Optimal active power flow solutions using a modified Hopfield neural network

Abstract

The optimal power flow is a general nonlinear programming problem with a nonlinear objective function and nonlinear functional equality and inequality constraints. This paper presents a proposed strategy for optimal active power flow using a modified Hopfield neural network. The objective function is the incremental generation cost function in quadratic form which is expanded in a second-order Taylor series. The equality and inequality constraints are modelled using a linearized network and appended to the objective function using suitable penalty functions to form an augmented cost function. The Hopfield neural network was simulated on a digital computer for fourteen-bus and thirty-bus test system. The optimal solution obtained using this approach is comparable to the solution obtained using the conventional method.