A Multi-agent Based Distributed Voltage Control Scheme Using Machine Learning and Smart Inverters

Md Rayhan Tanvir

doi:doi:10.11648/j.ijepe.20251405.12

Research Article |

| Peer-Reviewed

A Multi-agent Based Distributed Voltage Control Scheme Using Machine Learning and Smart Inverters

Md Rayhan Tanvir^*

Published in International Journal of Energy and Power Engineering (Volume 14, Issue 5)

Received: 27 October 2025 Accepted: 5 November 2025 Published: 9 December 2025

Views: Downloads:

Download PDF

Share This Article

Twitter
Linked In
Facebook

Abstract

A new distributed voltage control strategy for PV power systems that does not need support from centralized SVCs is proposed. The methodology uses smart inverters, agent-based coordination, and machine learning-based forecasting to offer a scalable and economical solution for decoupling voltage variations in the context of high penetration of PV. Each inverter acts as an autonomous agent that regulates its reactive power output using local voltage measurements and short-term irradiance predictions derived from a Long Short-Term Memory (LSTM) model. The agents cooperate with their neighbors, utilizing a consensus algorithm for coordinated voltage control throughout the network. This decentralized strategy enables fast, adaptive, and cost-effective voltage stabilization without relying on hardware-intensive centralized devices. The effectiveness and reliability of the proposed control strategy are verified through a simulation study using a five-bus radial distributed generation (DG) system with high PV penetration. Simulation results on a five-bus radial distribution feeder show better voltage stability, fault recovery, and reactive power utilization as compared with conventional and existing distributed control strategies. The findings confirm the feasibility of software-defined, inverter-based voltage regulation as a practical alternative for future smart grids. In addition, the proposed framework offers extensibility to hybrid renewable energy systems, such as wind and storage, supporting the transition toward resilient, low-carbon, and data-driven energy infrastructures.

Published in	International Journal of Energy and Power Engineering (Volume 14, Issue 5)
DOI	10.11648/j.ijepe.20251405.12
Page(s)	122-141
Creative Commons	This is an Open Access article, distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution and reproduction in any medium or format, provided the original work is properly cited.
Copyright	Copyright © The Author(s), 2025. Published by Science Publishing Group

Keywords

Decentralized Voltage Control, Smart Inverters, Multi-agent System, Voltage Fluctuation Compensation, PV Integration, Machine Learning Prediction

References

[1]	S. Allahmoradi, S. Afrasiabi, X. Liang, J. Zhao, and M. Shahidehpour, “Data-Driven Volt/VAR Optimization for Modern Distribution Networks: A Review,” IEEE Access, vol. 12, pp. 71184–71204, 2024, https://doi.org/10.1109/ACCESS.2024.3403035
[2]	Uchiyama N., Miyata H., Ito T., and Konishi H., “Reactive Power Control Method for Reducing Voltage Fluctuation in Large-scale Photovoltaic Systems,” IEEJ Trans. PE, vol. 130, no. 3, pp. 297–304, 2010, https://doi.org/10.1541/ieejpes.130.297
[3]	T. Van Dao, H. T. N. Nguyen, S. Chaitusaney, and R. Chatthaworn, “Local reactive power control of PV plants for voltage fluctuation mitigation,” in 2014 11th International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology (ECTI-CON), Nakhon Ratchasima, Thailand: IEEE, May 2014, pp. 1–6. https://doi.org/10.1109/ECTICon.2014.6839808
[4]	Md. S. Hossain, N. Abboodi Madlool, A. W. Al-Fatlawi, and M. El Haj Assad, “High Penetration of Solar Photovoltaic Structure on the Grid System Disruption: An Overview of Technology Advancement,” Sustainability, vol. 15, no. 2, p. 1174, Jan. 2023, https://doi.org/10.3390/su15021174
[5]	A. Rahmouni, “Impact of static reactive power compensator (SVC) on the power grid,” WSEAS TRANSACTIONS ON ELECTRONICS, vol. 11, pp. 96–104, Jun. 2020, https://doi.org/10.37394/232017.2020.11.12
[6]	K. Shimomukai, H. Maeda, and G. Fujita, “Volt-Var Control for Utility-scale Solar PV Plants to Replace SVCs,” in 2023 4th International Conference on High Voltage Engineering and Power Systems (ICHVEPS), Denpasar Bali, Indonesia: IEEE, Aug. 2023, pp. 176–181. https://doi.org/10.1109/ICHVEPS58902.2023.10257553
[7]	H. Jafarizadeh, E. Yamini, S. M. Zolfaghari, F. Esmaeilion, M. E. H. Assad, and M. Soltani, “Navigating challenges in large-scale renewable energy storage: Barriers, solutions, and innovations,” Energy Reports, vol. 12, pp. 2179–2192, Dec. 2024, https://doi.org/10.1016/j.egyr.2024.08.019
[8]	M. A. Alam, M. N. Sharker, M. B. A. Tamal, and M. I. Sazib, “Short-Term Solar Power Prediction using Machine Learning Algorithms: A High Performing approach,” GUB JOURNAL OF SCIENCE AND ENGINEERING, vol. 9, no. 1, pp. 82–95, Jul. 2024, https://doi.org/10.3329/gubjse.v9i1.74890
[9]	L. Wang, F. Bai, R. Yan, and T. K. Saha, “Real-Time Coordinated Voltage Control of PV Inverters and Energy Storage for Weak Networks With High PV Penetration,” IEEE Trans. Power Syst., vol. 33, no. 3, pp. 3383–3395, May 2018, https://doi.org/10.1109/TPWRS.2018.2789897
[10]	H. Akhavan-Hejazi and H. Mohsenian-Rad, “Power systems big data analytics: An assessment of paradigm shift barriers and prospects,” Energy Reports, vol. 4, pp. 91–100, Nov. 2018, https://doi.org/10.1016/j.egyr.2017.11.002
[11]	A. J. Lari, A. P. Sanfilippo, D. Bachour, and D. Perez-Astudillo, “Using Machine Learning Algorithms to Forecast Solar Energy Power Output,” Electronics, vol. 14, no. 5, p. 866, Feb. 2025, https://doi.org/10.3390/electronics14050866
[12]	B. I. Oladapo, M. A. Olawumi, and F. T. Omigbodun, “Machine Learning for Optimising Renewable Energy and Grid Efficiency,” Atmosphere, vol. 15, no. 10, p. 1250, Oct. 2024, https://doi.org/10.3390/atmos15101250
[13]	P. Suanpang and P. Jamjuntr, “Machine Learning Models for Solar Power Generation Forecasting in Microgrid Application Implications for Smart Cities,” Sustainability, vol. 16, no. 14, p. 6087, Jul. 2024, https://doi.org/10.3390/su16146087
[14]	T. Cao, Z. Ye, Q. Wu, X. Wan, J. Wang, and D. Li, “A Review of Adaptive Control Methods for Grid-Connected PV Inverters in Complex Distribution Systems,” Energies, vol. 18, no. 3, p. 473, Jan. 2025, https://doi.org/10.3390/en18030473
[15]	S. Xie, A. Kaneko, and Y. Hayashi, “A Decentralized Voltage Regulation Scheme Using Improved Volt‐Var Function of PV Smart Inverter,” IEEJ Transactions Elec Eng, vol. 19, no. 8, pp. 1300–1310, Aug. 2024, https://doi.org/10.1002/tee.24080
[16]	F. Liu, Y. Mu, and Z. Chen, “Control Strategy for Improving the Voltage Regulation Ability of Low-Carbon Energy Systems with High Proportion of Renewable Energy Integration,” Electronics, vol. 12, no. 11, p. 2513, Jun. 2023, https://doi.org/10.3390/electronics12112513
[17]	Y. Li and M. Ishikawa, “An Efficient Reactive Power Control Method for Power Network Systems with Solar Photovoltaic Generators Using Sparse Optimization,” Energies, vol. 10, no. 5, p. 696, May 2017, https://doi.org/10.3390/en10050696
[18]	T. Morstyn, B. Hredzak, and V. G. Agelidis, “Control Strategies for Microgrids With Distributed Energy Storage Systems: An Overview,” IEEE Trans. Smart Grid, vol. 9, no. 4, pp. 3652–3666, Jul. 2018, https://doi.org/10.1109/TSG.2016.2637958
[19]	J. Ma, X. Huang, B. Lou, X. Xiao, Y. Fan, and D. Zhou, “Adaptive Voltage Control of Distribution Network with High Proportion PV,” E3S Web Conf., vol. 252, p. 01033, 2021, https://doi.org/10.1051/e3sconf/202125201033
[20]	N. B. G. Brinkel et al., “Impact of rapid PV fluctuations on power quality in the low-voltage grid and mitigation strategies using electric vehicles,” International Journal of Electrical Power & Energy Systems, vol. 118, p. 105741, Jun. 2020, https://doi.org/10.1016/j.ijepes.2019.105741
[21]	F. Milano and M. Anghel, “Impact of Time Delays on Power System Stability,” IEEE Trans. Circuits Syst. I, vol. 59, no. 4, pp. 889–900, Apr. 2012, https://doi.org/10.1109/TCSI.2011.2169744
[22]	K. S. Turitsyn, P. Sulc, S. Backhaus, and M. Chertkov, “Local Control of Reactive Power by Distributed Photovoltaic Generators,” in 2010 First IEEE International Conference on Smart Grid Communications, Oct. 2010, pp. 79–84. https://doi.org/10.1109/SMARTGRID.2010.5622021
[23]	H. Pandzic, Y. Wang, T. Qiu, Y. Dvorkin, and D. S. Kirschen, “Near-Optimal Method for Siting and Sizing of Distributed Storage in a Transmission Network,” IEEE Trans. Power Syst., vol. 30, no. 5, pp. 2288–2300, Sep. 2015, https://doi.org/10.1109/TPWRS.2014.2364257
[24]	P. Sulc, K. Turitsyn, S. Backhaus, and M. Chertkov, “Options for Control of Reactive Power by Distributed Photovoltaic Generators,” Proc. IEEE, vol. 99, no. 6, pp. 1063–1073, Jun. 2011, https://doi.org/10.1109/JPROC.2011.2116750
[25]	Kouno K., Nakanishi E., Nagano Y., and Hojo M., “Reactive Power Control of Mega-solar System for Voltage Regulation with Long Distribution Line,” IEEJ Trans. PE, vol. 135, no. 5, pp. 276–289, 2015, https://doi.org/10.1541/ieejpes.135.276
[26]	D. Iioka, T. Fujii, T. Tanaka, T. Harimoto, and J. Motoyama, “Voltage Reduction in Medium Voltage Distribution Systems Using Constant Power Factor Control of PV PCS,” Energies, vol. 13, no. 20, p. 5430, Oct. 2020, https://doi.org/10.3390/en13205430
[27]	A. Safayet, P. Fajri, and I. Husain, “Reactive power management for overvoltage prevention at high PV penetration in low voltage distribution system,” IEEE Transactions on Industry Applications, vol. 53, no. 6, pp. 5786-5794, Nov.-Dec. 2017. https://doi.org/10.1109/TIA.2017.2741925

Cite This Article

Plain Text BibTeX RIS

APA Style

Tanvir, M. R. (2025). A Multi-agent Based Distributed Voltage Control Scheme Using Machine Learning and Smart Inverters. International Journal of Energy and Power Engineering, 14(5), 122-141. https://doi.org/10.11648/j.ijepe.20251405.12

Copy | Download

ACS Style

Tanvir, M. R. A Multi-agent Based Distributed Voltage Control Scheme Using Machine Learning and Smart Inverters. Int. J. Energy Power Eng. 2025, 14(5), 122-141. doi: 10.11648/j.ijepe.20251405.12

Copy | Download

AMA Style

Tanvir MR. A Multi-agent Based Distributed Voltage Control Scheme Using Machine Learning and Smart Inverters. Int J Energy Power Eng. 2025;14(5):122-141. doi: 10.11648/j.ijepe.20251405.12

Copy | Download

@article{10.11648/j.ijepe.20251405.12,
  author = {Md Rayhan Tanvir},
  title = {A Multi-agent Based Distributed Voltage Control Scheme Using Machine Learning and Smart Inverters},
  journal = {International Journal of Energy and Power Engineering},
  volume = {14},
  number = {5},
  pages = {122-141},
  doi = {10.11648/j.ijepe.20251405.12},
  url = {https://doi.org/10.11648/j.ijepe.20251405.12},
  eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.ijepe.20251405.12},
  abstract = {A new distributed voltage control strategy for PV power systems that does not need support from centralized SVCs is proposed. The methodology uses smart inverters, agent-based coordination, and machine learning-based forecasting to offer a scalable and economical solution for decoupling voltage variations in the context of high penetration of PV. Each inverter acts as an autonomous agent that regulates its reactive power output using local voltage measurements and short-term irradiance predictions derived from a Long Short-Term Memory (LSTM) model. The agents cooperate with their neighbors, utilizing a consensus algorithm for coordinated voltage control throughout the network. This decentralized strategy enables fast, adaptive, and cost-effective voltage stabilization without relying on hardware-intensive centralized devices. The effectiveness and reliability of the proposed control strategy are verified through a simulation study using a five-bus radial distributed generation (DG) system with high PV penetration. Simulation results on a five-bus radial distribution feeder show better voltage stability, fault recovery, and reactive power utilization as compared with conventional and existing distributed control strategies. The findings confirm the feasibility of software-defined, inverter-based voltage regulation as a practical alternative for future smart grids. In addition, the proposed framework offers extensibility to hybrid renewable energy systems, such as wind and storage, supporting the transition toward resilient, low-carbon, and data-driven energy infrastructures.},
 year = {2025}
}

Copy | Download

TY  - JOUR
T1  - A Multi-agent Based Distributed Voltage Control Scheme Using Machine Learning and Smart Inverters
AU  - Md Rayhan Tanvir
Y1  - 2025/12/09
PY  - 2025
N1  - https://doi.org/10.11648/j.ijepe.20251405.12
DO  - 10.11648/j.ijepe.20251405.12
T2  - International Journal of Energy and Power Engineering
JF  - International Journal of Energy and Power Engineering
JO  - International Journal of Energy and Power Engineering
SP  - 122
EP  - 141
PB  - Science Publishing Group
SN  - 2326-960X
UR  - https://doi.org/10.11648/j.ijepe.20251405.12
AB  - A new distributed voltage control strategy for PV power systems that does not need support from centralized SVCs is proposed. The methodology uses smart inverters, agent-based coordination, and machine learning-based forecasting to offer a scalable and economical solution for decoupling voltage variations in the context of high penetration of PV. Each inverter acts as an autonomous agent that regulates its reactive power output using local voltage measurements and short-term irradiance predictions derived from a Long Short-Term Memory (LSTM) model. The agents cooperate with their neighbors, utilizing a consensus algorithm for coordinated voltage control throughout the network. This decentralized strategy enables fast, adaptive, and cost-effective voltage stabilization without relying on hardware-intensive centralized devices. The effectiveness and reliability of the proposed control strategy are verified through a simulation study using a five-bus radial distributed generation (DG) system with high PV penetration. Simulation results on a five-bus radial distribution feeder show better voltage stability, fault recovery, and reactive power utilization as compared with conventional and existing distributed control strategies. The findings confirm the feasibility of software-defined, inverter-based voltage regulation as a practical alternative for future smart grids. In addition, the proposed framework offers extensibility to hybrid renewable energy systems, such as wind and storage, supporting the transition toward resilient, low-carbon, and data-driven energy infrastructures.
VL  - 14
IS  - 5
ER  -

Copy | Download

Author Information

Md Rayhan Tanvir

School of Electronic and Electrical Engineering, East China University of Technology, Nanchang, China

Contact Email

http://orcid.org/0000-0002-8263-0916

Download PDF

Submit an Article

Sections

Plain Text BibTeX RIS

APA Style

Tanvir, M. R. (2025). A Multi-agent Based Distributed Voltage Control Scheme Using Machine Learning and Smart Inverters. International Journal of Energy and Power Engineering, 14(5), 122-141. https://doi.org/10.11648/j.ijepe.20251405.12

Copy | Download

ACS Style

Tanvir, M. R. A Multi-agent Based Distributed Voltage Control Scheme Using Machine Learning and Smart Inverters. Int. J. Energy Power Eng. 2025, 14(5), 122-141. doi: 10.11648/j.ijepe.20251405.12

Copy | Download

AMA Style

Tanvir MR. A Multi-agent Based Distributed Voltage Control Scheme Using Machine Learning and Smart Inverters. Int J Energy Power Eng. 2025;14(5):122-141. doi: 10.11648/j.ijepe.20251405.12

Copy | Download

@article{10.11648/j.ijepe.20251405.12,
  author = {Md Rayhan Tanvir},
  title = {A Multi-agent Based Distributed Voltage Control Scheme Using Machine Learning and Smart Inverters},
  journal = {International Journal of Energy and Power Engineering},
  volume = {14},
  number = {5},
  pages = {122-141},
  doi = {10.11648/j.ijepe.20251405.12},
  url = {https://doi.org/10.11648/j.ijepe.20251405.12},
  eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.ijepe.20251405.12},
  abstract = {A new distributed voltage control strategy for PV power systems that does not need support from centralized SVCs is proposed. The methodology uses smart inverters, agent-based coordination, and machine learning-based forecasting to offer a scalable and economical solution for decoupling voltage variations in the context of high penetration of PV. Each inverter acts as an autonomous agent that regulates its reactive power output using local voltage measurements and short-term irradiance predictions derived from a Long Short-Term Memory (LSTM) model. The agents cooperate with their neighbors, utilizing a consensus algorithm for coordinated voltage control throughout the network. This decentralized strategy enables fast, adaptive, and cost-effective voltage stabilization without relying on hardware-intensive centralized devices. The effectiveness and reliability of the proposed control strategy are verified through a simulation study using a five-bus radial distributed generation (DG) system with high PV penetration. Simulation results on a five-bus radial distribution feeder show better voltage stability, fault recovery, and reactive power utilization as compared with conventional and existing distributed control strategies. The findings confirm the feasibility of software-defined, inverter-based voltage regulation as a practical alternative for future smart grids. In addition, the proposed framework offers extensibility to hybrid renewable energy systems, such as wind and storage, supporting the transition toward resilient, low-carbon, and data-driven energy infrastructures.},
 year = {2025}
}

Copy | Download

TY  - JOUR
T1  - A Multi-agent Based Distributed Voltage Control Scheme Using Machine Learning and Smart Inverters
AU  - Md Rayhan Tanvir
Y1  - 2025/12/09
PY  - 2025
N1  - https://doi.org/10.11648/j.ijepe.20251405.12
DO  - 10.11648/j.ijepe.20251405.12
T2  - International Journal of Energy and Power Engineering
JF  - International Journal of Energy and Power Engineering
JO  - International Journal of Energy and Power Engineering
SP  - 122
EP  - 141
PB  - Science Publishing Group
SN  - 2326-960X
UR  - https://doi.org/10.11648/j.ijepe.20251405.12
AB  - A new distributed voltage control strategy for PV power systems that does not need support from centralized SVCs is proposed. The methodology uses smart inverters, agent-based coordination, and machine learning-based forecasting to offer a scalable and economical solution for decoupling voltage variations in the context of high penetration of PV. Each inverter acts as an autonomous agent that regulates its reactive power output using local voltage measurements and short-term irradiance predictions derived from a Long Short-Term Memory (LSTM) model. The agents cooperate with their neighbors, utilizing a consensus algorithm for coordinated voltage control throughout the network. This decentralized strategy enables fast, adaptive, and cost-effective voltage stabilization without relying on hardware-intensive centralized devices. The effectiveness and reliability of the proposed control strategy are verified through a simulation study using a five-bus radial distributed generation (DG) system with high PV penetration. Simulation results on a five-bus radial distribution feeder show better voltage stability, fault recovery, and reactive power utilization as compared with conventional and existing distributed control strategies. The findings confirm the feasibility of software-defined, inverter-based voltage regulation as a practical alternative for future smart grids. In addition, the proposed framework offers extensibility to hybrid renewable energy systems, such as wind and storage, supporting the transition toward resilient, low-carbon, and data-driven energy infrastructures.
VL  - 14
IS  - 5
ER  -

Copy | Download