An adaptive TS‐fuzzy model based RBF neural network learning for grid integrated photovoltaic applications

Priyadarshi, Neeraj; Sanjeevikumar, P.; Bhaskar, Mahajan Sagar; Azam, Farooque; Taha, Ibrahim B. M.; Hussien, Mohamed G.

doi:10.1049/rpg2.12505

Cited by 23 publications

(8 citation statements)

References 26 publications

(35 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In partial shade conditions, the technique behaviour is examined, and it is found that precise GMPPT is accomplished with shortest tracking duration. 28 A hybrid simplified Firefly and neighbourhood attraction firefly (HSFNA)-MPPT approach invented, and it is used in the implementation of a high-power SEPIC converter powered by PV for ultra-fast charging systems. The HSFNA is capable of GMPPT in the presence of PSC and other dynamic operating situations; it also has faster tracking, more precise responses, and greater efficiency.…”

Section: Current Status Of Mppt Strategiesmentioning

confidence: 99%

“…The proposed MPPT controller outperforms GA‐RBF neural network and TS‐fuzzy‐MPPT in terms of recognition rate, resilience, and optimal PV power tracking across a wide range of environmental conditions. In partial shade conditions, the technique behaviour is examined, and it is found that precise GMPPT is accomplished with shortest tracking duration 28 . A hybrid simplified Firefly and neighbourhood attraction firefly (HSFNA)‐MPPT approach invented, and it is used in the implementation of a high‐power SEPIC converter powered by PV for ultra‐fast charging systems.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Hybrid two‐stage adaptive maximum power point tracking for stand‐alone, grid integration, and partial shaded PV system

Manna,

Singh,

Akella

2023

Adaptive Control & Signal

View full text Add to dashboard Cite

SummaryIn a PV array, the power‐voltage characteristic (P‐V) and output power are completely dependent on atmospheric conditions. Consequently, the P‐V curve's maximum power point (MPP) likewise changes significantly. This abrupt oscillation in the MPP may be caused by the PV panel being uniformly or partially shaded by trees, buildings, raindrops, and clouds. However, in both circumstances, the maximum power point tracking (MPPT) turns into a highly nonlinear issue with a time‐bounded solution. The unpredictable weather circumstances change P‐V characteristics after every short time interval. Therefore, this research presents a hybrid two‐stage adaptive MPPT to overcome the environmental uncertainties. The first stage is MPPT control block for determining reference voltage for each MPP and the second stage is modified model reference adaptive controller (MMRAC) block fine‐tunes converter duty cycle to maintain MPP of PV panel. The probabilistic evaluation is executed through four distinct levels of uncertainty, including stand‐alone, partially‐shaded, grid integration, and OPAL‐RT to examine the system robustness in diverse scenario. The possibility of the tracking failure caused by dynamic irradiance change is also verified. Moreover, efficiency, tracking ability, power loss, ripple, and error rate are compared with the state‐of‐the‐art strategies, that is, ANFIS, INC, P&O, and VSPO. The satisfactory performances of the new strategy under simultaneously varying irradiance, temperature, and load; partially shaded and grid integration shows the supremacy.

show abstract

Section: Current Status Of Mppt Strategiesmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Hybrid two‐stage adaptive maximum power point tracking for stand‐alone, grid integration, and partial shaded PV system

Manna,

Singh,

Akella

2023

Adaptive Control & Signal

View full text Add to dashboard Cite

show abstract

“…However, the isolated power converter networks have many disadvantages which lead to very low power transformation efciency, relatively very large volumes, more expensive, and very high design complexity. So, the current industry is focusing on the transformerless power converters which are buck-boost, Cuk, and Luo converters [39]. However, these fundamental power transformation circuits have the disadvantage of less power transmission efciency and are moderately suitable for peak load conditions [40,41].…”

Section: Introductionmentioning

confidence: 99%

A Novel Hybrid MPPT Controller for PEMFC Fed High Step-Up Single Switch DC-DC Converter

Rafikiran,

Basha,

Dhanamjayulu

2024

International Transactions on Electrical Energy Systems

View full text Add to dashboard Cite

At present, there are different types of Renewable Energy Resources (RESs) available in nature which are wind, tidal, fuel cell, and solar. The wind, tidal, and solar power systems give discontinuous power supply which is not suitable for the present automotive systems. Here, the Proton Exchange Membrane Fuel Stack (PEMFS) is used for supplying the power to the electrical vehicle systems. The features of fuel stack networks are very quick static response, plus low atmospheric pollution. Also, this type of power supply system consists of high flexibility and more reliability. However, the fuel stack drawback is a nonlinear power supply nature. As a result, the functioning point of the fuel stack varies from one position to another position on the V-I curve of the fuel stack. Here, the first objective of the work is the development of the Grey Wolf Optimization Technique (GWOT) involving a Fuzzy Logic Controller (FLC) for finding the Maximum Power Point (MPP) of the fuel stack. This hybrid GWOT-FLC controller stabilizes the source power under various operating temperature conditions of the fuel stack. However, the fuel stack supplies very little output voltage which is improved by introducing the Single Switch Universal Supply Voltage Boost Converter (SSUSVBC) in the second objective. The features of this proposed DC-DC converter are fewer voltage distortions of the fuel stack output voltage, high voltage conversion ratio, and low-level voltage stress on switches. The fuel stack integrated SSUSVBC is analyzed by selecting the MATLAB/Simulink window. Also, the proposed DC-DC converter is tested by utilizing the programmable DC source.

show abstract

“…Experimental implementation and verification of the proposed system, along with high tracking efficiency, were reported. In [ 40 ], an adaptive Takagi Sukeno (TS)-fuzzy model-based radial basis function (RBF) neural network learning for grid-integrated PV applications was presented. Rapid and accurate PV power tracking is reported to have been achieved under varying solar irradiance.…”

Section: Introductionmentioning

confidence: 99%

Nonlinear control of two-stage single-phase standalone photovoltaic system

Latif,

Khan,

Agha

et al. 2024

PLoS ONE

View full text Add to dashboard Cite

This paper presents a single-phase Photovoltaic (PV) inverter with its superior and robust control in a standalone mode. Initially, modeling and layout of the Buck-Boost DC-DC converter by adopting a non-linear Robust Integral Back-stepping controller (RIBSC) is provided. The controller makes use of a reference voltage generated through the regression plane so that the operating point corresponding to the maximum power point (MPP) could be achieved through the converter under changing climatic conditions. The other main purpose of the Buck-Boost converter is to act like a transformer and produce an increased voltage at the inverter input whenever desired. By not using a transformer makes the circuit size more compact and cost-effective. The proposed RIBSC is applied to an H-bridge inverter with an LC filter to produce the sinusoidal wave in the presence of variations in the output to minimize the difference between the output voltage and the reference voltage. Lyapunov stability criterion has been used to verify the stability and finite-time convergence of the overall system. The overall system is simulated in MATLAB/Simulink to test the system performance with different loads, varying climatic conditions and inverter reference voltages. The proposed methodology is compared with a back-stepping controller and Proportional Integral Derivative (PID) controller under rapidly varying climatic conditions. Results demonstrated that the proposed technique yielded a tracking time of 0.01s, a total harmonic distortion of 9.71% and a root means square error of 0.3998 in the case of resistive load thus showing superior control performance compared to the state-of-the-art control techniques.

show abstract

An adaptive TS‐fuzzy model based RBF neural network learning for grid integrated photovoltaic applications

Cited by 23 publications

References 26 publications

Hybrid two‐stage adaptive maximum power point tracking for stand‐alone, grid integration, and partial shaded PV system

Hybrid two‐stage adaptive maximum power point tracking for stand‐alone, grid integration, and partial shaded PV system

A Novel Hybrid MPPT Controller for PEMFC Fed High Step-Up Single Switch DC-DC Converter

Nonlinear control of two-stage single-phase standalone photovoltaic system

Contact Info

Product

Resources

About