5MART: A 5G SMART scheduling framework for optimizing QoS through reinforcement learning
- Submitting institution
-
Middlesex University
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 1260
- Type
- D - Journal article
- DOI
-
10.1109/TNSM.2019.2960849
- Title of journal
- IEEE Transactions on Network and Service Management
- Article number
- -
- First page
- 1110
- Volume
- 17
- Issue
- 2
- ISSN
- 1932-4537
- Open access status
- Compliant
- Month of publication
- December
- Year of publication
- 2019
- URL
-
http://eprints.mdx.ac.uk/29440/
- 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
-
3
- Research group(s)
-
-
- Citation count
- 0
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- In order to offer high flexibility and cope with both current and upcoming Quality of Service challenges within the very anticipated 5G networks, a smart radio resource management solution is required. This paper is significant because it is one of the first works to propose the integration of machine learning within the resource scheduling mechanism of an OFDMA-based 5G network for heterogeneous traffic. Simulation results reveal significant performance benefits with gains in excess of 50% when compared to other state-of-the-art schedulers when using the neural network approximator with the lowest complexity.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -