Abstract
The paper introduces the control and operation of a grid-connected converter with an energy storage system. A complete mathematical model is presented for a converter and its control. The system under study is a small microgrid comprising an AC grid that is feeding a DC load through a converter. The converter is connected to the AC grid through R-L filter. On the DC side an energy storage system ESS is connected to the DC bus. Classical linear controllers have limitations due to their slow transient performance and low robustness against parameter variations and load disturbances. In this paper, a machine learned controllers are used to deal with those drawbacks of the traditional controller. First, a study for conventional nested loop Proportional Integral for both outer and inner loops PI-PI controller is introduced. Then, a Data Driven Online Learning (DDOL) controller is proposed. This controller is a Proportional Integral Neural Network (PI-NN) that is used to enhance the system performance in terms of dynamic and steady-state responses. A comparison between the normal traditional PI-PI controller and the proposed DDOL ones is made under different operating scenarios. The converter control is tested under different operational conditions, and its dynamic and steady-state behavior is analyzed. The model is done through a MATLAB Simulink to check the normal operation of the network in a grid-connected mode under different load disturbances and AC input voltage. The results are showing that the intelligent controller can achieve the set reference points with better performance in terms of both dynamic and steady-state responses.