Adaptive neuro-fuzzy approach for maximum power point tracking with high gain converter for photo voltaic applications

Abstract

Energy is essential for improving the management of the power systems. One of the major concerns in the power sector is increasing demand of power that tends to increase the demand for fossil fuels causing environmental problems. Thus, it is essential to use variable renewable energies for direct current (DC) micro grid applications. Solar photo voltaic (PV) is one of the phenomena where the solar irradiance is converted to electrical power through solar cell. A new high gain converter is implemented which is fed from solar PV to track the maximum voltage and power so as to elevate the output efficiency of the PV panel. The envisioned converter can be effectively worked in continuous conduction mode (CCM) with same gating pulse for the two switches that guarantees wide plying range. The preferred converter comprises least number of components and achieves a maximum gain of 25 for the switch on period of 0.8 which makes the control circuit simpler compared to other non-coupled inductor topologies. Presently, special maximum power point tracking (MPPT) procedures have been acquainted to track the maximum power point (MPP) viably of which adaptive neuro fuzzy inference system (ANFIS) based controller is used in this article and high efficiency of about 98.96% is attained with good dynamic response. Over here, the potency of the system is endorsed by means of MATLAB/SIMULINK and compared with the other standard MPPT methods. Further, functioning and assessment of the conspired work are inspected carefully and verified effectively.

MPPT command enhancement based on an ameliorated grey wolf optimization algorithm for a standalone PV system

“…Likewise, artificial neural network (ANN) hold promises due to their self-learning and adaptive capabilities, enabling precise tracking under fluctuating solar radiation and temperature conditions but still being inefficient in terms of convergence speed, oscillation, and complexity in implementation. The performance of ANNs heavily relies on the quality and quantity of the training data, then insufficient or inaccurate data can lead to slow convergence, inaccurate tracking, and potential instability and also can lead to oversensitivity to noise and lead to unwanted oscillations around the GMPP [22,23].…”

“…Recent advancements in MPPT algorithms have incorporated metaheuristic optimization techniques, expanding the scope of MPPT control. Particle swarm optimization (PSO), artificial bee colony (ABC), ant colony optimization (ACO), and genetic algorithms (GA) have all shown promise in global optimization, effectively addressing the dynamic and nonlinear properties of photovoltaic systems However many metaheuristic methods rely on randomness in their search process, leading to non-deterministic convergence behavior, and also their performances are sensitive to their control parameters and configuration [23][24][25][26][27][28][29]. Inspired by the hunting strategies of grey wolves, GWO has emerged as a promising technique, demonstrating efficient and robust optimization capabilities well-suited for MPPT applications [8,[30][31][32].…”

Design and Analysis of Boost Topology Based on Sheppard-Taylor Converter for Renewable Power Integration

“…Also, SEPIC topology based on quazi-Z source structure with SC cell operated in boost mode for electric vehicle application is reported in [12], [30], [34], [39]. A DC-DC converter which employs active switched LC network and extracts maximum power from solar by utilizing fuzzy controller type MPPT is described in [7], [9], [26], [29]. A high step up converter with SC structure appropriate for solar PV applications is presented in [20], [32].…”