Adaptive Neural Network Linear Parameter-Varying Control of Shipboard Direct Current Microgrids

To avoid pollution of transportation applications, renewable energies are deployed. Whereas they uncontrolled, fully controlled pollution-free energy sources and storage units should be also considered. However, a complicated direct current (DC) microgrid (MG) is obtained, which suffers from nonlinearities, high order, uncertainties the power elements. Therefore, it vital to use advanced nonlinear controllers assure closed-loop stability performance overall system. In this paper, neural network (NN)-based adaptive linear parameter varying (LPV) controller suggested for whole DC MG The main advantage developed that deploys operating information all manipulate each component. This enhances margin fast regulation voltage. Besides, proposed has systematic offline design algorithm by combining numerical solvers theoretical theories. LPV designed via matrix inequality (LMI) approach adaptation law NN parameters based on Lyapunov theory. A benchmark including 5kW fuel cell, solar plant, 2kW battery package considered as case study, can utilized in future electric boats (EBs). Numerical simulations with different scenarios conducted verify controller. Furthermore, comparative results provided show advantages method dealing fluctuations plant loads over state-of-the-art methods.