Application of Artificial Intelligence Algorithms for Estimation Daily Peak Load of District Heating System in Ulaanbaatar
Main Article Content
Keywords
Artificial intelligence, peak load, statistical comparison, heat supply system
Abstract
The heating system of Ulaanbaatar, has been in operation for more than 60 years; therefore, optimizing system operation, implementing data-driven system planning and improvement, and supporting informed decision-making have become priority objectives. This study investigates the forecasting of daily peak loads in the district heating system (DHS) of Ulaanbaatar, Mongolia, which is recognized as the coldest capital city worldwide. A comprehensive dataset comprising more than 80,000 hours of historical heat load and ambient temperature data collected between 2018 and 2024 was used to develop an artificial intelligence (AI) model based on a feed-forward back-propagation neural network. The model incorporates outdoor air temperature and historical load values from the previous day and the corresponding day of the preceding week as input variables. The results show that the AI-based approach achieves higher predictive accuracy than conventional regression models, with a correlation coefficient of 0.953 and a coefficient of determination R2 of 0.925, compared with 0.91 for the regression-based method. These findings indicate that the proposed model is suitable for supporting operational planning and load management in district heating systems operating under extreme climatic conditions.
Downloads
References
https://doi.org/10.1016/j.energy.2023.127637.
2. S.Kuntuarova, T.Licklederer, T.Huynh, “Design and simulation of district heating networks: A review of modeling approaches and tools,” Energy Volume 305, 2024, https://doi.org/10.1016/j.energy.2024.132189.
3. Kh.Enkhjargal and L.Batmend, “Trends in Heat Supply Systems,” Energy & Engineering journal 2023-4(230),
4. E.Dotzauer, “Simple model for prediction of loads in district-heating systems,” Applied Energy Volume 73, Issues 3–4, 2002, Pages 277-284, https://doi.org/10.1016/S0306-2619(02)00078-8.
5. Ulaanbaatar District Heating JSC. The Current Situation of Central Heating Supply in the Capital City and Future Measures, URL: https://portal.dulaan.mn/.
6. W.Chung, Y.Hyeon Gu, S.Joon Yoo, “District heater load forecasting based on machine learning and parallel CNN-LSTM attention,” Energy Volume 246, 2022, https://doi.org/10.1016/j.energy.2022.123350.
7. P.Hua, H.Wang, Z.Xie, R.Lahdelma, “District heating load patterns and short-term forecasting for buildings and city level,” Energy Volume 289 2024, https://doi.org/10.1016/j.energy.2023.129866.
8. L.Batmend, “Future perspective of heat supply of Ulaanbaatar city until 2040” Proceedings of 3rd Mongolian Photovoltaic Conference - 2024.
9. S.Sainbold, “Study on Daily Peak Load Forecasting of the Central Regional Integrated Grid Using Artificial Intelligence Algorithms,” Energy & Engineering journal 2023-6(232).
10. H.Lund, B.Moller, A.Dyrelund, “The role of district heating in future renewable energy systems,” Energy 2010;35:1381–90. https://doi.org/10.1016/j.energy.2009.11.023
11. B.Amar “How Artificial Intelligence Will Transform Our Lives,” Energy & Engineering journal 2020-4(194),
12. D.Amarmurun, “Opportunities for Artificial Intelligence in Power Engineering Computation: Challenges and Solutions,” Energy & Engineering journal 2024-3(241),
13. Z.Wei, T.Zhang, B.Yue, “Prediction of residential district heating load based on machine learning: A case study,” Energy Volume 231, 2021, https://doi.org/10.1016/j.energy.2021.120950.
14. F.Souza, T.Badings, G.Postma and J.Jansen, "Integrating Expert and Physics Knowledge for Modeling Heat Load in District Heating Systems," in IEEE Transactions on Industrial Informatics, vol. 21, no. 5, pp. 3955-3965, May 2025, doi: 10.1109/TII.2025.3534419.
15. E.Calikus, S.Nowaczyk, A.Sant'Anna, “A data-driven approach for discover-ing heat load patterns in district heating,” Applied Energy Volume 252, 2019, https://doi.org/10.1016/j.apenergy.2019.113409.
16. G.Xue, Ch.Qi, H.Li, X.Kong, J.Song, “Heating load prediction based on attention long short term memory: A case study of Xingtai,” Energy, Volume 203, 2020, https://doi.org/10.1016/j.energy.2020.117846.
17. Yang, J.Yan, and X.Zhou. 2024. "A Heat Load Prediction Method for District Heating Systems Based on the AE-GWO-GRU Model" Applied Sciences 14, no. 13: 5446. https://doi.org/10.3390/app14135446
Article Sidebar
Article Details
This work is licensed under a Creative Commons Attribution 4.0 International License.