An AIAPO MPPT controller based real time adaptive maximum power point tracking technique for wind turbine system

Nowadays, the energy demand is increasing all over the world and conventional energy sources like fossil fuels are gradually emitting less harmful gases (as greenhouse gases). Therefore, the renewable energy (RE) sources are affordable and sustainable, which is essential to increase the demand for power generation. This manuscript proposes a novel Artificial Intelligence Based Adaptive P&O (AIAPO) for real-time adaptive hybrid Maximum Power Point Tracking (MPPT) controller to attain Maximum Power Point (MPP) from the Wind Turbine (WT) system The major objective of the proposed method is "to increase the mathematical calculation of the controller design and eliminate the disadvantage of the conventional MPPT and fuzzy logic (FL) controller". In the proposed method, the optimum perturbation is computed with respect to the variation of WS by FL controller. This optimum perturbation is fed into adaptive P&O technique that is desirable duty-cycle generated for dc-dc power converter using proposed system to achieve the MPP tracking and to enhance the efficiency of the proposed framework. It is estimated that these features can improve the power track by decreasing the steady-state fluctuations of the output power as well as improve the transient performance. Real-time outcomes with novel tracking technique is likened to the existing perturb & observe (P&O), fuzzy logic (FL) depend maximum power point tracking techniques for Wind Turbine Induction Generator (WTIG) system. The proposed algorithm is used to improve the results and to compare the power fluctuations on MPPT with variable wind speed (WS). The statistical analysis of proposed and existing techniques like P&O, FL and SVM are also analyzed. In the proposed method, the best value attains 230.5365, worst value attains 210.5934, mean value attains 230.952 and standard deviation attains 0.05314.