Data-Driven Benchmarking of Building Energy Performance Using Electricity and Gas Consumption Data

Buildings are a major contributor to global energy demand, making improved building energy performance an important component of energy management and decarbonisation strategies. This paper assesses the energy performance of a portfolio of ten buildings using historical electricity and gas consumption data. Annual energy consumption and Energy Use Intensity (EUI), expressed in kWh/m²/year, were calculated to compare energy intensity across buildings of different floor areas. The results showed substantial variation in EUI, ranging from 78.01 to 476.45 kWh/m²/year, with a mean of 191.35 kWh/m²/year and a median of 136.24 kWh/m²/year. Buildings A and B recorded the highest EUI values at 476.45 and 410.53 kWh/m²/year, respectively, while Buildings H, I, and J recorded the lowest values. Electricity and gas consumption showed a strong positive correlation r = 0.98. The findings indicate that consumption-based benchmarking can provide a practical screening approach for identifying buildings that warrant further investigation. However, EUI should be interpreted as an indicator of energy intensity rather than a direct measure of energy efficiency because building function, occupancy, operating schedules, and weather conditions were not fully incorporated. The study provides a basis for prioritising further energy audits and operational assessments, with future research recommended to incorporate weather normalisation, occupancy characteristics, building-function classification, and end-use energy data.

Building energy performance; Energy consumption; Building benchmarking; Data analytics; Decarbonisation.

1. ASHRAE. (2023). ASHRAE Handbook: HVAC Applications. Atlanta, GA [Google Scholar] [Crossref]

2. Chartered Institution of Building Services Engineers (CIBSE). (2020). Guide F: Energy Efficiency in Buildings [Google Scholar] [Crossref]

3. Hong, T., Wang, Y., Luo, X., & Hooper, B. (2020). An overview of data analytics approaches used in building energy prediction and management. Energy and Buildings, 221, 110021. [Google Scholar] [Crossref]

4. Ahmad, T., Chen, H., Guo, Y., & Wang, J. (2018). A comprehensive overview on building energy estimation, forecasting and management. Renewable and Sustainable Energy Reviews, 82, 446-465. [Google Scholar] [Crossref]

5. Capozzoli, A., & Piscitelli, M. S. (2015). Measuring and benchmarking energy performance of buildings. Energy and Buildings, 107, 62-76. [Google Scholar] [Crossref]

6. Chung, W. (2011). Review of building energy-use performance benchmarking methodologies. Applied Energy, 88(5), 1470-1479. [Google Scholar] [Crossref]

7. Yan, D., Hong, T., Dong, B., et al. (2015). IEA EBC Annex 53: Total energy use in buildings. Energy and Buildings, 90, 177-183. [Google Scholar] [Crossref]

8. Swan, L. G., & Ugursal, V. I. (2009). Modeling of end-use energy consumption in residential sectors. Renewable and Sustainable Energy Reviews, 13(8), 1819-1835. [Google Scholar] [Crossref]

9. Fumo, N. (2014). A review on the basics of building energy estimation. Renewable and Sustainable Energy Reviews, 31, 53-60. [Google Scholar] [Crossref]

10. Wei, Y., Zhang, X., Shi, Y., Xia, L., Pan, S., Wu, J., Han, M., & Zhao, X. (2018). A review of data-driven approaches for prediction and classification of building energy consumption. Renewable and Sustainable Energy Reviews, 82, 1027-1047. [Google Scholar] [Crossref]

11. Li, K., Su, H., & Chu, J. (2017). Forecasting building energy consumption using machine learning techniques. Energy and Buildings, 133, 281-291. [Google Scholar] [Crossref]

12. O'Dwyer, E., Pan, I., Acha, S., & Shah, N. (2019). Smart meter data analytics for building energy performance assessment. Applied Energy, 240, 943-956. [Google Scholar] [Crossref]

13. Bunse, K., Vodicka, M., Schönsleben, P., Brülhart, M., & Ernst, F. O. (2011). Integrating energy efficiency performance in production management. International Journal of Production Economics, 139(1), 56-65. [Google Scholar] [Crossref]

14. Wang, S., Yan, C., & Xiao, F. (2012). Quantitative energy performance assessment methods for existing buildings. Energy and Buildings, 55, 873-888. [Google Scholar] [Crossref]

15. Zhao, H. X., & Magoulès, F. (2012). A review on prediction of building energy consumption. Renewable and Sustainable Energy Reviews, 16(6), 3586-3592. [Google Scholar] [Crossref]

16. Ma, Z., Cooper, P., Daly, D., & Ledo, L. (2012). Existing building retrofits: Methodology and state-of-the-art. Energy and Buildings, 55, 889-902. [Google Scholar] [Crossref]

17. Burman, E., Mumovic, D., & Kimpian, J. (2014). Towards measurement and verification of energy performance. Energy and Buildings, 73, 153-164. [Google Scholar] [Crossref]

18. Delzendeh, E., Wu, S., Lee, A., & Zhou, Y. (2017). The impact of occupants' behaviours on building energy analysis. Renewable and Sustainable Energy Reviews, 80, 1061-1071. [Google Scholar] [Crossref]

19. Ahmad, M. W., Mourshed, M., Yuce, B., & Rezgui, Y. (2018). Computational intelligence techniques for building energy consumption forecasting. Building Simulation, 11, 533-548. [Google Scholar] [Crossref]

20. Li, D. H. W., Yang, L., & Lam, J. C. (2013). Impact of climate change on building energy consumption. Energy, 59, 759-777. [Google Scholar] [Crossref]

21. Yu, Z., Haghighat, F., Fung, B. C. M., & Yoshino, H. (2010). A review of data-driven approaches for building energy analysis. Energy and Buildings, 42(10), 1632-1642. [Google Scholar] [Crossref]

22. Dong, B., Cao, C., & Lee, S. E. (2005). Applying support vector machines to predict building energy consumption. Energy and Buildings, 37(5), 545-553. [Google Scholar] [Crossref]

23. Pérez-Lombard, L., Ortiz, J., & Pout, C. (2008). A review on buildings energy consumption information. Energy and Buildings, 40(3), 394–398. [Google Scholar] [Crossref]

24. Corgnati, S. P., Fabrizio, E., Filippi, M., & Monetti, V. (2013). Reference buildings for cost optimal analysis: Methodological approach and case studies. Applied Energy, 102, 983–993. [Google Scholar] [Crossref]

25. Hong, T., Wang, Y., Luo, X., & Hooper, B. (2020). An overview of data analytics approaches used in building energy prediction and management. Energy and Buildings, 221, 110021. [Google Scholar] [Crossref]