A HYBRID NEURO-GENETIC APPROACH TO FLOW CALCULATION BASED ON THE REPRESENTATION OF AN ELECTRICAL-POWER SYSTEM BY CRITICAL SWITCHES

This paper is intended to present an approach to decision making in th e operation of electrical power systems that will use a simple genetic algorithm as a teacher for the process of supervised learning of a fe edforward, backpropagation artificial neural network. The fitness func tion used in the genetic algorithms is based on a load flow program an d used to determine the optimal condition of the critical switches of the system. Reward and penalty functions are applied to it in order to emphasize environmental, economic, security, robustness, public polic y and other considerations as they are pre-determined by the philosoph y of operation of the utility. These considerations (policies) become a part of the training set and operation of the neural network. The fi tness function used by the genetic algorithm in order to rank the poss ible solutions is based on a load flow program. The binary nature of t he genetic algorithm is particularly appropriate for the operation of switches. The result of the methodology is the equivalent of an on-lin e implicit load flow program used to redesign the configuration of the system in real time by opening and closing critical switches that are placed. along the power system. Experiments leading towards the devel opment of this methodology using real data from the Peninsular Control Area (The Yucatan Peninsula) of the National Mexican Interconnected P ower Grid are presented. Concepts of electrical power engineering are presented as a general reference for the reader of this document who i s not a specialist on that field.