Deep Reinforcement Learning-Based Scheduling for Multiband Massive MIMO

Abstract

Fifth-generation (5G) cellular communication systems have embraced massive multipleinput-multiple-output (MIMO) in the low-and mid-band frequencies. In a multiband system, the base station can serve different users in each band, while the user equipment can operate only in a single band simultaneously. This paper considers a massive MIMO system where channels are dynamically allocated in different frequency bands. We treat multiband massive MIMO as a scheduling and resource allocation problem and propose deep reinforcement learning (DRL) agents to perform user scheduling. The DRL agents use buffer and channel information to compose their observation space, and the agent's reward function maximizes the transmitted throughput and minimizes the packet loss rate. We compare the proposed DRL algorithms with traditional baselines, such as maximum throughput and proportional fairness. The results show that the DRL models outperformed baselines obtaining a 20% higher network sum rate and an 84% smaller packet loss rate. Moreover, we compare different DRL algorithms focusing on training time to assess the online implementation of the DRL agents, showing that the best agent needs about 50K training steps to converge.

Deep Reinforcement Learning for Resource Constrained Multiclass Scheduling in Wireless Networks

“…APPENDIX A CLOSED-FORM EXPRESSIONS FOR (16) AND (19) a) i.i.d. fading (ρ = 0): This is the simplest case since there are no time dependencies on the fading, hence using (2) and ( 3), ( 16) and (19) become Φ(w u0,t ; d u0 ) = P f ail u0 (w u0,t , P ; d u0 ) and ( 25)…”

“…In cloud service provision, DRL has been used to schedule incoming tasks to servers according to their heterogeneous CPU and memory requirements [7]. DRL approaches have recently shown interesting gains in wireless communication systems [8]- [11], and has also been applied to wireless scheduling and resource allocation problems [12]- [19]. Nevertheless, none of previous works has studied the problem we consider here, that of multiclass scheduling with heterogeneous QoS constraints.…”

Joint Beam Management and Relay Selection Using Deep Reinforcement Learning for MmWave UAV Relay Networks

“…In this paper, we focus on band assignment that refers to the selection of operating bands over time slots in a sequential manner. Band assignment can be understood as a subproblem of the frequency resource allocation in multi-band systems [4].…”