Sizing of hybrid energy storage system in independent microgrid based on BP neural network

As a result of the uncertainties and significant fluctuations of both power generation and consumption in a microgrid, the battery energy storage system (BESS) endures large oscillations in absorbing and releasing active power. This paper proposes a hybrid energy storage system (HESS) composed of supercapacitors and batteries. An optimal design method of HESS capacity is introduced so that HESS can meet the technical requirements, such as smoothing out the wind power fluctuations and the economic requirement in a microgrid. Based on the level of smoothing (LOS) of power curves, a neural network model was established to reflect the interrelationship between characteristic parameters of HESS and LOS of output power transmitted to the independent microgrid. Besides, taking the economic demand into consideration, a long-term mathematical model was built. Optimal algorithm was used to determine optimal size of HESS by optimizing the objective function, which was derived from the built model. Finally, an example indicates the effectiveness of the proposed method.