2022
DOI: 10.1109/jsac.2022.3191114
|View full text |Cite
|
Sign up to set email alerts
|

Multiobjective Load Balancing for Multiband Downlink Cellular Networks: A Meta- Reinforcement Learning Approach

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1

Citation Types

0
10
0

Year Published

2023
2023
2024
2024

Publication Types

Select...
5
2

Relationship

1
6

Authors

Journals

citations
Cited by 19 publications
(10 citation statements)
references
References 36 publications
0
10
0
Order By: Relevance
“…For any ∈ (0, 1), a solution θ is found such that E[||θ ||] 2 ≤ + 2 , where is the meta training parameters. The convergence of multi-step MAML for RL is guaranteed to converge in O( 2 ) iterations if meta learning rate is chosen properly (Feriani et al, 2022). Therefore, the MAML-RL is basically guaranteed to converge.…”
Section: Appendix Bmentioning
confidence: 99%
“…For any ∈ (0, 1), a solution θ is found such that E[||θ ||] 2 ≤ + 2 , where is the meta training parameters. The convergence of multi-step MAML for RL is guaranteed to converge in O( 2 ) iterations if meta learning rate is chosen properly (Feriani et al, 2022). Therefore, the MAML-RL is basically guaranteed to converge.…”
Section: Appendix Bmentioning
confidence: 99%
“…Frequent handovers can lead to increased connection drop rates, higher transmission delays, and induce ping-pong effects [4]. These can be especially detrimental for heterogeneous deployments which typically have a smaller average cell size.…”
Section: A User Service Ratementioning
confidence: 99%
“…As the industry trends towards intelligent and open networks [21], [22], network measurements across BSs and users can be leveraged to make data-driven user association and load balancing decisions. As such, mobility-aware user association has been considered recently as a reinforcement learning (RL) problem [4], [23]- [30]. Among these, [26], [28] aim to optimize the network utility within the RL framework, [23], [24] maximize the sum-rate, and [4], [27] optimize cell individual offset parameters.…”
mentioning
confidence: 99%
See 1 more Smart Citation
“…It is also possible to use combinations of different events to drive the load balancing process. For example, Feriani et al (2022) considers a combination of A2 and A5 events. Specifically, if the following two conditions are satisfied, then a handover is triggered.…”
Section: Mlb Via Handover For Active Uesmentioning
confidence: 99%