On Meeting a Maximum Delay Constraint

Shafieirad, Hossein; Adve, Raviraj

doi:10.1109/globecom46510.2021.9685672

Cited by 1 publication

(2 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The SS-MCTS approach, combined with deep RL, addresses large-scale scenarios, as an extension to the work in [23], the main issue with tree search approaches. The main contribution and focus of this work compared to the work in [23] is considering a value and policy neural network combined with the SS-MCTS approach to improve the performance and reduce the computational complexity of the proposed approach. In this regard, we have proposed a distributed multi-agent RL framework which significantly improves the performance, in an online manner.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

On Meeting a Maximum Delay Constraint Using Reinforcement Learning

Shafieirad

Adve

2022

IEEE Access

Self Cite

View full text Add to dashboard Cite

Several emerging applications in wireless communications are required to achieve low latency, but also high traffic rates and reliabilities. From a latency point of view, most of the state-of-the-art techniques consider the average latency which may not directly apply to scenarios with stringent latency constraints. In this paper, we consider scheduling under a max-delay constraint; this is an NP-hard problem. We propose a novel approach to tackle the scheduling problem by directly addressing the constraint. We consider the downlink of a multi-cell wireless communication network with nodes communicating with users each facing their own delay constraint on randomly arrived packets. Packets must be scheduled to meet the users' delay constraints. Our main contributions are first, proposing a new search approach, Super State Monte-Carlo Tree Search (SS-MCTS), as a version of regular MCTS modified for large-scale probabilistic environments; second, developing trained value and policy networks to reduce computational complexity, and finally, addressing the scheduling problem through a reinforcement learning framework. Our numerical results demonstrate that the proposed approach significantly improves the packet delivery rate over a baseline approach while meeting the max-delay constraint, and addressing the scalability as the main issues in large action-state spaces. INDEX TERMSMonte-Carlo Tree Search, Scheduling, Reinforcement Learning, Max-Delay Constraints • First and foremost, proposing the Super State Monte-Carlo Tree Search (SS-MCTS) method as a modified version of regular MCTS to account for delay-sensitive VOLUME 4, 2016

show abstract

Section: Introductionmentioning

confidence: 99%

“…We also analyse the complexity of the proposed approach. As well as the aforementioned contributions, the scheduling problem considered in this work is selection of multiple tuples of users and their assigned channels per each timeslot in a multi-cell scenario while in [23] a single user is selected per timeslot in a single-cell scenario.…”

Section: Introductionmentioning

confidence: 99%