Building energy optimization: An extensive benchmark of global search algorithms

Waibel, Christoph; Wortmann, Thomas; Evins, Ralph; Carmeliet, Jan

doi:10.1016/j.enbuild.2019.01.048

Cited by 85 publications

(57 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In this context, Galapagos, Goat, Silvereye, Opossum, Dodo, and Nelder-Mead optimization plug-ins, shown in Figure 2, are explained. Some of these plug-ins have been compared in building optimization problems in the literature, that can be found in [12][13][14][15].…”

Section: Current Optimization Tools In Grasshoppermentioning

confidence: 99%

“…These are constrained optimization by linear approximation (COBYLA), bound optimization by quadratic approximation (BOBYQA), subplex algorithm (Sbplx), the dividing rectangles algorithm (DIRECT), and controlled random search 2 (CRS2). Very recently, Goat is used for building energy optimization [14] and structure optimization [29,30].…”

Section: Goatmentioning

confidence: 99%

“…The tool considers ParticleSwarmOptimization.dll, which is a shared library containing an implementation of the core version of the PSO. In the literature, Silvereye is used in the design optimization problems that are focusing on energy [14], micro climate [31] and structural [29].…”

Section: Silvereyementioning

confidence: 99%

“…RBFOpt library uses the radial basis function with local search while discovering satisfactory solutions with a small number of function evaluations. Opossum is used in several design problems to deal with daylight [34], structure [29,30] and energy [14].…”

Section: Opossummentioning

confidence: 99%

See 3 more Smart Citations

OPTIMUS: Self-Adaptive Differential Evolution with Ensemble of Mutation Strategies for Grasshopper Algorithmic Modeling

et al. 2019

View full text Add to dashboard Cite

Most of the architectural design problems are basically real-parameter optimization problems. So, any type of evolutionary and swarm algorithms can be used in this field. However, there is a little attention on using optimization methods within the computer aided design (CAD) programs. In this paper, we present Optimus, which is a new optimization tool for grasshopper algorithmic modeling in Rhinoceros CAD software. Optimus implements self-adaptive differential evolution algorithm with ensemble of mutation strategies (jEDE). We made an experiment using standard test problems in the literature and some of the test problems proposed in IEEE CEC 2005. We reported minimum, maximum, average, standard deviations and number of function evaluations of five replications for each function. Experimental results on the benchmark suite showed that Optimus (jEDE) outperforms other optimization tools, namely Galapagos (genetic algorithm), SilverEye (particle swarm optimization), and Opossum (RbfOpt) by finding better results for 19 out of 20 problems. For only one function, Galapagos presented slightly better result than Optimus. Ultimately, we presented an architectural design problem and compared the tools for testing Optimus in the design domain. We reported minimum, maximum, average and number of function evaluations of one replication for each tool. Galapagos and Silvereye presented infeasible results, whereas Optimus and Opossum found feasible solutions. However, Optimus discovered a much better fitness result than Opossum. As a conclusion, we discuss advantages and limitations of Optimus in comparison to other tools. The target audience of this paper is frequent users of parametric design modelling e.g., architects, engineers, designers. The main contribution of this paper is summarized as follows. Optimus showed that near-optimal solutions of architectural design problems can be improved by testing different types of algorithms with respect to no-free lunch theorem. Moreover, Optimus facilitates implementing different type of algorithms due to its modular system.

show abstract

Section: Current Optimization Tools In Grasshoppermentioning

confidence: 99%

Section: Goatmentioning

confidence: 99%

Section: Silvereyementioning

confidence: 99%

Section: Opossummentioning

confidence: 99%

See 2 more Smart Citations

OPTIMUS: Self-Adaptive Differential Evolution with Ensemble of Mutation Strategies for Grasshopper Algorithmic Modeling

et al. 2019

View full text Add to dashboard Cite

show abstract

“…Nowadays, the artificial neural network based modeling has been widely implemented in the building energy performance optimization. Waibel et al . investigated the effectiveness of different black‐box optimization algorithms on the single‐objective optimization problem, such as the randomized, deterministic, and model‐based algorithms, from perspectives of convergence times, stability, and robustness.…”

Section: Introductionmentioning

confidence: 99%

Numerical Study on the Thermal and Optical Performances of an Aerogel Glazing System with the Multivariable Optimization Using an Advanced Machine Learning Algorithm

Zheng

Zhou

2019

Advcd Theory and Sims

View full text Add to dashboard Cite

The implementation of advanced materials in high‐efficient glazing system is important for green buildings. In this study, aerogel granules are implemented in the glazing system to form a translucent window with super‐insulating performance. An experimentally validated numerical modeling integrating both heat transfer model and optical model is developed to characterize the sophisticated heat transfer and solar radiation transmission mechanisms. Sensitivity analysis is presented with quantifiable contribution ratio of each parameter to the total heat gain. Instead of returning back to numerical modeling repeatedly, an advanced optimization engine implemented with a generic optimization methodology with competitive computational efficiency and accuracy is proposed by implementing the supervised machine learning and advanced optimization algorithms. The research results show that the developed artificial neural network modeling is more accurate and computational‐efficient than the traditional lsqcurvefit fitting methodology. In addition, the optimal case through the teaching‐learning‐based optimization is more robust and competitive than the optimal case through the particle swarm optimization in terms of the total heat gain. This study presents an in‐depth understanding of heat transfer and solar radiation transmission of nanoporous aerogel granules together with a robust optimal design, which is important for the promotion of green buildings with high‐energy performance.

show abstract

AI for AEC: KI für Bauplanung und Bau

et al. 2022

Self Cite

View full text Add to dashboard Cite

Bei KI denkt man heute v. a. an Methoden des maschinellen Lernens und insbesondere an Deep Learning -maschinelles Lernen mit neuronalen Netzen, die aus vielen Lagen aufgebaut sind [1]. Fortschritte (1) im Vorhandensein von Trainingsdaten (z. B. durch das Internet und das Internet der Dinge), (2) in der zum Training nötigen Rechenkapazität (z. B. spezialisierte Grafikkarten und Rechenzentren in der Cloud) und (3) in der entsprechenden Datenverarbeitung (z. B. Open-Source-Pakete wie Tensorflow oder PyTorch) haben zu wichtigen Durchbrüchen mit diesem subsymbolischen, datengetriebenen Ansatz geführt. Allerdings werden in vielen Industrien schon länger symbolische, wissensgetriebene KI-Methoden wie Expertensysteme, Bahnplaner oder Produktionsplaner eingesetzt [2]. Insofern kann man zwei KI-Paradigmen unterscheiden: ein symbolisches, modellbasiertes und wissensgetriebenes Paradigma und ein subsymbolisches, funktionsbasiertes und datengetriebenes Paradigma.

show abstract

Building energy optimization: An extensive benchmark of global search algorithms

Cited by 85 publications

References 44 publications

OPTIMUS: Self-Adaptive Differential Evolution with Ensemble of Mutation Strategies for Grasshopper Algorithmic Modeling

OPTIMUS: Self-Adaptive Differential Evolution with Ensemble of Mutation Strategies for Grasshopper Algorithmic Modeling

Numerical Study on the Thermal and Optical Performances of an Aerogel Glazing System with the Multivariable Optimization Using an Advanced Machine Learning Algorithm

AI for AEC: KI für Bauplanung und Bau

Contact Info

Product

Resources

About