A Neural Adaptive Assisted Backstepping Controller for MPPT in Photovoltaic Applications
| Autor: | Samia Semcheddine, Gabriele Maria Lozito, Alberto Reatti, Fabio Corti, Okba Boutebba, Antonino Laudani |
|---|---|
| Přispěvatelé: | aa. vv., Boutebba, O., Laudani, A., Lozito, G. M., Corti, F., Reatti, A., Semcheddine, S. |
| Rok vydání: | 2020 |
| Předmět: |
Maximum Power Point Tracking
0209 industrial biotechnology Operating point Artificial neural network Computer science business.industry Adaptive backstepping Photovoltaic system Neural Network 02 engineering and technology 021001 nanoscience & nanotechnology Maximum power point tracking Power (physics) 020901 industrial engineering & automation Photovoltaics Control theory Backstepping DC-DC Converter 0210 nano-technology business Photovoltaic Single-Diode Model Efficient energy use |
| Zdroj: | 2020 IEEE International Conference on Environment and Electrical Engineering and 2020 IEEE Industrial and Commercial Power Systems Europe (EEEIC / I&CPS Europe). |
| DOI: | 10.1109/eeeic/icpseurope49358.2020.9160518 |
| Popis: | Maximum power point tracking is a key asset to ensure an efficient energy conversion when a photovoltaic power source is involved. In this work, a novel approach combining a Neural-Network based tracking technique with an highly efficient algorithm for non-inverting buck-boost DC-DC converter (NIBB) control is proposed. The approach is validated through comparison against the well-known P&O algorithm, resulting superior both in terms of identifying the correct operating point for the PV device, and in terms of dynamic stability of the converter. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|