XVII International Conference on Systems, Automatic Control and Measurements, SAUM 2024 (pp. 169-172)
АУТОР(И) / AUTHOR(S): Milica Tasić 
, Ivan Ćirić , Marko Ignjatović , Dušan Stojiljković
Download Full Pdf 
DOI: 10.46793/SAUM24.169T
САЖЕТАК / ABSTRACT:
This paper explores the potential application of supervised machine learning for predicting the energy performance of the district heating system at the Faculty of Mechanical Engineering in Niš. The operation of this heating system is controlled automatically, while the energy performance is monitored through a SCADA system. Although the SCADA system provides detailed data insights, optimization decisions aimed at saving energy and reducing costs are made by the heating plant operator. The objective of this research is to apply two different machine learning methods, artificial neural networks and random forest analysis, to predict the heating load based on a set of various energy indicators used as input parameters, derived from the SCADA system of the heating plant. The predictions were made for a period spanning 15 days, and the results were obtained using different algorithms of neural networks and random forest analysis in the MATLAB software tool. The primary goal was to present the results of applying these two machine learning methods for heating load prediction, and to compare them by providing a detailed analysis of their performance.
КЉУЧНЕ РЕЧИ / KEYWORDS:
machine learning; artificial neural networks; explainable artificial intelligence; district heating
ЛИТЕРАТУРА / REFERENCES
[1] Milan Zdravković, Ivan Ćirić, Marko Ignjatović, Towards explainable AI-assisted operations in district heating systems, IFAC PapersOnLine 54-1 (2021) 390–395, Niš, 2021.
[2] I. Shesho, et al., „Optimization Model for Improvement of District Heating System by Integration of Cogeneration,“ Thermal Science, vol. 25, no. 1, pp. 307-320, 2021.
[3] Ivan Ćirić, Marko Ignjatović, Mirko Stojiljković, Dušan Stojiljković, Milan Gocić, Milica Ćirić, Intelligent Heat Demand prediction for Advanced District Heat Plant Control, 10th International Conference on Information Society and Technology, Belgrade, Serbia, 2020.
[4] K. Oh, E-J. Kim, and C-Y. Park, „A Physical Model-Based Data-Driven Approach to Overcome Data Scarcity and Predict Building Energy Consumption,“ in Sustainability, vol. 14, no. 15, 2022, pp. 9464.
[5] S. E. Fahlman and C. Lebiere, „The cascade-correlation learning architecture,“ in Advances in Neural Information Processing Systems (NIPS), vol. 2, 1990, pp. 524-532.
[6] M. and F. Collopy, „How effective are neural networks at forecasting and prediction? A review and evaluation,“ J. Forecasting, vol. 17, no. 5-6, pp. 481-495, 1998.
[7] P. Zhang, C. Lan, J. Xing, W. Zeng, J. Xue and N. Zheng, „View Adaptive Neural Networks for High Performance Skeleton-Based Human Action Recognition,“ in IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 41, no. 8, pp. 1963-1978, 1 Aug. 2019, doi: 10.1109/TPAMI.2019.2896631.
[8] Wu, Wenbo, and Yun Pan, „Adaptive Modular Convolutional Neural Network for Image Recognition“ Sensors 22, no. 15: 5488, 28 June 2022, https://doi.org/10.3390/s22155488
[9] R. Chandra and M. Zhang, „Cooperative coevolution of Elman recurrent neural networks for chaotic time series prediction,“ Neurocomputing, vol. 86, pp. 116-123, Apr. 2012.
[10] J. L. Elman, „Finding structure in time,“ Cogn. Sci., vol. 14, no. 2, pp. 179-211, Apr. 1990.
[11] S. Hochreiter and J. Schmidhuber, „Long short-term memory,“ Neural Comput., vol. 9, no. 8, pp. 1735-1780, Nov. 1997.
[12] A. Graves and J. Schmidhuber, „Framewise phoneme classification with bidirectional LSTM and other neural network architectures,“ Neural Networks, vol. 18, no. 5-6, pp. 602-610, Jul. 2005.
[13] A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, Ł. Kaiser, and I. Polosukhin, „Attention is all you need,“ in Proc. Advances in Neural Information Processing Systems (NIPS), Long Beach, CA, USA, 2017, pp. 5998-6008.
[14] Z. C. Lipton, „A critical review of recurrent neural networks for sequence learning,“ arXiv preprint, arXiv:1506.00019, Jun. 2015.
[15] Y. Qin, D. Song, H. Chen, W. Cheng, G. Jiang, and G. Cottrell, „A dual-stage attention-based recurrent neural network for time series prediction,“ in Proc. Int. Joint Conf. Artificial Intelligence (IJCAI), Melbourne, Australia, 2017, pp. 2627-2633. doi: 10.24963/ijcai.2017/366
[16] Biau, G. „Analysis of a Random Forests Model“ Journal of Machine Learning Research, vol. 13, no. 1, 2012, pp. 1063-1095.
[17] M. Borovykh, S. Bohte, and C. W. Oosterlee, „Conditional time series forecasting with convolutional neural networks,“ arXiv preprint, arXiv:1703.04691, Mar. 2017. [Online]. Available: https://arxiv.org/abs/1703.04691
[18] Y. Lai, L. Shao, Y. Xu, and X. Wu, „Recurrent convolutional neural networks for traffic prediction in transportation networks,“ IEEE Trans. Intelligent Transportation Systems, vol. 19, no. 5, pp. 1457-1467, May 2018. doi: 10.1109/TITS.2017.2722160
[19] J. Zhao, M. Zhang, H. Liu, and Y. Xu, „Time-series anomaly detection with end-to-end CNN transform and attention mechanism,“ IEEE Access, vol. 8, pp. 10465-10474, Jan. 2020. doi: 10.1109/ACCESS.2020.2964938
[20] Bukhari, A., S. H. Yusoff, M. S. F. M. Yunus, N. S. I. Razali, Virtual Power Plant Management Using PID Controller, Journal of Renewable Energy and Power Systems, Volume 9 (2021), Issue, pp. 818–827.