Full Text Views
51
In this paper, user set selection in the allocation sequences of round-robin (RR) scheduling for distributed antenna transmission with block diagonalization (BD) pre-coding is proposed. In prior research, the initial phase selection of user equipment allocation sequences in RR scheduling has been investigated. The performance of the proposed RR scheduling is inferior to that of proportional fair (PF) scheduling under severe intra-cell interference. In this paper, the multi-input multi-output technology with BD pre-coding is applied. Furthermore, the user equipment (UE) sets in the allocation sequences are eliminated with reinforcement learning. After the modification of a RR allocation sequence, no estimated throughput calculation for UE set selection is required. Numerical results obtained through computer simulation show that the maximum selection, one of the criteria for initial phase selection, outperforms the weighted PF scheduling in a restricted realm in terms of the computational complexity, fairness, and throughput.
Go OTSURU
Keio University
Yukitoshi SANADA
Keio University
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Go OTSURU, Yukitoshi SANADA, "UE Set Selection for RR Scheduling in Distributed Antenna Transmission with Reinforcement Learning" in IEICE TRANSACTIONS on Communications,
vol. E106-B, no. 7, pp. 586-594, July 2023, doi: 10.1587/transcom.2022EBP3136.
Abstract: In this paper, user set selection in the allocation sequences of round-robin (RR) scheduling for distributed antenna transmission with block diagonalization (BD) pre-coding is proposed. In prior research, the initial phase selection of user equipment allocation sequences in RR scheduling has been investigated. The performance of the proposed RR scheduling is inferior to that of proportional fair (PF) scheduling under severe intra-cell interference. In this paper, the multi-input multi-output technology with BD pre-coding is applied. Furthermore, the user equipment (UE) sets in the allocation sequences are eliminated with reinforcement learning. After the modification of a RR allocation sequence, no estimated throughput calculation for UE set selection is required. Numerical results obtained through computer simulation show that the maximum selection, one of the criteria for initial phase selection, outperforms the weighted PF scheduling in a restricted realm in terms of the computational complexity, fairness, and throughput.
URL: https://global.ieice.org/en_transactions/communications/10.1587/transcom.2022EBP3136/_p
Copy
@ARTICLE{e106-b_7_586,
author={Go OTSURU, Yukitoshi SANADA, },
journal={IEICE TRANSACTIONS on Communications},
title={UE Set Selection for RR Scheduling in Distributed Antenna Transmission with Reinforcement Learning},
year={2023},
volume={E106-B},
number={7},
pages={586-594},
abstract={In this paper, user set selection in the allocation sequences of round-robin (RR) scheduling for distributed antenna transmission with block diagonalization (BD) pre-coding is proposed. In prior research, the initial phase selection of user equipment allocation sequences in RR scheduling has been investigated. The performance of the proposed RR scheduling is inferior to that of proportional fair (PF) scheduling under severe intra-cell interference. In this paper, the multi-input multi-output technology with BD pre-coding is applied. Furthermore, the user equipment (UE) sets in the allocation sequences are eliminated with reinforcement learning. After the modification of a RR allocation sequence, no estimated throughput calculation for UE set selection is required. Numerical results obtained through computer simulation show that the maximum selection, one of the criteria for initial phase selection, outperforms the weighted PF scheduling in a restricted realm in terms of the computational complexity, fairness, and throughput.},
keywords={},
doi={10.1587/transcom.2022EBP3136},
ISSN={1745-1345},
month={July},}
Copy
TY - JOUR
TI - UE Set Selection for RR Scheduling in Distributed Antenna Transmission with Reinforcement Learning
T2 - IEICE TRANSACTIONS on Communications
SP - 586
EP - 594
AU - Go OTSURU
AU - Yukitoshi SANADA
PY - 2023
DO - 10.1587/transcom.2022EBP3136
JO - IEICE TRANSACTIONS on Communications
SN - 1745-1345
VL - E106-B
IS - 7
JA - IEICE TRANSACTIONS on Communications
Y1 - July 2023
AB - In this paper, user set selection in the allocation sequences of round-robin (RR) scheduling for distributed antenna transmission with block diagonalization (BD) pre-coding is proposed. In prior research, the initial phase selection of user equipment allocation sequences in RR scheduling has been investigated. The performance of the proposed RR scheduling is inferior to that of proportional fair (PF) scheduling under severe intra-cell interference. In this paper, the multi-input multi-output technology with BD pre-coding is applied. Furthermore, the user equipment (UE) sets in the allocation sequences are eliminated with reinforcement learning. After the modification of a RR allocation sequence, no estimated throughput calculation for UE set selection is required. Numerical results obtained through computer simulation show that the maximum selection, one of the criteria for initial phase selection, outperforms the weighted PF scheduling in a restricted realm in terms of the computational complexity, fairness, and throughput.
ER -