DDPG algorithm for power optimization and control of solar PV-integrated DFIG wind energy systems

Area of Science:

• Electrical Engineering
• Renewable Energy Systems
• Control Theory

Background:

• Modern power systems face challenges integrating diverse renewable energy sources like solar and wind.
• Traditional Proportional-Integral (PI) controllers struggle with the dynamic complexities of these integrated systems.

Purpose of the Study:

• To develop and evaluate a novel control strategy for solar photovoltaic (PV)-integrated Doubly Fed Induction Generator (DFIG) wind energy systems.
• To demonstrate the adaptive learning capabilities and improved dynamic performance of the proposed control method.

Main Methods:

• Implementation of the Deep Deterministic Policy Gradient (DDPG) algorithm for controlling both the Rotor Side Converter (RSC) and Grid Side Converter (GSC).
• Integration of solar PV at the DC link of the DFIG wind energy system.
• Comparative simulation analysis against conventional PI control methods.

Main Results:

• The DDPG-based control strategy exhibited superior performance in power quality and dynamic response.
• Enhanced system stability and fault ride-through capability were observed compared to PI controllers.
• Simulation results indicated an overall improvement in annual energy production.

Conclusions:

• The proposed DDPG algorithm offers an effective adaptive control solution for solar PV-integrated DFIG wind systems.
• This approach surpasses conventional PI controllers in key performance metrics, including stability and energy efficiency.
• The DDPG strategy enhances the reliability and performance of renewable energy integration in modern power grids.