TY - GEN
T1 - Multi-agent double deep Q-Learning for beamforming in mmWave MIMO networks
AU - Wang, Xueyuan
AU - Cenk Gursoy, M.
N1 - Publisher Copyright:
© 2020 IEEE.
PY - 2020/8
Y1 - 2020/8
N2 - Beamforming is one of the key techniques in millimeter wave (mmWave) multi-input multi-output (MIMO) communications. Designing appropriate beamforming not only improves the quality and strength of the received signal, but also can help reduce the interference, consequently enhancing the data rate. In this paper, we propose a distributed multi-agent double deep Q-learning algorithm for beamforming in mmWave MIMO networks, where multiple base stations (BSs) can automatically and dynamically adjust their beams to serve multiple highly-mobile user equipments (UEs). In the analysis, largest received power association criterion is considered for UEs, and a realistic channel model is taken into account. Simulation results demonstrate that the proposed learning-based algorithm can achieve comparable performance with respect to exhaustive search while operating at much lower complexity.
AB - Beamforming is one of the key techniques in millimeter wave (mmWave) multi-input multi-output (MIMO) communications. Designing appropriate beamforming not only improves the quality and strength of the received signal, but also can help reduce the interference, consequently enhancing the data rate. In this paper, we propose a distributed multi-agent double deep Q-learning algorithm for beamforming in mmWave MIMO networks, where multiple base stations (BSs) can automatically and dynamically adjust their beams to serve multiple highly-mobile user equipments (UEs). In the analysis, largest received power association criterion is considered for UEs, and a realistic channel model is taken into account. Simulation results demonstrate that the proposed learning-based algorithm can achieve comparable performance with respect to exhaustive search while operating at much lower complexity.
KW - Beamforming
KW - Deep reinforcement learning
KW - MIMO
KW - MmWave communications
KW - Multi-agent systems
UR - http://www.scopus.com/inward/record.url?scp=85094139294&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85094139294&partnerID=8YFLogxK
U2 - 10.1109/PIMRC48278.2020.9217114
DO - 10.1109/PIMRC48278.2020.9217114
M3 - Conference contribution
AN - SCOPUS:85094139294
T3 - IEEE International Symposium on Personal, Indoor and Mobile Radio Communications, PIMRC
BT - 2020 IEEE 31st Annual International Symposium on Personal, Indoor and Mobile Radio Communications, PIMRC 2020
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 31st IEEE Annual International Symposium on Personal, Indoor and Mobile Radio Communications, PIMRC 2020
Y2 - 31 August 2020 through 3 September 2020
ER -