XVII International Conference on Systems, Automatic Control and Measurements, SAUM 2024 (pp. 134-137)
АУТОР(И) / AUTHOR(S): Rajko Turudija , Marko Ignjatović , Branka Radovanović , Dušan Stojiljković , Ivan Ćirić , Mina Mirović
Download Full Pdf
DOI: 10.46793/SAUM24.134T
САЖЕТАК / ABSTRACT:
District heating systems (DHS) are currently operated semi-automatically, presenting significant opportunities for improvement, particularly through the utilization of advanced Artificial Intelligence (AI). This study is part of a broader research initiative aimed at enhancing DHS control methodologies. It focuses on understanding data obtained from the currently used Supervisory Control and Data Acquisition (SCADA) system and integrated supplementary data sourced from Visual Crossing Weather Data and Weather API. The goal is to evaluate the potential benefits of combining these data sets, as well as to understand the interdependences of gathered parameters. The academic importance of this study lies in investigating the potential of AI technologies to improve DHS systems, which will also lead to better control and management of DHS. Enhancing the DHS will optimize energy transfer, ensuring that energy is used efficiently throughout the DHS operation. This will also enhance the system’s environmental friendliness by minimizing unnecessary heat exchange. The methodology includes descriptive statistics, histograms, correlation matrices, and random forest methodologies to analyze the data. The key findings indicate that the current one-hour interval for data collection is insufficient for accurately reflecting energy transmission changes, and a reduction to 1 or 3 minutes is recommended. Additionally, solar radiation, wind direction, and wind speed were identified as critical parameters for improving the heating control process. However, future efforts should focus on constructing thorough and high-quality prediction models for effective energy transmission.
КЉУЧНЕ РЕЧИ / KEYWORDS:
DHS, SCADA, parameter correlation, AI
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:
- Zach, S. Erker, and G. Stoeglehner, „Factors influencing the environmental and economic feasibility of district heating systems—a perspective from integrated spatial and energy planning,“ Energ. Sustain. Soc., vol. 9, p. 25, 2019.
- Weinberger, S. Amiri, and B. Moshfegh, „Investigating techno-economic effects and environmental impacts of energy renovation of residential building clusters on a district heating system,“ Energy and Buildings, vol. 251, 111327, 2021
- Brand, A. Calvén, J. Englund, H. Landersjö, and P. Lauenburg, „Smart district heating networks – A simulation study of prosumers’ impact on technical parameters in distribution networks,“ Applied Energy, vol. 129, pp. 39-48, 2014.
- Živković and D. Ivezić, „Utilizing sewage wastewater heat in district heating systems in Serbia: effects on sustainability,“ Clean Techn. Environ. Policy, vol. 24, pp. 579–593, 2022.
- V. Kljajić, A. S. Anđelković, V. Hasik, V. M. Munćan, and M. Bilec, „Shallow geothermal energy integration in district heating system: An example from Serbia,“ Renewable Energy, vol. 147, Part 2, pp. 2791-2800, 2020.
- Zdravković, I. Ćirić, and M. Ignjatović, „Explainable heat demand forecasting for the novel control strategies of district heating systems,“ Annual Reviews in Control, vol. 53, pp. 405-413, 2022.
- Turudija, D. Stojiljković, M. Zdravković, and M. Ignjatović, „Towards an Approach to Multivariate Outlier Detection for District Heating System Data,“ in Disruptive Information Technologies for a Smart Society, M. Trajanović, N. Filipović, and M. Zdravković, Eds., ICIST 2024, Lecture Notes in Networks and Systems, vol. 860, Springer, Cham, 2024.