Analysing and forecasting the energy consumption of healthcare facilities in the short and medium term : a case study

• Autorzy: Koç Ali , Seçkiner Serap Ulusam

Identyfikatory

DOI

10.37190/ord240309

• Języki publikacji: EN

Abstrakty

EN

Healthcare facilities consist of multiple large buildings with complex energy systems and high energy consumption, resulting in high carbon emissions. The increasing trend in energy consumption of these facilities and the process of selecting an energy supplier from the open market requires reliable and robust energy forecasting studies. This situation calls for the use of reliable and accurate energy consumption prediction models for the energy needs of healthcare buildings. The aim of this study is to present a prediction framework based on historical energy consumption at different time intervals using six supervised regression algorithms, three linear single, one non-linear single and two non-linear ensembles. The approach adopted for predicting hospital energy consumption involves five steps: data acquisition, data pre-processing, data prediction, hyper-parameter optimisation and feature analysis. Furthermore, all regression algorithms have undergone hyper-parameter optimisation using random search, grid search and Bayesian optimisation to achieve the minimum prediction errors represented by different metrics. The results displayed that the two ensemble models, Extreme Gradient Boosting and Random Forest, outperformed single models in hourly, daily, and monthly energy load prediction. Nevertheless, when considering the computational time for all regression models, the single models have better computational times, although the error metrics are not as good as for the ensemble models. In addition, grid search and Bayesian optimisation performed better than random search in finding optimal hyperparameter values for all datasets. Finally, thanks to feature importance analysis, the most influential features under the hourly, daily, and monthly electrical and monthly natural gas prediction were identified.

Słowa kluczowe

EN

health care facilities; electricity; natural gas; consumption; forecasting; machine learning

• Wydawca: Oficyna Wydawnicza Politechniki Wrocławskiej
• Czasopismo: Operations Research and Decisions
• Rocznik: 2024
• Tom: Vol. 34, No. 3
• Strony: 165--192
• Opis fizyczny: Bibliogr. 46 poz., rys.

Twórcy

autor

Koç Ali

• Department of Industrial Engineering, Gaziantep University, Gaziantep, Turkey

• https://orcid.org/0000-0001-6380-125X

autor

Seçkiner Serap Ulusam

• Department of Industrial Engineering, Gaziantep University, Gaziantep, Turkey

• https://orcid.org/0000-0002-1612-6033

Bibliografia

• [1] Ahmad, T., and Chen, H. Short and medium-term forecasting of cooling and heating load demand in building environment with data-mining based approaches. Energy and Buildings 166 (2018), 460–476.
• [2] Amber, K. P, Ahmad, R., Aslam, M. W., Kousar, A., Usman, M., and Khan, M. S. Intelligent techniques for forecasting electricity consumption of buildings. Energy 157 (2018), 886–893.
• [3] Bagnasco, A., Fresi, F., Saviozzi, M., Silvestro, F., and Vinci, A. Electrical consumption forecasting in hospital facilities: An application case. Energy and Buildings 103 (2015), 261–270.
• [4] Beyca, O. F., Ervural, B. C., Tatoglu, E., Ozuyar, P. G., and Zaim, S. Using machine learning tools for forecasting natural gas consumption in the province of Istanbul. Energy Economics 80 (2019), 937–949.
• [5] Biswas, M. A. R., Robinson, M. D., and Fumo, N. Prediction of residential building energy consumption: A neural network approach. Energy 117, Part 1, (2015), 84-92.
• [6] Braun, M. R., Altan, H., and Beck, S. B. M. Using regression analysis to predict the future energy consumption of a supermarket in the UK. Applied Energy 130 (2014), 305–313.
• [7] Breiman, L. Random Forests. Machine Learning 45, 1 (2001), 5–32.
• [8] Cao, L., Li, Y., Zhang, J., Jiang, Y., Han, Y., and Wei, J. Electrical load prediction of healthcare buildings through single and ensemble learning. Energy Reports 6 (2020), 2751–2767.
• [9] Chen, T., and Guestrin, C. XGBoost: A scalable tree boosting system. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (San Francisco, California, USA, 2016), B. Krishnapuram, M. Shah, A. J. Smola, C. Aggarwal, D. Shen, and R. Rastogi, Eds., ACM, pp. 785–794.
• [10] Chen, T., He, T., Benesty, M., and Khotilovich, V. (2019). xgboost: Extreme Gradient Boosting (accessed on 25 July 2024).
• [11] Ciulla, G., and D’Amico, A. Building energy performance forecasting: A multiple linear regression approach. Applied Energy 253 (2019), 113500.
• [12] Costa, O. L. V., de Oliveira Ribeiro, C., Ho, L. L., Rego, E. E., Parente, V., and Toro, J. A robust least square approach for forecasting models: an application to Brazil’s natural gas demand. Energy Systems 11 (2020), 1111–1135.
• [13] Dulce, E., and Martinez-de Pison, F. J. Parsimonious modeling for estimating hospital cooling demand to reduce maintenance costs and power consumption In Hybrid Artificial Intelligent Systems, 14th International Conference, HAIS 2019, León, Spain, September 4–6, 2019, Proceedings (Cham, 2019), H. Pérez García, L. Sánchez González, M. Castejón Limas, H. Quintián Pardo and E. Corchado Rodríguez, Eds., vol. 11734 of Lecture Notes in Computer Science series, Springer, pp. 181–192.
• [14] D’Amico, A., Ciulla, G., Tupenaite, L., and Kaklauskas, A. Multiple criteria assessment of methods for forecasting building thermal energy demand. Energy and Buildings 224 (2020), 110220.
• [15] Eckelman, M. J., and Sherman, J. Environmental impacts of the U.S. health care system and effects on public health. PLOS ONE 11, 6 (2016), e0157014.
• [16] EuropeanCommission (17 February 2020) In focus: Energy efficiency in buildings (accessed on 5 march 2022).
• [17] Fathi, S., Srinivasan, R., Fenner, A., and Fathi, S. Machine learning applications in urban building energy performance forecasting: A systematic review. Renewable and Sustainable Energy Reviews 133 (2020), 110287.
• [18] Frazier, P. I. A Tutorial on Bayesian Optimization, 2018. Working paper version avaiable from arXiv: https://arxiv.org/abs/1807.02811.
• [19] González-Domínguez, J., Sánchez-Barroso, G., García-Sanz-Calcedo, J., and de Sousa Neves, N. Cox proportional hazards model used for predictive analysis of the energy consumption of healthcare buildings. Energy and Buildings 257 (2022), 111784.
• [20] Gordillo-Orquera, R., Lopez-Ramos, L. M., Muñoz-Romero, S., Iglesias-Casarrubios, P., Arcos-Avilés, D., Marques, A. G., and Rojo-Álvarez, J. L. Analyzing and forecasting electrical load consumption in healthcare buildings. Energies 11, 3 (2018), 493.
• [21] Houimli, R., Zmami, M., and Ben-Salha, O. Short-term electric load forecasting in Tunisia using artificial neural networks. Energy Systems 11, 2 (2020), 357–375.
• [22] Hwang, J., Suh, D., and Otto, M.-O. Forecasting electricity consumption in commercial buildings using a machine learning approach . Energies 13 (2020), 5885.
• [23] Iglewicz, B., and Hoaglin D. C. How to Detect and Handle Outliers. ASQC Quality Press, 1993.
• [24] James, G., Witten, D., Hastie, T., and Tibshirani, R. An Introduction to Statistical Learning with Applications in R. Springer, New York, 2013.
• [25] Karabiber, O. A., and Xydis, G. Forecasting day-ahead natural gas demand in Denmark. Journal of Natural Gas Science and Engineering 76 (2020), 103193.
• [26] Katsatos, A. L., and Moustris, K. P. Application of artificial neuron networks as energy consumption forecasting tool in the building of Regulatory Authority of Energy, Athens, Greece. Energy Procedia 157 (2019), 851–867.
• [27] Kavousi-Fard, A., Samet, H., and Marzbani, F. A new hybrid modified firefly algorithm and Support Vector Regression model for accurate short term load forecasting. Expert Systems with Applications 41, 13 (2014), 6047–6056.
• [28] Li, K., and Zhang, T. A novel grey forecasting model and its application in forecasting the energy consumption in Shanghai. Energy Systems 12, 2 (2021), 357–372.
• [29] Liu, T., Tan, Z., Xu, C., Chen, H., and Li, Z. Study on deep reinforcement learning techniques for building Energy consumption forecasting. Energy and Buildings 208 (2020), 109675.
• [30] Luo, X. J., and Oyedele, L. O. Forecasting building energy consumption: Adaptive long-short term memory neural networks driven by genetic algorithm. Advanced Engineering Informatics 50 (2021), 101357.
• [31] Moriñigo-Sotelo, D., Duque-Pérez, O., García-Escudero, L. A., Fernández-Temprano, M., FraileLlorente, P., Riesco-Sanz, M. V., and Zorita-Lamadrid, A. L. Short-term hourly load forecasting of a hospital using an artificial neural network. Renewable Energy and Power Quality Journal 9, 1 (2011), 441–446.
• [32] Mui, K. W., Satheesan, M. K., and Wong, L. T. Building cooling energy consumption prediction with a hybrid simulation approach: Generalization beyond the training range. Energy and Buildings 276 (2022), 112502.
• [33] Neto, A. H., and Fiorelli, F. A. S. Comparison between detailed model simulation and artificial neural network for forecasting building energy consumption. Energy and Buildings 40, 12 (2008), 2169–2176.
• [34] Riedmiller, M., and Braun, H. RPROP - a fast adaptive learning algorithm. In Proceedings of the International Symposium on Computer and Information Science VII (Antalya, Turkey, 1992), pp. 279–286.
• [35] Smola, A. J., and Schölkopf, B. A tutorial on Support Vector Regression. Statistics and Computing 14, 3 (2004), 199–222.
• [36] Somu, N., M R, G. R., and Ramamritham, K. A hybrid model for building energy consumption forecasting using long short term memory networks. Applied Energy 261 (2020), 114131.
• [37] Somu, N., M R, G. R., and Ramamritham, K. A deep learning framework for building energy consumption forecast. Renewable and Sustainable Energy Reviews 137 (2021), 110591.
• [38] Song, Y., Xie, H., Zhu, Z., and Ji, R. Predicting energy consumption of chiller plant using WOA-BiLSTM hybrid prediction model: A case study for a hospital building. Energy and Buildings 300 (2023), 113642.
• [39] Tan, Z., De, G., Li, M., Lin, H., Yang, S., Huang, L., and Tan, Q. Combined electricity-heat-cooling-gas load forecasting model for integrated energy system based on multi-task learning and least square support vector machine. Journal of Cleaner Production 248 (2020), 119252.
• [40] Timur, O., Zor, K., Çelik, Ő., Teke, A., and İbrikci, T. Application of statistical and artificial intelligence techniques for medium-term electrical energy forecasting: A case study for a regional hospital. Journal of Sustainable Development of Energy, Water and Environment Systems 8, 3 (2020), 520–536.
• [41] Tran, D.-H., Luong, D.-L., and Chou, J.-S. Nature-inspired metaheuristic ensemble model for forecasting energy consumption in residential buildings. Energy 191 (2020), 116552.
• [42] Vapnik, V. N. The Nature of Statistical Learning Theory. Springer, New York, 1995.
• [43] Vapnik, V. N. Statistical Learning Theory. Wiley, 1998.
• [44] Wang, L., Lee, E. W. M., and Yuen, R. K. K. Novel dynamic forecasting model for building cooling loads combining an artificial neural network and an ensemble approach. Applied Energy 228 (2018), 1740–1753.
• [45] Yuan, J., Farnham, C., Azuma, C., and Emura, K. Predictive artificial neural network models to forecast the seasonal hourly electricity consumption for a University Campus. Sustainable Cities and Society 42 (2018), 82–92.
• [46] Zhao, J., and Liu, X. A hybrid method of dynamic cooling and heating load forecasting for office buildings based on artificial intelligence and regression analysis. Energy and Buildings 174 (2018), 293–308.

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa nr POPUL/SP/0154/2024/02 w ramach programu "Społeczna odpowiedzialność nauki II" - moduł: Popularyzacja nauki (2025).