Design optimization of renewable energy systems for NZEBs based on deep residual learning

Abstract The design of renewable energy systems for Nearly Zero Energy Buildings (NZEB) is a complex optimization problem. In recent years, simulation-based optimization has demonstrated to be able to support the search for optimal design, but improvements to the method that are able to reduce the high computation time are needed. This study presents a new approach based on deep residual learning to make the search for optimal design solutions more efficient. It is applied to the problem of system design optimization for an Italian multi-family building case-study equipped with a solar cooling system. Given a design space defined by set of variables related to Heating, Ventilation and Air Conditioning systems (HVAC) and renewable systems, a machine learning method based on residual neural networks to predict and minimize the objective function characterizing non-renewable primary energy consumptions is proposed. Results have shown that the approach is able to successfully identify optimized design solutions (energy performance improved by 47%) with good prediction accuracy (error smaller than 3%) while reducing the overall computation time and maximizing the exploration of the design space, paving the way for further advancements in simulation-based optimization for NZEB design.

[1]  Maria Ferrara.  Simulation-based optimization for NZEB design: insights and beyond , 2019 .

[2]  Delia D’Agostino,et al.  What is a Nearly zero energy building? Overview, implementation and comparison of definitions , 2019, Journal of Building Engineering.

[3]  Chuanqi Zhu,et al.  Uncertainty calibration of building energy models by combining approximate Bayesian computation and machine learning algorithms , 2020 .

[4]  Tianzhen Hong,et al.  State-of-the-art on research and applications of machine learning in the building life cycle , 2020, Energy and Buildings.

[5]  Martin Tamke,et al.  Machine learning for architectural design: Practices and infrastructure , 2018, International Journal of Architectural Computing.

[6]  Sukho Lee,et al.  Using deep learning approaches with variable selection process to predict the energy performance of a heating and cooling system , 2020 .

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

[8]  Enrico Fabrizio,et al.  Energy Demand and Supply Simultaneous Optimization to Design a Nearly Zero-Energy House , 2019, Applied Sciences.

[9]  Philipp Geyer,et al.  Deep Component-Based Neural Network Energy Modelling for Early Design Stage Prediction , 2018 .

[10]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[11]  Francesco Calise,et al.  Thermoeconomic optimization of a solar-assisted heat pump based on transient simulations and computer Design of Experiments , 2016 .

[12]  A. Palombo,et al.  Development and validation of a new TRNSYS Type for thermosiphon flat-plate solar thermal collectors: energy and economic optimization for hot water production in different climates , 2019, Renewable Energy.

[13]  Ivana Dusparic,et al.  Multi-agent Deep Reinforcement Learning for Zero Energy Communities , 2018, 2019 IEEE PES Innovative Smart Grid Technologies Europe (ISGT-Europe).

[14]  Wiesław Gazda,et al.  Influence of power source type on energy effectiveness and environmental impact of cooling system with adsorption refrigerator , 2014 .

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

[16]  K. Aliakbari,et al.  Sensitivity analysis and multi-objective optimization of energy consumption and thermal comfort by using interior light shelves in residential buildings , 2020 .

[17]  Roberto Lamberts,et al.  Application and characterization of metamodels based on artificial neural networks for building performance simulation: A systematic review , 2020 .

[18]  Guoqiang Zhang,et al.  A state-of-the-art-review on phase change materials integrated cooling systems for deterministic parametrical analysis, stochastic uncertainty-based design, single and multi-objective optimisations with machine learning applications , 2020 .

[19]  Yuan Yu,et al.  TensorFlow: A system for large-scale machine learning , 2016, OSDI.

[20]  Pascal Henry Biwole,et al.  Multi-Objective Optimization Methodology for Net Zero Energy Buildings , 2018 .

[21]  Shahaboddin Shamshirband,et al.  Estimating building energy consumption using extreme learning machine method , 2016 .

[22]  Enrico Fabrizio.  Zero Energy Buildings: A Reached Target or a Starting Point? , 2020 .

[23]  Goran Krajačić,et al.  The role of cool thermal energy storage (CTES) in the integration of renewable energy sources (RES) and peak load reduction , 2012 .

[24]  Xing Shi,et al.  Ineffectiveness of optimization algorithms in building energy optimization and possible causes , 2019 .

[25]  Antonino Bonanno,et al.  Components and design guidelines for solar cooling systems: The experience of ZEOSOL , 2019, Renewable Energy.

[26]  Enrico Fabrizio,et al.  Trade-off between environmental and economic objectives in the optimization of multi-energy systems , 2009 .

[27]  Jean-Louis Scartezzini,et al.  Machine learning methods to assist energy system optimization , 2019, Applied Energy.

[28]  Soteris A. Kalogirou,et al.  Latest progress in Sustainable Development using renewable energy technology , 2020 .

[29]  Fraisse Gilles,et al.  Decision-making based on network visualization applied to building life cycle optimization , 2017 .

[30]  Zheng O'Neill,et al.  A methodology for meta-model based optimization in building energy models , 2012 .

[31]  Salvatore Carlucci,et al.  Assessing gaps and needs for integrating building performance optimization tools in net zero energy buildings design , 2013 .

[32]  Amanda D. Smith,et al.  Predicting heating demand and sizing a stratified thermal storage tank using deep learning algorithms , 2018, Applied Energy.

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

[34]  Ryozo Ooka,et al.  Predictive control strategies based on weather forecast in buildings with energy storage system: A review of the state-of-the art , 2017 .

[35]  Zeyu Wang,et al.  A review of artificial intelligence based building energy use prediction: Contrasting the capabilities of single and ensemble prediction models , 2017 .

[36]  Philipp Geyer,et al.  Component-based machine learning for performance prediction in building design , 2018, Applied Energy.

[37]  Lynne E. Parker,et al.  Constructing large scale surrogate models from big data and artificial intelligence , 2017 .

[38]  Nazri Mohd Nawi,et al.  The Effect of Data Pre-processing on Optimized Training of Artificial Neural Networks , 2013 .

[39]  Enrico Fabrizio,et al.  Building energy performance assessment through simplified models: Application of the ISO 13790 quasi-steady state method , 2007 .

[40]  Elisa Sirombo,et al.  Energy-optimized versus cost-optimized design of high-performing dwellings: The case of multifamily buildings , 2018 .

[41]  Carlo Roselli,et al.  A novel energy index to assess the impact of a solar PV-based ground source heat pump on the power grid , 2019 .

[42]  Dirk Müller,et al.  Real-world application of machine-learning-based fault detection trained with experimental data , 2020 .

[43]  Enrico Fabrizio,et al.  Cost optimal nZEBs in future climate scenarios , 2017 .

[44]  Younes Noorollahi,et al.  Sustainable development using renewable energy technology , 2020 .

[45]  Morteza M. Ardehali,et al.  Development of pattern recognition based ANN for energy auditing and inefficiency diagnostics of influential design elements utilising electrical energy data , 2010 .

[46]  Eleonora Riva Sanseverino,et al.  A review on optimization and cost-optimal methodologies in low-energy buildings design and environmental considerations , 2019, Sustainable Cities and Society.

[47]  P Pieter-Jan Hoes,et al.  Simulation-based design optimization of houses with low grid dependency , 2019 .

[48]  Xing Shi,et al.  A review on building energy efficient design optimization rom the perspective of architects , 2016 .

[49]  K. Lee,et al.  Development of a simulation-optimization model for sustainable operation of groundwater heat pump system , 2020 .

[50]  E. Fabrizio,et al.  Performance assessment and optimization of a solar cooling system to satisfy renewable energy ratio (RER) requirements in multi-family buildings , 2020 .

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