Title :
A model predictive approach for community battery energy storage system optimization
Author :
Pezeshki, H. ; Wolfs, Peter ; Ledwich, Gerard
Author_Institution :
Sch. of Electr. Eng. & Comput. Sci., Queensland Univ. of Technol., Brisbane, QLD, Australia
Abstract :
This paper presents an efficient algorithm for optimizing the operation of battery storage in a low voltage distribution network with a high penetration of PV generation. A predictive control solution is presented that uses wavelet neural networks to predict the load and PV generation at hourly intervals for twelve hours into the future. The load and generation forecast, and the previous twelve hours of load and generation history, is used to assemble load profile. A diurnal charging profile can be compactly represented by a vector of Fourier coefficients allowing a direct search optimization algorithm to be applied. The optimal profile is updated hourly allowing the state of charge profile to respond to changing forecasts in load.
Keywords :
Fourier analysis; battery management systems; load forecasting; neurocontrollers; optimisation; photovoltaic power systems; power distribution control; power generation control; predictive control; search problems; wavelet neural nets; Fourier coefficients vector; PV generation; assemble load profile; community battery energy storage system optimization; direct search optimization algorithm; diurnal charging profile; load forecasting; load prediction; low voltage distribution network; model predictive control approach; power generation forecasting; wavelet neural networks; Batteries; Load forecasting; Load modeling; Neural networks; Optimization; Wavelet transforms; Community energy storage; Predictive control; Short term load forecasting; Wavelet neural network;
Conference_Titel :
PES General Meeting | Conference & Exposition, 2014 IEEE
Conference_Location :
National Harbor, MD
DOI :
10.1109/PESGM.2014.6938788
