Skip to main content

Research Repository

Advanced Search

Towards 5G: A Reinforcement Learning-Based Scheduling Solution for Data Traffic Management

Comsa, Ioan Sorin; Zhang, Sijing; Aydin, Mehmet Emin; Kuonen, Pierre; Lu, Yao; Trestian, Ramona; Ghinea, Gheorghita

Towards 5G: A Reinforcement Learning-Based Scheduling Solution for Data Traffic Management Thumbnail


Authors

Ioan Sorin Comsa

Sijing Zhang

Profile Image

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

Pierre Kuonen

Yao Lu

Ramona Trestian

Gheorghita Ghinea



Abstract

© 2004-2012 IEEE. Dominated by delay-sensitive and massive data applications, radio resource management in 5G access networks is expected to satisfy very stringent delay and packet loss requirements. In this context, the packet scheduler plays a central role by allocating user data packets in the frequency domain at each predefined time interval. Standard scheduling rules are known limited in satisfying higher quality of service (QoS) demands when facing unpredictable network conditions and dynamic traffic circumstances. This paper proposes an innovative scheduling framework able to select different scheduling rules according to instantaneous scheduler states in order to minimize the packet delays and packet drop rates for strict QoS requirements applications. To deal with real-time scheduling, the reinforcement learning (RL) principles are used to map the scheduling rules to each state and to learn when to apply each. Additionally, neural networks are used as function approximation to cope with the RL complexity and very large representations of the scheduler state space. Simulation results demonstrate that the proposed framework outperforms the conventional scheduling strategies in terms of delay and packet drop rate requirements.

Citation

Comsa, I. S., Zhang, S., Aydin, M. E., Kuonen, P., Lu, Y., Trestian, R., & Ghinea, G. (2018). Towards 5G: A Reinforcement Learning-Based Scheduling Solution for Data Traffic Management. IEEE Transactions on Network and Service Management, 15(4), 1661-1675. https://doi.org/10.1109/TNSM.2018.2863563

Journal Article Type Article
Acceptance Date Jul 22, 2018
Online Publication Date Aug 6, 2018
Publication Date Dec 1, 2018
Deposit Date Aug 13, 2018
Publicly Available Date Aug 14, 2018
Journal IEEE Transactions on Network and Service Management
Print ISSN 1932-4537
Electronic ISSN 1932-4537
Publisher Institute of Electrical and Electronics Engineers
Peer Reviewed Peer Reviewed
Volume 15
Issue 4
Pages 1661-1675
DOI https://doi.org/10.1109/TNSM.2018.2863563
Keywords delays, quality of service, scheduling algorithms, resource management, dynamic scheduling, 5G mobile communication, 5G, packet scheduling, optimization, radio resource management, reinforcement learning, neural networks
Public URL https://uwe-repository.worktribe.com/output/855212
Publisher URL https://ieeexplore.ieee.org/document/8425580/
Additional Information Additional Information : © 2018 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

Files





You might also like



Downloadable Citations