Research Repository

See what's under the surface

Enhancing user fairness in OFDMA radio access networks through machine learning

Comsa, Ioan-Sorin; Zhang, Sijing; Aydin, Mehmet; Kuonen, Pierre; Trestian, Ramona; Ghinea, Gheorghita

Authors

Ioan-Sorin Comsa

Sijing Zhang

Mehmet Aydin Mehmet.Aydin@uwe.ac.uk
Senior Lecturer in Networks and Mobile Computing

Pierre Kuonen

Ramona Trestian

Gheorghita Ghinea

Abstract

The problem of radio resource scheduling subject to fairness satisfaction is very challenging even in future radio access networks. Standard fairness criteria aim to find the best trade-off between overall throughput maximization and user fairness satisfaction under various types of network conditions. However, at the Radio Resource Management (RRM) level, the existing schedulers are rather static being unable to react according to the momentary networking conditions so that the user fairness measure is maximized all time. This paper proposes a dynamic scheduler framework able to parameterize the proportional fair scheduling rule at each Transmission Time Interval (TTI) to improve the user fairness. To deal with the fra- mework complexity, the parameterization decisions are appro- ximated by using the neural networks as non-linear functions. The actor-critic Reinforcement Learning (RL) algorithm is used to learn the best set of non-linear functions that approximate the best fairness parameters to be applied in each momentary state. Simulations results reveal that the proposed framework outperforms the existing fairness adaptation techniques as well as other types of RL-based schedulers.

Start Date Apr 24, 2019
Publication Date Jul 13, 2019
Publisher Institute of Electrical and Electronics Engineers (IEEE)
Peer Reviewed Peer Reviewed
Pages 1-8
Book Title 2019 Wireless Days (WD)
Institution Citation Comsa, I., Zhang, S., Aydin, M., Kuonen, P., Trestian, R., & Ghinea, G. (2019). Enhancing user fairness in OFDMA radio access networks through machine learning. In 2019 Wireless Days (WD), 1-8. https://doi.org/10.1109/WD.2019.8734262
DOI https://doi.org/10.1109/WD.2019.8734262
Keywords throughput, resource management, quality of service,dynamic scheduling, heuristic algorithms, optimization,wireless communication
Publisher URL http://doi.org/10.1109/WD.2019.8734262
Additional Information Title of Conference or Conference Proceedings : Wireless Days 2019