New operation scheme and control of Smart Grids using Fuzzy Cognitive Networks

“Smart Grid” is the term used to characterize an electricity grid that has been modernized using computer based remote control and automation. Such systems are beginning to be used at electricity networks, from the power plants and wind farms all the way to the consumers. Fuzzy Cognitive Maps (FCM) were initially introduced by Kosko to model complex behavioral systems in various scientific areas. Fuzzy Cognitive Networks (FCN) have been used to identify nonlinear systems. The aim of FCN in this work is to predict and perform the necessary actions for supplying different ancillary services to the grid, such as fast active power compensation, voltage and frequency regulation, and back-up supply. The FCN manages to regulate the PV-inverters power output, the battery bank current and the loads consumption effectively, thus keeping the voltage and frequency of the microgrid in acceptable levels, maintaining at the same time its optimal, in respect to cost, operation.