In this paper we propose a fuzzy classifier of energy production in solar photovoltaic installations based on the values of some environmental parameters. The classifier is built through a hierarchical process and is obtained by merging basic fuzzy models built on input domain regions increasingly smaller, as the result of the construction of appropriate grids on the input domain. The system parameters are optimized by means of a genetic algorithm. The interpretability of the fuzzy system helps the electric grid (e.g., smart grid) operator have fast and easy understanding of the energy production, thus allowing easier and faster decision making about electricity production and management. The achieved results show an average correct classification rate of 97.38% with a maximum of 97.91%.
Computational intelligence techniques for solar photovoltaic system applications
D'ANDREA, ELEONORA;LAZZERINI, BEATRICE
2012-01-01
Abstract
In this paper we propose a fuzzy classifier of energy production in solar photovoltaic installations based on the values of some environmental parameters. The classifier is built through a hierarchical process and is obtained by merging basic fuzzy models built on input domain regions increasingly smaller, as the result of the construction of appropriate grids on the input domain. The system parameters are optimized by means of a genetic algorithm. The interpretability of the fuzzy system helps the electric grid (e.g., smart grid) operator have fast and easy understanding of the energy production, thus allowing easier and faster decision making about electricity production and management. The achieved results show an average correct classification rate of 97.38% with a maximum of 97.91%.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
