Artificial Super Intelligence-Optimized Electric Spring for Hybrid Renewable Energy Systems

¹ Department of EEE, Professor and Head, Vidya Jyothi Institute of Technology, Hyderabad, 500075, India
² Department of EEE, Associate Professor, Vidya Jyothi Institute of Technology, Hyderabad, 500075, India
³ Department of EEE, Assistant Professor, Vidya Jyothi Institute of Technology, Hyderabad, 500075, India
⁴ Department of EEE, Associate Professor and Head, Pallavi Engineering College, Nagole, Hyderabad, 501505, India

^* Corresponding author: naag198222@gmail.com

Abstract

This article introduces the design of an advanced smart grid model that optimizes power management through the integration of renewable energy sources. A key innovation lies in the use of a Renewable-Powered Smart Grid System driven by an Artificial Super Intelligence Network (ASIN) to ensure stable voltage profiles and balanced reactive power. The system harnesses solar and wind energy, employing ASIN techniques alongside Electric Spring technology for efficient reactive power control. The seamless integration of renewable sources allows the system to meet grid power demands while managing reactive power effectively. A Feed Forward Neural Network (FFNN) is utilized to optimize power calculations, determining voltage profiles, and minimizing power losses based on varying load conditions. The Electric Spring acts as an optimal VAR compensating device, keeping reactive power within permissible limits, thereby improving voltage stability, reducing losses, and maintaining reactive power balance across the grid. The proposed system is implemented and tested in a MATLAB/Simulink environment under three distinct scenarios. Results indicate that the hybrid energy-powered smart grid meets its performance objectives efficiently. Notably, the integration of renewable sources with ASIN enhances the voltage profile by approximately 97.70% increasing it from 1.074 to 1.083 p. u. Additionally, real power losses are reduced from 3.531 MW to 3.45 MW, demonstrating the system’s improved efficiency.