KR-20260067352-A - METHOD AND APPARATUS FOR CHANNEL STATE INFORMATION FEEDBACK BASED ON ARTIFICIAL INTELLIGENCE/MACHINE LEARNING MODEL

Abstract

A method and apparatus for channel state information feedback based on an AI/ML (artificial intelligence/machine learning) model are disclosed. A method for a terminal for channel state information feedback comprises the steps of: receiving at least one channel state information-reference signal (CSI-RS) including an associated ID from a base station; predicting channel state information through an AI/ML model based on the at least one CSI-RS; determining whether the associated ID is set as an information element (IE) within a CSI-ReportConfig; and, if it is determined that the associated ID is set as an IE within the CSI-ReportConfig, transmitting a channel state information report that does not include the associated ID to the base station based on the channel state information prediction result.

Inventors

• 윤영준
• 이유로
• 권용진
• 방승재
• 이안석
• 이희수
• 김윤주
• 박현서
• 배정숙
• 손정보

Assignees

• 한국전자통신연구원

Dates

Publication Date

20260512

Application Date

20251104

Priority Date

20241105

Claims (1)

1. By means of the terminal, A step of receiving at least one channel state information-reference signal (CSI-RS) including an associated ID from a base station; A step of predicting channel state information through an AI/ML model based on at least one CSI-RS; A step of determining whether the above-mentioned association ID is set as an information element (IE) within the CSI-ReportConfig; and If it is determined that the above association ID is set to IE within the CSI reporting settings, the method includes the step of transmitting a channel state information report that does not include the above association ID to the base station based on the channel state information prediction result. Method of the terminal.

Description

Method and apparatus for channel state information feedback based on an AI/ML model The present disclosure relates to intelligent technology for communication networks, and more specifically, to a method and apparatus for channel state information feedback based on an AI/ML (artificial intelligence/machine learning) model in a communication network. 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). Intelligent technologies can be utilized in communication systems for beam management, positioning accuracy enhancement, or channel state information (CSI) feedback enhancement. Intelligent technologies can be based on the training of AI/ML models, and life cycle management (LCM) can be performed to create intelligent functions, models, or perform maintenance in response to changes in training data. Life cycle management may include detailed processes such as data collection, model training, model inference, model deployment, model activation, model deactivation, model selection, model switching, model fallback, and model monitoring. In a channel state information feedback method using intelligent technology, a transmitting node, e.g., a base station, can transmit a reference signal for measuring channel state, e.g., CSI-RS, to a receiving node, e.g., a terminal. The terminal can receive the CSI-RS from the base station and predict channel state information from the CSI-RS using an AI/ML model. The terminal can transmit the predicted channel state information to the base station, and the base station can perform encoding levels, power allocation, or beamforming for data signal transmission to the terminal based on the channel state information. Here, to improve the accuracy of the AI/ML model's channel state information prediction, consistency between the training and inference operations of the AI/ML model must be guaranteed. For example, if the network-side conditions set during the training process of the AI/ML model differ from the network-side conditions set during the inference process, the accuracy of the AI/ML model's inference results may be degraded. Therefore, a method capable of guaranteeing consistency between the training and inference operations of the AI/ML model is required. Figure 1 is a conceptual diagram showing an example of a communication network. FIG. 2 is a block diagram showing an example of a communication node of a communication network. Figure 3 is a conceptual diagram showing an example of a wireless frame structure of a communication network. Figure 4 is a conceptual diagram showing an example of a slot structure of a wireless frame. Figure 5 is a conceptual diagram showing an example of symbol type information of a slot in a wireless frame. Figure 6 is a conceptual diagram showing an example of a signal transmission procedure between a base station and a terminal in a communication network. FIG. 7 is a conceptual diagram showing an example of an SS/PBCH block for initial cell connection of a terminal. FIGS. 8A and FIGS. 8B are conceptual diagrams showing an example of a slot in which an SS/PBCH block is transmitted. FIG. 9 is a conceptual diagram illustrating an example of a procedure for transmitting control information of a base station in a communication network. FIG. 10 is a conceptual diagram showing an example of a CCE-based PDCCH structure for transmitting control information of a base station. FIG. 11 is a conceptual diagram showing an example of a CORESET for PDCCH transmission in a communication network. FIG. 12 is a conceptual diagram illustrating an example of a method for setting up a PDCCH search space in a communication network. FIG. 13 is a conceptual diagram showing an example of single-carrier communication in a communication network. FIG. 14 is a conceptual diagram showing an example of multi-carrier communication in a communication network. FIG. 15 is a conceptual diagram showing an example of a cross-carrier scheduling method in a communication network.