MATRYCS
Published July 25, 2022 | Version v1
Conference paper Open

Monitoring the impact of energy conservation measures with Artificial Neural Networks

Creators

  • 1. Decision Support Systems Laboratory, School of Electrical and Computer Engineering, National Technical University of Athens
  • 2. The Latvian Environmental Investment Fund

Description

Energy Conservation Measures are mandatory in order to improve buildings’ energy performance by using upgraded technologies, systems and installations. However, the lack of accurate techniques for Measurement & Verification (M&V) imposes insurmountable barriers towards their extended financing. The development of precise M&V techniques to estimate energy savings is a critical issue that can be tackled through the adoption of predictive models for the adjusted baseline energy consumption in the reporting period.

The most commonly used M&V practices to date are reported in the International Performance Measurement and Verification Protocol (IPMVP), where the most widespread techniques per case for calculating energy savings are defined. More specifically, the IPMVP indicates the adoption of linear regression methods to predict the adjusted baseline energy consumption of a building, exploiting outdoor temperature and heating degree days.

In this paper, utilisation of Deep Learning for training energy consumption predictive models is examined, as vast amount of data from Internet of Things devices are available nowadays. Thus, the feedforward Artificial Neural Network (ANN) is proposed for predicting the adjusted baseline energy consumption, using the hour of the day, the day of the week and weather data as training features. The proposed models incorporate both linear and non-linear relationships, in contrast to linear regression methods.

To validate the proposed method, an experimental application is implemented, applying the developed models on an educational institution in Latvia. The building has been renovated regarding its heating supply and ventilation system, as well as its enclosing structures insulation. The predictions from the ANN models are compared with the ones from the traditional degree days method, indicating that ANN achieves higher accuracy in energy savings estimation for electricity and diesel fuel consumption.

Files

4-280-22_Sarmas.pdf

Files (556.2 kB)

Name Size Download all
md5:bc7cba45e318a00ee0bf3bb68643ed96
556.2 kB Preview Download

Additional details

Related works

Is described by
Conference paper: 2001-7960 (ISSN)
Conference paper: gnd:978-91-983878-9-3 (gnd)

Funding

MATRYCS – Modular Big Data Applications for Holistic Energy Services in Buildings 101000158
European Commission

References

  • Adnan, W. N. W. M., Dahlan, N. Y., & Musirin, I. (2020). Development of option c measurement and verification model using hybrid artificial neural network-cross valida- tion technique to quantify saving. IAES International Journal of Artificial Intelligence, 9(1), 25.
  • Agenis-Nevers, M., Wang, Y., Dugachard, M., Salvazet, R., Becker, G., & Chenu, D. (2021). Measurement and Veri- fication for multiple buildings: An innovative baseline model selection framework applied to real energy perfor- mance contracts. Energy and Buildings, 249, 111183.
  • Agostinelli, F., Hoffman, M., Sadowski, P., & Baldi, P. (2014). Learning activation functions to improve deep neural networks. arXiv preprint arXiv:1412.6830.
  • Annunziata, E., Frey, M., & Rizzi, F. (2013). Towards nearly zero-energy buildings: The state-of-art of national regula- tions in Europe. Energy, 57, 125-133.
  • Aris, S. M., Dahlan, N. Y., Nawi, M. N. M., Nizam, T. A., & Tahir, M. Z. (2015). Quantifying energy savings for retrofit centralized hvac systems at Selangor state secretary com- plex. Jurnal Teknologi, 77(5).
  • Arsenopoulos, A., Sarmas, E., Stavrakaki, A., Giannouli, I., & Psarras, J. (2021). A Data-Driven Decision Support Tool at the service of Energy suppliers and Utilities for Tackling Energy Poverty: A case study in Greece. In 2021 12th 578 ECEEE 2022 SUMMER STUDY 4. MONITORING AND EVALUATION FOR A WISE, JUST AND … International Conference on Information, Intelligence, Systems & Applications (IISA) (pp. 1-6). IEEE.
  • ASHRAE (2002). Guideline 14-2002: Measurement of Energy and Demand Savings. ASHRAE, Atlanta, available: http:// www.eeperformance.org/uploads/8/6/5/0/8650231/ ashrae_guideline_14-2002_measurement_of_energy_ and_demand_saving.pdf
  • Atkinson, P. M., & Tatnall, A. R. (1997). Introduction neural networks in remote sensing. International Journal of remote sensing, 18(4), 699–709.
  • Azimi, R., Ghayekhloo, M., & Ghofrani, M. (2016). A hybrid method based on a new clustering technique and multilayer perceptron neural networks for hourly solar radiation fore- casting. Energy Conversion and Management, 118, 331-344.
  • Bishop, C. M. (1995). Neural Networks for Pattern Recogni- tion, Oxford, UK: Oxford University Press.
  • Eckle, K., & Schmidt-Hieber, J. (2019). A comparison of deep networks with ReLU activation function and linear spline- type methods. Neural Networks, 110, 232–242.
  • Ehsan, R. M., Simon, S. P., & Venkateswaran, P. R. (2017). Day-ahead forecasting of solar photovoltaic output power using multilayer perceptron. Neural Computing and Ap- plications, 28(12), 3981–3992.
  • Ehteram, M., Ahmed, A. N., Kumar, P., Sherif, M., & El-Shafie, A. (2021). Predicting freshwater production and energy consumption in a seawater greenhouse based on ensem- ble frameworks using optimized multi-layer perceptron. Energy Reports, 7, 6308–6326.
  • Ekonomou, L. (2010). Greek long-term energy consumption prediction using artificial neural networks. Energy, 35(2), 512–517.
  • EU Smart Readiness Indicator, available: https://energy. ec.europa.eu/topics/energy-efficiency/energy-efficient- buildings/smart-readiness-indicator
  • European Commission (2019), The European Green Deal, Brussels, 11 December 2019, available: https://ec.europa. eu/info/strategy/priorities-2019-2024/european-green- deal_en EU Building Stock Observatory, available: https:// ec.europa.eu/energy/eu-buildings-database_en
  • European Commission (2020) – Department: Energy – In focus, Energy efficiency in buildings, Brussels, 17 Febru- ary 2020, available: https://ec.europa.eu/info/news/focus- energy-efficiency-buildings-2020-feb-17_en
  • Ferreira, M. A. P. S., Almeida, M., & Rodrigues, A. C. R. A. (2016). Cost-optimal energy efficiency levels are the first step in achieving cost effective renovation in residential buildings with a nearly-zero energy target. Energy and Buildings, 133, 724-737.
  • Gardner, M. W., & Dorling, S. R. (1998). Artificial neural networks (the multilayer perceptron)—a review of applica- tions in the atmospheric sciences. Atmospheric environ- ment, 32(14-15), 2627-2636.
  • Granderson, J., Touzani, S., Custodio, C., Sohn, M. D., Jump, D., & Fernandes, S. (2016). Accuracy of automated measure- ment and verification (M&V) techniques for energy savings in commercial buildings. Applied Energy, 173, 296-308.
  • Grillone, B., Mor, G., Danov, S., Cipriano, J., & Sumper, A. (2021). A data-driven methodology for enhanced measure- ment and verification of energy efficiency savings in com- mercial buildings. Applied Energy, 301, 117502.
  • Haykin, S. (1999). Neural Networks. A Comprehensive Foun- dation, Upper Saddle River, NJ: Prentice Hall.
  • Heo, Y., & Zavala, V. M. (2012). Gaussian process modeling for measurement and verification of building energy sav- ings. Energy and Buildings, 53, 7–18.
  • IPMVP Committee. (2001). International Performance Measurement and Verification Protocol: Concepts and op- tions for determining energy and water savings, Volume I, available: https://evo-world.org/en/products-services- mainmenu-en/protocols/ipmvp
  • Kaiser, M. J., & Pulsipher, A. G. (2010). Preliminary as- sessment of the Louisiana Home Energy Rebate Offer program using IPMVP guidelines. Applied Energy, 87(2), 691–702.
  • Keras, C. F. (2015). Theano-based deep learning libraryCode: https://github.com/fchollet. Documentation: http://keras. io.
  • Marinakis V. (2020). Big data for energy management and energy-efficient buildings. Energies, 13(7), 1555.
  • Marinakis V., Doukas H. (2018). An advanced IoT-based sys- tem for intelligent energy management in buildings. Sen- sors, 18(2), 610.
  • Marinakis V., Doukas H., Karakosta C., Psarras J. (2013). An integrated system for buildings' energy-efficient automa- tion: Application in the tertiary sector. Applied Energy, 101, 6–14.
  • Marinakis V., Doukas H., Tsapelas J., Mouzakitis S., Sicilia Á., Madrazo L., Sgouridis S. (2020). From big data to smart energy services: An application for intelligent energy management. Future Generation Computer Systems, 110, 572–586.
  • Mas, J. F., & Flores, J. J. (2008). The application of artificial neural networks to the analysis of remotely sensed data. International Journal of Remote Sensing, 29(3), 617–663.
  • Mokhtar, A. (2022). Examining the Deviation in Energy Saving Estimations Due to the Use of the Degree Days Method. In Sustainability in Energy and Buildings 2021 (pp. 1-10). Springer, Singapore.
  • Mustapa, R. F., Dahlan, N. Y., Yassin, A. I. M., & Nordin, A. H. M. (2020). Quantification of energy savings from an awareness program using NARX-ANN in an educational building. Energy and Buildings, 215, 109899.
  • Nikolaidis, Y., Pilavachi, P. A., & Chletsis, A. (2009). Economic evaluation of energy saving measures in a common type of Greek building. Applied Energy, 86(12), 2550–2559.
  • Olaussen, J. O., Oust, A., & Solstad, J. T. (2017). Energy performance certificates–Informing the informed or the indifferent? Energy Policy, 111, 246-254.
  • Papapostolou, A., Mexis, F. D., Sarmas, E., Karakosta, C., & Psarras, J. (2020). Web-based Application for Screening Energy Efficiency Investments: A MCDA Approach. In 2020 11th International Conference on Information, Intel- ligence, Systems and Applications (IISA (pp. 1–7). IEEE.
  • Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., ... & Duchesnay, E. (2011). Scikit- learn: Machine learning in Python. the Journal of machine Learning research, 12, 2825–2830.
  • Razali, N. S., & Dahlan, N. Y. (2015). Whole Facility Measure- ment for Quantifying Energy Saving in an Office Building,Malaysia. In Applied Mechanics and Materials (Vol. 785, pp. 676–681). Trans Tech Publications Ltd.
  • Santamouris, M. (2016). Innovating to zero the building sector in Europe: Minimising the energy consumption, eradication of the energy poverty and mitigating the local climate change. Solar Energy, 128, 61–94.
  • Sarmas, E., Spiliotis, E., Marinakis, V., Koutselis, T., & Doukas, H. (2022). A meta-learning classification model for supporting decisions on energy efficiency investments. Energy and Buildings, doi: https://doi.org/10.1016/j. enbuild.2022.111836
  • Schmidt-Hieber, J. (2020). Nonparametric regression using deep neural networks with ReLU activation function. The Annals of Statistics, 48(4), 1875–1897.
  • Soofastaei, A., Aminossadati, S. M., Arefi, M. M., & Kizil, M. S. (2016). Development of a multi-layer perceptron artificial neural network model to determine haul trucks energy consumption. International Journal of Mining Sci- ence and Technology, 26(2), 285–293.
  • Touzani, S., Granderson, J., & Fernandes, S. (2018). Gradient boosting machine for modeling the energy consumption of commercial buildings. Energy and Buildings, 158, 1533–1543.
  • Velo, R., López, P., & Maseda, F. (2014). Wind speed estima- tion using multilayer perceptron. Energy Conversion and Management, 81, 1–9.
  • Xu, Y., Loftness, V., & Severnini, E. (2021). Using Machine Learning to Predict Retrofit Effects for a Commercial Building Portfolio. Energies, 14(14), 4334.
  • Ye, K. K., Demirezen, G., Fung, A. S., & Janssen, E. (2020). The use of artificial neural networks (ANN) in the prediction of ener- gy consumption of air-source heat pump in retrofit residential housing. In IOP Conference Series: Earth and Environmental Science (Vol. 463, No. 1, p. 012165). IOP Publishing.
  • Yeh, W. C., Yeh, Y. M., Chang, P. C., Ke, Y. C., & Chung, V. (2014). Forecasting wind power in the Mai Liao Wind Farm based on the multi-layer perceptron artificial neural network model with improved simplified swarm optimi- zation. International Journal of Electrical Power & Energy Systems, 55, 741–748.
  • Zhang, Y., O'Neill, Z., Dong, B., & Augenbroe, G. (2015). Comparisons of inverse modeling approaches for predict- ing building energy performance. Building and Environ- ment, 86, 177–190.
  • Zhang, Z. (2018). Improved adam optimizer for deep neural networks. In 2018 IEEE/ACM 26th International Sympo- sium on Quality of Service (IWQoS) (pp. 1-2). IEEE.
  • Zou, J., Han, Y., & So, S. S. (2008). Overview of artificial neural networks. Artificial Neural Networks, 14–22.