Modeling and Identification of Photovoltaic Systems Using Fuzzy Logic Models
| dc.contributor.author | Mohammed Elhadi | |
| dc.contributor.author | Belmekki Bakhouche Nour EL ISLEM | |
| dc.contributor.author | encadré par Abdelaziz Aouich | |
| dc.date.accessioned | 2026-11-19T11:04:45Z | |
| dc.date.available | 2026-11-19T11:04:45Z | |
| dc.date.issued | 2026-06 | |
| dc.description.abstract | Photovoltaic (PV) systems are characterized by nonlinear power-voltage characteristics that vary significantly with solar irradiance and cell temperature. Conventional Maximum Power Point Tracking (MPPT) techniques often suffer from oscillations, slow response, and reduced efficiency under rapidly changing and partial shading conditions. This thesis presents the modeling and identification of photovoltaic systems using intelligent techniques. A single-diode equivalent circuit model was studied and implemented in MATLAB for the KC200GT PV module. The effects of environmental conditions on the I-V and P-V characteristics and the location of the Maximum Power Point (MPP) were thoroughly analyzed. Classical MPPT methods, including Perturb and Observe (P&O), Incremental Conductance (IncCond), and Particle Swarm Optimization (PSO), were reviewed and their limitations highlighted. To overcome these limitations, a proposed intelligent models based on Multi-Layer Perceptron (MLP) and Adaptive Neuro-Fuzzy Inference System (ANFIS) were designed for accurate MPP identification. These models were trained using data generated from the validated photovoltaic model under a wide range of irradiance and temperature conditions. Simulation results demonstrated that the proposed intelligent models achieve superior tracking accuracy, faster convergence, and significantly reduced oscillations compared to conventional methods, even under dynamic and non-uniform irradiance conditions. The developed approach offers a robust and efficient solution for improving the performance of photovoltaic systems. | |
| dc.description.provenance | Submitted by Bibliotheque ST (assma-st@univ-tebessa.dz) on 2026-11-19T11:04:45Z No. of bitstreams: 1 Modeling and Identification of Photovoltaic Systems Using Fuzzy Logic Models.pdf: 9914329 bytes, checksum: d97dad1fdff28195c2c0357c82760b14 (MD5) | en |
| dc.description.provenance | Made available in DSpace on 2026-11-19T11:04:45Z (GMT). No. of bitstreams: 1 Modeling and Identification of Photovoltaic Systems Using Fuzzy Logic Models.pdf: 9914329 bytes, checksum: d97dad1fdff28195c2c0357c82760b14 (MD5) Previous issue date: 2026-06 | en |
| dc.identifier.uri | http://raseed.univ-tebessa.dz:4000/handle/123456789/13982 | |
| dc.language.iso | en | |
| dc.publisher | UNIVERSITE DE ECHAHID CHEIKH LARBI TEBESSI | |
| dc.subject | PV-modul | |
| dc.subject | MPPT | |
| dc.subject | Photovoltaic systems | |
| dc.subject | Single-diode circuit model | |
| dc.subject | ANFIS | |
| dc.subject | MLP | |
| dc.subject | RBF | |
| dc.subject | Fuzzy logic | |
| dc.subject | Intelligent MPPT | |
| dc.subject | MPPT techniques. | |
| dc.title | Modeling and Identification of Photovoltaic Systems Using Fuzzy Logic Models | |
| dc.type | Thesis |
Files
Original bundle
1 - 1 of 1
No Thumbnail Available
- Name:
- Modeling and Identification of Photovoltaic Systems Using Fuzzy Logic Models.pdf
- Size:
- 9.46 MB
- Format:
- Adobe Portable Document Format
License bundle
1 - 1 of 1
No Thumbnail Available
- Name:
- license.txt
- Size:
- 1.71 KB
- Format:
- Item-specific license agreed upon to submission
- Description: