ANN MPPT for Grid-Connected PV Wind Battery System
We'll explore the fascinating world of a grid-connected hybrid DC and AC microgrid system. This advanced system is controlled by a Neural Network MPPT (Maximum Power Point Tracking) method, integrating solar PV (photovoltaic) panels, wind turbines, and battery storage to optimize energy efficiency. Let’s delve into the components and functionality of this innovative energy management system.
System Overview
The hybrid microgrid comprises multiple components working seamlessly together:
Wind Energy Conversion System (WECS): This includes a wind turbine and a Permanent Magnet Synchronous Generator (PMSG), which converts wind energy into electrical power. The generated AC power is then rectified to DC using a rectifier.
Solar PV System: This includes solar panels rated at 2,000 watts, which are connected to a DC bus via a boost converter.
Battery Energy Storage System: A bi-directional DC-DC converter manages the charging and discharging of the battery, maintaining a stable DC bus voltage.
Grid Connection: The system can import and export power from/to the grid, depending on the power balance within the microgrid.
Wind Energy Conversion and MPPT
The wind energy conversion system uses a rectifier to convert AC to DC, followed by a boost converter to step up the voltage. The boost converter is controlled by a neural network-based MPPT algorithm, which maximizes the power extraction from the wind energy. The MPPT controller takes the rectified voltage and current as inputs and generates a duty cycle for the boost converter's MOSFET switch, optimizing the power output.
Solar PV System and MPPT
Similar to the wind energy system, the solar PV system uses a boost converter controlled by a neural network MPPT algorithm. The algorithm takes the PV panel's voltage and current as inputs to generate the appropriate duty cycle, ensuring maximum power extraction from the solar panels.
Battery Energy Storage and Bi-Directional Converter
The battery system is connected to the DC bus through a bi-directional DC-DC converter. This converter maintains the DC bus voltage at 400V using a voltage control method. An FPA controller processes the bus voltage and generates a duty cycle, which is then used to control the converter's switches. The battery charges or discharges based on the power balance within the microgrid.
Inverter and Grid Connection
The system includes an inverter to manage the AC grid connection. The inverter is controlled using a current control method, which generates reference currents based on the PV power and the state of charge (SOC) of the battery. The reference currents are converted into AC form using a Phase-Locked Loop (PLL) and other transformations to ensure synchronous operation with the grid.
Simulation and Results
The system's performance was simulated under varying conditions:
Wind Speed: Initially at 12 m/s, dropping to 10.8 m/s after 2 seconds.
Solar Irradiation: Starting at 1000 W/m², changing to 500 W/m², and then back to 1000 W/m².
Battery SOC: Initially set at 50%.
The simulation results showed that the PV power output varied with the changing irradiation levels, maintaining maximum power extraction under all conditions. The wind energy conversion system also adjusted its output based on wind speed changes. The battery system effectively managed the DC bus voltage, transitioning between charging and discharging modes as needed. The grid connection provided or absorbed power based on the microgrid's needs, maintaining stable operation throughout the simulation.
Conclusion
The hybrid DC and AC microgrid controlled by a neural network MPPT demonstrates effective integration of renewable energy sources and battery storage. By optimizing power extraction from both wind and solar resources and efficiently managing battery storage, this system ensures reliable and sustainable energy supply. The ability to seamlessly connect to the grid further enhances its flexibility and resilience.
Comments