English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Cellular traffic prediction is an indispensable part for intelligenttelecommunication networks. Nevertheless, due to the frequent user mobility andcomplex network scheduling mechanisms, cellular traffic often inheritscomplicated spatial-temporal patterns, making the prediction incrediblychallenging. Although recent advanced algorithms such as graph-based predictionapproaches have been proposed, they frequently model spatial dependencies basedon static or dynamic graphs and neglect the coexisting multiple spatialcorrelations induced by traffic generation. Meanwhile, some works lack theconsideration of the diverse cellular traffic patterns, result in suboptimalprediction results. In this paper, we propose a novel deep learning networkarchitecture, Adaptive Hybrid Spatial-Temporal Graph Neural Network (AHSTGNN),to tackle the cellular traffic prediction problem. First, we apply adaptivehybrid graph learning to learn the compound spatial correlations among celltowers. Second, we implement a Temporal Convolution Module with multi-periodictemporal data input to capture the nonlinear temporal dependencies. Inaddition, we introduce an extra Spatial-Temporal Adaptive Module to conquer theheterogeneity lying in cell towers. Our experiments on two real-world cellulartraffic datasets show AHSTGNN outperforms the state-of-the-art by a significantmargin, illustrating the superior scalability of our method forspatial-temporal cellular traffic prediction.

Adaptive Hybrid Spatial-Temporal Graph Neural Network for Cellular Traffic Prediction