GA Tuned ANFIS MPPT for Solar PV System
Solar PV Panel Characteristics
Before diving into the implementation, let's review the key characteristics of the solar PV panel used:
Rated Power: 250.2 watts
Open Circuit Voltage: 37.3 volts
Voltage at Maximum Power Point: 30.7 volts
Short Circuit Current: 8.66 amps
Current at Maximum Power Point: 8.15 amps
Temperature Coefficients: Voltage and current coefficients influence panel performance under temperature changes.
Modeling the Solar PV System
The solar PV system model is structured using MATLAB equations:
Inputs: Irradiance and temperature data.
Outputs: Maximum voltage at the power point, critical for MPPT.
Here's a snippet of the code used to model the system:
Training the ANFIS Model with GA
Data Collection:
Input data includes irradiance and temperature variations.
Output data focuses on maximum voltage at the power point (Vmax).
GA Training:
GA optimizes the ANFIS parameters for accurate prediction of Vmax under varying conditions.
Parameters are tuned iteratively over multiple generations to minimize error and improve accuracy.
Implementation Details:
MATLAB's Fuzzy Logic Toolbox is utilized to develop and train the ANFIS model.
Training involves iterating over input-output pairs to adjust model parameters until convergence criteria are met.
Simulation Results
Performance under Dynamic Conditions:
Load Variations:
Test conditions vary irradiance while maintaining constant load.
ANFIS, tuned by GA, consistently tracks and extracts maximum power from the PV panel.
Irradiance Changes:
Simulation tests at different irradiance levels (1000, 800, 600, 400, 200 W/m²).
ANFIS adjusts to these changes, accurately predicting Vmax for optimal power extraction.
Comparison with Theoretical Values:
The model's output is compared with theoretical values to validate accuracy.
Results show close alignment between predicted and actual performance, verifying the effectiveness of GA trained ANFIS.
Conclusion
The integration of GA trained ANFIS for MPPT in solar PV systems demonstrates significant improvements in energy extraction efficiency. By dynamically adjusting to environmental changes, the system optimizes power output and ensures robust performance across varying conditions.
Comentários