Radio Environment Map and Deep Q-Learning for 5G Dynamic Point Blanking

TL;DR

This paper introduces a Deep Q-Learning approach to optimize Dynamic Point Blanking in 5G networks, significantly enhancing cell-edge user throughput by approximately 20.6%.

Contribution

It presents a novel Deep Q-Learning based method for optimizing muting patterns in DPB to improve 5G cell-edge performance.

Findings

Improves cell-edge throughput by 20.6%.

Uses location-dependent data for training.

Demonstrates effectiveness through simulations.

Abstract

Dynamic Point Blanking (DPB) is one of the Coordinated MultiPoint (CoMP) techniques, where some Base Stations (BSs) can be temporarily muted, e.g., to improve the cell-edge users throughput. In this paper, it is proposed to obtain the muting pattern that improves cell-edge users throughput with the use of a Deep Q-Learning. The Deep Q-Learning agent is trained on location-dependent data. Simulation studies have shown that the proposed solution improves cell-edge user throughput by about 20.6%.