Data-driven Approaches for Intelligent Control in District Heating Systems

XVII International Conference on Systems, Automatic Control and Measurements, SAUM 2024 (pp. 35-38)

АУТОР(И) / AUTHOR(S): Dušan Stojiljković , Ivan Ćirić , Stevica Cvetković , Rajko Turudija , Danijela Srećković 

Download Full Pdf  

DOI:  10.46793/SAUM24.035S

САЖЕТАК / ABSTRACT:

An intelligent control system to manage district heating systems is presented in this research with the goals of maximizing energy efficiency, minimizing environmental effects, and reducing heat loss. DHS is a centralized system that uses an insulated network to transfer thermal energy across multiple facilities. Conventional DHS setups use Data Acquisition (DAQ) systems and Programmable Logic Controllers (PLCs) to collect data and control heating processes. However, by adding intelligent control and real-time monitoring and decision-making capabilities, these systems become more efficient. At the University of Niš, Faculty of Mechanical Engineering, we suggest an intelligent DHS control model that uses cutting-edge techniques like machine learning algorithms and model-based predictive control to dynamically modify the heat supply in response to demand and weather predictions. IoT sensors, weather stations, and smart meters are just a few of the sources of data that our Data Acquisition Platform (DAP) aggregates into a consolidated PostgreSQL database with a time-series analysis. This platform supports automatic data retrieval scheduled by cron tasks and integrates SCADA for managing remote data gathering and real-time system monitoring. Predictive load balance, better energy distribution, and the possibility of incorporating renewable sources are some of the main advantages. By providing end users with efficient, dependable, and reasonably priced heating options, the suggested method provides a sustainable approach to DHS management.

КЉУЧНЕ РЕЧИ / KEYWORDS:

weather station, SCADA, DAQ, DHS, IoT

ПРОЈЕКАТ/ ACKNOWLEDGEMENT:

This research was supported by the Science Fund of the Republic of Serbia, Grant No. 23-SSF-PRISMA-206, Explainable AI-assisted operations in district heating systems – XAI4HEAT.

ЛИТЕРАТУРА / REFERENCES

  1. Moustakidis, I. Meintanis, G. Halikias, and N. Karcanias, „An innovative control framework for district heating systems: Conceptualisation and preliminary results,“ Resources, vol. 8, no. 1, p. 27, 2019. doi: 10.3390/resources8010027.
  2. van Dreven, V. Boeva, S. Abghari, H. Grahn, J. A. Koussa, and E. Motoasca, „Intelligent approaches to fault detection and diagnosis in district heating: Current trends, challenges, and opportunities,“ Electronics, vol. 12, no. 6, p. 1448, 2023. doi: 10.3390/electronics12061448.
  3. B. Gunay, A. Ashouri, and W. Shen, „Load forecasting and equipment sequencing in a central heating and cooling plant: A case study,“ ASHRAE Trans., vol. 125, pp. 513–523, 2019.
  4. Runge and E. Saloux, „A comparison of prediction and forecasting artificial intelligence models to estimate the future energy demand in a district heating system,“ Energy, vol. 269, p. 126661, 2023. doi: 10.1016/j.energy.2023.126661.
  5. Saloux, J. Runge, and K. Zhang, „Field implementation of a predictive control strategy in district heating systems: A tale of two demonstration sites,“ in Energy Informatics, B. N. Jørgensen, L. C. P. da Silva, and Z. Ma, Eds. Cham: Springer, 2024, vol. 14468, doi: 10.1007/978-3-031-48652-4_21.
  6. Van Oevelen, D. Vanhoudt, C. Johansson, and E. Smulders, „Testing and performance evaluation of the STORM controller in two demonstration sites,“ Energy, vol. 197, p. 117177, 2020. doi: 10.1016/j.energy.2020.117177.
  7. Cotrufo, E. Saloux, J. M. Hardy, and J. A. Candanedo, „A practical artificial intelligence-based approach for predictive control in commercial and institutional buildings,“ Energy Build., vol. 206, p. 109563, 2019. doi: 10.1016/j.enbuild.2019.109563.
  8. Saloux and J. A. Candanedo, „Model-based predictive control to minimize primary energy use in a solar district heating system with seasonal thermal energy storage,“ Appl. Energy, vol. 291, p. 116840, 2021. doi: 10.1016/j.apenergy.2021.116840.
  9. Saloux, K. Zhang, and J. A. Candanedo, „Data-driven model-based control strategies to improve the cooling performance of commercial and institutional buildings,“ Buildings, vol. 13, no. 2, p. 474, 2023. doi: 10.3390/buildings13020474.
  10. A. Candanedo, E. Saloux, J. M. Hardy, R. Platon, and V. Raissi-Dehkordi, „Preliminary assessment of a weather forecast tool for building operation,“ presented at the 5th Int. High Perform. Buildings Conf., Purdue, 2018.
  11. Van Oevelen, T. Neven, A. Brès, R.-R. Schmidt, and D. Vanhoudt, „Testing and evaluation of a smart controller for reducing peak loads and return temperatures in district heating networks,“ Smart Energy, vol. 10, p. 100105, 2023. doi: 10.1016/j.segy.2023.100105.
  12. Saloux, N. Cotrufo, and J. A. Candanedo, „A practical data-driven multi-model approach to model predictive control: Results from implementation in an institutional building,“ presented at the 6th Int. High Perform. Buildings Conf., Purdue, 2021.
  13. Qi, Q. Ouyang, and L. Ma, „Application of artificial intelligence control in the control system of cooling and heating energy stations,“ Thermal Science, vol. 28, pp. 1321–1328, 2024. doi: 10.2298/TSCI2402321Q.
  14. Ding, T. Timoudas, Q. Wang, S. Chen, H. Brattebø, and N. Nord, „A study on data-driven hybrid heating load prediction methods in low-temperature district heating: An example for nursing homes in Nordic countries,“ Energy Convers. Manage., vol. 269, p. 116163, 2022. doi: 10.1016/j.enconman.2022.116163.
  15. Vansovitš, A. Tepljakov, K. Vassiljeva, and E. Petlenkov, „Towards an intelligent control system for district heating plants: Design and implementation of a fuzzy logic based control loop,“ in Proc. IEEE 14th Int. Conf. Ind. Informatics (INDIN), 2016, pp. 405–410. doi: 10.1109/INDIN.2016.7819193.
  16. Gong, Y. Liu, J. Sun, W. Xu, W. Li, C. Yan, and W. Fu, „Intelligent control of district heating system based on RDPG,“ Eng. Appl. Artif. Intell., vol. 129, p. 107672, 2024. doi: 10.1016/j.engappai.2023.107672.