Multi-Building Energy Forecasting Through Weather-Integrated Temporal Graph Neural Networks DOI Creative Commons
Samuel Moveh,

Emmanuel Alejandro Merchán-Cruz,

Maher Abuhussain

et al.

Buildings, Journal Year: 2025, Volume and Issue: 15(5), P. 808 - 808

Published: March 3, 2025

While existing building energy prediction methods have advanced significantly, they face fundamental challenges in simultaneously modeling complex spatial–temporal relationships between buildings and integrating dynamic weather patterns, particularly dense urban environments where interactions significantly impact consumption patterns. This study presents an deep learning system combining temporal graph neural networks with data parameters to enhance accuracy across diverse types through innovative modeling. approach integrates LSTM layers convolutional networks, trained using from 150 commercial over three years. The incorporates spatial a weighted adjacency matrix considering proximity operational similarities, while are integrated via specialized network component. Performance evaluation examined normal operations, gaps, seasonal variations. results demonstrated 3.2% mean absolute percentage error (MAPE) for 15 min predictions 4.2% MAPE 24 h forecasts. showed robust recovery, maintaining 95.8% effectiveness even 30% missing values. Seasonal analysis revealed consistent performance conditions (MAPE: 3.1–3.4%). achieved 33.3% better compared conventional methods, 75% efficiency four GPUs. These findings demonstrate the of prediction, providing valuable insights management systems planning. system’s scalability make it suitable practical applications smart sustainability.

Language: Английский

A Smart Roller Shutters Control for Enhancing Thermal Comfort and Sustainable Energy Efficiency in Office Buildings DOI Open Access
Chaima Magraoui, Lotfi Derradji,

Abdelkader Hamid

et al.

Sustainability, Journal Year: 2025, Volume and Issue: 17(5), P. 2116 - 2116

Published: Feb. 28, 2025

This work focuses on the impact of different types glazing and dynamic control shading using roller shutters thermal comfort energy consumption office buildings. Shading systems is based solar radiation outdoor temperature during winter period adapted to Algerian climatic context. The main objective evaluate efficiency strategies in reducing heating demands CO2 emissions. research was conducted experimentally numerically TRNSYS 17 (Transient System Simulation Program). A validation done prototype building then a parametric study aimed at verifying influence various parameters, including type, climate, proposed scenarios or both demand comfort. Different were reduce environmental impact. obtained results demonstrate that are beneficial even highlight effectiveness controlling compared for studied regions standard building. approach achieves reductions up 21% consumption, along with significant decrease carbon footprint, contributing sustainability management

Language: Английский

Citations

0
Multi-Building Energy Forecasting Through Weather-Integrated Temporal Graph Neural Networks DOI Creative Commons
Samuel Moveh,

Emmanuel Alejandro Merchán-Cruz,

Maher Abuhussain

et al.

Buildings, Journal Year: 2025, Volume and Issue: 15(5), P. 808 - 808

Published: March 3, 2025

While existing building energy prediction methods have advanced significantly, they face fundamental challenges in simultaneously modeling complex spatial–temporal relationships between buildings and integrating dynamic weather patterns, particularly dense urban environments where interactions significantly impact consumption patterns. This study presents an deep learning system combining temporal graph neural networks with data parameters to enhance accuracy across diverse types through innovative modeling. approach integrates LSTM layers convolutional networks, trained using from 150 commercial over three years. The incorporates spatial a weighted adjacency matrix considering proximity operational similarities, while are integrated via specialized network component. Performance evaluation examined normal operations, gaps, seasonal variations. results demonstrated 3.2% mean absolute percentage error (MAPE) for 15 min predictions 4.2% MAPE 24 h forecasts. showed robust recovery, maintaining 95.8% effectiveness even 30% missing values. Seasonal analysis revealed consistent performance conditions (MAPE: 3.1–3.4%). achieved 33.3% better compared conventional methods, 75% efficiency four GPUs. These findings demonstrate the of prediction, providing valuable insights management systems planning. system’s scalability make it suitable practical applications smart sustainability.

Language: Английский

Citations

0