Wireless network resources allocation using coherent Ising machines with error correction

¹ School of Artificial Intelligence, Beijing Normal University - Beijing 100875, China
² China Mobile (Suzhou) Software Technology Company Limited - Suzhou 215163, China
³ Beijing QBoson Quantum Technology Co., Ltd. - Beijing 100015, China
⁴ School of Science, Beijing University of Posts and Telecommunications - Beijing 100876, China

Received: 27 December 2024
Accepted: 3 March 2025

Abstract

With the unprecedented growth of smart devices and the rapid expansion of internet of things (IoT) networks, researchers are delving deeper into studying the next generation of 6G communication technology. Within 6G wireless communication networks, there are more devices with massive data requirements, necessitating the reduction of latency to make the network more reliable and faster. Related works have shown that coherent Ising machines (CIM) possess greater computational power when tackling combinatorial optimization problems. To validate the efficiency of CIM in communication scenarios, we employed a pulse-neural-network–based coherent Ising machine (PNN-CIM) to investigate allocation issues concerning the base stations, users, and channels in wireless communications. Also, we compare the performance of simulated annealing algorithms and other CIM approaches, and we found that PNN-CIM exhibits higher allocation success rates across wireless communication network scenarios of varying scales. Furthermore, the scheme consumes less computation time than other algorithms when dealing with large-scale communication scenarios.