.png){kind=icon}
.png){kind=icon}
Return
RL-Based Waveform Adaptation With Partial Overlapping Tones in HetNets
.png){kind=icon}
OA
AI
DOI：10.1109/LCOMM.2021.3088841.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Partially-overlapping tones (POT) mitigate the co-channel interference in a wireless network by exploiting the space between adjacent subcarriers through intentional frequency offsets (FOs). In this letter, we use partially-overlapping tones (POT) in a two-tier heterogeneous network, where multiple small cells (SCs) interfere with a macro cell. We propose a multi-agent Q-learning-based approach to obtain transmit power and intentional FOs assigned to SCs for filtered multi-tones with various pulse shapes. We show that the proposed method reduces the total interference and in turn, increases the throughput in the network. We then compare the performance of the proposed approach to the existing schemes and demonstrate its advantage with numerical results.
Keywords:
Interference
Shape
Signal to noise ratio
Resource management
Indexes
Heuristic algorithms
Base stations
HetNets
partial overlapping
Q-learning
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
4.4
Papers:
1.3W
Citations:
2.2W