Intelligent perturb and observe control based on support vector machine for photovoltaic pumping system. (29th August 2019)

• Record Type: Journal Article
• Authors: Dahhani, Omar; Boumhidi, Ismail
• Is Part Of: International journal of modelling, identification and control. Volume 32:Number 1(2019)
• Page Start: 60
• Page End: 69
• Publication Date: 2019-08-29
• Subjects: adaptive perturb and observe -- maximum power point tracking -- MPPT -- support vector machine -- SVM -- photovoltaic power system control; Engineering -- Methodology -- Periodicals; Science -- Methodology -- Periodicals; 001.42
• Languages: English
• ISSNs: 1746-6172

Abstract

In this paper, an intelligent maximum power point tracking control is proposed for a photovoltaic (PV) water pumping system. This strategy combines the least squares support vector machines (LS-SVM) technique with the exponential adaptive perturb and observe (EAP&O) control. The reason for combining these two techniques is to overcome the steady states oscillations, low convergence rate as well as failure problems in standard P&O. The main purpose of the LS-SVM in this work, is to design an accurate off-line MPP model, which gives back the optimal value of duty cycle at present illumination intensity. These former values serve to initialise the proposed EAP&O in online implementation. To validate and to show the effectiveness of the proposed control, both strategies, EAP&O based on LS-SVM and standard P&O, are applied to the PV pumping system, and finally some important simulation results are presented.