PV Wind Battery Based DC Microgrid with Neural Network MPPT
Introduction:
We'll explore the simulation of a DC microgrid powered by photovoltaic (PV) panels, wind energy, and a battery. The unique aspect of this system is the utilization of a neural network-based Maximum Power Point Tracking (MPPT) algorithm to efficiently control both PV and wind energy systems.
Wind Energy Conversion System:
Wind Turbine: Generates a maximum of 6.5 kW at 10 m/s.
Permanent Magnet Synchronous Generator (PMSG): Converts wind energy to electrical energy.
Diode Rectifier: Converts AC to DC.
Boost Converter: Boosts voltage, controlled by a neural network for MPPT.
PV System:
PV Array: Comprising panels generating up to 6 kW at standard conditions.
Boost Converter: Boosts voltage to maintain around 400 V DC, controlled by the neural network MPPT.
DC Microgrid:
Load: A constant load of 2000 W.
Battery: 240 V, 48 Ah, connected via a bidirectional converter controlled by voltage control.
Neural Network MPPT:
Inputs: Rectifier voltage and current.
Output: Duty cycle for the Boost Converter.
Trained using data from both PV and wind systems to efficiently extract maximum power.
Simulation Results:
Varied wind speed from 10 to 8 m/s and irradiation from 1700 to 400 W/m².
Analyzed Boost Converter power, PV parameters, DC bus voltage, load power, battery parameters, and state of charge (SOC).
Results Summary:
Boost Converter efficiently maintains DC bus voltage around 400 V.
PV and wind powers adapt to changing conditions.
Battery operates in charging mode when surplus power is available and switches to discharging mode when renewable sources can't meet the load demand.
Conclusion:
The simulation showcases the robustness of the DC microgrid system in response to dynamic changes in wind speed and irradiation. The integration of neural network-based MPPT ensures optimal power extraction from both PV and wind sources. The bidirectional converter enables seamless power flow between the battery and the DC bus, ensuring continuous power supply to the load. This approach enhances the reliability and efficiency of renewable energy-based microgrid systems.
Comments