Neural network-based power system dynamic state estimation using hybrid data from SCADA and phasor measurement units

Abstract

Summary This paper points out the application of artificial neural network for short‐term load forecasting where the projected loads are utilized to define a discrete‐time state transition model (i.e., process model). The model is applied to estimate states dynamically and to generate pseudo measurements. Weights of neural network are not treated static and would be carried out under reevaluation alongside the estimation of state vector dynamically. The unscented Kalman filter estimation approach, which requires less approximation of power system, is used in the proposed method. The unscented Kalman filter is implemented through a dual structure due to the interactions of the state vector and the dynamic model of power system. The performance of the proposed method from accuracy prospective is compared with a couple of widely used methods. An optimum solution for wide‐area monitoring system would be realized through implementation of more realistic process model along the simplicity of the proposed method and its capability to handle hybrid measurement data from SCADA and phasor measurement units.

The nonlinear autoregressive network with exogenous inputs (NARX) neural network to damp power system oscillations

“…The loads in the two areas are such that Area 1 exports 413 MW to Area 2. More details of this system can be found in 33 …”

Data mining based excitation system parameters estimation considering DCS and PMU measurements using cubature Kalman filter

“…The states of the fluctuant area, however, change extremely fast and the state estimation is performed by only PMUs data. Lack of data integrity due to different sample rates of RTUs and PMUs is resolved by using the state reconstruction technique in Reference 23. Both measurement vectors are combined into a single vector and as long as there is no data provided by RTUs, pseudo‐measurements generated by a modified state transition model provide sufficient data.…”

Identification of Wind Turbine using Fractional Order Dynamic Neural Network and Optimization Algorithm

“…In these cases, dynamic neural networks perform more efficient than static neural networks due to their richer structure in modeling dynamics of nonlinear systems [7]. Moreover, representation capability is essential in every application especially while dealing with dynamic systems [8]. The famous Hopfield neural network was introduced in 1982 and since then it has been one of the most successful dynamic neural networks.…”