Application of a neural network and heuristic model for voltage-reactive power control

This paper presents a new approach based on a neural network and heuristic model for voltage-reactive power control. The idea is to combine the learning and parallel-processing characteristics of a neural network as well as the fuzzy reasoning of a heuristic model to simplify the problem and improve the efficiency of calculation. The control variables are determined using a neural network type knowledge base and the quantities of the control actions are calculated with the heuristic model. The modified IEEE 30-bus test system is used to demonstrate the application of the proposed approach.