Abstract
Forecasting with high accuracy the volume of data traffic that mobile users will consume is becoming increasingly important for precision traffic engineering, demand-aware network resource allocation, as well as public transportation. Measurements collection in dense urban deployments is however complex and expensive, and the post-processing required to make predictions is highly non-trivial, given the intricate spatio-temporal variability of mobile traffic due to user mobility. To overcome these challenges, in this paper we harness the exceptional feature extraction abilities of deep learning and propose a Spatio-Temporal neural Network (STN) architecture purposely designed for precise network-wide mobile traffic forecasting. We present a mechanism that fine tunes the STN and enables its operation with only limited ground truth observations. We then introduce a Double STN technique (D-STN), which uniquely combines the STN predictions with historical statistics, thereby making faithful long-term mobile traffic projections. Experiments we conduct with real-world mobile traffic data sets, collected over 60 days in both urban and rural areas, demonstrate that the proposed (D-)STN schemes perform up to 10-hour long predictions with remarkable accuracy, irrespective of the time of day when they are triggered. Specifically, our solutions achieve up to 61% smaller prediction errors as compared to widely used forecasting approaches, while operating with up to 600 times shorter measurement intervals.
Original language | English |
---|---|
Title of host publication | The Nineteenth International Symposium on Mobile Ad Hoc Networking and Computing (ACM MobiHoc 2018) |
Place of Publication | Los Angeles, CA, USA |
Publisher | ACM |
Pages | 231-240 |
Number of pages | 10 |
ISBN (Print) | 978-1-4503-5770-8 |
DOIs | |
Publication status | Published - 26 Jun 2018 |
Event | 19th International Symposium on Mobile Ad Hoc Networking and Computing - University of California, Los Angeles Campus, Los Angeles , United States Duration: 26 Jun 2018 → 29 Jun 2018 https://www.sigmobile.org/mobihoc/2018/ |
Conference
Conference | 19th International Symposium on Mobile Ad Hoc Networking and Computing |
---|---|
Abbreviated title | MobiHoc 2018 |
Country/Territory | United States |
City | Los Angeles |
Period | 26/06/18 → 29/06/18 |
Internet address |
Fingerprint
Dive into the research topics of 'Long-Term Mobile Traffic Forecasting Using Deep Spatio-Temporal Neural Networks'. Together they form a unique fingerprint.Profiles
-
Paul Patras
- School of Informatics - Personal Chair of Mobile Intelligence
- Institute for Computing Systems Architecture
- Computer Systems
Person: Academic: Research Active