Maximum Power Point Tracking Scheme For PV Systems Operating Based On SVR

Energy and power are material basis and driving force of human social development, the total reserve of fossil fuel is dwindling, even in the crisis of exhausted. In addition, extensive use of fossil fuels has caused serious environmental problems. So the discovery and exploitation of green and renewable energy is significant. The clean renewable solar energy received widespread attention, photovoltaic power generation industry also has a good prospect in the future. In this paper, the research object is the photovoltaic power generation system, and the research objective is the maximum power point scheme for PV systems operation under partial shadow.This paper build a simulation model of a photovoltaic cell in matlab/simulink, then analysis the output characteristics of PV array operating under conditions of partial shade variation curve and uniform illumination, All of this are preparing for MPPT algorithm design of PV systems operating under partial shadow.Comparing has been made between four traditional MPPT methods, that is constant voltage method, perturbation and observation method, incremental conductance method and FLC method. The incremental conductance method and the P&O method was simulated.When PV module is under local shadow or non-uniform illumination conditions, the output characteristics of PV arrays will change. P-U characteristic curve present multiple peaks, traditional MPPT algorithm based on single peak P-U curve may fail, it is difficult to accurately track the global maximum power point. To address this drawback, this paper puts forward a MPPT fusion algorithm based on combination of perturbation method and SVM. Use the particle swarm algorithm and genetic algorithm to do parameter optimization for support vector machine regression prediction model.The algorithm uses the global optimization and high generalization performance characteristics of support vector machine which combining with easy of calculation and control and realization of perturbation method to achieve maximum power point tracking. The simulation results show that in real external conditions, such as light, temperature and illumination mutation, compared with traditional perturbation method, the new fusion algorithm can not be trapped in local peak, the system can quickly and accurately track the global maximum power point.