No abstract

No abstract

Abstract-Improved solar cell models and control methods using synergies of soft-computing techniques are used to demonstrate increased energy efficiencies of photovoltaic (PV) power plants connected to the electricity grid via space-vector-modulated threephase inverters. The models and control strategies are combined to form two new model-based controllers that are more accurate and resilient than existing solutions resulting in increased power production. A radial-basis-function-network (RBFN) model with a neuro-fuzzy regulator applied to a plant well characterized by the conventional solar cell model provided an estimated 1.5% increase in power production over an existing conventional model proportional integral (PI)-regulator combination. A neuro-fuzzy model with a neuro-fuzzy controller applied to a plant poorly characterized by the conventional solar cell model gave an 8.6% increase in power. An analysis of the net contributions to the increased efficiencies shows that the improved models had the most effect on power gains.Index Terms-Fuzzy neural networks, photovoltaic (PV) power systems, power system modeling, power system simulation.

No abstract