Reference : Toward Optimally Efficient Search With Deep Learning for Large-Scale MIMO Systems

	Document type :	Scientific journals : Article
	Discipline(s) :	Engineering, computing & technology : Electrical & electronics engineering
	To cite this reference:	http://hdl.handle.net/10993/53134

Title :	Toward Optimally Efficient Search With Deep Learning for Large-Scale MIMO Systems
Language :	English
Author, co-author :	He, Le [Guangzhou University > School of Computer Science and Cyber Engineering]
	He, Ke [University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > SigCom > ; Guangzhou University > Computer Science and Cyber Engineering]
	Fan, Lisheng [Guangzhou University > Computer Science and Cyber Engineering]
	Lei, Xianfu [Southwest Jiaotong University > School of Information Science and Technology]
	Nallanathan, Arumugam [Queen Mary University of London > School of Electronic Engineering and Computer Science]
	Karagiannidis, George [Aristotle University of Thessaloniki > Wireless Communications and Information Processing Group (WCIP)]
Publication date :	May-2022
Journal title :	IEEE Transactions on Communications
Publisher :	Institute of Electrical and Electronics Engineers
Volume :	70
Issue/season :	5
Pages :	3157-3168
Peer reviewed :	Yes
Audience :	International
ISSN :	0090-6778
Country :	United States
Keywords :	[en] integer least-squares ; sphere decoding ; MIMO
Abstract :	[en] This paper investigates the optimal signal detection problem with a particular interest in large-scale multiple-input multiple-output (MIMO) systems. The problem is NP-hard and can be solved optimally by searching the shortest path on the decision tree. Unfortunately, the existing optimal search algorithms often involve prohibitively high complexities, which indicates that they are infeasible in large-scale MIMO systems. To address this issue, we propose a general heuristic search algorithm, namely, hyper-accelerated tree search (HATS) algorithm. The proposed algorithm employs a deep neural network (DNN) to estimate the optimal heuristic, and then use the estimated heuristic to speed up the underlying memory-bounded search algorithm. This idea is inspired by the fact that the underlying heuristic search algorithm reaches the optimal efficiency with the optimal heuristic function. Simulation results show that the proposed algorithm reaches almost the optimal bit error rate (BER) performance in large-scale systems, while the memory size can be bounded. In the meanwhile, it visits nearly the fewest tree nodes. This indicates that the proposed algorithm reaches almost the optimal efficiency in practical scenarios, and thereby it is applicable for large-scale systems. Besides, the code for this paper is available at https://github.com/skypitcher/hats.
Funders :	Natrual Sicence Foundation of China
Target :	Researchers ; Students
Permalink :	http://hdl.handle.net/10993/53134
DOI :	10.1109/TCOMM.2022.3158367
Other URL :	https://ieeexplore.ieee.org/abstract/document/9732440
Mentions required by the publisher for OA :	0090-6778 © 2022 IEEE. Personal use is permitted, but republication/redistribution requires IEEE permission. See https://www.ieee.org/publications/rights/index.html for more information. Authorized licensed use limited to: University of Luxembourg. Downloaded on December 14,2022 at 12:35:10 UTC from IEEE Xplore. Restrictions apply.

	File(s) associated to this reference
	Fulltext file(s): File Commentary Version Size Access Limited access Toward_Optimally_Efficient_Search_With_Deep_Learning_for_Large-Scale_MIMO_Systems.pdf Publisher postprint 1.42 MB Request a copy

All documents in ORBi^lu are protected by a user license.

 

University of Luxembourg Library |  Feedback |  Legal notices Site Map