Loading article...
Loading article...
Stream/Area:
-
Subject:
-
Paper ID:
IJSREM66994
Volume:
10 |
8 |
Aug 2026
Pages:
1-8
Publication Frequency:
Monthly (12 issues per year)
License:International Journal of Scientific Research in Engineering and Management follows the Creative Commons Attribution 4.0 (CC BY 4.0) License, allowing free use and distribution with proper attribution.
Electrical Engg
Mauli Group of Institution college Engg Shegaon
Electrical Engg
Mauli Group of Institution college Engg Shegaon
The increasing penetration of renewable energy sources (RESs), particularly photovoltaic and wind generation, is transforming conventional power systems into predominantly inverter-based networks. Although renewable generation supports decarbonisation, its intermittent nature and the absence of inherent rotational inertia introduce significant challenges related to frequency regulation, voltage stability, transient response, and weak-grid operation. Grid-forming (GFM) inverters have emerged as an important technology for addressing these challenges because they can establish voltage and frequency references and provide virtual inertial and damping characteristics. This paper proposes an AI-enabled Digital Twin-based adaptive control framework for grid-forming inverters operating in renewable-rich power systems. The proposed architecture combines a physics-based Digital Twin of the GFM inverter with an artificial-intelligence supervisory controller. The Digital Twin continuously estimates the operating state of the physical inverter and evaluates system responses under changing renewable generation, load variations, and grid disturbances. Based on the estimated operating conditions, the AI controller adaptively modifies selected GFM control parameters, including virtual inertia, damping, and droop coefficients. The proposed strategy is intended to overcome the fixed-parameter limitation of conventional droop and virtual synchronous-machine control. A MATLAB/Simulink-based test system is proposed for evaluating the framework under normal operation, solar irradiance variation, wind-power fluctuation, sudden load changes, weak-grid operation, and three-phase faults. Performance is evaluated using frequency deviation, voltage deviation, settling time, overshoot, rate of change of frequency (ROCOF), power oscillation, and total harmonic distortion. The expected contribution is a physically constrained adaptive control architecture in which the Digital Twin provides a safe virtual environment for AI-assisted parameter adaptation. Unlike purely data-driven control, the proposed approach retains the physical constraints of the inverter and power network. The framework provides a foundation for intelligent, adaptive, and resilient operation of renewable-rich low-inertia power systems.
KEYWORDS
This paper proposed an AI-enabled Digital Twin-based adaptive control architecture for grid-forming inverters operating in renewable-rich power systems. The motivation arises from the increasing penetration of inverter-based renewable generation and the associated reduction in conventional synchronous inertia. The proposed framework integrates a physics-based Digital Twin with an AI supervisory controller to dynamically adapt selected GFM parameters according to changing operating conditions. Unlike an unrestricted black-box AI controller, the proposed architecture maintains predefined physical constraints on the adaptive parameters. A MATLAB/Simulink-based evaluation framework has been defined for normal operation, renewable intermittency, load disturbances, weak-grid operation, and fault conditions. Frequency deviation, voltage deviation, ROCOF, settling time, overshoot, IAE, and ISE are proposed as objective performance metrics. The next stage of the research is to implement the proposed architecture in MATLAB/Simulink and obtain actual simulation results. Hardware-in-the-loop validation can subsequently be used to assess real-time feasibility.
1. Y. H. Abudyak, M. H. Rezaei, A. A. Bany Abdelnabi, H. Salimian Rizi, I. Batarsheh, and A. Q. Huang, “Grid-Forming Inverters Review: Control, Stability, and the Next Stage With Artificial Intelligence and Digital Twins,” IEEE Open Journal of Power Electronics, vol. 7, pp. 351–387, 2026, doi: 10.1109/OJPEL.2026.3654526. 2. P. J. D. de Oliveira Evald, L. Schmitz, J. M. de Andrade, F. J. Viglus, and T. B. Lazzarin, “Towards the future low-inertia power systems: A review on grid-forming inverter control—advances, challenges, and opportunities,” Renewable and Sustainable Energy Reviews, vol. 235, 116948, 2026. 3. S. Mabuwa and K. Moloi, “Physics-Informed Neural Networks for Real-Time Control of Grid-Forming Inverters: Embedding Physical System Laws into Deep Learning Architectures,” Energies, vol. 19, no. 11, 2690, 2026, doi: 10.3390/en19112690. 4. A. G.Kamble, V. A. Ghodeswar, D. S. Tayade, A. P. Padol, M. Z. Sheikh and S. Kamble, "Transient Stability Analysis of a Multi-Machine Power System," 2026 International Conference on Innovations in Communication, Geoscience and Robotics (ICICGR), Shegaon, India, 2026, “Integration of AI-driven digital twins for real-time optimization of renewable energy grids,” Frontiers in Energy Research, 2026. 5. “Digital twin and artificial intelligence–driven optimization for renewable-dominated energy systems: A system-level integration framework,” Energy Conversion and Management: X, vol. 31, 102010, 2026.
Publication Date
8/28/2026
Peer Review Type
Double-Blind Peer Review
Review Rounds: 2
Documents
Article Views
0
Total views since publication
PDF Downloads
5
Total downloads since publication
Geographic Reach
5
Digital Preservation: This article is permanently archived on Zenodo and complies with all data preservation standards across major indexing platforms.
Plagiarism Screening
This manuscript has been checked for plagiarism using TurnitinPlagiarismChecker software.
Conflict of Interest
The authors declare no conflict of interest related to this research work.
Funding Information
No funding information available for this research.
Related research in the same subject area
Loading similar articles...