliminate the redundant features, principle component analysis (PCA) is used to select the most relevant features extracted by MRWT. Radial Basis Function (RBF) neural network is adopted to estimate system VSM using the dominant extracted features of the voltage profile by MRWT and PCA. Using voltage profile as the original data makes the proposed approach capable of estimating system VSM in both static and quasi dynamic conditions. The proposed approach has been implemented in New England 39-bus test system with promising results demonstrating its effectiveness and applicability.

► Network voltage profile is adopted as the original data for VSM estimation.
► The need to complicated modeling of power system is obviated by this approach.
► Wavelet feature extraction method is considered as the main core of this approach.
► Extracting features of voltage profiles provides high discrimination between them.
► This approach is able to estimate VSM in both static and quasi dynamic conditions.