The research is aimed at increasing the accuracy of forecasting the state of multi-zone thermal facilities. Such facilities include multi-room premises, multi-zone greenhouses, tunnel kilns for brick production, and others. The high inertia of such facilities reduces the effectiveness of "ad hoc control". Modern proactive control systems based on forecasting are mainly based on using neural network training. However, to forecast the state of a specific multi-zone thermal facility, training the network requires a very large dataset, which is difficult to create and use. A combined neuro-structural method for forecasting the state of multi-zone thermal facilities is proposed, in which the structure of the neural model reflects the structure of the mutual influence of the facility zones. The research of the method has shown the possibility of ensuring sufficiently high forecast accuracy with a smaller size of the training dataset.
References
[1] Armstrong J:. Extrapolation for Time-Series and Cross-Sectional Data. Armstrong J. S. (eds.): Principles of Forecasting. International Series in Operations Research & Management Science 30. Springer, Boston 2001 [http://doi.org/10.1007/978-0-306-47630-3_11].
[2] Bisikalo O., et al.: Parameterization of the Stochastic Model for Evaluating Variable Small Data in the Shannon Entropy Basis. Entropy 25(2), 2023, 184.
[3] Collopy F., Adya M., Armstrong J.: Expert Systems for Forecasting. Armstrong J. (eds.): Principles of Forecasting. International Series in Operations Research & Management Science 30. Springer, Boston, 2011 [http://doi.org/10.1007/978-0-306-47630-3_14].
[4] Dias G. F., Kapetanios G.: Estimation and forecasting in vector autoregressive moving average models for rich datasets. Journal of Econometrics 202(1), 2018, 75–91.
[5] Dubovoi V., et al.: Model-Oriented Training of Coordinators of the Decentralized Control System of Technological Facilities with Resource Interaction. IEEE Access 13, 2025, 13414–13426.
[6] Dubovoi V., et al.: Functional safety assessment of one-level coordination of distributed cyber-physical objects. Przegląd Elektrotechniczny 97(9), 2021, 38–41.
[7] Geysena D., et al.: Operational thermal load forecasting in district heating networks using machine learning and expert advice. 2017, arXiv:1710.06134v1.
[8] Gyeera T., Simons A., Stannett M.: Kalman filter based prediction and forecasting of cloud server KPIs. TechRxiv. May 19, 2021 [https://doi.org/10.36227/techrxiv.14583342.v1].
[9] Hasan M., Wathodkar G., Muia M.: ARMA Model Development and Analysis for Global Temperature Uncertainty. arXiv, 2023, 2303.02070v1.
[10] Hou P., et al.: Vector Autoregression Model-Based Forecasting of Reference Evapotranspiration in Malaysia. Sustainability 15, 2023, 3675 [http://doi.org/10.3390/su15043675].
[11] Hyndman R., et al.: Forecasting with Exponential Smoothing. Springer Berlin, Heidelberg 2008 [https://doi.org/10.1007/978-3-540-71918-2].
[12] Kolobrodov V. G., Nguyen Q. A., Tymchik G. S.: The problems of designing coherent spectrum analyzers. Proc. of SPIE 9066, 2013.
[13] Kukharchuk V. V., et al.: Information Conversion in Measuring Channels with Optoelectronic Sensors. Sensors 22(1), 2022, 271 [https://doi.org/10.3390/s22010271].
[14] Ivanovski Z., Milenkovski A., Narasanov Z.: Time Series Forecasting Using a Moving Average Model for Extrapolation of Number of Tourist. UTMS Journal of Economics 9(2), 2018, 121–132.
[15] Thorsten J., et al.: Predicting structured objects with support vector machines. Communications of the ACM 52(11), 2024, 97–104 [https://doi.org/10.1145/1592761.1592783].