A machine learning-based surrogate model to approximate optimal building retrofit solutions

Abstract The building sector has the highest share of operational energy consumption and greenhouse gas emissions among all sectors. Environmental targets set by many countries impose the need to improve the environmental footprint of the existing building stock. Building retrofit is considered one of the most promising solutions towards this direction. In this paper, a surrogate model for evaluating the necessary building envelope and energy system measures for building retrofit is presented. Artificial neural networks are exploited to build up this model in order to provide a good balance between accuracy and computational cost. The proposed model is trained and tested for the case study of the city of Zurich, in Switzerland, and is compared with one of the most advanced models for building retrofit that uses building simulation and optimization tools. The surrogate model operates on a smaller input set and the time required to derive retrofit solutions is reduced from 3.5 min to 16.4 μsec. Results show that the proposed model can provide significantly reduced computational cost without compromising accuracy for most of the retrofit dimensions. For instance, the retrofit costs and the energy system selections are approximated with an average accuracy of R 2 = 0.9408 and f 1 s c o r e = 0.9450 , respectively. Finally, yet importantly, such surrogate retrofit models may effectively be used for bottom-up retrofit analyses for wide areas and can contribute towards accelerating the adoption of retrofit measures.

[1]  Soteris A. Kalogirou,et al.  Implementing artificial neural networks in energy building applications — A review , 2018, 2018 IEEE International Energy Conference (ENERGYCON).

[2]  Mary Ann Piette,et al.  Energy retrofit analysis toolkits for commercial buildings: A review , 2015 .

[3]  G. Andersson,et al.  Energy hubs for the future , 2007, IEEE Power and Energy Magazine.

[4]  George Baird,et al.  Energy Performance Buildings , 2017 .

[5]  Jan Carmeliet,et al.  MULTI-OBJECTIVE OPTIMISATION TO SIMULTANEOUSLY ADDRESS ENERGY HUB SIZING AND SCHEDULING USING A LINEAR FORMULATION , 2014 .

[6]  Gerardo Maria Mauro,et al.  CASA, cost-optimal analysis by multi-objective optimisation and artificial neural networks: A new framework for the robust assessment of cost-optimal energy retrofit, feasible for any building , 2017 .

[7]  Juha Jokisalo,et al.  Energy performance and environmental impact analysis of cost-optimal renovation solutions of large panel apartment buildings in Finland , 2017 .

[8]  Paul Cooper,et al.  Existing building retrofits: Methodology and state-of-the-art , 2012 .

[9]  Eduardo Álvarez-Miranda,et al.  A simulation and optimisation methodology for choosing energy efficiency measures in non-residential buildings , 2019, Applied Energy.

[10]  Mahdi Mahdikhani,et al.  Energy performance optimization of existing buildings: A literature review , 2020 .

[11]  Rasmus Lund Jensen,et al.  Early stage decision support for sustainable building renovation – A review , 2016 .

[12]  Soteris A. Kalogirou,et al.  Artificial neural networks in renewable energy systems applications: a review , 2001 .

[13]  Yitao Liu,et al.  Deep learning based ensemble approach for probabilistic wind power forecasting , 2017 .

[14]  Daniel Castro-Lacouture,et al.  GA-based decision support system for housing condition assessment and refurbishment strategies , 2009 .

[15]  Fariborz Haghighat,et al.  Multiobjective optimization of building design using TRNSYS simulations, genetic algorithm, and Artificial Neural Network , 2010 .

[16]  Constantine Kontokosta,et al.  Applications of machine learning methods to identifying and predicting building retrofit opportunities , 2016 .

[17]  Xiaohua Xia,et al.  A multi-objective optimization model for energy-efficiency building envelope retrofitting plan with rooftop PV system installation and maintenance , 2017 .

[18]  Periklis Gogas,et al.  Forecasting energy markets using support vector machines , 2014 .

[19]  Luis C. Dias,et al.  Multi-objective optimization for building retrofit: A model using genetic algorithm and artificial neural network and an application , 2014 .

[20]  Bo Wang,et al.  Large-scale building energy efficiency retrofit: Concept, model and control , 2016 .

[21]  Robin Girard,et al.  Joint optimization of building-envelope and heating-system retrofits at territory scale to enhance decision-aiding , 2020 .

[22]  Bistra N. Dilkina,et al.  Sustainable Building Design: A Challenge at the Intersection of Machine Learning and Design Optimization , 2015, AAAI Workshop: Computational Sustainability.

[23]  Jun Yuan,et al.  Evaluation of cost-effective building retrofit strategies through soft-linking a metamodel-based Bayesian method and a life cycle cost assessment method , 2019, Applied Energy.

[24]  Gilles Notton,et al.  Uncertainties in global radiation time series forecasting using machine learning: The multilayer perceptron case , 2017 .

[25]  Ling Tang,et al.  A compressed sensing based AI learning paradigm for crude oil price forecasting , 2014 .

[26]  Gerardo Maria Mauro,et al.  Retrofit of villas on Mediterranean coastlines: Pareto optimization with a view to energy-efficiency and cost-effectiveness , 2019, Applied Energy.

[27]  Fabio Peron,et al.  Cost-Optimal measures for renovation of existing school buildings towards nZEB , 2017 .

[28]  Xing Shi,et al.  Towards adoption of building energy simulation and optimization for passive building design: A survey and a review , 2018 .

[29]  Jan Carmeliet,et al.  CESAR: A bottom-up building stock modelling tool for Switzerland to address sustainable energy transformation strategies , 2018, Energy and Buildings.

[30]  Nilay Shah,et al.  Diagnostic tools of energy performance for supermarkets using Artificial Neural Network algorithms , 2013 .

[31]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[32]  Martin Kumar Patel,et al.  Techno-economic potential of large-scale energy retrofit in the Swiss residential building stock , 2017 .

[33]  Shahaboddin Shamshirband,et al.  State of the Art of Machine Learning Models in Energy Systems, a Systematic Review , 2019, Energies.

[34]  Xiaofeng Guo,et al.  Modeling and forecasting building energy consumption: A review of data-driven techniques , 2019, Sustainable Cities and Society.

[35]  Zhi-Hua Zhou,et al.  Isolation Forest , 2008, 2008 Eighth IEEE International Conference on Data Mining.

[36]  Georgios Mavromatidis,et al.  Model-based design of distributed urban energy systems under uncertainty , 2017 .

[37]  Javier Neila González,et al.  A systematic review of genetic algorithm-based multi-objective optimisation for building retrofitting strategies towards energy efficiency , 2020 .

[38]  Gerardo Maria Mauro,et al.  A new methodology for cost-optimal analysis by means of the multi-objective optimization of building energy performance , 2015 .

[39]  Jan Carmeliet,et al.  Multiobjective optimisation of energy systems and building envelope retrofit in a residential community , 2017 .

[40]  Manel Martínez-Ramón,et al.  Advanced detection of HVAC faults using unsupervised SVM novelty detection and Gaussian process models , 2017 .

[41]  David Hsu,et al.  How much information disclosure of building energy performance is necessary , 2014 .

[42]  J. Carmeliet,et al.  Evaluation of photovoltaic integration potential in a village , 2015 .

[43]  Georgios Mavromatidis,et al.  Optimal transformation strategies for buildings, neighbourhoods and districts to reach CO2 emission reduction targets , 2020, Energy and Buildings.

[44]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[45]  Alessandro Prada,et al.  On the performance of meta-models in building design optimization , 2018 .

[46]  Thomas Vogt,et al.  Comparative life cycle assessment of battery storage systems for stationary applications. , 2015, Environmental science & technology.