Combination of an Improved P&amp;O Technique with ANN for MPPT of a Solar PV System

Kesraoui, Mohamed; Benine, A.; Boudhina, N.

doi:10.1007/978-3-319-05708-8_45

Cited by 4 publications

(7 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…It usually consists of a three‐layer fully connected neural network which is fed by physical inputs measurable by small sensors 9,10 . Other approaches towards artificial neural network (ANN)‐based modeling of MPPT involve the application of radial basis functions (RBF), 11 fuzzy logic operators, 12 genetic algorithms, 13 heuristic search‐based algorithms, 14 and a combination with traditional MPPT techniques such as P&O 15 and incremental conductance 16 . Apart from the traditional fully connected ANN approach, some works have attempted the MPPT task using approaches such as reinforcement learning (RL) 17 and classical machine learning approaches 18 such as decision trees, k‐nearest neighbors, and recurrent neural networks (RNNs).…”

Section: Introductionmentioning

confidence: 99%

Transformer‐based time series prediction of the maximum power point for solar photovoltaic cells

Agrawal

Bansal

Gautam

et al. 2022

Energy Science & Engineering

View full text Add to dashboard Cite

This paper proposes an improved deep learning-based maximum power point tracking (MPPT) in solar photovoltaic cells considering various time seriesbased environmental inputs. Generally, artificial neural network-based MPPT algorithms use basic neural network architectures and inputs which do not represent the ambient conditions in a comprehensive manner. In this article, the ambient conditions of a location are represented through a comprehensive set of environmental features. Furthermore, the inclusion of time-based features in the input data is considered to model cyclic patterns temporally within the atmospheric conditions leading to robust modeling of the MPPT algorithm. A transformer-based deep learning architecture is trained as a time series prediction model using multidimensional time series input features. The model is trained on a dataset containing typical meteorological-year data points of ambient weather conditions from 50 locations. The attention mechanism in the transformer modules allows the model to learn temporal patterns in the data efficiently. The proposed model achieves a 0.47% mean average percentage error of prediction on non-zero operating voltage points in a test dataset consisting of data collected over a period of 200 consecutive hours; resulting in the average power efficiency of 99.54% and peak power efficiency of 99.98%. The proposed model is validated through real-time simulations. The proposed model performs power point tracking in a robust, dynamic, and nonlatent manner, over a wide range of atmospheric conditions.

show abstract

Section: Introductionmentioning

confidence: 99%

Transformer‐based time series prediction of the maximum power point for solar photovoltaic cells

Agrawal

Bansal

Gautam

et al. 2022

Energy Science & Engineering

View full text Add to dashboard Cite

show abstract

“…Hence, the increase in V is maintained in the first case or a negative V is applied in the second one. This process is repeated until validation (Bouchafaa et al, 2011;Bounechba et al, 2014;Kesraoui et al, 2012Kesraoui et al, , 2014Liu et al, 2014). The flow chart corresponding to this method is given in Figure 7.…”

Section: Pando Mppt Algorithmmentioning

confidence: 99%

“…And it will be used in the training (Kesraoui et al, 2014;Norgaad et al, 2003). So a set of eighty points of optimal voltages at different irradiances in W/m 2 [50; 1000] and changing temperatures in degree °C [25; 35; 50; 75] were extracted based on the characteristic of our panel (Kesraoui et al, 2014). Then, the MATLAB-Simulink block of the ANN with a two-layer feed-forward with sigmoid hidden neurons and a linear output neuron was developed using the neural network fitting tool GUI (nftool).…”

Section: Improved Pando Techniquementioning

confidence: 99%

“…The network was trained with Levenberg-Marquardt back propagation algorithm. The inputs data are divided into three sets: used in the training of the network, for the validation, and the rest for the test, to fit the target as chosen to be Vop (Kesraoui et al, 2014). …”

Section: Improved Pando Techniquementioning

confidence: 99%

“…Secondly, the output power of PV cells is influenced by the irradiance and ambient temperature. Since, solar cell I-V characteristics is nonlinear and changes with weather condition, there is only one point on the P-V curve, called maximum power point (MPP), at which the entire PV system operates with maximum efficiency and produces its maximum output power (Bounechba et al, 2014;Kesraoui et al, 2014;Liu et al, 2014).…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Fuzzy logic MPPT control for a solar PV module applied to water pumping

Lazizi

Kesraoui

Chaib

2016

IJIED

View full text Add to dashboard Cite

Abstract:In this paper, the fuzzy logic control for maximum power point tracking (MPPT) of a solar photovoltaic (PV) module in water pumping application is presented. A PV system including a solar module, a DC/DC boost converter, a fuzzy MPP tracker and a resistive load is modelled and simulated for various atmospheric conditions. The P-V and I-V characteristics are first obtained for various values of solar irradiation and temperature. Also, the increased efficiency of the photovoltaic system using MPPT is computed and plotted. The fuzzy control method is compared with the perturb and observe (P&O) method in one hand and with an improved P&O technique using artificial neural network (ANN) in the other. The fuzzy MPP tracker is then applied to the water pumping system composed of a solar panel, DC/DC boost converter, DC/AC inverter, induction motor and centrifugal pump.Keywords: photovoltaic modules; DC/DC boost converter; maximum power point tracking; MPPT; fuzzy logic; perturb and observe; P&O; water pumping system. This paper is a revised and expanded version of a paper entitled 'Fuzzy logic maximum power point tracking control for a solar PV

show abstract

Real-Time Maximum Power Point Estimation of Photovoltaic Systems Using Shading Information

Wang

et al. 2021

IEEE Trans. on Ind. Applicat.

View full text Add to dashboard Cite

Combination of an Improved P&O Technique with ANN for MPPT of a Solar PV System

Cited by 4 publications

References 5 publications

Transformer‐based time series prediction of the maximum power point for solar photovoltaic cells

Transformer‐based time series prediction of the maximum power point for solar photovoltaic cells

Fuzzy logic MPPT control for a solar PV module applied to water pumping

Real-Time Maximum Power Point Estimation of Photovoltaic Systems Using Shading Information

Contact Info

Product

Resources

About