Abstract
In the coming 6th generation (6G) and beyond in wireless communication, an increasing number of ultrascale intelligent factors, including mobile robot users and smart cars, will result in interference exploitation. The management of this exploitation will be a great challenge for detection algorithms in uplink massive multiple-input and multiple-output (MIMO) systems, especially for high-order quadrature amplitude modulation (QAM) signals. Artificial intelligence technology employing machine learning is one of the key approaches among the 6G technical solutions. In this paper, a convolutional-neural-network-based likelihood ascent search (CNNLAS) detection algorithm is proposed on the basis of a graphical detection model for uplink multiuser massive MIMO systems. Compared with other algorithms, the proposed CNNLAS detection algorithm has a stronger robustness against the channel estimation errors, and requires lower average received signal-to-noise ratios to obtain better bit error rate performance and to achieve the theoretical spectral efficiency with a lower polynomial average per symbol computational complexity, both for the graphical low-order and high-order QAM signals in uplink multiuser massive MIMO systems.
Highlights
The growing number of ultrascale intelligent factors, including mobile robot users and smart cars, create the core requirements for ultrahigh-speed and low-latency communications and innovation in the communication systems architecture, and the 6th generation (6G) and beyond wireless communications are coming [1], [2]
The main contribution of this paper is to propose a convolutional neural network (CNN)-based likelihood ascent search (CNNLAS) detection algorithm on the basis of the presented graphical detection model for uplink multiuser massive multiple-input and multiple-output (MIMO) systems
The results show that the spectral efficiency of the semidefinite relaxation decoder (SDR), LLLDR, MMSELAS and minimum mean square error (MMSE) detection algorithms increase along with the average received signal-to-noise ratio (SNR) and converge to 1316 bps/Hz or 1265 bps/Hz, which are much lower than the theoretical value 1728 bps/Hz
Summary
The growing number of ultrascale intelligent factors, including mobile robot users and smart cars, create the core requirements for ultrahigh-speed and low-latency communications and innovation in the communication systems architecture, and the 6th generation (6G) and beyond wireless communications are coming [1], [2]. More aggressive resource sharing and tighter cooperation in these intelligent factors will result in interference exploitation. In uplink massive multiple-input and multiple-output (MIMO) systems, obtaining the optimum bit error rate (BER) performance with a low polynomial computational complexity is a. Interference exploitation and management will be a great challenge for detection algorithms in uplink massive MIMO systems in the future, especially for high-order quadrature amplitude modulation (QAM) signals at an ultrascale. The development of a low-complexity detection algorithm for uplink high-order modulated massive MIMO systems is one of the most difficult but urgent issues that needs to be addressed
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
