Title :
Online tuned neural networks for fuzzy supervisory control of pv-battery systems
Author :
Ciabattoni, Lucio ; Ippoliti, Gianluca ; Longhi, Sauro ; Cavalletti, M.
Author_Institution :
Dipt. di Ingeg-neria dell´Inf., Univ. Politec. delle Marche, Ancona, Italy
Abstract :
The paper deals with a neural network based fuzzy supervisor control to manage power flows in a Photo-Voltaic (PV) - Battery system. An on-line self-learning prediction algorithm is used to forecast, over a determined time horizon, the power mismatch between PV production and electrical consumptions. The learning algorithm is based on a Radial Basis Function (RBF) network and combines the growing criterion and the pruning strategy of the minimal resource allocating network technique. The power flows are scheduled by a Fuzzy Logic Supervisor (FLS) which controls the charge and discharge of a battery used as an energy buffer. The proposed solution has been experimentally tested on a 14 KWp PV plant and a lithium battery pack.
Keywords :
fuzzy control; load flow control; neural nets; photovoltaic power systems; radial basis function networks; resource allocation; secondary cells; energy buffer; fuzzy logic supervisor; fuzzy supervisory control; lithium battery pack; online self learning prediction algorithm; online tuned neural networks; photovoltaic battery systems; power flows; power mismatch; pruning strategy; radial basis function network; resource allocating network technique; Artificial neural networks; Batteries; Fuzzy logic; Inverters; Neurons; Prediction algorithms; Production;
Conference_Titel :
Innovative Smart Grid Technologies (ISGT), 2013 IEEE PES
Conference_Location :
Washington, DC
Print_ISBN :
978-1-4673-4894-2
Electronic_ISBN :
978-1-4673-4895-9
DOI :
10.1109/ISGT.2013.6497901
