The Application of Feed - Forward Neural Network Architecture for Improving Energy Efficiency
DOI:
https://doi.org/10.18662/po/14.2/604Keywords:
Feed – Forward Neural Network, Energy Consumption, Prediction Model, Building EnergyAbstract
The energy sector contributes approximately two-thirds of global greenhouse gas emissions. In this context, the sector must adapt to new supply and demand networks for all future energy sources. The ongoing transformation in the European energy field is driven by the ambition of the European Union to reach the climate objectives set for 2030. The main actions are increasing renewable energy production, adapting transition fuels like natural gas to reduce emissions, improving energy efficiency across all economic sectors, prioritizing building, transportation, and industry, developing Carbon Capture and Storage technologies, and ensuring universal access to clean and affordable energy. The significant changes envisaged in the energy sector to increase renewable energy production and consumption require improved integration and more use of predictive tools to support stakeholders' decision-making processes. This article presents a case study to assess the performance of predictive models based on a Feed-Forward Neural Network architecture that employ Root Mean Squared Propagation as their optimization function in terms of choosing the most appropriate activation function for this kind of data input and output. The training and testing phases of the models use data about building energy consumption. The lowest training time and Root Mean Square Error values were similar for Rectified Linear Unit and Tanh activation functions. The model with the Rectified linear Unit activation function performed best.
References
Amasyali, K., & El-Gohary, N. (2018). A review of data-driven building energy consumption prediction studies. Renewable and Sustainable Energy Reviews, 81 https://doi.org/10.1016/j.rser.2017.04.095 1192-1205
Aydinalp, M., Ugursal, V., & Fung, A. (2004). Modelling of the space and domestic hot-water heating energy-consumption in the residential sector using neural networks. Applied Energy, 79, 159-178 https://doi.org/10.1016/j.apenergy.2003.12.006
Chatterjee, A., Engelen, R., Kawa, S., Sweeney, C., & Michalak, A. (2013, July 24). Background error covariance estimation for atmospheric CO2 data assimilation. JGR Atmospheres, 118(10140-10154), https://doi.org/10.1002/jgrd.50654
D’Amico, A., Ciulla, G., Traverso, M., Brano, V., & Palumbo, E. (2019). Artificial Neural Networks to assess energy and environmental performance of buildings: An Italian case study. Journal of Cleaner Production, 239 https://doi.org/10.1016/j.jclepro.2019.117993 117993.
European Comission. (2019, May 9). Root mean square error (RMSE). Retrieved May 2023, from Collaboration in Research and Methodology for Official Statistics: https://cros-legacy.ec.europa.eu/content/root-mean-square-error-rmse_en
Government of British Columbia. (2018). How It Works: Energy Step Code. https://energystepcode.ca/how-it-works
Government of Canada. (2022). Natual resources Canada, energy efficiency. https://natural-resources.canada.ca/energy-efficiency/green-buildings/24572
Haibo, F., Jianfeng, Z., Haonan, Z., Shiyao, Z., Dezhi, L., & Niraj, T. (2022). Uncertainties in whole-building life cycle assessment: A systematic review. Journal of Building Engineering, 50, ISSN 2352-7102, https://doi.org/10.1016/j.jobe.2022.104191
Hestness, J., Narang, S., Ardalani, N., Diamos, G., Jun, H., Kianinejad, H., . . . Zhou, Y. (2017, December 1). Deep learning scaling is predictable, empirically. Cornell University: https://arxiv.org/abs/1712.00409
Howard, A., Balbach, C., Miller, C., Haberl, J., Gowri, K., & Dane, S. (2019). ASHRAE - Great Energy Predictor III . Retrieved December 2022, from ASHRAE: https://kaggle.com/competitions/ashrae-energy-prediction
International Energy Agency. (2020, March 23). If the energy sector is to tackle climate change, it must also think about water. Retrieved May 2023, from IEA: https://www.iea.org/commentaries/if-the-energy-sector-is-to-tackle-climate-change-it-must-also-think-about-water
Jerez, S., Montávez, J., Jimenez-Guerrero, P., Gómez-Navarro, J., Lorente-Plazas, R., & Zorita, E. (2012, January). A multi-physics ensemble of present-day climate regional simulations over the Iberian Peninsula. Climate Dynamics, 40, 3023-3046, DOI: 10.1007/s00382-012-1539-1
Johnson, M., & Nguyen, D. (2017). How much data is enough? Predicting how accuracy varies with training data size. Macquarie University, Sydney https://web.science.mq.edu.au/~mjohnson/papers/Johnson17Power-talk.pdf
Kaplan, J., McCandlish, S., Henighan, T., Brown, T., Chess, B., Child, R., . . . Amodei, D. (2020, January 23). Scaling laws for neural language models. Cornell University: https://arxiv.org/abs/2001.08361
Karunathilake, H., Hewage, K., & Sadiq, R. (2018). Opportunities and challenges in energy demand reduction for Canadian residential sector: A review. Renewable and Sustainable Energy Reviews, 82 https://doi.org/10.1016/j.rser.2017.07.021
Mathieu, B., Xiao, q. Z., Elyes, N., Xiaofeng, G., & Patrice, C. (2019). Modeling and forecasting building energy consumption: A review of data driven techniques. Sustainable Cities and Society, 48, https://doi.org/10.1016/j.scs.2019.101533
McKeen, S., Wilczak, J., Grell, G., Djalalova, I., Peckham, S., Hsie, E., . . . Mathur, R. (2005). Assessment of an ensemble of seven realtime ozone forecasts over eastern North America during the summer of 2004. Journal of Geophysical Research, 110 doi:10.1029/2005JD005858
Mihalakakou, G., Santamouris, M., & Tsangrassoulis, A. (2022). On the energy consumption in residential buildings. Energy and Buildings, 34(7) 727-736. https://doi.org/10.1016/S0378-7788(01)00137-2
Prabatha, T., Hewage, K., Karunathilake, H., & Sadiq, R. (2020). To retrofit or not? Making energy retrofit decisions through life cycle thinking for Canadian residences. Energy and Buildings, 226, 110393. https://doi.org/10.1016/j.enbuild.2020.110393
Rosenfeld, J., Rosenfeld, A., Belinkov, Y., & Shavit, N. (2019). A constructive prediction of the generalization error across scales. https://arxiv.org/abs/1909.12673
Seyedzadeh, S., Rahimian, F., Oliver, S., Glesk, I., & Kumar, B. (2020). Data driven model improved by multi-objective optimisation for prediction of building energy loads. Automation in Construction, 116, https://doi.org/10.1016/j.autcon.2020.103188
Taylor, M. H., Losch, M., Wenzel, M., & Schröter, J. (2013). On the sensitivity of field reconstruction and prediction using empirical orthogonal functions derived from gappy data. Journal of Climate, 26(22), https://doi.org/10.1175/JCLI-D-13-00089.1
Thrampoulidis, E., Mavromatidis, G., Lucchi, A., & Orehounig, K. (2021). A machine learning-based surrogate model to approximate optimal building retrofit solutions. Applied Energy, 281, https://doi.org/10.1016/j.apenergy.2020.116024
Tian, Z., Si, B., Shi, X., & Fang, Z. (2019). An application of Bayesian Network approach for selecting energy efficient HVAC systems. Journal of Building Engineering, 25 https://doi.org/10.1016/j.jobe.2019.100796
Wei, Y., Zhang, X., Shi, Y., Xia, L., Pan, S., Wu, J., . . . Zhao, X. (2018). A review of data-driven approaches for prediction and classification of building energy consumption. Renewable and Sustainable Energy Reviews, 82 https://doi.org/10.1016/j.rser.2017.09.108 1027-1047.
Zhang, H., Hewage, K., Prabatha, T., & Sadiq, R. (2021). Life cycle thinking-based energy retrofits evaluation framework for Canadian residences: A Pareto optimization approach. Building and Environment, 204 https://doi.org/10.1016/j.buildenv.2021.108115
Zhichao, T., Binghui, S., Xing, S., & Zigeng, F. (2019). An application of Bayesian Network approach for selecting energy efficient HVAC systems. Journal of Building Engineering, 25, https://doi.org/10.1016/j.jobe.2019.100796
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2023 The Authors & LUMEN Publishing House
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant this journal right of first publication, with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work, with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g. post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g. in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as an earlier and greater citation of published work (See The Effect of Open Access).
Postmodern Openings Journal has an Attribution-NonCommercial-NoDerivs
CC BY-NC-ND
