A Deep Reinforcement Learning-Based Resource Scheduler for Massive MIMO Networks
Sep 15, 2023·,,,
·
0 min read
Qing An
Chris Dick
Santiago Segarra
Ashutosh Sabharwal
Rahman Doost-Mohammady
Abstract
We present a deep reinforcement learning (DRL) framework for joint user
scheduling and power control in massive MIMO networks. The proposed
scheduler learns to allocate resources across users in real time,
adapting to channel dynamics and traffic demands while satisfying
fairness and quality-of-service constraints. Evaluations on realistic
channel models demonstrate substantial throughput and fairness
improvements over conventional schedulers.
Type
Publication
IEEE Transactions on Machine Learning in Communications and Networking
Authors
Authors
Authors
Authors
Authors
Rahman Doost-Mohammady
(he/him)
Assistant Research Professor
I work at the intersection of computer systems and wireless
networking — building programmable, intelligent infrastructure for
5G/6G and Open RAN. A common thread across my projects is algorithm
and system design across FPGA, GPU, and CPU — spanning real-time
massive MIMO baseband on commodity servers, many-antenna hardware
platforms, and learning-driven schedulers. I am currently focused on
virtualized Open RAN systems and ML-enabled RAN software design.