Real time preventive actions for transient stability enhancement with a hybrid neural network-optimization approach

Abstract

This paper reports a new approach in defining preventive control measures to assure transient stability relatively to one or several contingencies that may occur separately in a power system. Generation dispatch is driven not only by economic functions but also with the derivatives of the transient energy margin value; these derivatives are obtained directly from a trained Artificial Neural Network (ANN), using real time monitorable system values. Results obtained from computer simulations, for several contingencies in the CIGRE test system, confirm the validity of the developed approach.

Stability-constrained optimal power flow

“…Here we convert the differential-algebraic equations to numerically equivalent algebraic equations using some appropriate rule. For our equations (8)- (10) and using the trapezoidal rule this yields: (12) (13) (14) (15) where is the integration step length, is the integration step counter, and is the number of integration steps [28]. The stability constraints can thus be expressed as follows: (16) Note that we must set up the equations needed for computing initial values of rotor angle, and equations for computing parameters of the swing equations.…”

“…formulation [15]. Other attempts to solve this preventive control problem can be found in, for example, references [4], [5], [16], [17]- [30].…”

“…It is, however, an open question as to how to include stability constraints since stability is a dynamic concept and differential equations are involved. We note that attempts based on either energy function method or pattern recognition have been pursued [12]- [15].…”

Preventive and Emergency Control of Power System for Transient Stability Enhancement

“…Transient stability enhancement through generation rescheduling can be found in [7][8][9][10][11][12][13][14]. In [7], a hybrid approach is proposed for on-line security evaluation and generator rescheduling as preventive control.…”

“…An optimal generation rescheduling method is proposed in [8] for transient stability enhancement for multiple unstable contingencies. Artificial neural network (ANN) based real-time preventive control was proposed in [9] for transient stability enhancement. A trajectory sensitivity based generator rescheduling as preventive control considering the dynamic security constraint has been proposed in [10].…”