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

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 13, 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.