Ultra-Reliable Communication in 5G mmWave Networks: A Risk-Sensitive Approach

TL;DR

This paper introduces a risk-sensitive reinforcement learning framework for 5G mmWave networks that optimizes beamwidth and power to enhance reliability and throughput amidst blockage challenges.

Contribution

It proposes a novel distributed risk-sensitive RL approach for joint beamwidth and power optimization in 5G mmWave networks, considering blockage effects.

Findings

Achieves over 9 Gbps throughput with 90% reliability

Outperforms baseline with less than 7.5 Gbps throughput

Identifies a rate-reliability-network density tradeoff

Abstract

This letter investigates the problem of providing gigabit wireless access with reliable communication in 5G millimeter-Wave (mmWave) massive multiple-input multiple-output (MIMO) networks. In contrast to the classical network design based on average metrics, a distributed risk-sensitive reinforcement learning-based framework is proposed to jointly optimize the beamwidth and transmit power, while taking into account the sensitivity of mmWave links due to blockage. Numerical results show that our proposed algorithm achieves more than 9 Gbps of user throughput with a guaranteed probability of 90%, whereas the baselines guarantee less than 7.5 Gbps. More importantly, there exists a rate-reliability-network density tradeoff, in which as the user density increases from 16 to 96 per km2, the fraction of users that achieve 4 Gbps are reduced by 11.61% and 39.11% in the proposed and the baseline models, respectively.