Adaptive neuro-fuzzy inference system based output power controller in grid-connected photovoltaic systems
Sachpreet Kaur, Tarlochan Kaur, Rintu Khanna
Abstract
The power obtained from the photovoltaic (PV) module is greatly influenced by module temperature and the Sun’s irradiations. To extract optimal power from PV modules, usually a maximum power point tracking controller is incorporated in the system. Previously, methods like Perturb & Observe and Incremental Conductance were used to control output power. These methods, though easy to implement, face certain challenges. They have low tracking speed, poor convergence rate and face rapid variations even during steady-state conditions. Alternatively, artificially intelligent (AI) techniques are more robust and are known to effectively handle non-linearities associated with any system. In this study, the Adaptive Neuro Fuzzy Inference System (ANFIS) has been developed to extract maximum power from a non-linear PV module. The designed ANFIS controller directly take the irradiance and temperature as input parameters to give the crisp value of voltage, which can deliver the maximum power in all situations. For optimal design of the ANFIS controller, Taguchi’s method-based optimization approach has been implemented. The extensive simulations reveal satisfactory power tracking performance of the PV module by using the proposed ANFIS controller. RMSE value of 0.0054 and R2 value of 0.993 verifies the effectiveness of the proposed ANFIS controller. The proposed controller shows a faster track response with negligible oscillations in comparison to the conventional Perturb & Observe controller.