# Contextual Bandit Learning for Machine Type Communications in the Null Space of Multi-Antenna Systems

## TL;DR

This paper introduces a novel interference management approach for machine type communications in multi-antenna systems, utilizing opportunistic spatial orthogonalization and online learning to operate without full channel state information.

## Contribution

It proposes a new OSO-based interference management method combined with a contextual bandit learning approach that eliminates the need for full CSI in multi-antenna systems.

## Key findings

- OSO can effectively reduce interference in MTC systems.
- The online learning method achieves near-optimal interference management without CSI.
- Simulation results validate the practical feasibility of the proposed approach.

## Abstract

In this paper, a novel approach based on the concept of opportunistic spatial orthogonalization (OSO) is proposed for interference management between machine type communications (MTC) and conventional cellular communications. In particular, a cellular system is considered with a multi-antenna BS in which a receive beamformer is designed to maximize the rate of a cellular user, and, a machine type aggregator (MTA) that receives data from a large set of MTDs. If there is a large number of MTDs to choose from for transmission at each time for each beamformer, one MTD can be selected such that it causes almost no interference on the BS. A comprehensive analytical study of the characteristics of such interference from several MTDs on the same beamformer is carried out. It is proven that, for each beamformer, an MTD exists such that the interference on the BS is negligible. However, the optimal implementation of OSO requires the CSI of all the links in the BS, which is not practical for MTC. To solve this problem, an online learning method based on the concept of contextual multi-armed bandits (MAB) learning is proposed. Simulation results show that is possible to implement OSO with no CSI from MTDs to the BS.