Learning-Based Scheduling: Contextual Bandits for Massive MIMO Systems

Maurício, Weskley Vinicius Fernandes; Maciel, Tarcísio F.; Klein, Anja; Lima, F. Rafael M.

doi:10.1109/iccworkshops49005.2020.9145188

Cited by 2 publications

(6 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The precoder (18) does not fulfill the constant amplitude constraint of analog beamformers. However, it is possible to implement such a precoder by combining two RF chains for each MS stream, as discussed in [28].…”

Section: Hybrid Beamforming and Data Ratementioning

confidence: 99%

“…There are other methods, such as those presented in [28] that enable the use of one RF chain per stream up to a negligible performance loss. We choose the simplest approach that consists in constructing the analog beamforming using the phases of each entry in the matrix defined in (18).…”

Section: Hybrid Beamforming and Data Ratementioning

confidence: 99%

“…Since hybrid beamforming gained a lot of attention by allowing the use of massive MIMO, [16]- [18] propose new scheduling methods for massive MIMO under hybrid beamforming architecture. The authors in [16] propose a scheduling based on statistical CSI with the objective of system throughput maximization.…”

Section: Introductionmentioning

confidence: 99%

“…The scheduler main idea is to pre-select different sets of MSs based on the Pearson correlation coefficient, whose MSs are scheduled afterwards to maximize the throughput. In [18] the authors propose a scheduling based on contextual bandits to maximize the system throughput while satisfying the QoS. The main idea is that the scheduler learns over time the best scheduling strategy and adapts it to maximize the system performance.…”

Section: Introductionmentioning

confidence: 99%

“…The authors propose two schedulers, one based on stable matching and another based on greedy search. However, the works [16]- [18] do not consider the scheduling of multiple SUs.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

A Framework for Radio Resource Allocation and SDMA Grouping in Massive MIMO Systems

et al. 2021

Self Cite

View full text Add to dashboard Cite

This work proposes a framework for multiuser massive Multiple Input Multiple Output (MIMO) systems which is composed of three partsclustering, grouping, and scheduling -and aims at maximizing the total system data rate considering Quality of Service (QoS) constraints. We firstly use a clustering algorithm to create clusters of spatially correlated Mobile Stations (MSs). Secondly, in the grouping part, we select a set of Space-Division Multiple Access (SDMA) groups from each cluster. These groups are used as candidate groups to receive Scheduling Unit (SU) in the scheduling part. In order to compose a group, we employ a metric that takes into account the trade-off between the spatial channel correlation and channel gain of MSs. In this context, it is proposed a suboptimal solution to avoid the high complexity required by the optimal solution. Thirdly and finally, we use the candidate SDMA groups from the grouping part to solve the data rate maximization problem considering QoS requirements. The scheduling part can be solved by our proposed optimal solution based on Branch and Bound (BB). However, since it has high computational complexity, we propose a suboptimal scheduling algorithm that presents a reduced complexity. In the simulation results, we evaluate the performance of both optimal and suboptimal solutions, as well as an adaptation of the Joint Satisfaction Maximization (JSM) scheduler to a massive MIMO scenario. Although the suboptimal solution presents a performance loss compared to the optimal one, it is more suitable for practical settings as it is able to obtain a good performance-complexity trade-off. Furthermore, we show that the choice of a suitable trade-off between the spatial channel correlation and channel gain improves the system performance. Finally, for a low number of available SDMA groups, the suboptimal solution presents near optimal outage and a throughput loss of only 10% in comparison to the high-complexity optimal solution while it outperforms the JSM solution in terms of outage and system throughput.

show abstract

Section: Hybrid Beamforming and Data Ratementioning

confidence: 99%

Section: Hybrid Beamforming and Data Ratementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

“…The authors propose two schedulers, one based on stable matching and another based on greedy search. However, the works [16]- [18] do not consider the scheduling of multiple SUs.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations