Sliding mode control for photovoltaic water pumping system based on support vector machines

In this paper, the sliding mode control (SMC) is combined with the support vector machines (SVMs) for the photovoltaic (PV) water pumping system control to force it to operate at the maximum power point (MPP). The main objective is to overcome the limitation of SMC in term of chattering phenomenon caused by the needed high switching gain for large system uncertainties. SVM technique is used in this work to predict the unknown part of the PV pumping system model, which enables the well description of the real system. Therefore, the switching gain can be chosen enough lower. The new SVM-SMC strategy is applied on the PV system through the converter duty cycle, which is considered as the control low. The performance of the proposed controller is verified through simulations.