Next Article in Journal
Synchronization of Low-Frequency Thermoacoustic Oscillation in Can-Annular Combustor via Compressor Combustion Casing
Previous Article in Journal
Cold CO2 Injection into Depleted Gas Reservoirs: Implications for Capacity, Injectivity and Containment
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
Journals
Energies
Volume 19
Issue 11
10.3390/en19112551
energies-logo
Submit to this Journal Review for this Journal Propose a Special Issue
► Article Menu

Article Menu

share Share announcement Help format_quote Cite
first_page
settings
Order Article Reprints
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
This is an early access version, the complete PDF, HTML, and XML versions will be available soon.
Article

Load Forecasting and Optimization of District Heating System Based on GAN Data Augmentation and LSTM–Prophet †

by
Xuejing Zheng
1,
Shisong Yan
1,
Yaran Wang
1,2,*,
Zhiyuan Shi
1,
Zhiyun Tang
1,
Yuyang Wu
1 and
Xiaguo Hu
1
1
School of Environmental Science and Engineering, Tianjin University, Tianjin 300350, China
2
Key Laboratory of Efficient Utilization of Low and Medium Grade Energy (Tianjin University), Ministry of Education of China, Tianjin 300350, China
*
Author to whom correspondence should be addressed.
†
This paper is an extended version of our paper published in Proceedings of the 12th International Conference on Cold Climate HVAC & Energy (Volume 1), CCHVAC 2025. Harbin, China, 6–8 August 2025, Environmental Science and Engineering, Springer, Singapore, 2025; pp. 292–302.
Energies 2026, 19(11), 2551; https://doi.org/10.3390/en19112551 (registering DOI)
Submission received: 29 March 2026 / Revised: 10 May 2026 / Accepted: 18 May 2026 / Published: 25 May 2026
Versions Notes

Abstract

Efficient and precise control of district heating (DH) networks is a critical pathway for achieving energy optimization and carbon emission reduction. This study proposes a systematic approach integrating data augmentation, hybrid model forecasting, and cost optimization. First, a Generative Adversarial Network (GAN) is employed to generate scenarios from limited meteorological and operational data, constructing an expanded dataset. Based on this, a personalized load forecasting model utilizing a dynamically weighted LSTM–Prophet combination is developed. This model assigns personalized weights to each heating station to accommodate the operational requirements of different functional zones. Validated using a district heating network in Tianjin, the results indicate that with an optimal weight of w = 0.9, the average relative error for load forecasting at Heating Station566 is −0.65%. Furthermore, the K-means algorithm is used to cluster the scenario database. The resulting typical scenarios are input into the LSTM–Prophet model to obtain real-time loads for each station, and a cost optimization model based on the APSO algorithm is subsequently constructed. Evaluated using a representative day, the optimized system achieves a reduction in distribution-stage cost of approximately 270,600 RMB, with a saving rate of 38%.
Keywords: district heating systems; thermal load prediction; generative adversarial networks; LSTM–Prophet hybrid model; K-means ScenarioClustering; system optimization district heating systems; thermal load prediction; generative adversarial networks; LSTM–Prophet hybrid model; K-means ScenarioClustering; system optimization

Share and Cite

MDPI and ACS Style

Zheng, X.; Yan, S.; Wang, Y.; Shi, Z.; Tang, Z.; Wu, Y.; Hu, X. Load Forecasting and Optimization of District Heating System Based on GAN Data Augmentation and LSTM–Prophet. Energies 2026, 19, 2551. https://doi.org/10.3390/en19112551

AMA Style

Zheng X, Yan S, Wang Y, Shi Z, Tang Z, Wu Y, Hu X. Load Forecasting and Optimization of District Heating System Based on GAN Data Augmentation and LSTM–Prophet. Energies. 2026; 19(11):2551. https://doi.org/10.3390/en19112551

Chicago/Turabian Style

Zheng, Xuejing, Shisong Yan, Yaran Wang, Zhiyuan Shi, Zhiyun Tang, Yuyang Wu, and Xiaguo Hu. 2026. "Load Forecasting and Optimization of District Heating System Based on GAN Data Augmentation and LSTM–Prophet" Energies 19, no. 11: 2551. https://doi.org/10.3390/en19112551

APA Style

Zheng, X., Yan, S., Wang, Y., Shi, Z., Tang, Z., Wu, Y., & Hu, X. (2026). Load Forecasting and Optimization of District Heating System Based on GAN Data Augmentation and LSTM–Prophet. Energies, 19(11), 2551. https://doi.org/10.3390/en19112551

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Back to TopTop