Data Augmentation based Cellular Traffic Prediction in Edge Computing Enabled Smart City
- Submitting institution
-
University of Exeter
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 6340
- Type
- D - Journal article
- DOI
-
10.1109/tii.2020.3009159
- Title of journal
- IEEE Transactions on Industrial Informatics
- Article number
- -
- First page
- 4179
- Volume
- 17
- Issue
- 6
- ISSN
- 1551-3203
- Open access status
- Compliant
- Month of publication
- July
- Year of publication
- 2020
- URL
-
-
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- No
- Number of additional authors
-
4
- Research group(s)
-
-
- Citation count
- -
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This paper proposes a brand-new GAN-based data augmentation method and a LSTM model for cellular traffic prediction, which significantly outperforms reference models on a real-world city-scale cellular traffic dataset. The proposed algorithms made large contributions to an ongoing industrial research project on “anomaly prediction and prevention for cloud services”. Based on this work, I was invited to give an invited talk at IEEE ScalCom'2019 workshop on Data & Model-Driven Methods for Trustworthy Systems. The proposed method leads to collaboration with Dr. Liang Hu (hu.liang@samsung.com) from Samsung Electronics to develop a Federated deep learning-based spatial-temporal data analysis model.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -