This paper explores the increasing role of photovoltaic (PV) systems in power networks due to their economic and technical benefits. PV systems, used in sectors like electric vehicles and residential applications, are expected to supply up to 45% of global energy demand. However, their output is influenced by factors like irradiance and temperature, emphasizing the need for efficient maximum power point tracking (MPPT). This study presents an Adaptive Neuro-Fuzzy Inference System (ANFIS)-based MPPT controller for a DC-DC converter with a 2.5 kW PV array. The ANFIS controller combines neural networks and fuzzy logic, providing enhanced performance with minimal complexity. Simulations show that ANFIS outperforms traditional AI-based MPPT methods, achieving superior results in dynamic conditions and showing zero mean squared error. This approach highlights the potential of ANFIS for optimizing PV system performance in renewable energy applications. 

This paper focuses on the development of improve Wind Energy Conversion Systems (WECS) efficiency using advanced Maximum Power Point Tracking (MPPT) algorithms. Traditional methods like Perturb and Observe (P&O) and Incremental Conductance (InC) are simple but have drawbacks, such as oscillations and slow response under dynamic wind conditions. The research explores Artificial Neural Network (ANN)-based MPPT algorithms, including Levenberg-Marquardt (LM), Bayesian Regularization (BR), and Scaled Conjugate Gradient (SCG), for their ability to handle nonlinearities and adapt to variable wind profiles. MATLAB Simulink simulations evaluate these algorithms on metrics like efficiency, response time, and stability. Results show ANN algorithms outperform conventional methods, with BR achieving the highest power output, SCG excelling in speed-efficiency balance, and LM ensuring fast, accurate tracking.

This paper explores the increasing role of photovoltaic (PV) systems in power networks due to their economic and technical benefits. PV systems, used in sectors like electric vehicles and residential applications, are expected to supply up to 45% of global energy demand. However, their output is influenced by factors like irradiance and temperature, emphasizing the need for efficient maximum power point tracking (MPPT). This study presents an Adaptive Neuro-Fuzzy Inference System (ANFIS)-based MPPT controller for a DC-DC converter with a 2.5 kW PV array. The ANFIS controller combines neural networks and fuzzy logic, providing enhanced performance with minimal complexity. Simulations show that ANFIS outperforms traditional AI-based MPPT methods, achieving superior results in dynamic conditions and showing zero mean squared error. This approach highlights the potential of ANFIS for optimizing PV system performance in renewable energy applications.