Flexible Power Point Tracking Using a Neural Network for Power Reserve Control in a Grid-Connected PV System

Abstract

Renewable energy penetration in the global energy sector is in a state of steady growth. A major criterion imposed by the regulatory boards in the wake of electronic-driven power systems is frequency regulation capability. As more rooftop PV systems are under installation, the inertia response of the power utility system is descending. The PV systems are not equipped inherently with inertial or governor control for unseen frequency deviation scenarios. In the proposed method, inertial and droop frequency control is implemented by creating the necessary power reserve by the derated operation of the PV system. While, traditionally, PV systems operate in normal MPPT mode, a derated PV system follows a flexible power point tracking (FPPT) algorithm for creating virtual energy storage. The point of operation for the FPPT of the PV is determined by using a neural network block set available in MATLAB. For the verification of the controller, it is applied to a PV array in a modified IEEE-13 bus system modeled in the MATLAB/Simulink platform. The simulation results prove that when the proposed control is applied to the test network with renewable energy penetration, there is an improved system inertia response.

Analysing active power reserve strategies for photovoltaic systems under varying shading scenarios: a comparative study

“…A neural network based FPPT control was proposed in [75], in this control, the ANNs are trained to directly produce the regulated reference voltages required for the FPPT operation. The ANNs are trained using three inputs; irradiance, temperature, and power reserve (∆P), irradiance and temperature are obtained using sensors and ∆P is obtained from the frequency regulation control, the control scheme is depicted in figure 26.…”