Adaptive Neural Network-Based PI (ANN-PI) Control for DC Microgrids in Renewable Hydrogen Production Systems

S. Khodakaramzadeh; P. Bauer; H. Vahedi

doi:10.1109/IECON58223.2025.11221909

Adaptive Neural Network-Based PI (ANN-PI) Control for DC Microgrids in Renewable Hydrogen Production Systems

DC systems, Energy conversion & Storage

Research output: Chapter in Book/Conference proceedings/Edited volume › Conference contribution › Scientific › peer-review

Abstract

This research presents a neural-adaptive control technique for DC microgrids in renewable hydrogen production systems. The proposed approach tackles voltage stability issues arising from variable solar production and fluctuating electrolyzer loads with an adaptive neural network-based proportional-integral (ANN-PI) controller with online system identification. The control architecture utilizes two concurrent multilayer perceptron (MLP) networks: one for real-time system identification to estimate the Jacobian matrix, and another for adaptive proportional-integral (PI) parameter adjustment. The decentralized architecture removes communication dependencies among converters, hence improving reliability and scalability. Simulation results indicate a better dynamic response with a 50% decrease in settling time, increased voltage stability retaining the DC bus voltage within ±2% of the nominal 400 V, and resilient performance under diverse situations, including load transitions and changes in solar irradiation. The neural-adaptive method effectively facilitates intelligent, model-free regulation for electric-hydrogen DC microgrids.

Original language	English
Title of host publication	Proceedings of the IECON 2025 – 51st Annual Conference of the IEEE Industrial Electronics Society
Publisher	IEEE
Number of pages	6
ISBN (Electronic)	979-8-3315-9681-1
ISBN (Print)	979-8-3315-9682-8
DOIs	https://doi.org/10.1109/IECON58223.2025.11221909
Publication status	Published - 2025
Event	IECON 2025 – 51st Annual Conference of the IEEE Industrial Electronics Society - Madrid, Spain Duration: 14 Oct 2025 → 17 Oct 2025

Conference

Conference	IECON 2025 – 51st Annual Conference of the IEEE Industrial Electronics Society
Country/Territory	Spain
City	Madrid
Period	14/10/25 → 17/10/25

Bibliographical note

Green Open Access added to TU Delft Institutional Repository as part of the Taverne amendment. More information about this copyright law amendment can be found at https://www.openaccess.nl. Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.

Keywords

DC microgrid
renewable hydrogen production
neural networks
adaptive control
system identification

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1109/IECON58223.2025.11221909

Embargoed Document

Adaptive_Neural_Network-Based_PI_ANN-PI_Control_for_DC_Microgrids_in_Renewable_Hydrogen_Production_Systems
Final published version, 1.84 MB
Embargo ends: 6/05/26

Cite this

@inproceedings{8cba303580284e8aacf38f16f3ca0773,

title = "Adaptive Neural Network-Based PI (ANN-PI) Control for DC Microgrids in Renewable Hydrogen Production Systems",

abstract = "This research presents a neural-adaptive control technique for DC microgrids in renewable hydrogen production systems. The proposed approach tackles voltage stability issues arising from variable solar production and fluctuating electrolyzer loads with an adaptive neural network-based proportional-integral (ANN-PI) controller with online system identification. The control architecture utilizes two concurrent multilayer perceptron (MLP) networks: one for real-time system identification to estimate the Jacobian matrix, and another for adaptive proportional-integral (PI) parameter adjustment. The decentralized architecture removes communication dependencies among converters, hence improving reliability and scalability. Simulation results indicate a better dynamic response with a 50% decrease in settling time, increased voltage stability retaining the DC bus voltage within ±2% of the nominal 400 V, and resilient performance under diverse situations, including load transitions and changes in solar irradiation. The neural-adaptive method effectively facilitates intelligent, model-free regulation for electric-hydrogen DC microgrids.",

keywords = "DC microgrid, renewable hydrogen production, neural networks, adaptive control, system identification",

author = "S. Khodakaramzadeh and P. Bauer and H. Vahedi",

note = "Green Open Access added to TU Delft Institutional Repository as part of the Taverne amendment. More information about this copyright law amendment can be found at https://www.openaccess.nl. Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.; IECON 2025 – 51st Annual Conference of the IEEE Industrial Electronics Society ; Conference date: 14-10-2025 Through 17-10-2025",

year = "2025",

doi = "10.1109/IECON58223.2025.11221909",

language = "English",

isbn = "979-8-3315-9682-8",

booktitle = "Proceedings of the IECON 2025 – 51st Annual Conference of the IEEE Industrial Electronics Society",

publisher = "IEEE",

address = "United States",

}

Khodakaramzadeh, S , Bauer, P & Vahedi, H 2025, Adaptive Neural Network-Based PI (ANN-PI) Control for DC Microgrids in Renewable Hydrogen Production Systems. in Proceedings of the IECON 2025 – 51st Annual Conference of the IEEE Industrial Electronics Society. IEEE, IECON 2025 – 51st Annual Conference of the IEEE Industrial Electronics Society, Madrid, Spain, 14/10/25. https://doi.org/10.1109/IECON58223.2025.11221909

Adaptive Neural Network-Based PI (ANN-PI) Control for DC Microgrids in Renewable Hydrogen Production Systems. / Khodakaramzadeh, S.; Bauer, P.; Vahedi, H.
Proceedings of the IECON 2025 – 51st Annual Conference of the IEEE Industrial Electronics Society. IEEE, 2025.

Research output: Chapter in Book/Conference proceedings/Edited volume › Conference contribution › Scientific › peer-review

TY - GEN

T1 - Adaptive Neural Network-Based PI (ANN-PI) Control for DC Microgrids in Renewable Hydrogen Production Systems

AU - Khodakaramzadeh, S.

AU - Bauer, P.

AU - Vahedi, H.

N1 - Green Open Access added to TU Delft Institutional Repository as part of the Taverne amendment. More information about this copyright law amendment can be found at https://www.openaccess.nl. Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.

PY - 2025

Y1 - 2025

N2 - This research presents a neural-adaptive control technique for DC microgrids in renewable hydrogen production systems. The proposed approach tackles voltage stability issues arising from variable solar production and fluctuating electrolyzer loads with an adaptive neural network-based proportional-integral (ANN-PI) controller with online system identification. The control architecture utilizes two concurrent multilayer perceptron (MLP) networks: one for real-time system identification to estimate the Jacobian matrix, and another for adaptive proportional-integral (PI) parameter adjustment. The decentralized architecture removes communication dependencies among converters, hence improving reliability and scalability. Simulation results indicate a better dynamic response with a 50% decrease in settling time, increased voltage stability retaining the DC bus voltage within ±2% of the nominal 400 V, and resilient performance under diverse situations, including load transitions and changes in solar irradiation. The neural-adaptive method effectively facilitates intelligent, model-free regulation for electric-hydrogen DC microgrids.

AB - This research presents a neural-adaptive control technique for DC microgrids in renewable hydrogen production systems. The proposed approach tackles voltage stability issues arising from variable solar production and fluctuating electrolyzer loads with an adaptive neural network-based proportional-integral (ANN-PI) controller with online system identification. The control architecture utilizes two concurrent multilayer perceptron (MLP) networks: one for real-time system identification to estimate the Jacobian matrix, and another for adaptive proportional-integral (PI) parameter adjustment. The decentralized architecture removes communication dependencies among converters, hence improving reliability and scalability. Simulation results indicate a better dynamic response with a 50% decrease in settling time, increased voltage stability retaining the DC bus voltage within ±2% of the nominal 400 V, and resilient performance under diverse situations, including load transitions and changes in solar irradiation. The neural-adaptive method effectively facilitates intelligent, model-free regulation for electric-hydrogen DC microgrids.

KW - DC microgrid

KW - renewable hydrogen production

KW - neural networks

KW - adaptive control

KW - system identification

U2 - 10.1109/IECON58223.2025.11221909

DO - 10.1109/IECON58223.2025.11221909

M3 - Conference contribution

SN - 979-8-3315-9682-8

BT - Proceedings of the IECON 2025 – 51st Annual Conference of the IEEE Industrial Electronics Society

PB - IEEE

T2 - IECON 2025 – 51st Annual Conference of the IEEE Industrial Electronics Society

Y2 - 14 October 2025 through 17 October 2025

ER -

Adaptive Neural Network-Based PI (ANN-PI) Control for DC Microgrids in Renewable Hydrogen Production Systems

Abstract

Conference

Bibliographical note

Keywords

UN SDGs

Access to Document

Embargoed Document

Fingerprint

Cite this