Economic power dispatch for piecewise quadratic cost function using Hopfield neural network

The authors present a new method to solve the problem of economic power dispatch with piecewise quadratic cost function using a Hopfield neural network. Traditionally, one coat function for each generator is assumed, but it is more accurate to represent a coat function of each generator as a piecewise quadratic function rather than a quadratic function. In this study, multiple intersecting cost functions are used. Instead of a counting method and binary number representation, a new representation scheme of a Hopfield network is proposed to represent a large number by one neuron. Compared with the numerical method of hierarchical structure, the proposed approach is much simpler and shows the better results at lower cost.<
>