ANN method for size determination of storage systems in microgrids

Author(s): Yaser Qudaih, Thongchart Kerdphol, Yasunori Mitani
Department of Electrical and Electronics Engineering, Kyushu Institute of Technology, 1-1, Sensui-cho, Tobata-ku, Kitakyu-shu, Fukuoka, 804-8550, Japan
International Journal of Smart Grid and Clean Energy, vol. 4, no. 3, July 2015: pp. 247-254
ISSN: 2315-4462 (Print)
ISSN: 2373-3594 (Online)
Digital Object Identifier: 10.12720/sgce.4.3.247-254

Abstract: In the recent years, storage systems played significant roles than ever. One of the reasons behind such a phenomenon could be associated with the increase dependency on Renewable Energy Resources (RES) in power systems. Hence, the ability to calculate Battery Energy Storage System (BESS) size for the stand-alone microgrid is very crucial. Artificial Neural Network (ANN) has been proven to be a successful type of Artificial Intelligence (AI) in many applications. This paper presents the design of optimum size of BESS using artificial neural network. The patterns used in the neural network training are sets of frequency and voltage of the stand-alone or isolated system considered as microgrid. The neural network model is developed using simulation data from a nonlinear model. Simulation results show that the proposed neural network can provide an accurate and effective estimation of BESS size for the microgrid. Moreover, the optimal size of BESS-based ANN gives an improved performance than the BESS-based predefined size in the microgrid system.

Keywords: Artificial neural network, battery energy storage system, frequency control, microgrid, optimization

Full Paper.pdf
Copyright © 2023 International Journal of Smart Grid and Clean Energy, All Rights Reserved