Adjustable Robust Optimization for Hybrid Hydrogen-Battery Microgrids with LSTM-QR Forecaster

Zuqing Zheng; Zhaoyang Dong; Tong Li; Yuechuan Tao; Guo Chen; Fushuan Wen

doi:10.1109/ICPIES65420.2025.11070144

Adjustable Robust Optimization for Hybrid Hydrogen-Battery Microgrids with LSTM-QR Forecaster

Zuqing Zheng, Zhaoyang Dong, Tong Li, Yuechuan Tao, Guo Chen^*, Fushuan Wen

^*Corresponding author for this work

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

Abstract

To address the challenges posed by renewable energy variability and carbon emissions in traditional fossil fuel-powered microgrids, this paper proposes an emission-free microgrid system integrated with hybrid hydrogen-battery energy storage. First, a Long Short-Term Memory with Quantile Regression (LSTM-QR) forecaster is employed to estimate the upper and lower bounds of renewable energy generation, which are then used to construct an uncertainty set. Next, an adjustable robust optimization model is developed to minimize the total operational cost while accounting for the uncertainty in renewable energy generation. The model's robustness can be flexibly controlled by adjusting the time budget. Using linear decision rules, the model is reformulated as a mixed-integer linear programming problem, which can be efficiently solved by standard optimization solvers. Numerical simulations demonstrate the effectiveness of the model and solution approach. © 2025 IEEE.

Original language	English
Title of host publication	Proceedings of 2025 IEEE International Conference on Power and Integrated Energy Systems (ICPIES 2025)
Publisher	IEEE
Pages	349-354
Number of pages	6
ISBN (Electronic)	979-8-3315-1185-2
DOIs	https://doi.org/10.1109/ICPIES65420.2025.11070144
Publication status	Published - 2025
Event	2025 IEEE International Conference on Power and Integrated Energy Systems (ICPIES 2025) - Haikou, China Duration: 7 Apr 2025 → 9 Apr 2025

Publication series

Name	IEEE International Conference on Power and Integrated Energy Systems, ICPIES

Conference

Conference	2025 IEEE International Conference on Power and Integrated Energy Systems (ICPIES 2025)
Place	China
City	Haikou
Period	7/04/25 → 9/04/25

UN SDGs

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

SDG 7 Affordable and Clean Energy
SDG 13 Climate Action

Research Keywords

adjustable robust optimization
Hydrogen-Battery energy storage
linear decision rules
LSTM-QR forecaster

Access Output

10.1109/ICPIES65420.2025.11070144

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

Zheng, Z., Dong, Z., Li, T., Tao, Y., Chen, G., & Wen, F. (2025). Adjustable Robust Optimization for Hybrid Hydrogen-Battery Microgrids with LSTM-QR Forecaster. In Proceedings of 2025 IEEE International Conference on Power and Integrated Energy Systems (ICPIES 2025) (pp. 349-354). (IEEE International Conference on Power and Integrated Energy Systems, ICPIES). IEEE. https://doi.org/10.1109/ICPIES65420.2025.11070144

@inproceedings{5cd8ffe6dce1458e8158305cd345dc36,

title = "Adjustable Robust Optimization for Hybrid Hydrogen-Battery Microgrids with LSTM-QR Forecaster",

abstract = "To address the challenges posed by renewable energy variability and carbon emissions in traditional fossil fuel-powered microgrids, this paper proposes an emission-free microgrid system integrated with hybrid hydrogen-battery energy storage. First, a Long Short-Term Memory with Quantile Regression (LSTM-QR) forecaster is employed to estimate the upper and lower bounds of renewable energy generation, which are then used to construct an uncertainty set. Next, an adjustable robust optimization model is developed to minimize the total operational cost while accounting for the uncertainty in renewable energy generation. The model's robustness can be flexibly controlled by adjusting the time budget. Using linear decision rules, the model is reformulated as a mixed-integer linear programming problem, which can be efficiently solved by standard optimization solvers. Numerical simulations demonstrate the effectiveness of the model and solution approach. {\textcopyright} 2025 IEEE.",

keywords = "adjustable robust optimization, Hydrogen-Battery energy storage, linear decision rules, LSTM-QR forecaster",

author = "Zuqing Zheng and Zhaoyang Dong and Tong Li and Yuechuan Tao and Guo Chen and Fushuan Wen",

year = "2025",

doi = "10.1109/ICPIES65420.2025.11070144",

language = "English",

series = "IEEE International Conference on Power and Integrated Energy Systems, ICPIES",

publisher = "IEEE",

pages = "349--354",

booktitle = "Proceedings of 2025 IEEE International Conference on Power and Integrated Energy Systems (ICPIES 2025)",

address = "United States",

note = "2025 IEEE International Conference on Power and Integrated Energy Systems (ICPIES 2025) ; Conference date: 07-04-2025 Through 09-04-2025",

}

Zheng, Z, Dong, Z, Li, T, Tao, Y, Chen, G & Wen, F 2025, Adjustable Robust Optimization for Hybrid Hydrogen-Battery Microgrids with LSTM-QR Forecaster. in Proceedings of 2025 IEEE International Conference on Power and Integrated Energy Systems (ICPIES 2025). IEEE International Conference on Power and Integrated Energy Systems, ICPIES, IEEE, pp. 349-354, 2025 IEEE International Conference on Power and Integrated Energy Systems (ICPIES 2025), Haikou, China, 7/04/25. https://doi.org/10.1109/ICPIES65420.2025.11070144

Adjustable Robust Optimization for Hybrid Hydrogen-Battery Microgrids with LSTM-QR Forecaster. / Zheng, Zuqing; Dong, Zhaoyang; Li, Tong et al.
Proceedings of 2025 IEEE International Conference on Power and Integrated Energy Systems (ICPIES 2025). IEEE, 2025. p. 349-354 (IEEE International Conference on Power and Integrated Energy Systems, ICPIES).

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

TY - GEN

T1 - Adjustable Robust Optimization for Hybrid Hydrogen-Battery Microgrids with LSTM-QR Forecaster

AU - Zheng, Zuqing

AU - Dong, Zhaoyang

AU - Li, Tong

AU - Tao, Yuechuan

AU - Chen, Guo

AU - Wen, Fushuan

PY - 2025

Y1 - 2025

N2 - To address the challenges posed by renewable energy variability and carbon emissions in traditional fossil fuel-powered microgrids, this paper proposes an emission-free microgrid system integrated with hybrid hydrogen-battery energy storage. First, a Long Short-Term Memory with Quantile Regression (LSTM-QR) forecaster is employed to estimate the upper and lower bounds of renewable energy generation, which are then used to construct an uncertainty set. Next, an adjustable robust optimization model is developed to minimize the total operational cost while accounting for the uncertainty in renewable energy generation. The model's robustness can be flexibly controlled by adjusting the time budget. Using linear decision rules, the model is reformulated as a mixed-integer linear programming problem, which can be efficiently solved by standard optimization solvers. Numerical simulations demonstrate the effectiveness of the model and solution approach. © 2025 IEEE.

AB - To address the challenges posed by renewable energy variability and carbon emissions in traditional fossil fuel-powered microgrids, this paper proposes an emission-free microgrid system integrated with hybrid hydrogen-battery energy storage. First, a Long Short-Term Memory with Quantile Regression (LSTM-QR) forecaster is employed to estimate the upper and lower bounds of renewable energy generation, which are then used to construct an uncertainty set. Next, an adjustable robust optimization model is developed to minimize the total operational cost while accounting for the uncertainty in renewable energy generation. The model's robustness can be flexibly controlled by adjusting the time budget. Using linear decision rules, the model is reformulated as a mixed-integer linear programming problem, which can be efficiently solved by standard optimization solvers. Numerical simulations demonstrate the effectiveness of the model and solution approach. © 2025 IEEE.

KW - adjustable robust optimization

KW - Hydrogen-Battery energy storage

KW - linear decision rules

KW - LSTM-QR forecaster

UR - http://www.scopus.com/inward/record.url?scp=105012243933&partnerID=8YFLogxK

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-105012243933&origin=recordpage

U2 - 10.1109/ICPIES65420.2025.11070144

DO - 10.1109/ICPIES65420.2025.11070144

M3 - RGC 32 - Refereed conference paper (with host publication)

T3 - IEEE International Conference on Power and Integrated Energy Systems, ICPIES

SP - 349

EP - 354

BT - Proceedings of 2025 IEEE International Conference on Power and Integrated Energy Systems (ICPIES 2025)

PB - IEEE

T2 - 2025 IEEE International Conference on Power and Integrated Energy Systems (ICPIES 2025)

Y2 - 7 April 2025 through 9 April 2025

ER -

Zheng Z, Dong Z, Li T, Tao Y, Chen G, Wen F. Adjustable Robust Optimization for Hybrid Hydrogen-Battery Microgrids with LSTM-QR Forecaster. In Proceedings of 2025 IEEE International Conference on Power and Integrated Energy Systems (ICPIES 2025). IEEE. 2025. p. 349-354. (IEEE International Conference on Power and Integrated Energy Systems, ICPIES). Epub 2025 Jul 14. doi: 10.1109/ICPIES65420.2025.11070144

Adjustable Robust Optimization for Hybrid Hydrogen-Battery Microgrids with LSTM-QR Forecaster

Abstract

Publication series

Conference

UN SDGs

Research Keywords

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this