Abstract
Data-driven mobile network management hinges on accurate traffic measurements, which routinely require expensive specialized equipment and substantial local storage capabilities, and bear high data transfer overheads. To overcome these challenges, in this paper we propose Spider, a deep-learningdriven mobile traffic measurement collection and reconstruction framework, which reduces the cost of data collection while retaining state-of-the-art accuracy in inferring mobile traffic consumption with fine geographic granularity. Spider harnesses Reinforcement Learning and tackles large action spaces to train a policy network that selectively samples a minimal number of cells where data should be collected. We further introduce a fast and accurate neural model that extracts spatiotemporal correlations from historical data to reconstruct network-wide traffic consumption based on sparse measurements. Experiments we conduct with a real-world mobile traffic dataset demonstrate that Spider samples 48% fewer cells as compared to several benchmarks considered, and yields up to 67% lower reconstruction errors than state-of-the-art interpolation methods. Moreover, our framework can adapt to previously unseen traffic patterns.
Original language | English |
---|---|
Title of host publication | IEEE Global Communications Conference (GLOBECOM) |
Publisher | Institute of Electrical and Electronics Engineers |
Number of pages | 6 |
ISBN (Electronic) | 978-1-7281-8104-2 |
ISBN (Print) | 978-1-7281-8105-9 |
DOIs | |
Publication status | Published - 2 Feb 2022 |
Event | 2021 IEEE Global Communications Conference - Madrid, Spain Duration: 7 Dec 2021 → 11 Dec 2021 https://globecom2021.ieee-globecom.org/ |
Publication series
Name | IEEE Conference and Exhibition on Global Telecommunications (GLOBECOM) |
---|---|
Publisher | IEEE |
ISSN (Print) | 1930-529X |
ISSN (Electronic) | 2576-6813 |
Conference
Conference | 2021 IEEE Global Communications Conference |
---|---|
Abbreviated title | GLOBECOM 2021 |
Country/Territory | Spain |
City | Madrid |
Period | 7/12/21 → 11/12/21 |
Internet address |