Optimal Active and Reactive Power Sharing between several Distributed Generation Units in a Stand-Alone MicroGrid Using Artificial Neural Network

This paper is concerned with the generation control in small stand-alone MicroGrids consisting of inverter interfaced Distributed Generation (DG) units. An intelligent and on line Microgrid Management System (MGMS) using Artificial Neural Network (ANN) controller is used in this study and it determines the amount of power produced from generation units in a stand-alone MicroGrid. The ANN trained with a data generated from a Genetic Algorithm (GA) solved optimal power flow problem, which defines generation unit’s power in order to have a minimum power loss in the system, considering normal buses voltage and rating of generation units. Simulation results in a typical distribution system consisting two DG units show that the proposed method can meet the requirements of the system and DG units rating in stand alone operations. In this way the system is managed in an on-line, optimal, and reliable situation that guarantee the continuity of power to loads in stand-alone mode of a MicroGrid.