Thinking of Green, Low Carbon, and Energy-Saving Designs Based on the Variable Ventilation of Natatoriums: Taking the Jiading Natatorium of Tongji University as an Example DOI Open Access
Feng Qian,

Zedao Shi,

Li Yang

et al.

Sustainability, Journal Year: 2024, Volume and Issue: 16(11), P. 4476 - 4476

Published: May 24, 2024

With the increasing demand for sports activities, architecture is flourishing. Creating a comfortable and healthy fitness environment while reducing energy consumption has become focus architects. Taking Jiading Natatorium at Tongji University in Shanghai as an example, this study researched green variable ventilation of venues. The Autodesk Ecotect Analysis 2011 was used to conduct computational fluid dynamics (CFD) simulation analyses on four scenarios opening closing swimming pool’s roof, with velocity primary evaluation indicator assess each scenario. relationship between ratio roof buildings explored. results showed that when 37.5%, it achieves good effectiveness avoids excessive wind pressure. also summarized six common forms structures compared differences environments different forms. indicated shape decisive impact distribution indoor speed buildings. Six optimal ratios summer suitable site conditions were summarized, providing reference design selection pool roofs. Furthermore, types trend gradually becoming uniform increase area. However, position peak related form size opening. This research provides valuable references low carbon energy-efficient future

Language: Английский

Residential building energy consumption estimation: A novel ensemble and hybrid machine learning approach DOI
Behnam Sadaghat, Sadegh Afzal,

Ali Javadzade Khiavi

et al.

Expert Systems with Applications, Journal Year: 2024, Volume and Issue: 251, P. 123934 - 123934

Published: April 18, 2024

Language: Английский

Citations

19
Load Forecasting with Machine Learning and Deep Learning Methods DOI Creative Commons
Moisés Cordeiro-Costas, Daniel Villanueva, Pablo Eguía

et al.

Applied Sciences, Journal Year: 2023, Volume and Issue: 13(13), P. 7933 - 7933

Published: July 6, 2023

Characterizing the electric energy curve can improve efficiency of existing buildings without any structural change and is basis for controlling optimizing building performance. Artificial Intelligence (AI) techniques show much potential due to their accuracy malleability in field pattern recognition, using these models it possible adjust services real time. Thus, objective this paper determine AI technique that best forecasts electrical loads. The suggested are random forest (RF), support vector regression (SVR), extreme gradient boosting (XGBoost), multilayer perceptron (MLP), long short-term memory (LSTM), temporal convolutional network (Conv-1D). conducted research applies a methodology considers bias variance models, enhancing robustness most suitable modeling forecasting electricity consumption buildings. These evaluated single-family dwelling located United States. performance comparison obtained by analyzing 10-fold cross-validation technique. By means evaluation different sets, i.e., validation test capacity reproduce results ability properly forecast on future occasions also evaluated. model with less dispersion, both set set, LSTM. It presents errors −0.02% nMBE 2.76% nRMSE −0.54% 4.74% set.

Language: Английский

Citations

41
Optimizing the sustainable performance of public buildings: A hybrid machine learning algorithm DOI
Wen Xu,

Xianguo Wu,

Shishu Xiong

et al.

Energy, Journal Year: 2025, Volume and Issue: unknown, P. 135283 - 135283

Published: Feb. 1, 2025

Language: Английский

Citations

1
Building energy performance prediction: A reliability analysis and evaluation of feature selection methods DOI
Razak Olu-Ajayi, Hafiz Alaka, Ismail Sulaimon

et al.

Expert Systems with Applications, Journal Year: 2023, Volume and Issue: 225, P. 120109 - 120109

Published: April 15, 2023

Language: Английский

Citations

22
Predicting the PCM-incorporated building's performance using optimized linear kernel and tree-based machine learning methods DOI

Kashif Nazir,

Shazim Ali Memon, Assemgul Saurbayeva

et al.

Journal of Energy Storage, Journal Year: 2024, Volume and Issue: 94, P. 112495 - 112495

Published: June 16, 2024

Language: Английский

Citations

6
Energy Consumption Prediction Model for Smart Homes via Decentralized Federated Learning With LSTM DOI
Dawid Połap, Gautam Srivastava, Antoni Jaszcz

et al.

IEEE Transactions on Consumer Electronics, Journal Year: 2023, Volume and Issue: 70(1), P. 990 - 999

Published: Oct. 19, 2023

The rapid pace of development the Internet Things and requirements various devices have allowed us to perform calculations at edge, especially in terms consumer electronics. Such progress makes it possible design new solutions for energy distribution prediction smart homes. In this paper, we propose a solution that can be used optimize by analyzing demand individual proposed methodology is based on edge technology, where dedicated LSTM network with multi-head self-attention trained measurement data from different sensors predicting demand. Training extended decentralized learning process an additional aggregation decision module (that allows rejection model case worst adaptation private data). order increase security, added blockchain Byzantine strategy Proof Stake (PoS) consensus. was tested publicly available database demonstrate possibilities advantages such architecture.

Language: Английский

Citations

15
Thermal energy simulation of the building with heating tube embedded in the wall in the presence of different PCM materials DOI
Talal Obaid Alshammari, Sayed Fayaz Ahmad, Mohamad Abou Houran

et al.

Journal of Energy Storage, Journal Year: 2023, Volume and Issue: 73, P. 109134 - 109134

Published: Oct. 10, 2023

Language: Английский

Citations

13
Advanced Energy Performance Modelling: Case Study of an Engineering and Technology Precinct DOI Creative Commons
Faham Tahmasebinia, Lin Lin,

Shuo Wu

et al.

Buildings, Journal Year: 2024, Volume and Issue: 14(6), P. 1774 - 1774

Published: June 12, 2024

The global demand for energy is significantly impacted by the consumption patterns within building sector. As such, importance of simulation and prediction growing exponentially. This research leverages Building Information Modelling (BIM) methodologies, creating a synergy between traditional software methods algorithm-driven approaches comprehensive analysis. study also proposes method monitoring select management factors, step that could potentially pave way integration digital twins in systems. grounded case newly constructed educational New South Wales, Australia. physical model was created using Autodesk Revit, conventional BIM methodology. EnergyPlus, facilitated OpenStudio, employed software-based analysis output then used to develop preliminary algorithm models regression strategies Python. In this analysis, temperature relative humidity each unit were as independent variables, with their being dependent variable. sigmoid model, known its accuracy interpretability, advanced simulation. combined sensor data real-time prediction. A basic twin (DT) example simulate dynamic control air conditioning lighting, showcasing adaptability effectiveness system. explores potential machine learning, specifically reinforcement optimizing response environmental changes usage conditions. Despite current limitations, identifies future directions. These include enhancing developing complex algorithms boost efficiency reduce costs.

Language: Английский

Citations

4
Performance optimization of high-rise residential buildings in cold regions considering energy consumption DOI Creative Commons

Liwei Song

Deleted Journal, Journal Year: 2025, Volume and Issue: 7(2)

Published: Jan. 27, 2025

Language: Английский

Citations

0
Hybrid feature-based neural network regression method for load profiles forecasting DOI Creative Commons

Aidos Satan,

Nurkhat Zhakiyev, Aliya Nugumanova

et al.

Energy Informatics, Journal Year: 2025, Volume and Issue: 8(1)

Published: Feb. 10, 2025

This study addresses the critical need for improved demand forecasting models that can accurately predict energy consumption, particularly in context of varying geographical and climatic conditions. The work introduces a novel model integrates clustering techniques feature engineering into neural network regression, with specific focus on incorporating correlations air temperature. Evaluation model's efficacy utilized benchmark dataset from Tetouan, Morocco, where existing methods yielded RMSE values ranging 6429 to 10,220 [MWh]. In contrast, proposed approach achieved significantly lower 5168, indicating its superiority. Subsequent application forecast Astana, Kazakhstan, as case study, showcased further. Comparative analysis against baseline method revealed notable improvement, exhibiting MAPE 5.19% compared baseline's 17.36%. These findings highlight potential enhance accuracy, across diverse contexts, by leveraging climate-related inputs, methodology also demonstrates broader applications, such flood forecasting, agricultural yield prediction, or water resource management.

Language: Английский

Citations

0