Machine Learning Methods to Increase the Energy Efficiency of Buildings

: pp. 189- 209
Lviv Polytechnic National University, Software Development Department
Lviv Polytechnic National University, Software Engineering Department

Predicting a building’s energy consumption plays an important role as it can help assess its energy efficiency, identify and diagnose energy system faults, and reduce costs and improve climate impact. An analysis of current research in the field of ensuring the energy efficiency of buildings, in particular, their energy assessment, considering the types of models under consideration, was carried out. The principles, advantages, limitations, and practical application of the main data-based models are considered in detail, and priority future directions for forecasting the energy efficiency of buildings are highlighted. It is shown that the effectiveness of the methods is different for the main types of models and depends on the following factors: input data and parameters, the type and quality of available data for training, the suitability of the method for a specific type of model, etc. The need to consider the element of uncertainty when forecasting energy consumption due to the impossibility of accurate modeling of meteorological factors and the behavior of residents is emphasized. Therefore, machine learning methods, particularly deep learning-based models, are chosen to represent complex nonlinear input-output relationships, as they show higher performance than statistical time series forecasting methods. The analysis of published works revealed a lack of works describing a comprehensive energy forecasting information system for use in commercial projects. We proposed a new approach to combining semantic modeling and machine learning technologies for the energy management system of smart buildings, using the knowledge system of the semantic model we developed.

  1. Dandotiya, B. (2020). Climate Change and Its Impact on Terrestrial Ecosystems, Impacts of Climate Change on Agriculture and Aquaculture, 140–157. IGI Global.
  2. Popa A. (2022). A Semantically Data-Driven Classification Framework for Energy Consumption in Buildings. Energies, 2022, 15(9), 3155.
  3. Runge J. & Zmeureanu R. (2019). Forecasting Energy Use in Buildings Using Artificial Neural Networks: A Review. Energies, 2019, 12(17), 3254.
  4. Amasyali K. & El-Gohary N. M. (2018). A review of data-driven building energy consumption prediction studies. Renewable and Sustainable Energy Reviews, Vol. 81, Part 1, January 2018, 1192–1205.
  5. Sanzana M. R. & Maul T. (2022). Application of deep learning in facility management and maintenance for heating, ventilation, and air conditioning. Automation in Construction, Vol. 141, September 2022, 104445.
  6. Khandelwal, I., Adhikari, R. & Verma, G. (2015). Time series forecasting using hybrid ARIMA and ANN models based on DWT decomposition. Procedia Computer Science, 48, 173–179.
  7. Markoska E. (2019). A Framework for Automated Real-Time Performance Evaluation of Smart Buildings.
  8. Wang, Z. & Hong, T. Building thermal load prediction through shallow machine learning and deep learning. Applied Energy, Vol. 263, 1 April 2020, 114683.
  9. Guss H. & Linus R. (2020) Applying Machine Learning Algorithms for  Anomaly Detection in Electricity Data: Improving the Energy Efficiency of Residential Buildings. Digitala Vetenskapliga Arkivet. Batish A., Agrawal A. (2019). Building Energy Prediction for Early-Design-Stage Decision Support: A Review of Data- driven Techniques. Conference: Building Simulation 2019, Rome, Italy, September 2019.
  10. Faiq, M & Tan, K. (2023). Prediction of energy consumption in campus buildings using long short-term memory. Alexandria Engineering Journal, Vol. 67, 15 March 2023, 65–76.
  11. Liu, D. & Wang, H. (2023). Time series analysis model for forecasting unsteady electric load in buildings. Energy and Built Environment, 15 July 2023.
  12. Гече, Ф., Мулеса, О.  (2021). Навчання комбінованої моделі прогнозування часових  рядів. Український журнал інформаційних технологій. Вип. 3, № 1 : 44–48.
  13. Hammoudeh A. & Dupont S. (2022). The prediction of residential building consumption using profiling and time encoding, Procedia Computer Science, Vol. 210, 7–11.
  14. Chen, Y. & Chen, Z. (2022). Short-term load forecasting for multiple buildings: A length sensitivity-based approach. Energy Reports, 8:14274–14288.
  15. Luo, X. & Oyedele, L. (2023). A self-adaptive deep learning model for building electricity load prediction with moving horizon. Mach Learn Appl., 7 (2022), Article 100257.
  16. Wang Z. & Liu X.( 2023). A multivariate time series graph neural network for district heat load forecasting. Energy, Vol. 278, Part A, 1 September 2023, 127911.
  17. Panjapornpon, С. & Santi Bardeeniz, S. (2023) Explainable deep transfer learning for energy efficiency prediction based on uncertainty detection and identification. Energy and AI, Vol. 12, April 2023, 100224.
  18. Granderson J. & Fernandes, S. (2023). Accuracy of hourly energy predictions for demand flexibility applications. Energy and Buildings, Vol. 295, 15 September 2023, 113297.
  19. González-Vida, A. & Jiménez, F. (2019) A methodology for energy multivariate time series forecasting in smart buildings based on feature selection. Energy and Buildings, Vol. 196, 1 August 2019, 71–82.
  20. Yang, B. & Haghighat, F. (2021). Season-Based Occupancy Prediction in Residential Buildings Using Machine Learning Models. e-Prime – Advances in Electrical Engineering, Electronics and Energy, Vol. 1, 100003.
  21. Qiao, Q. & Yunusa-Kaltungo, A. (2023). Developing a machine learning based building energy consumption prediction approach using limited data: Boruta feature selection and empirical mode decomposition. Energy Reports, Vol. 9, December 2023, 3643–3660.
  22. Avendano, I. & Javan, F. (2023). Assessing the impact of employing machine learning-based baseline load prediction pipelines with sliding-window training scheme on offered flexibility estimation for different building categories. Energy and Buildings, Vol. 294, 1 September 2023, 113217.
  23. Fotopoulou E. (2017). Providing Personalized Energy Management and Awareness Services for Energy Efficiency in Smart Buildings. Sensors, 17(9), 2054.
  24. Shapi, M. & Ramli, N. (2021). Energy consumption prediction by using machine learning for smart building: Case study in Malaysia. Developments in the Built Environment, Vol. 5, March 2021, 100037.
  25. Lei, L. & Wei Chen, W. (2021). A building energy consumption prediction model based on rough set theory and deep learning algorithms. Energy and Buildings, Vol. 240, 1 June 2021, 110886.
  26. Jogunola, O. (2022). CBLSTM-AE: A Hybrid Deep Learning Framework for Predicting Energy Consumption. Energies, 15(3), 810.
  27. Amalou, I. & Mouhni N. (2022). Multivariate time series prediction by RNN architectures for energy consumption forecasting. Energy Reports Volume 8, Supplement 9, November 2022, 1084–1091.
  28. Schmida, L. & Roidl, M.(2023). Comparing statistical and machine learning methods for time series forecasting in data-driven logistics – A simulation study. arXiv – STAT – Machine Learning. March 2023.
  29. ASHRAE Handbook (2023).
  30. Batish A., Agrawal A. (2019). Building Energy Prediction for Early-Design-Stage Decision Support: A Review of Data-driven Techniques. Conference: Building Simulation 2019, Rome, Italy, September 2019.
  31. Zhao, H. & Magoulès, F. (2012). A Review on the Prediction of Building Energy Consumption. Renewable and Sustainable Energy Reviews, Vol. 16 (6): 3586–92.
  32. Encorp (2023). Balancing Energy Supply and Demand.
  33. Chen Y. & Guo M. (2022). Physical energy and data-driven models in building energy prediction: A review. Energy Reports, Vol. 8, November 2022, 2656–2671.
  34. Liu H. & Liang J. (2023). A Review of Data-Driven Building Energy Prediction, Buildings 2023, 13(2),532. Guss. pdf