An H-ELM Based Equivalent Droop Control for Hybrid Power Systems

Primary frequency regulation plays an important role in a hybrid power system which is composed of battery energy storage systems (BESSs), photovoltaic (PV) systems and thermal power plants. Droop control is a basic primary frequency control method. In this paper, an equivalent droop control method based on hierarchical extreme learning machine (H-ELM) is proposed for hybrid power plants. Therefore the \(P - f\) droop characteristics can be fitted by an H-ELM rather than traditional fixed droop control curve. Finally, the effectiveness of the proposed method is justified by the simulation results.