Nonlinear Model Predictive Control Using Relevance Vector Machine for Maximum Power Point Tracking of Photovoltaic Arrays
24 Pages Posted: 20 Apr 2018
Date Written: April 6, 2018
Abstract
This paper proposes the control of photovoltaic (PV) array Maximum Power Point Tracker (MPPT) through Nonlinear Model Predictive Control (NMPC) strategy which uses Relevance Vector Machines (RVM) regression model. Another Relevance Vector Regression (RVR) model is employed to offer the reference Maximum Power Point (MPP) trajectory to the model predictive control system by predicting the maximum power point current and voltage of the nonlinear PV module at different operating conditions. The above control algorithm is speeded up by simplifying the optimization problem by Finite Control Set Model Predictive Control (FCS-MPC) technique. Thus an improved system performance is guaranteed by an accurate predictive model and simple control algorithm. The obtained simulation results show the superiority of the proposed method compared to deterministic sparse kernel learning Least squares support vector machines (LS-SVM) based model predictive control (MPC) and state space model based NMPC.
Keywords: Photovoltaic arrays; Relevance vector machines; Maximum power point tracking; Nonlinear model predictive control; Finite control set model predictive control
Suggested Citation: Suggested Citation