Development of Methods for Optimizing Reactive Power Modes Based on Neural Network Technologies

Abstract

The high cost of electric power, as well as the considerable length and branching of electrical networks, necessitate reduce electric power consumption, and losses in electrical networks. One of solutions of this problem is optimizing the reactive power mode. Reducing the reactive power factor at the point of common coupling (PCC) to the economic level established by the power system is not taking into account that in a complex network, power flows with a non-optimal arrangement of compensating devices and improper determination of their power can reach large values, that resulting in an increase in losses in the network. A program has been developed that implements prediction algorithms using neural networks, as well as optimizing the reactive power mode.