Graph-based deep learning for communication networks: A survey

Jiang, Weiwei

doi:10.1016/j.comcom.2021.12.015

Cited by 147 publications

(82 citation statements)

References 58 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The first direction is to extend the study of comparing the effect of external factors to the multivariate time series case, for example, load data collected in multiple locations, in which the spatial relationship can be extracted with the vector autoregression model or graph neural networks. 19,20 The second direction is to extend the external factors and compare them with weather information, for example, COVID-19 relevant information, which has been proven useful in load forecasting. 21…”

Section: Discussionmentioning

confidence: 99%

Deep learning based short‐term load forecasting incorporating calendar and weather information

Jiang

2022

Internet Technology Letters

Self Cite

View full text Add to dashboard Cite

Short-term load forecasting has been an important approach for economical and sustainable power systems. Various methods have been proposed for obtaining an accurate forecasting result, among which deep learning models achieve state-of-the-art performance. While external factors have been considered in the modeling of the load forecasting process, there is a lack of comparison between the effect of calendar and weather information. In this letter, a TCN-based load forecasting model incorporating calendar and weather information is proposed and outperforms three deep learning and four machine learning baselines on an open real-world load dataset, with and without leveraging the calendar or weather information. It is found that weather information is more helpful for improving the load forecasting performance than calendar information through numerical experiments.

show abstract

Section: Discussionmentioning

confidence: 99%

Deep learning based short‐term load forecasting incorporating calendar and weather information

Jiang

2022

Internet Technology Letters

Self Cite

View full text Add to dashboard Cite

show abstract

“…Key issues in employing these algorithms are outlined; however, the discussion on RA is limited only to those that are based on GNNs. The article [ 12 ] presents a more expansive view on the applications of GNNs by including problems in not just wireless, but also wired and software-defined networks. For each kind of network, the relevant problems and the types of GNNs are categorized.…”

Section: Motivationmentioning

confidence: 99%

“…It is also an appropriate instrument for solving these tasks, because wireless nodes and their parameters (type, frequency resources, location, transmission power and interference limits, and computational capabilities) can amply be represented as a graph. Some general communication problems that have utilized graph methods include (but are not limited to) RA and transmission power control in cellular networks, beamforming, link scheduling, traffic prediction, channel estimation, localization, cooperation and information transfer between vehicles for autonomous driving, compression of point clouds for transfer of images, UAV trajectory control for throughput maximization, detection of unauthorized traffic and of its sources, user association (UA), cooperative caching of data between D2D wireless nodes, wired networks configuration and communication delay analysis, and encrypted traffic classification [ 9 , 10 , 11 , 12 ].…”

Section: Introductionmentioning

confidence: 99%

Graph-Based Resource Allocation for Integrated Space and Terrestrial Communications

Ivanov

Tonchev

Poulkov

et al. 2022

Sensors

View full text Add to dashboard Cite

Resource allocation (RA) has always had a prominent place in wireless communications research due to its significance for network throughput maximization, and its inherent complexity. Concurrently, graph-based solutions for RA have also grown in importance, providing opportunities for higher throughput and efficiency due to their representational capabilities, as well as challenges for realizing scalable algorithms. This article presents a comprehensive review and analysis of graph-based RA methods in three major wireless network types: cellular homogeneous and heterogeneous, device-to-device, and cognitive radio networks. The main design characteristics, as well as directions for future research, are provided for each of these categories. On the basis of this review, the concept of Graph-based Resource allocation for Integrated Space and Terrestrial communications (GRIST) is proposed. It describes the inter-connectivity and coexistence of various terrestrial and non-terrestrial networks via a hypergraph and its attributes. In addition, the implementation challenges of GRIST are explained in detail. Finally, to complement GRIST, a scheme for determining the appropriate balance between different design considerations is introduced. It is described via a simplified complete graph-based design process for resource management algorithms.

show abstract

“…While estimating the traffic information can only give us the historical states, the aim of traffic prediction is to predict the future situation based on the historical input and adopt appropriate measures accordingly, e.g., traffic control. Various methods have been proposed for traffic estimation and prediction tasks, including statistical models, machine learning models, and deep-learning models, in which deep-learning models are becoming dominant because they show the best performance [12][13][14][15]. The success of deep-learning models is partially attributed to big data because these models rely on a large training dataset.…”

Section: Introductionmentioning

confidence: 99%

Big Data for Traffic Estimation and Prediction: A Survey of Data and Tools

Jiang

Luo

2022

ASI

Self Cite

View full text Add to dashboard Cite

Big data have been used widely in many areas, including the transportation industry. Using various data sources, traffic states can be well estimated and further predicted to improve the overall operation efficiency. Combined with this trend, this study presents an up-to-date survey of open data and big data tools used for traffic estimation and prediction. Different data types are categorized, and off-the-shelf tools are introduced. To further promote the use of big data for traffic estimation and prediction tasks, challenges and future directions are given for future studies.

show abstract

Graph-based deep learning for communication networks: A survey

Cited by 147 publications

References 58 publications

Deep learning based short‐term load forecasting incorporating calendar and weather information

Deep learning based short‐term load forecasting incorporating calendar and weather information

Graph-Based Resource Allocation for Integrated Space and Terrestrial Communications

Big Data for Traffic Estimation and Prediction: A Survey of Data and Tools

Contact Info

Product

Resources

About