Mobile Data Traffic Prediction by Exploiting Time-Evolving User Mobility Patterns

Sun, Fengyuan; Wang, Pinghui; Zhao, Junzhou; Xu, Nuo; Zeng, Juxiang; Tao, Jing; Song, Kaikai; Deng, Chao; Lui, John C. S.; Guan, Xiaohong

doi:10.1109/tmc.2021.3079117

Cited by 21 publications

(12 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…NETS prediction. The problem of NETS prediction has been studied extensively in various contexts; see [3,5,9,11,15,22,30,34,38,39,42,44] and references therein. Its extension to tenor-valued NETS has also been considered [6,13,16].…”

Section: Related Workmentioning

confidence: 99%

“…Most existing methods require complete data for training. They typically use GCN [18] to capture inter-time series correlations, and variants of CNN [37] or RNN [32] to capture temporal correlations [3,9,11,15,22,30,34,38,39,42]. For the tensor-valued extension, [16] proposes Tensor GCN and Tensor RNN.…”

Section: Related Workmentioning

confidence: 99%

“…An important task in such applications is to predict the future values of a NETS based on its historical values and the underlying graph. This has been studied extensively and many prediction methods have been proposed in various contexts; see [3,5,9,11,15,22,30,34,38,39,42,44] and references therein. Most of these methods use deep learning and require complete data for training [3,9,11,15,22,30,34,38,39,42].…”

Section: Introductionmentioning

confidence: 99%

“…This has been studied extensively and many prediction methods have been proposed in various contexts; see [3,5,9,11,15,22,30,34,38,39,42,44] and references therein. Most of these methods use deep learning and require complete data for training [3,9,11,15,22,30,34,38,39,42]. However, in real-world scenarios, it is not uncommon to have missing data due to sensor malfunction, incomplete sensing coverage, etc.…”

Section: Introductionmentioning

confidence: 99%

“…Existing methods typically use GCN [18] to capture inter-time series correlations, and variants of Convolutional Neural Network (CNN) [37] or Recurrent Neural Network (RNN) [32] to capture temporal correlations, e.g. [3,9,11,15,22,30,34,38,39,42,44]. However, these networks are not designed for incomplete data.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Networked Time Series Prediction with Incomplete Data

Zhu¹,

Zhang²,

Jiang³

et al. 2021

Preprint

View full text Add to dashboard Cite

A networked time series (NETS) is a family of time series on a given graph, one for each node. It has found a wide range of applications from intelligent transportation, environment monitoring to mobile network management. An important task in such applications is to predict the future values of a NETS based on its historical values and the underlying graph. Most existing methods require complete data for training. However, in real-world scenarios, it is not uncommon to have missing data due to sensor malfunction, incomplete sensing coverage, etc. In this paper, we study the problem of NETS prediction with incomplete data. We propose NETS-ImpGAN, a novel deep learning framework that can be trained on incomplete data with missing values in both history and future. Furthermore, we propose novel Graph Temporal Attention Networks by incorporating the attention mechanism to capture both inter-time series correlations and temporal correlations. We conduct extensive experiments on three real-world datasets under different missing patterns and missing rates. The experimental results show that NETS-ImpGAN outperforms existing methods except when data exhibit very low variance, in which case NETS-ImpGAN still achieves competitive performance.

show abstract