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

Telecommunication networks play a critical role in modern society. With thearrival of 5G networks, these systems are becoming even more diversified,integrated, and intelligent. Traffic forecasting is one of the key componentsin such a system, however, it is particularly challenging due to the complexspatial-temporal dependency. In this work, we consider this problem from theaspect of a cellular network and the interactions among its base stations. Wethoroughly investigate the characteristics of cellular network traffic and shedlight on the dependency complexities based on data collected from a denselypopulated metropolis area. Specifically, we observe that the traffic shows bothdynamic and static spatial dependencies as well as diverse cyclic temporalpatterns. To address these complexities, we propose an effectivedeep-learning-based approach, namely, Spatio-Temporal Hybrid GraphConvolutional Network (STHGCN). It employs GRUs to model the temporaldependency, while capturing the complex spatial dependency through a hybrid-GCNfrom three perspectives: spatial proximity, functional similarity, and recenttrend similarity. We conduct extensive experiments on real-world trafficdatasets collected from telecommunication networks. Our experimental resultsdemonstrate the superiority of the proposed model in that it consistentlyoutperforms both classical methods and state-of-the-art deep learning models,while being more robust and stable.

Spatio-Temporal Hybrid Graph Convolutional Network for Traffic Forecasting in Telecommunication Networks