Towards 5G: A Reinforcement Learning-Based Scheduling Solution for Data Traffic Management
- Submitting institution
-
University of the West of England, Bristol
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 855220
- Type
- D - Journal article
- DOI
-
10.1109/TNSM.2018.2863563
- Title of journal
- IEEE Transactions on Network and Service Management
- Article number
- -
- First page
- 1661
- Volume
- 15
- Issue
- 4
- ISSN
- 1932-4537
- Open access status
- Compliant
- Month of publication
- August
- Year of publication
- 2018
- URL
-
https://ieeexplore.ieee.org/document/8425580/
- 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
-
6
- Research group(s)
-
-
- Citation count
- 16
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This paper is one of the earliest to study packet scheduling in 5G wireless networks using reinforcement learning approaches. It focuses on dynamically optimising resource usage to achieve minimum packet loss and delay in data transfer subject to highly dynamic and constraint environment. The problem is modelled considering a wide range of variability and the reinforcement learning approaches were widely studied with respect to policy and value refinement. The results demonstrated significant improvement in data traffic management of 5G networks.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -
