Optimization and prediction in the early design stage of office buildings using genetic and XGBoost algorithms

Article Computer Science, Artificial Intelligence

Highly accurate energy consumption forecasting model based on parallel LSTM neural networks

Ning Jin et al.

Summary: The study introduces a novel hybrid AI-enhanced forecasting model for energy consumption by combining SSA and PLSTM, which outperforms existing models in terms of prediction accuracy and computational efficiency.

ADVANCED ENGINEERING INFORMATICS (2022)

添加到收藏夹

Article Construction & Building Technology

Key control variables affecting interior visual comfort for automated louver control in open-plan office -- a study using machine learning

Zhaoyang Luo et al.

Summary: This paper comprehensively analyzes the importance of control-related variables for machine learning-assisted automated louvers in open-plan offices and provides an efficient but compact set of control variables.

BUILDING AND ENVIRONMENT (2022)

添加到收藏夹

Article Thermodynamics

Federated learning-based short-term building energy consumption prediction method for solving the data silos problem

Junyang Li et al.

Summary: The study introduces a federated learning-based method to learn transferable knowledge from building operational data without leaking privacy. The federated model outperforms the standalone model in prediction accuracy and training time, providing a solution for the data silos problem in building energy management.

BUILDING SIMULATION (2022)

添加到收藏夹

Article Computer Science, Theory & Methods

Collaborative deep learning framework on IoT data with bidirectional NLSTM neural networks for energy consumption forecasting

Ke Yan et al.

Summary: Energy consumption forecasting based on IoT data and deep learning algorithm is improved through a sophisticated multi-channel bidirectional nested LSTM framework combined with discrete stationary wavelet transform. Experimental results show the superior performance of the proposed method.

JOURNAL OF PARALLEL AND DISTRIBUTED COMPUTING (2022)

添加到收藏夹

Article Construction & Building Technology

A metamodel for building information modeling-building energy modeling integration in early design stage

M. K. Bracht et al.

Summary: This study describes the development and validation of a tool that integrates BIM and metamodels to predict thermal load of dwellings through gbXML, showing its feasibility. However, inconsistencies in gbXML files from different BIM authoring tools were observed, requiring manual adjustments. This highlights the importance of standardized exportation tools for open interoperability formats by software manufacturers.

AUTOMATION IN CONSTRUCTION (2021)

添加到收藏夹

Article Construction & Building Technology

Multi-objective optimization (MOO) for high-rise residential buildings' layout centered on daylight, visual, and outdoor thermal metrics in China

ShanShan Wang et al.

Summary: Nowadays, building performance optimization has been extended to urban planning Multi-Objective Optimization (MOO). This paper proposes a method to optimize visual comfort and outdoor thermal performances in the layout of high-rise residential buildings by integrating different building performance areas. By using an Artificial Neural Network (ANN) and conducting MOO, integrated solutions for building layouts can be found, leading to significant improvements in performance compared to baseline cases.

BUILDING AND ENVIRONMENT (2021)

添加到收藏夹

Article Construction & Building Technology

An architectural building cluster morphology generation method to perceive, derive, and form based on cyborg-physical wind tunnel (CPWT)

Philip F. Yuan et al.

Summary: This paper introduces the impact of rapid deduction based on environmental data on conceptual design decisions and presents a new cyborg-physical wind tunnel (CPWT) design platform, which combines a customized physical wind tunnel with an optimization algorithm to quickly derive a large amount of data for evaluation and prediction. The experimental results demonstrate that the CPWT is able to provide a more rapid and accurate method for wind environment performance-based design.

BUILDING AND ENVIRONMENT (2021)

添加到收藏夹

Article Green & Sustainable Science & Technology

A deep learning framework for building energy consumption forecast

Nivethitha Somu et al.

Summary: This study introduces a deep learning framework called kCNN-LSTM for accurate building energy consumption forecasts, utilizing k-means clustering, Convolutional Neural Networks (CNN), and Long Short Term Memory (LSTM) neural networks. The efficiency and applicability of kCNN-LSTM were demonstrated using real-time building energy consumption data, showing its suitability for energy consumption forecast problems through comparison with state-of-the-art models and observation of its ability to learn spatio-temporal dependencies in energy consumption data.

RENEWABLE & SUSTAINABLE ENERGY REVIEWS (2021)

添加到收藏夹

Article Construction & Building Technology

Proposal of a new automated workflow for the computational performance-driven design optimization of building energy need and construction cost

Diana D'Agostino et al.

Summary: This study aims to improve designers' control over thermal and geometric variables of buildings in the early stages of the design process through early building performance analysis, in order to obtain optimized building designs from multiple perspectives.

ENERGY AND BUILDINGS (2021)

添加到收藏夹

Article Construction & Building Technology

Design subspace learning: Structural design space exploration using performance-conditioned generative modeling

Renaud Danhaive et al.

Summary: Designers increasingly rely on parametric design studies, but manual design variations and optimization methods have limitations. Integrating conditional variational autoencoders into a performance-driven design exploration framework can help designers effectively explore high-performing design options.

AUTOMATION IN CONSTRUCTION (2021)

添加到收藏夹

Article Construction & Building Technology

Predictive models for daylight performance of general floorplans based on CNN and GAN: A proof-of-concept study

Qiushi He et al.

Summary: This study proposes proxy models for daylight simulation for general floorplans based on convolutional neural network and generative adversarial network, which show promise in predicting daylight metrics and illuminance distribution and providing real-time feedback for designers. The experiments demonstrate the potential of using deep neural networks for feature extraction from general building forms and building predictive models to aid in automatic form-finding and design optimization.

BUILDING AND ENVIRONMENT (2021)

添加到收藏夹

Article Construction & Building Technology

Developing a parametric morphable annual daylight prediction model with improved generalization capability for the early stages of office building design

Yunsong Han et al.

Summary: Early building design decisions significantly affect the daylight performance of office buildings, with machine learning models being used to reduce prediction time. The study introduces an artificial neural network-based modeling approach to predict annual daylight performance, proposing a workflow for developing a model with higher generalization capability.

BUILDING AND ENVIRONMENT (2021)

添加到收藏夹

Article Construction & Building Technology

CM-210903-4973158 MOOSAS-A systematic solution for multiple objective building performance optimization in the early design stage

Borong Lin et al.

Summary: This study presents a systematic solution to the critical issues in building performance optimization (BPO) process in the early design stage, including model integration, real-time performance analysis, and interactive optimization design. The development of a multi-objective BPO design software, MOOSAS, enables real-time performance feedback, dynamic parameter analysis, and interactive optimization, improving optimization efficiency and result satisfaction.

BUILDING AND ENVIRONMENT (2021)

添加到收藏夹

Article Construction & Building Technology

A metamodel based on intermediary features for daylight performance prediction of facade design

Chuan-Hsuan Lin et al.

Summary: Recent studies have developed a novel daylight prediction model by converting design models into intermediary features as input parameters, allowing for a wider range of applicability. The proposed model demonstrated good performance in predicting daylight performance of different types of facades and showed potential for significant time savings in daylighting evaluation compared to traditional simulation methods.

BUILDING AND ENVIRONMENT (2021)

添加到收藏夹

Article Construction & Building Technology

Occupancy-based energy consumption modelling using machine learning algorithms for institutional buildings

Prashant Anand et al.

Summary: Occupancy information is crucial in modeling and predicting building energy use, but the correlation between occupancy and energy consumption varies among different space types under different time resolutions. The study found a weak correlation between occupants and energy use due to common plug and lighting loads. A Deep Neural Network model showed slightly better prediction accuracy than conventional machine learning models, but gradient boosting model was faster in computation time. The integrated model developed in this study will better equip building facility management for occupant-oriented control of building systems for energy efficiency.

ENERGY AND BUILDINGS (2021)

添加到收藏夹

Article Construction & Building Technology

Generative design and performance optimization of residential buildings based on parametric algorithm

Jingyu Zhang et al.

Summary: This study combines energy-efficient green design and artificial intelligence technology to develop a parametric generative algorithm for automatically generating design schemes of typical Chinese urban residences. Through a case study in Beijing, it was found that the parametric generative design can facilitate passive green design in the early stage and enhance energy efficiency.

ENERGY AND BUILDINGS (2021)

添加到收藏夹

Article Construction & Building Technology

Modular approach to multi-objective environmental optimization of buildings

Benedek Kiss et al.

AUTOMATION IN CONSTRUCTION (2020)

添加到收藏夹

Review Construction & Building Technology

Energy performance optimization of existing buildings: A literature review

Najme Hashempour et al.

SUSTAINABLE CITIES AND SOCIETY (2020)

添加到收藏夹

Article Energy & Fuels

Model predictive control with adaptive machine-learning-based model for building energy efficiency and comfort optimization

Shiyu Yang et al.

APPLIED ENERGY (2020)

添加到收藏夹

Article Construction & Building Technology

A novel comprehensive workflow for modelling outdoor thermal comfort and energy demand in urban canyons: Results and critical issues

Gianpiero Evola et al.

ENERGY AND BUILDINGS (2020)

添加到收藏夹

Article Construction & Building Technology

Multi-objective optimization of building retrofit in the Mediterranean climate by means of genetic algorithm application

Federica Rosso et al.

ENERGY AND BUILDINGS (2020)

添加到收藏夹

Article Computer Science, Information Systems

AI@ntiPhish - Machine Learning Mechanisms for Cyber-Phishing Attack

Yu-Hung Chen et al.

IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS (2019)

添加到收藏夹

Article Behavioral Sciences

Prediction of antiepileptic drug treatment outcomes of patients with newly diagnosed epilepsy by machine learning

Lijun Yao et al.

EPILEPSY & BEHAVIOR (2019)

添加到收藏夹

Article Green & Sustainable Science & Technology

Optimization of HVAC system energy consumption in a building using artificial neural network and multi-objective genetic algorithm

Nasruddin et al.

SUSTAINABLE ENERGY TECHNOLOGIES AND ASSESSMENTS (2019)

添加到收藏夹

Article Automation & Control Systems

Prediction of weld bead geometry of MAG welding based on XGBoost algorithm

Kai Chen et al.

INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY (2019)

添加到收藏夹

Article Construction & Building Technology

Developing window behavior models for residential buildings using XGBoost algorithm

Hao Mo et al.

ENERGY AND BUILDINGS (2019)

添加到收藏夹

Article Construction & Building Technology

LCA and BIM: Visualization of environmental potentials in building construction at early design stages

Martin Roeck et al.

BUILDING AND ENVIRONMENT (2018)

添加到收藏夹

Review Construction & Building Technology

Towards adoption of building energy simulation and optimization for passive building design: A survey and a review

Zhichao Tian et al.

ENERGY AND BUILDINGS (2018)

添加到收藏夹

Article Thermodynamics

Comparison of Support Vector Machine and Extreme Gradient Boosting for predicting daily global solar radiation using temperature and precipitation in humid subtropical climates: A case study in China

Junliang Fan et al.

ENERGY CONVERSION AND MANAGEMENT (2018)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Improved Random Forest for Classification

Angshuman Paul et al.

IEEE TRANSACTIONS ON IMAGE PROCESSING (2018)

添加到收藏夹

Article Construction & Building Technology

Window opening model using deep learning methods

Romana Markovic et al.

BUILDING AND ENVIRONMENT (2018)

添加到收藏夹

Article Energy & Fuels

Integrated Daylighting Design by Combining Passive Method with DaySim in a Classroom

Choul Woong Kwon et al.

ENERGIES (2018)

添加到收藏夹

Review Engineering, Multidisciplinary

Performance-based Generative Architecture Design: A Review on Design Problem Formulation and Software Utilization

Shenghuan Zhao et al.

JOURNAL OF INTEGRATED DESIGN & PROCESS SCIENCE (2018)

添加到收藏夹

Article Construction & Building Technology

Exploration of the Bayesian Network framework for modelling. window control behaviour

Verena M. Barthelmes et al.

BUILDING AND ENVIRONMENT (2017)

添加到收藏夹

Article Construction & Building Technology

Investigation of visual comfort metrics from subjective responses in China: A study in offices with daylight

Yu Bian et al.

BUILDING AND ENVIRONMENT (2017)

添加到收藏夹

Article Energy & Fuels

A short-term building cooling load prediction method using deep learning algorithms

Cheng Fan et al.

APPLIED ENERGY (2017)

添加到收藏夹

Article Energy & Fuels

Shape optimization of free-form buildings based on solar radiation gain and space efficiency using a multi-objective genetic algorithm in the severe cold zones of China

Longwei Zhang et al.

SOLAR ENERGY (2016)

添加到收藏夹

Article Thermodynamics

Daylight factor estimation at an early design stage to reduce buildings' energy consumption due to artificial lighting: A numerical approach based on Doehlert and Box-Behnken designs

Lazaros Elias Mavromatidis et al.

ENERGY (2014)

添加到收藏夹

Article Construction & Building Technology

Assessing gaps and needs for integrating building performance optimization tools in net zero energy buildings design

Shady Attia et al.

ENERGY AND BUILDINGS (2013)

添加到收藏夹

Article Geography

AN INTRODUCTION TO THE UNIVERSAL THERMAL CLIMATE INDEX (UTCI)

Krzysztof Blazejczyk et al.

GEOGRAPHIA POLONICA (2013)

添加到收藏夹

Article Biophysics

Deriving the operational procedure for the Universal Thermal Climate Index (UTCI)

Peter Broede et al.

INTERNATIONAL JOURNAL OF BIOMETEOROLOGY (2012)

添加到收藏夹

Optimization and prediction in the early design stage of office buildings using genetic and XGBoost algorithms

相关参考文献

导出引文

分享论文