Two-phase neural network based modelling framework of constrained economic load dispatch

A two-phase optimisation neural network based modelling framework and a solution technique is proposed for solving the economic load dispatch problem in large-scale systems. The method is based on the solution of a set of differential equations obtained from transformation of an augmented Lagrangian energy function. The main objective is to minimise the total cost of generation while meeting the load demand and satisfying a number of constraints like power balance, unit generation limits, maximum ramp-rate limits, network losses and prohibited zone avoidance. It compares the proposed technique with the lambda iteration and genetic algorithm methods while investigating its applicability to large-scale power systems. The technique has shown the potential for achieving improved and feasible results with proper selection of control parameters.