Quantum Computing for Artificial Intelligence Based Mobile Network Optimization

TL;DR

This paper explores using quantum computing to optimize radio network configurations, demonstrating a case study on LTE/NR RSI assignment, and comparing quantum and classical algorithms for network automation.

Contribution

It formulates the RSI assignment as a QUBO problem and evaluates quantum annealing solutions, highlighting the framework's flexibility and potential in mobile network automation.

Findings

Quantum annealing can assign conflict-free RSIs successfully.

Classical heuristics sometimes outperform quantum solutions in quality and speed.

The framework shows promise despite current quantum hardware limitations.

Abstract

In this paper, we discuss how certain radio access network optimization problems can be modelled using the concept of constraint satisfaction problems in artificial intelligence, and solved at scale using a quantum computer. As a case study, we discuss root sequence index (RSI) assignment problem - an important LTE/NR physical random access channel configuration related automation use-case. We formulate RSI assignment as quadratic unconstrained binary optimization (QUBO) problem constructed using data ingested from a commercial mobile network, and solve it using a cloud-based commercially available quantum computing platform. Results show that quantum annealing solver can successfully assign conflict-free RSIs. Comparison with well-known heuristics reveals that some classic algorithms are even more effective in terms of solution quality and computation time. The non-quantum advantage is due to the fact that current implementation is a semi-quantum proof-of-concept algorithm. Also, the results depend on the type of quantum computer used. Nevertheless, the proposed framework is highly flexible and holds tremendous potential for harnessing the power of quantum computing in mobile network automation.