Adaptive terminal synergetic-backstepping technique based machine learning regression algorithm for MPPT control of...

Area of Science:

• Electrical Engineering
• Renewable Energy Systems
• Control Theory

Background:

• Traditional maximum power point tracking (MPPT) methods like perturb and observe (P&O), hill climbing (HC), and incremental conductance (Inc) are widely used in photovoltaic (PV) systems due to their simplicity.
• However, artificial intelligence (AI)-based techniques, such as linear regression, are gaining attention for improved performance, especially concerning the inherent nonlinearities of PV systems.

Purpose of the Study:

• To comparatively evaluate nonlinear controllers for MPPT in photovoltaic systems.
• To develop and validate an adaptive terminal synergetic backstepping controller for a single-ended primary inductance converter (SEPIC) used in PV systems.

Main Methods:

• A novel adaptive terminal synergetic backstepping controller was developed, combining non-singular terminal synergetic control, integral backstepping, and a neural network.
• The neural network component approximates unmeasured variables to ensure finite-time convergence.
• The controller's performance was evaluated using Matlab/Simulink simulations under various conditions, including load variations and different environmental settings.

Main Results:

• The proposed adaptive terminal synergetic backstepping controller demonstrated satisfactory performance.
• It showed superior results compared to the adaptive integral backstepping controller under identical climatic conditions.
• Simulations confirmed robust performance across diverse test scenarios, including dynamic load changes.

Conclusions:

• The adaptive terminal synergetic backstepping controller offers a significant advancement for MPPT in PV systems.
• This AI-driven approach provides enhanced efficiency and stability over conventional methods.
• The controller's effectiveness is validated through simulation under realistic and varied operating conditions.