Estimating the Energy Savings of Energy Efficiency Actions with Ensemble Machine Learning Models
Source abstract
Abstract
Energy efficiency financing is considered among the top priorities in the energy sector among several stakeholders. In this context, accurately estimating the energy savings achieved by energy efficiency actions before being approved and implemented is of major importance to ensure the optimal allocation of the available financial resources. This study aims to provide a machine-learningbased methodological framework for a priori predicting the energy savings of energy efficiency renovation actions. The proposed solution consists of three tree-based algorithms that exploit bagging and boosting as well as an additional ensembling level that further mitigates prediction uncertainty. The proposed models are empirically evaluated using a database of various, diverse energy efficiency renovation investments. Results indicate that the ensemble model outperforms the three individual models in terms of forecasting accuracy. Also, the generated predictions are relatively accurate for all the examined project categories, a finding that supports the robustness of the proposed approach.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Energy Efficiency and Management · Energy Load and Power Forecasting · Building Energy and Comfort Optimization
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Decision Support Systems Laboratory, School of Electrical & Computer Engineering, National Technical University of Athens, 10682 Athens, Greece
Forecasting and Strategy Unit, School of Electrical & Computer Engineering, National Technical University of Athens, 10682 Athens, Greece
Funding
European Union’s Horizon 2020 research and innovation programme
References (59)
Show source-provided references
1. Hamilton, I., Kennard, H., Rapf, O., Kockat, J., Zuhaib, S., Abergel, T., Oppermann, M., Otto, M., Loran, S., and Steurer, N. (2020). Global Status Report for Buildings and Construction: Towards a Zero-Emission, United Nations Environment Programme, Efficient and Resilient Buildings and Construction Sector.
2. (2023, February 20). European Commission. Available online: https://eur-lex.europa.eu/legal-content/EN/TXT/?uri=CELEX%3A02010L0031-20100708.
3. European Commission (2023, February 20). Directive 2010/31/EU of the European Parliament and of the Council of 19 May 2010 on the Energy Performance of Buildings. Available online: https://eur-lex.europa.eu/LexUriServ/LexUriServ.do?uri=OJ:L:2010:153:0013:0035:EN:PDF.
4. IEA (2023, February 20). Tracking Buildings 2021. Available online: https://www.iea.org/reports/buildings.
5. Reinventing energy efficiency for net zero10.1016/j.erss.2022.102602 ↗
6. Sarmas, E., Marinakis, V., and Doukas, H. (2022). A data-driven multicriteria decision making tool for assessing investments in energy efficiency. Oper. Res., 5597–5616.10.1007/s12351-022-00727-9 ↗
7. A meta-learning classification model for supporting decisions on energy efficiency investments10.1016/j.enbuild.2022.111836 ↗
8. Investment decision-making optimization of energy efficiency retrofit measures in multiple buildings under financing budgetary restraint10.1016/j.jclepro.2019.01.119 ↗
9. Cost-benefit analysis for Energy Efficiency Retrofit of existing buildings: A case study in China10.1016/j.jclepro.2017.12.225 ↗
10. DOE, U. (2023, February 20). International Performance Measurement & Verification Protocol, Available online: https://www.nrel.gov/docs/fy02osti/31505.pdf.
11. NREL (2023, February 20). The Uniform Methods Project: Methods for Determining Energy Efficiency Savings for Specific Measures, Available online: https://www.nrel.gov/docs/fy18osti/70472.pdf.
12. ASHRAE (2014). Measurement of Energy, Demand, and Water Savings, ASHRAE. ASHRAE Guideline.
13. Manfren, M., and Nastasi, B. (2020). Parametric performance analysis and energy model calibration workflow integration—A scalable approach for buildings. Energies, 13.10.3390/en13030621 ↗
14. Development and application of a machine learning supported methodology for measurement and verification (M&V) 2.010.1016/j.enbuild.2018.02.023 ↗
15. Sarmas, E., Dimitropoulos, N., Marinakis, V., Zucika, A., and Doukas, H. (2022, January 6–11). Monitoring the impact of energy conservation measures with Artificial Neural Networks. Proceedings of the ECEEE 2022 Summer Study Proceedings Agents of Change (ECEEE), Online.
16. How successful are energy efficiency investments? A comparative analysis for classification & performance prediction10.1007/s10614-021-10098-6 ↗
17. A review of deterministic and data-driven methods to quantify energy efficiency savings and to predict retrofitting scenarios in buildings10.1016/j.rser.2020.110027 ↗
18. Marinakis, V. (2020). Big data for energy management and energy-efficient buildings. Energies, 13.10.3390/en13071555 ↗
19. Data-driven building energy modelling—An analysis of the potential for generalisation through interpretable machine learning10.1016/j.rser.2022.112686 ↗
20. Modeling heating and cooling loads by artificial intelligence for energy-efficient building design10.1016/j.enbuild.2014.07.036 ↗
21. Deep-learning neural-network architectures and methods: Using component-based models in building-design energy prediction10.1016/j.aei.2018.06.004 ↗
22. An ensemble learning approach for accurate energy load prediction in residential buildings10.1109/ACCESS.2019.2909470 ↗
23. Early predicting cooling loads for energy-efficient design in office buildings by machine learning10.1016/j.enbuild.2018.10.004 ↗
24. Energy use predictions with machine learning during architectural concept design10.1080/23744731.2017.1319176 ↗
25. Component-based machine learning for performance prediction in building design10.1016/j.apenergy.2018.07.011 ↗
26. Estimating building energy consumption using extreme learning machine method10.1016/j.energy.2015.11.037 ↗
27. Applications of machine learning methods to identifying and predicting building retrofit opportunities10.1016/j.enbuild.2016.06.092 ↗
28. Statistical learning to estimate energy savings from retrofitting in the Norwegian food retail market10.1016/j.rser.2022.112691 ↗
29. A data-driven approach to optimize urban scale energy retrofit decisions for residential buildings10.1016/j.apenergy.2020.114861 ↗
30. Application of clustering for the development of retrofit strategies for large building stocks10.1016/j.aei.2016.02.001 ↗
31. Impacts of energy-efficiency investments on internal conditions in low-income households10.1080/09613218.2017.1314641 ↗
32. Forecasting with trees10.1016/j.ijforecast.2021.10.004 ↗
33. Random forests10.1023/A:1010933404324 ↗
34. Decision Trees for Time-Series Forecasting
35. Extremely randomized trees10.1007/s10994-006-6226-1 ↗
36. Ensemble learning: A survey10.1002/widm.1249 ↗
37. Bagging predictors10.1007/BF00058655 ↗
38. Newer classification and regression tree techniques: Bagging and random forests for ecological prediction10.1007/s10021-005-0054-1 ↗
39. An introduction to recursive partitioning: Rationale, application, and characteristics of classification and regression trees, bagging, and random forests10.1037/a0016973 ↗
40. Examining non-linear built environment effects on elderly’s walking: A random forest approach10.1016/j.trd.2020.102552 ↗
41. Ensemble model of non-linear feature selection-based extreme learning machine for improved natural gas reservoir characterization10.1016/j.jngse.2015.02.012 ↗
42. A comparison among interpretative proposals for Random Forests
43. Comprehensible classification models: A position paper10.1145/2594473.2594475 ↗
44. Scikit-learn: Machine Learning in Python
45. Gradient boosting machines, a tutorial10.3389/fnbot.2013.00021 ↗
46. Schapire, R.E. (2003). Nonlinear Estimation and Classification, Springer.
47. Chen, T., and Guestrin, C. (2016, January 13–17). XGBoost: A Scalable Tree Boosting System. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD ’16, San Francisco, CA, USA.10.1145/2939672.2939785 ↗
48. Wade, C. (2020). Hands-On Gradient Boosting with XGBoost and Scikit-Learn: Perform Accessible Machine Learning and Extreme Gradient Boosting with Python, Packt Publishing Ltd.
49. Exploiting GPUs for efficient gradient boosting decision tree training10.1109/TPDS.2019.2920131 ↗
50. Accelerating the XGBoost algorithm using GPU computing10.7717/peerj-cs.127 ↗
51. Ke, G., Meng, Q., Finley, T., Wang, T., Chen, W., Ma, W., Ye, Q., and Liu, T.Y. (2017, January 4–9). Lightgbm: A highly efficient gradient boosting decision tree. Proceedings of the Advances in Neural Information Processing Systems 30 (NIPS 2017), Long Beach, CA, USA.
52. M5 accuracy competition: Results, findings, and conclusions10.1016/j.ijforecast.2021.11.013 ↗
53. SwiftIDS: Real-time intrusion detection system based on LightGBM and parallel intrusion detection mechanism10.1016/j.cose.2020.101984 ↗
54. Comparison between XGBoost, LightGBM and CatBoost using a home credit dataset
55. Forecasting: Theory and practice10.1016/j.ijforecast.2021.11.001 ↗
56. Factors affecting green office building investment in Malaysia10.1016/j.sbspro.2013.11.015 ↗
57. Determinants of renewable energy growth: A global sample analysis10.1016/j.enpol.2014.02.036 ↗
58. Exploring the sources of uncertainty: Why does bagging for time series forecasting work?10.1016/j.ejor.2018.01.045 ↗
59. On the selection of forecasting accuracy measures10.1080/01605682.2021.1892464 ↗