Times series forecasting for urban building energy consumption based on graph convolutional network

Hu, Yuqing; Cheng, Xiaoyuan; Wang, Suhang; Chen, Jianli; Zhao, Tianxiang; Dai, Enyan

doi:10.1016/j.apenergy.2021.118231

Cited by 38 publications

(13 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The basic idea of GNNs is that the representation of each node in a graph is determined by its own features and the aggregation of the features of its neighbouring nodes through edges. GNNs have better performance in processing relationships among nodes (Hu et al, 2022), while traditional deep learning approaches, such as CNNs and RNNs, assume that nodes are independent of each other and ignore the topological information (Wu et al, 2021b). There are three types of tasks that GNNs can perform:…”

Section: Graph Neural Network (Gnns)mentioning

confidence: 99%

“…In addition to point cloud semantic segmentation, GNNs are also applied to the prediction of building energy consumption. Hu et al (2022) mapped the relationships of building shadows into a directed dynamic graph, in which buildings are regarded as nodes, and shadows cast from one building to another are regarded as edges. The edge attributes reflect the solar impact, and the edge attributes represent the features of buildings and weather.…”

Section: Planningmentioning

confidence: 99%

“…GNNs have been widely applied to chemistry, biology, recommendation systems, traffic networks, etc (Zhou et al, 2020). Some studies in the AEC sector also investigated the applications of GNNs such as BIM segmentation enrichment (Wang et al, 2022), point cloud semantic segmentation (Feng et al, 2021), and prediction of building energy consumption (Hu et al, 2022). However, the adoption of GNNs in AEC is still in its infancy.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Graph neural networks in building life cycle: a review

Yilong¹,

Wang²,

Reza³

et al. 2022

Proceedings of the 2022 European Conference on Computing in Construction

View full text Add to dashboard Cite

Graph neural networks (GNNs) have attracted much attention in the field of machine learning because of their excellent performance on graph data. Graph data in the architecture, engineering and construction (AEC) sector is very common, such as bubble diagrams for space planning and point clouds for scan-to-BIM models. Some studies in AEC have adopted GNNs to solve practical problems. However, there has been a limited focus on the outcomes of these studies. Therefore, this paper aims to review the applications of GNNs in the building lifecycle. A wide range of existing literature was retrieved. The result shows that the adoption of GNNs is still in its infancy but has been increasing dramatically in recent years. Ten application domains were identified from the planning stage to the operation stage. In addition, the challenges and opportunities of GNNs adoption in AEC were discussed providing directions for future research.

show abstract

Section: Graph Neural Network (Gnns)mentioning

confidence: 99%

Section: Planningmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Graph neural networks in building life cycle: a review

Yilong¹,

Wang²,

Reza³

et al. 2022

Proceedings of the 2022 European Conference on Computing in Construction

View full text Add to dashboard Cite

show abstract

“…The recent interest in urban building energy modeling continues to increase [9]. UBEMs are also supportive for the design of energy efficient cities when used effectively [10]. However, current approaches have limitations in representing a realistic UBEM and assessing energy use for these scales.…”

Section: Introductionmentioning

confidence: 99%

A comprehensive survey of the urban building energy modeling (UBEM) process and approaches

Yakut

ESEN

2023

International Journal of Energy Studies

View full text Add to dashboard Cite

Fossil fuels increase the emission values of greenhouse gases such as CO2 in the atmosphere and cause global warming and climate change. At the same time, fossil fuel reserves are facing depletion in the near future, and energy supply also has an important dimension such as national security and foreign dependency. All these show that turning to renewable energy sources and developing solutions and policies for energy saving has become a necessity both globally and locally. For such reasons, modeling of urban structures, which have a great contribution to energy consumption, and simulating the energy demand on an urban scale are of great importance for the effective use of energy. Research on this has shown that UBEM (Urban Building Energy Modeling) is an effective solution to these problems. However, UBEM contains different technical problems for implementation. Due to its versatility, various concepts related to this field lead to complexity. With this increasing complexity, there is a growing need to compile concepts from a holistic perspective. In this study, it is aimed to create a solution to these challenges. For this purpose, a comprehensive and up-to-date research of various modeling approaches and model creation process used in urban building energy modeling has been conducted. Studies on these approaches are summarized and a systematic review of the literature is made. At the same time, the study is in the nature of guiding and forming the general knowledge level with the basic concepts that should be known to those who will work on UBEM.

show abstract

“…In the energy industry, energy conservation is one of the crucial issues of the 21st century [11]. Recently, the application of AI and ML approaches to provide solutions to complex engineering problems has received considerable attention in the energy industry [12], [13], [14], [15], due to their successful application in various areas, including, electricity demand and consumption forecasting [16], [17], [18]; controlling room temperature to minimize electricity cost [19]; forecasting building energy consumption [20]; providing explicit demand response from domestic boilers [21]; and, evaluating energy efficiency parameters [22]. Despite the successful application of AI and ML approaches in the energy industry, there are comparatively fewer studies utilizing AI and ML techniques to predict the deliverability of natural gas storage in depleted reservoirs.…”

Section: Introductionmentioning

confidence: 99%