KR-20260067311-A - METHOD AND APPARATUS FOR DETECTING SYMBOL IN MULTIPLE INPUT MULTIPLE OUTPUT SYSTEM

Abstract

The method includes the steps of: obtaining a channel matrix based on a receiving vector; determining a gram matrix using the channel matrix and the receiving vector; performing a symbol detection operation on a layer-by-layer basis using the gram matrix and the receiving vector; repeating the symbol detection operation based on the fact that the index of the layer is less than or equal to the maximum layer number; and outputting an estimated symbol vector based on the repetition of the symbol detection operation based on the fact that the index of the layer exceeds the maximum layer number.

Inventors

• 윤상부
• 김남일
• 김재화
• 이영주

Assignees

• 한국전자통신연구원

Dates

Publication Date

20260512

Application Date

20250926

Priority Date

20241105

Claims (1)

1. As a method of base station, A step of obtaining a received vector from a terminal; A step of obtaining a channel matrix based on the above-mentioned reception vector; A step of determining a gram matrix using the channel matrix and the reception vector; A step of performing a symbol detection operation on a layer-by-layer basis using the above gram matrix and the above received vector; A step of repeatedly performing the symbol detection operation based on the fact that the index of the above layer is less than or equal to the maximum layer number; and A step comprising outputting an estimated symbol vector based on the iterative execution of the symbol detection operation, based on the fact that the index of the above layer exceeds the maximum layer number. Base station method.

Description

Method and apparatus for detecting symbols in a multiple input multiple output system The present disclosure relates to a symbol detection technology in a multi-input multi-output system, and more specifically, to a deep learning-based symbol detection technology in a multi-input multi-output system. Along with the advancement of information and communication technology, various wireless communication technologies are being developed. Representative wireless communication technologies include LTE (long term evolution) and NR (new radio), which are defined in the 3GPP (3rd generation partnership project) standards. LTE can be one of the wireless communication technologies among 4G (4th Generation) wireless communication technologies, and NR can be one of the wireless communication technologies among 5G (5th Generation) wireless communication technologies. To handle the surge in wireless data following the commercialization of 4G communication systems (e.g., communication systems supporting LTE), 5G communication systems (e.g., communication systems supporting NR) that use frequency bands higher than those of 4G communication systems (e.g., frequency bands below 6 GHz) are being considered. 5G communication systems can support eMBB (enhanced Mobile BroadBand), URLLC (Ultra-Reliable and Low Latency Communication), and mMTC (massive Machine Type Communication). Wireless communication technology can be utilized in various fields, and the demand for data traffic may increase. Multiple Input Multiple Output (MIMO) technology can improve spectrum and power efficiency. MIMO technology allows for the simultaneous operation of multiple transmitting and receiving antennas and the utilization of spatially distinct transmission paths. MIMO technology enables the parallel transmission of multiple data streams within the same frequency resource and can increase data throughput. Furthermore, MIMO technology can improve power efficiency by applying beamforming and ensure immunity against fading in wireless channels through transmission via multiple paths. In small-scale MIMO systems, symbol detection can be achieved using simple algorithms. Meanwhile, due to the surge in demand for wireless communication, there may be an increase in cases where base stations transmit and receive high-speed and high-capacity data from multiple terminals, making it difficult to detect symbols using simple algorithms. When detecting symbols in Massive MIMO systems, non-linear algorithms can be applied. When applying non-linear algorithms, the complexity of the algorithm may increase, the amount of computation may increase, and system delay may occur. FIG. 1 is a conceptual diagram illustrating embodiments of a communication system. FIG. 2 is a block diagram illustrating embodiments of communication nodes constituting a communication system. FIG. 3 is a conceptual diagram illustrating the symbol detection method of the present disclosure. Figure 4a is a conceptual diagram illustrating the MomentNet-based symbol detection network structure in a MIMO system. Figure 4b is a conceptual diagram illustrating the MomentNet-based symbol detection network structure in a MIMO system. Figure 5a is a graph comparing the learning speeds of deep learning-based symbol detection methods when the number of receiving antennas is 16 and the number of transmitting antennas is 8. Figure 5b is a graph comparing the learning speeds of deep learning-based symbol detection methods when the number of receiving antennas is 32 and the number of transmitting antennas is 16. Figure 6 is a graph comparing symbol detection performance when the number of receiving antennas is 16. Figure 7 is a graph comparing symbol detection performance when the number of receiving antennas is 32. Figure 8 is a graph comparing the computational complexity of deep learning-based symbol detection methods. Figure 9 is a conceptual diagram comparing the efficiency of deep learning-based symbol detection methods. Figure 10 is a flowchart illustrating the process of symbol detection according to the MomentNet-based method. The present disclosure is capable of various modifications and may have various embodiments, and specific embodiments are illustrated in the drawings and described in detail. However, this is not intended to limit the present disclosure to specific embodiments, and it should be understood that it includes all modifications, equivalents, and substitutions that fall within the spirit and scope of the present disclosure. Terms such as "first," "second," etc., may be used to describe various components, but said components should not be limited by said terms. Such terms are used solely for the purpose of distinguishing one component from another. For example, without departing from the scope of the present disclosure, the first component may be named the second component, and similarly, the second component may be named the first component. The term "and/or" includes a combination of