Adaptive Vector Control of VSC-HVDC Systems Using Lightweight Fuzzy Q-Learning

Authors

DOI:

https://doi.org/10.63623/cz1s3d42

Keywords:

Adaptive control, Fuzzy logic, Q-Learning, Smart grid, VSC-HVDC

Abstract

This paper presents an adaptive vector control framework for Voltage Source Converter-based High Voltage Direct Current (VSC-HVDC) systems using a novel Lightweight Fuzzy-Enhanced Q-Learning (LFQL) controller. The proposed LFQL architecture integrates a fuzzy inference layer with a reinforcement learning agent to enable real-time self-tuning of current and voltage references, overcoming the limitations of conventional fixed-gain PI controllers. Designed for bidirectional power transfer and asynchronous grid interconnection, the controller ensures robust regulation of DC-link voltage and accurate tracking of active and reactive power under dynamic grid conditions. Comparative simulation results highlight the advantages of LFQL over traditional PI control: settling time for DC-link voltage is reduced from 0.45 s to 0.21 s, reactive power overshoot drops from 7.8% to 2.3%, and active power steady-state error is limited to below 0.5%. Furthermore, the LFQL control scheme maintains waveform integrity and dynamic stability even during frequency mismatch and power reversal scenarios. Its low computational footprint and superior adaptability make LFQL a practical and scalable solution for intelligent HVDC control in evolving power systems.

Author Biographies

  • Ganesh Moorthy Jagadeesan, Department of Electrical and Electronics Engineering, KSR College of Engineering, Tiruchengode, Tamil Nadu, India

    EEE, ASSISTANT PROFESSOR

  • Vani Easwaran, Department of Electrical and Electronics Engineering, KSR College of Engineering, Tiruchengode, Tamil Nadu, India

    EEE, ASSOCIATE PROFESSOR

References

[1]Babayomi O, Li Y, Zhang Z, Park KB. Advanced control of grid-connected microgrids: challenges, advances and trends. IEEE Transactions on Power Electronics, 2025, 40(6), 7681-7708. DOI: 10.1109/TPEL.2025.3526246

[2]Shazon MNH, Nahid-Al-Masood, Jawad A. Frequency control challenges and potential countermeasures in future low-inertia power systems: A review. Energy Reports, 2022, 8, 6191-219. DOI: 10.1016/j.egyr.2022.04.063

[3]Hannan MA, Hussin I, Ker PJ, Hoque MM, Lipu MH, et al. Advanced control strategies of VSC based HVDC transmission system: Issues and potential recommendations. Ieee Access, 2018, 6, 78352-69. DOI: 10.1109/ACCESS.2018.2885010

[4]Sanchez Garciarivas R, Rasilla Gonzalez D, Navarro JA, Soriano LA, Rubio JD, et al. Vsc-hvdc and its applications for black start restoration processes. Applied Sciences, 2021, 11(12), 5648. DOI: 10.3390/app11125648

[5]Zhang Y, Ravishankar J, Fletcher J, Li R, Han M. Review of modular multilevel converter based multi-terminal HVDC systems for offshore wind power transmission. Renewable and Sustainable Energy Reviews, 2016, 61, 572-86. DOI: 10.1016/j.rser.2016.01.108

[6]Jacobson D, Ibrahim I, Modi N, Wilson D, Cheng Y, et al. Power System Planning and Operational Studies in Inverter-Dominated Networks: Interactions and Oscillation Studies, System Strength, and Inertia Determination. Power System Planning and Operational Studies in Inverter-Dominated Networks: Interactions and Oscillation Studies, System Strength, and Inertia Determination. InPower System Dynamic Modelling and Analysis in Evolving Networks, Z. Badrzadeh Babak and Emin, Ed., Cham: Springer Nature Switzerland, 2024, 567-653. DOI: 10.1007/978-3-031-47821-5_13

[7]Ahmad N, Ghadi YG, Adnan M, Ali M. From smart grids to super smart grids: a roadmap for strategic demand management for next generation SAARC and European power infrastructure. IEEE Access, 2023, 11, 12303-12341. DOI: 10.1109/ACCESS.2023.3241686

[8]Hossain MI, Shafiullah M, Abido M. VSC controllers for multiterminal HVDC transmission system: A comparative study. Arabian Journal for Science and Engineering, 2020, 45(8), 6411-6422. DOI: 10.1007/s13369-020-04500-y

[9]Adiche S, Toumi D, Larbi M, Bouddou R, Bouchikhi N, et al. Robust modified adaptive PI-based controller for managing uncertainties in distributed generation systems of AC microgrids. Results in Engineering, 2025, 26, 104949. DOI: 10.1016/j.rineng.2025.104949

[10]Minchala-Ávila C, Arévalo P, Ochoa-Correa D. A systematic review of model predictive control for robust and efficient energy management in electric vehicle integration and V2G applications. Modelling, 2025, 6(1), 20. DOI: 10.3390/modelling6010020

[11]Boopathi R, Indragandhi V. Enhancement of power quality in grid-connected systems using a predictive direct power controlled based PV-interfaced with multilevel inverter shunt active power filter. Scientific Reports, 2025, 15(1), 7967. DOI: 10.1038/s41598-025-92693-3

[12]Ebrahim MA, Ahmed MN, Ramadan HS, Becherif M, Zhao J. Optimal metaheuristic-based sliding mode control of VSC-HVDC transmission systems. Mathematics and Computers in Simulation, 2021, 179, 178-913. DOI: 10.1016/j.matcom.2020.08.009

[13]Subedi S, Gui Y, Xue Y. Applications of data-driven dynamic modeling of power converters in power systems: An overview. IEEE Transactions on Industry Applications, 2025, 61(2), 2434-2456. DOI: 10.1109/TIA.2025.3529797

[14]Pandey B, Nguyen N. A Model-Free Approach for Load Frequency Control Using Deep Reinforcement Learning. In 2025 IEEE Texas Power and Energy Conference (TPEC), 2025, 1-6. DOI: 10.1109/TPEC63981.2025.10907186

[15]Arun V, Rangaiah YP, Dutt A, Al-Allak MA, Garg M, et al. Adaptive Demand Response Optimization Using Reinforcement Learning for Enhanced Grid Stability and Renewable Integration. In 2025 International Conference on Cognitive Computing in Engineering, Communications, Sciences and Biomedical Health Informatics (IC3ECSBHI), 2025, 724-729. DOI: 10.1109/IC3ECSBHI63591.2025.10991189

[16]Karatzinis GD, Boutalis YS. A review study of fuzzy cognitive maps in engineering: applications, insights, and future directions. Eng, 2025, 6(2), 37. DOI: 10.3390/eng6020037

[17]Babayomi O, Li Y, Zhang Z, Park KB. Advanced control of grid-connected microgrids: challenges, advances and trends. IEEE Transactions on Power Electronics, 2025, 40(6,), 7681-7708. DOI: 10.1109/TPEL.2025.3526246

[18]Venkata Pavan Kumar Y, Naga Venkata Bramareswara Rao S, Pradeep DJ. Fuzzy-based current-controlled voltage source inverter for improved power quality in photovoltaic and fuel cell integrated sustainable hybrid microgrids. Sustainability, 2025, 17(10), 4520. DOI: 10.3390/su17104520

[19]Bi X, He M, Sun Y. Mix Q-learning for lane changing: a collaborative decision-making method in multi-agent deep reinforcement learning. IEEE Transactions on Vehicular Technology, 2025, 1-14. DOI: 10.1109/TVT.2025.3533006

[20]Ngamroo I, Surinkaew T, Mitani Y. Small-signal stability enhancement through integration of distributed grid-forming loads considering multi-agent collaboration. IEEE Transactions on Power Systems, 2025, 1-15. DOI: 10.1109/TPWRS.2025.3561231

[21]Yousaf MZ, Singh AR, Khalid S, Bajaj M, Kumar BH, et al. Bayesian-optimized LSTM-DWT approach for reliable fault detection in MMC-based HVDC systems. Scientific Reports, 2024, 14(1), 17968. DOI: 10.1038/s41598-024-68985-5

[22]Camarillo-Penaranda JR, Cunha AC, Franca BW, de Abreu Oliveira F, de Oliveira Senna L. A review on VSC-HVDC control schemes. Annual Reviews in Control, 2025, 59, 100988. DOI: 10.1016/j.arcontrol.2025.100988

[23]Xu F, Ni X, Zheng M, Chen Q, Qiu P, et al. Comparison and analysis of distributed power flow controller technology. Energy Reports, 2022, 8, 785-792. DOI: 10.1016/j.egyr.2021.11.074

[24]Xua B, Yang G. Interpretability research of deep learning: A literature survey. Information Fusion, 2025, 115, 102721. DOI: 10.1016/j.inffus.2024.102721

Downloads

Published

2025-06-25

Issue

Vol. 1 No. 2 (2025)

Section

Articles

License

Copyright (c) 2025 Advances in Power Systems Research

Creative Commons License

This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.