An Efficient Optimisation-Trained Feedforward Neural Network for Predicting the Maximum Power Point of the Photovoltaic Array
Nitin Machindra Pardeshi
, Prof. Samadhan Patil
Artificial neural network (ANN), Solar Photovoltaic (PV), Maximum power point tracking (MPPT), Particle Swarm Optimization (PSO), Perturb and observe.
The evolution of an advanced feedforward Artificial Neural Network (ANN) framework tuned for exact prediction of the Maximum Power Point (MPP) in photovoltaic (PV) arrays is presented in this work. Particle Swarm Optimization (PSO) for best tuning of the ANN’s initial weights and structural parameters is proposed to solve the difficulties presented by the nonlinear behavior of PV systems under different climatic conditions. This dual-stage optimization method guarantees a strong balance between computational efficiency and prediction accuracy, so reducing the mean squared error (MSE) and so addressing overfitting problems common in conventional ANN-based models. Using real-world experimental datasets gathered under various atmospheric conditions, including clear and cloudy scenarios, extensive simulations are run in the MATLAB/Simulink environment. Comparative analyses against accepted MPPT methods—such as Perturb and Observe (P&O), Fuzzy Logic Controllers (FLC), and
standard ANN models—showcase the better performance of the PSO-enhanced ANN framework. Achieving average power tracking efficiencies exceeding 99.6% in sunny conditions and 99.3% during intermittent cloud cover, the results show marked improvements in convergence speed, stability, and dependability.” In grid-connected PV systems, the suggested answer greatly improves operational resilience and energy collecting efficiency. Extending the hybrid AI-optimizing approach to major PV installations and including extra environmental variables will help to increase the prediction capacity even more.
"An Efficient Optimisation-Trained Feedforward Neural Network for Predicting the Maximum Power Point of the Photovoltaic Array", IJSDR - International Journal of Scientific Development and Research (www.IJSDR.org), ISSN:2455-2631, Vol.10, Issue 3, page no.b634-b643, March-2025, Available :https://ijsdr.org/papers/IJSDR2503183.pdf
Volume 10
Issue 3,
March-2025
Pages : b634-b643
Paper Reg. ID: IJSDR_301152
Published Paper Id: IJSDR2503183
Downloads: 000214
Research Area: Science and Technology
Country: Raigad, Mumbai, India
ISSN: 2455-2631 | IMPACT FACTOR: 9.15 Calculated By Google Scholar | ESTD YEAR: 2016
An International Scholarly Open Access Journal, Peer-Reviewed, Refereed Journal Impact Factor 9.15 Calculate by Google Scholar and Semantic Scholar | AI-Powered Research Tool, Multidisciplinary, Monthly, Multilanguage Journal Indexing in All Major Database & Metadata, Citation Generator
Publisher: IJSDR(IJ Publication) Janvi Wave
