40th International Conference on Production Engineering of Serbia
ICPES 2025
Nis, Serbia, 18-19th september 2025
SMART ENERGY PRODUCTION AND INDUSTRY 5.0: XAI AND IRREGULAR TIME SERIES FORECASTING
Milica Tasic, Ivan Ciric, Vladan Jovanovic, Miloš Simonovic, Marko Ignjatovic
DOI: 10.46793/ICPES25.498T
Modern energy production systems, particularly in the district heating sector, face challenges caused by irregularly sampled time series resulting from asynchronous measurements, missing values, and variable operating conditions. These issues complicate the application of traditional forecasting methods. In this context, interpolation procedures play an important role, where the error depends on the curvature of the function and indicates the extent to which a polynomial of a given degree can approximate the observed signal, which is particularly important in irregular time series. In this way, a theoretical foundation is provided for understanding the limitations of data regularization and the irregularity of time series. The proposed work combines the theoretical analysis of interpolation with advanced time series processing and machine learning methods in order to support reliable forecasting, process optimization, and decision-making. The results highlight how theoretical insights into interpolation errors can guide the design of explainable and transparent forecasting models, thereby advancing smart energy production strategies aligned with Industry 5.0
Irregular time series, polynomial interpolation error, artificial intelligence, explainable artificial intelligence, energy consumption forecasting, industry 5.0, smart energy production
[1] C. Trivedi, P. Bhattacharya, V. K. Prasad, et al., “Explainable AI for Industry 5.0: Vision, Architecture, and Potential Directions,” IEEE Open Journal of Industry Applications, vol. PP, no. 99, pp. 1–12, Sep. 2023, doi: 10.1109/OJIA.2024.3399057.
[2] J.-L. Hu, Y. Li, and J.-C. Chew, “Industry 5.0 and Human-Centered Energy System: A Comprehensive Review with Socio-Economic Viewpoints,” Energies, vol. 18, no. 9, p. 2345, 2025. doi: 10.3390/en18092345.
[3] R. Alsaigh, R. Mehmood, and I. Katib, “AI Explainability and Governance in Smart Energy Systems: A Review,” arXiv preprint, arXiv:2211.00069, Nov. 2022.
[4] R. Machlev, L. Heistrene, M. Perl, et al., “Explainable Artificial Intelligence (XAI) techniques for energy and power systems: Review, challenges and opportunities,” Energy and AI, vol. 9, p. 100169, May 2022, doi: 10.1016/j.egyai.2022.100169
[5] T. Rojat, R. Puget, D. Filliat, J. Del Ser, R. Gelin, and N. Díaz-Rodríguez, “Explainable AI on Time Series Data: A Survey,” arXiv preprint, arXiv:2104.00950, 2021.
[6] J. Chen, J. Yuan, W. Chen, A. Zeb, M. Suzauddola, and Y. A. Nanehkaran, “Research on Interpolation Method for Missing Electricity Consumption Data,” Computers, Materials & Continua, vol. 78, no. 2, pp. 2576–2591, Feb. 2024, doi:10.32604/cmc.2024.050414.
[7] Bhandary, V. Dobariya, G. Yenduri, S. K. Pasupuleti, S. K. Maddikunta, and F. Benedetto, “Enhancing Household Energy Consumption Predictions Through Explainable AI Frameworks,” IEEE Access, vol. 12, pp. 1–1, Jan.2024, doi: 10.1109/ACCESS.2024.3373552.
[8] Lecture Notes, Errors in Polynomial Interpolation, Lecture 15–16, 2010.
[9] D. Levy, Numerical Analysis – Interpolation, University of Maryland, 2010.
[10] Kværnø, Polynomial Interpolation: Error Theory, NTNU, 2021.
[11] Ron, Y. Li, M. Cowlishaw, and N. Fillmore, “Polynomial Interpolation: Error Analysis and Introduction to Splines,” Lecture Notes in Numerical Analysis, Univ. of Wisconsin, 2010.
[12] Runge, “Über empirische Funktionen und die Interpolation zwischen äquidistanten Ordinaten,” Zeitschrift für Mathematik und Physik, vol. 46, pp. 224–243, 1901.
[13] Y. Mehari, “Easy Way to Find Multivariate Interpolation,” Int. J. Emerging Trends in Science and Technology, vol. 4, no. 5, pp. 5189–5193, 2017.
[14] M. Aldroubi and A. Papoulis, “Two-dimensional polynomial interpolation from nonuniform samples,” IEEE Trans. Signal Processing, vol. 40, no. 2, pp. 333–339, 1992.
[15] S. Cvetkovic, M. Zdravkovic, and M. Ignjatovic, “Exploring district heating systems: A SCADA dataset for enhanced explainability,” Data in Brief, vol. 59, p. 111320, 2025, doi: 10.1016/j.dib.2025.111320.
[16] M. Schaffer, T. Tvedebrink, and A. Marszal-Pomianowska, “Three years of hourly data from 3021 smart heat meters installed in Danish residential buildings,” Scientific Data, vol. 9, p. 420, 2022, doi: 10.1038/s41597-022-01502-3.
[17] S. Chatterjee, P. K. Jana, and A. Bandyopadhyay, “Prediction of household-level heat consumption using PSO-kSVR with accumulated smart meter data,” arXiv preprint, arXiv:2112.01908, Dec. 2021.
[18] G. Steindl, M. Kathan, and G. N. Almbauer, “Comparison of black box models for load profile generation of district heating substations,” Proceedings of the 11th International Modelica Conference, 2015, pp. 711–719, doi: 10.3384/ecp15118711.
[19] F. Theusch, P. Diaconescu, J. Tuschy, and R. T. Stankovic, “Fault detection and condition monitoring in district heating using smart meter data,” Proceedings of the European Conference of the PHM Society, vol. 6, no. 1, pp. 1–11, 2021, doi: 10.36001/phme.2021.v6i1.2786.
[20] Stecher, A. A. Nielsen, M. K. Andersen, and H. Madsen, “Creating a labeled district heating data set: From anomaly detection towards fault detection,” Energy, vol. 313, p. 134016, 2024, doi: 10.1016/j.energy.2024.134016.
[21] Potocnik, P., Škerl, P., and E. Govekar. 2021. Machine-learning-based multi-step heademand forecasting in a district heating system. Energy & Buildings 233:110673
[22] Zdravkovic, M., Ciric, I., and M. Ignjatovic. 2022. Explainable heat demand forecasting for the novel control strategies of district heating systems. Annual Reviews in Control 53:405–413.
[23] Kurek, T., Bielecki, A., Swirski, K., Wojdan, K., Guzek, M., Bialek, J., Brzozowski, R., and R. Serafin. 2021. Heat demand forecasting algorithm for a Warsaw district heating network. Energy 217:119347.
[24] Runge, J., and E. Saloux. 2023. A comparison of prediction and forecasting artificial intelligence models to estimate the future energy demand in a district heating system. Energy 269:126661.
[25] Shakeel, A., Chong, D., and J. Wang. 2023. District heating load forecasting with a hybrid model based on LightGBM and FB-prophet. Journal of Cleaner Production 409:137130.
[26] Liu, G., Zhou, X., Yan, J., and G. Yan. 2023. Dynamic integrated control for Chinese district heating system to balance the heat supply and heat demand. Sustainable Cities and Society 88:104286.
[27] Morteza, A., Yahyaeian, A.A., Mirzaeibonehkhater, M., Sadeghi, S., Mohaimeni, A., and S. Taheri. 2023. Deep learning hyperparameter optimization: Application to electricity and heat demand prediction for buildings. Energy and Buildings 289:113036.
[28] S. Cvetkovic, D. Stojiljkovic, I. Ciric, R. Turudija, and M. Špeletic, “Integrated data acquisition platform for explainable control in district heating systems,” Facta Universitatis, Series: Automatic Control and Robotics, vol. 23, no. 2, pp. 133–143, 2024.
[29] S. Cvetkovic, M. Zdravkovic, and M. Ignjatovic, “Exploring district heating systems: A SCADA dataset for enhanced explainability,” Data in Brief, vol. 59, p. 111320, Jan. 2025.
[30] Neubauer, S. Brandt, and M. Kriegel, “Explainable multi-step heating load forecasting: Using SHAP values and temporal attention mechanisms for enhanced interpretability,” Energy and AI, vol. 20, p. 100480, Feb. 2025.