Method performed by a network node and network node

Abstract

This application relates to a method performed by a network node and the network node itself. The method includes: determining MU pairing groups that have control channel element (CCE) resource conflicts with each other based on MU pairing information of each multi-user (MU) pairing group and a first signal-to-interference-plus-noise ratio (SINR) for each UE in each MU pairing group with respect to the physical downlink control channel (PDCCH); and performing the following operations for each MU pairing group: adjusting a first transmit power for each UE in the MU pairing group and updating the first SINR for each UE in the MU pairing group based on first information including the MU pairing information of the MU pairing group and the first SINR for each UE in the MU pairing group, using a first AI model; and determining schedulable MU pairing groups and second CCE resource occupancy information and a second transmit power for each UE in each schedulable MU pairing group based on the adjusted transmit power and the updated SINR for each UE.

Description

Technical Field

[0001] This application relates to the field of wireless communication, and more specifically, to a method performed by a network node and a network node. Background Technology

[0002] Given the successive generations of wireless communication development, these technologies have primarily been developed for human-oriented services such as voice calls, multimedia services, and data services. With the commercialization of 5th-generation (5G) communication systems, the number of connected devices is expected to grow exponentially. These will increasingly connect to communication networks. Examples of the Internet of Things (IoT) can include vehicles, robots, drones, home appliances, displays, smart sensors connected to various infrastructures, construction machinery, and factory equipment. Mobile devices are expected to evolve in various forms, such as augmented reality glasses, virtual reality headsets, and holographic devices. Efforts are underway to develop improved 6G communication systems to provide a wide range of services by connecting hundreds of billions of devices and things in the sixth-generation (6G) era.

[0003] The 6G communication system, expected to be commercially available around 2030, will offer significant improvements in all aspects compared to existing 5G systems. Its peak speed will reach at least 50 Gbit / s, user experience speed will reach at least 300 Mbit / s, air interface latency will be less than 1 ms, and air interface reliability will reach 10... -5 In addition to the basic communication indicators mentioned above, 6G communication systems will also have sensing capabilities, AI-related capabilities, and better security, interoperability, and sustainability.

[0004] To achieve the aforementioned performance indicators in 6G communication systems, more advanced air interface and network technologies are needed. Currently, the evolution of extreme multiple input multiple output (MIMO) is being considered, including the use of very large-scale antenna arrays, the development and evolution of distributed antenna systems, and the design of MIMO air interface algorithms assisted by artificial intelligence (AI). This technology can achieve higher spectral efficiency, greater coverage, and more precise positioning and sensing capabilities. Furthermore, technologies that contribute to improving high-frequency coverage, such as metamaterial-based lenses and antennas, novel antenna architectures, and reconfigurable intelligence surfaces (RIS), also require further evolution and development.

[0005] To meet the new functionalities added to 6G communication systems, it is necessary to develop new technologies in areas such as network energy saving, air interface security, and network security, while also studying the feasibility of converged technologies such as integrated communication and sensing.

[0006] In addition, to improve spectrum efficiency and overall network performance, the following technologies have been developed for 6G communication systems: full-duplex technology to enable uplink and downlink transmissions to use the same frequency resources simultaneously; network technologies that utilize satellites, high-altitude platform stations (HAPS), etc., in a comprehensive manner; improved network architecture to support mobile base stations, etc., and to enable network operation optimization and automation; dynamic spectrum sharing technology based on spectrum usage prediction and conflict avoidance; the use of artificial intelligence (AI) in wireless communication to improve overall network operation by utilizing AI from the design phase of 6G development and internalizing end-to-end AI support functions; and next-generation distributed computing technologies that overcome the computing power limitations of user equipment (UE) by leveraging ultra-high-performance communication and computing resources (such as mobile edge computing (MEC), cloud, etc.) achievable on the network. Furthermore, efforts are continuing to enhance connectivity between devices, optimize networks, promote the software-defined networking of network entities, and increase the openness of wireless communications by designing new protocols to be used in 6G communication systems, developing mechanisms for achieving hardware-based secure environments and secure data use, and developing technologies for maintaining privacy.

[0007] The research and development of 6G communication systems, encompassing hyper-connectivity for both person-to-machine (P2M) and machine-to-machine (M2M) interactions, is expected to deliver the next wave of hyper-connected experiences. Specifically, services such as truly immersive extended reality (XR), high-fidelity mobile holograms, and digital replicas are anticipated to be provided through 6G communication systems. Furthermore, services such as remote surgery for enhanced security and reliability, industrial automation, and emergency response will be available via 6G communication systems, enabling the technology to be applied across a wide range of sectors including industry, healthcare, automotive, and home appliances. Summary of the Invention

[0008] The purpose of this application is to address at least one of the technical shortcomings of existing communication methods in order to better meet communication needs. To achieve this purpose, the technical solution proposed in this application is as follows.

[0009] According to a first aspect of the embodiments of this application, a method executed by a network node is provided, comprising: determining MU pairing groups that have control channel element (CCE) resource conflicts with each other based on MU pairing information of each multi-user (MU) pairing group and a first signal-to-interference-plus-noise ratio (SINR) with respect to the physical downlink control channel (PDCCH) for each UE in each MU pairing group; performing the following operations for each MU pairing group: adjusting a first transmit power for each UE in the MU pairing group and updating the first SINR for each UE in the MU pairing group based on first information including the MU pairing information of the MU pairing group and the first SINR for each UE in the MU pairing group through a first AI model, wherein if there are other MU pairing groups that have CCE resource conflicts with the MU pairing group, the first information also includes the MU pairing information of the other MU pairing groups and the first SINR with respect to the PDCCH for each UE in the other MU pairing groups; determining schedulable MU pairing groups and second CCE resource occupancy information and second transmit power for each UE in each schedulable MU pairing group based on the adjusted transmit power and the updated SINR for each UE.

[0010] Optionally, the step of determining MU pairing groups that have CCE resource conflicts with each other based on the MU pairing information of each MU pairing group and the first SINR of each UE in each MU pairing group regarding the PDCCH includes: determining the first CCE resource occupancy information for each UE based on the MU pairing information of each MU pairing group and the first SINR of each UE in each MU pairing group; and determining the MU pairing groups that have CCE resource conflicts with each other based on the first CCE resource occupancy information for each UE.

[0011] Optionally, the step of determining schedulable MU pairing groups and the second CCE resource occupancy information and second transmit power for each UE in each schedulable MU pairing group based on the adjusted transmit power and updated SINR for each UE includes: updating the first CCE resource occupancy information for each UE based on the updated SINR for each UE in each MU pairing group; determining whether there is still a first conflict group in the MU pairing group that has CCE resource conflicts with each other based on the updated CCE resource occupancy information for each UE in each MU pairing group; if there is no first conflict group, then determining all MU pairing groups as schedulable MUs. Pairing groups; or, if the first conflict group still exists, then based on the transmit power margin for each MU pairing group other than the first conflict group in all MU pairing groups, the MU pairing information of the first conflict group, the updated SINR and adjusted transmit power for each UE in the first conflict group, the transmit power for at least one UE in the first conflict group is adjusted by the second AI model and the updated SINR for that at least one UE is updated; the updated CCE resource occupancy information for each UE is updated according to the updated SINR for each UE in all MU pairing groups, and the schedulable MU pairing group is determined.

[0012] Optionally, after adjusting the transmit power for at least one UE in the first conflict group using the second AI model, the step of determining the schedulable MU pairing group includes: determining whether a second conflict group still exists after the first conflict group has undergone transmit power adjustment using the second AI model and has CCE resource conflicts with each other; if no second conflict group exists, then all MU pairing groups are determined as schedulable MU pairing groups; or, if a second conflict group exists, then the schedulable MU pairing groups in the second conflict group determined based on the scheduling priority of each UE in the second conflict group, and the MU pairing groups in all MU pairing groups other than the second conflict group are determined as schedulable MU pairing groups.

[0013] Optionally, the transmit power margin for each MU pairing group other than the first conflict group is determined by the following operation: calculating the transmit power margin for each MU pairing group based on the adjusted transmit power of each UE in each MU pairing group other than the first conflict group.

[0014] Optionally, the step of determining the schedulable MU pairing group and the second CCE resource occupancy information and the second transmit power for each UE in each schedulable MU pairing group based on the adjusted transmit power and updated SINR for each UE further includes: determining whether the total transmit power for all schedulable MU pairing groups is less than the maximum transmit power of the base station; if the total transmit power is less than the maximum transmit power of the base station, then allocating the remaining transmit power of the base station to at least one UE in all schedulable MU pairing groups to adjust the transmit power for the at least one UE, and keeping the updated CCE resource occupancy information and updated SINR for the at least one UE unchanged.

[0015] Optionally, the step of determining schedulable MU pairing groups and the second CCE resource occupancy information and the second transmit power for each UE in each schedulable MU pairing group based on the adjusted transmit power and updated SINR for each UE includes: determining whether a first condition is met based on the adjusted transmit power, updated SINR, and CCE resource occupancy information associated with the updated SINR for each UE in each schedulable MU pairing group; if the first condition is met, determining the adjusted transmit power and updated CCE resource occupancy information for each UE in each schedulable MU pairing group as the second transmit power and the second CCE resource occupancy information for that UE; or, if the predetermined condition is not met, determining schedulable MU pairing groups in all MU pairing groups based on the scheduling priority of each UE in all MU pairing groups, and determining the first transmit power and the first CCE resource occupancy information associated with the first transmit power for each UE as the second transmit power and the second CCE resource occupancy information for that UE.

[0016] Optionally, the predetermined condition is satisfied when the following three conditions are met simultaneously: the sum of the adjusted transmit power for each UE in all schedulable MU pairings satisfies the power constraint; the sum of the CCE resource occupancy for all schedulable MU pairings satisfies the CCE resource constraint; and the updated SINR for each UE in all schedulable MU pairings satisfies the SINR constraint.

[0017] Optionally, the first SINR for each UE is obtained by the following operations: determining the second SINR for each UE with respect to the PDCCH based on the sounding reference signal (SRS) and channel state information (CSI) reported by each UE; determining the SINR offset for each UE with respect to the PDCCH; determining the multi-user loss for each UE; and calculating the first SINR for each UE based on the second SINR for each UE, the SINR offset, and the multi-user loss.

[0018] Optionally, the step of determining the second SINR for each UE with respect to the PDCCH based on the sounding reference signal (SRS) and channel state information (CSI) reported by each UE includes: calculating the first demodulation SINR and the second demodulation SINR for each UE with respect to the PDSCH based on the SRS and CSI reported by each UE; calculating the SINR difference between the first and second demodulation SINR for each UE; calculating the third SINR for each UE with respect to the PDSCH based on the CSI reported by each UE; and calculating the second SINR for each UE with respect to the PDCCH based on the SINR difference and the third SINR for each UE.

[0019] Optionally, the step of determining the SINR offset value of PDCCH for each UE includes: predicting the discontinuous transmission DTX result of PDCCH based on historical scheduling information at a preset time for each UE; and calculating the SINR offset value of PDCCH for each UE based on the DTX result of PDCCH for each UE.

[0020] Optionally, for each UE, the step of predicting the discontinuous transmission DTX result of PDCCH based on historical scheduling information over a preset time includes: performing conversion and padding processing on the historical scheduling information over the preset time to obtain continuous scheduling information in time units; for each UE, predicting the DTX result of PDCCH in the current scheduling time unit using a third AI model based on the continuous scheduling information in time units, wherein the continuous scheduling information in time units includes continuous CCE AL, continuous MU pairing information, SINR for PDCCH, continuous SRS flag, and continuous CSI flag associated with each UE within the preset time period.

[0021] Optionally, for each UE, the step of predicting the DTX result of the PDCCH for the current scheduling time unit using the third AI model based on the continuous scheduling information in the time unit includes: for each UE, obtaining the PDCCH channel state related features for the current scheduling time unit using the first sub-AI model in the third AI model based on the continuous scheduling information in the time unit; and for each UE, determining the DTX result of the PDCCH for the current scheduling time unit using the second sub-AI model in the third AI model based on the PDCCH channel state related features for the current scheduling time unit.

[0022] Optionally, the method further includes: when receiving a Hybrid Automatic Repeat Request (HARQ) feedback from the UE associated with a PDSCH scheduled by the first PDCCH, determining whether to update the third AI model.

[0023] Optionally, the step of determining whether to update the third AI model includes: if the non-DTX corresponding to the HARQ feedback is inconsistent with the first DTX result of the first PDCCH predicted by the scheduling time unit before receiving the HARQ feedback, determining to update the third AI model; or, if the non-DTX corresponding to the HARQ feedback is consistent with the first DTX result, determining not to update the third AI model.

[0024] Optionally, when it is determined that the third AI model needs to be updated, the third AI model is updated based on the non-DTX and the first scheduling information used to predict the first DTX result in the continuous scheduling information in the time unit.

[0025] Optionally, the step of updating the third AI model based on the non-DTX and the first scheduling information used to predict the first DTX result in the continuous scheduling information in time units includes: if the CCE AL in the first scheduling information is not the highest CCE AL, then obtain a training dataset by data expansion of the non-DTX and the first scheduling information, and update the third AI model based on the training dataset; or, if the CCE AL in the first scheduling information is the highest CCE AL, then update the third AI model using the non-DTX and the first scheduling information as the training dataset.

[0026] Optionally, the step of obtaining a training dataset by expanding the non-DTX and the first scheduling information includes: obtaining at least one scheduling information by adjusting the CCE AL in the first scheduling information to at least one CCE AL higher than the CCE AL; and constructing a training dataset by combining the at least one scheduling information, the first scheduling information, and the non-DTX.

[0027] Optionally, the step of determining the multi-user loss for each UE includes: determining the channel correlation at the next SRS reporting time for each UE; determining the mobility weight factor associated with each UE based on the channel correlation for each UE, wherein the mobility weight factor represents the degree of channel change caused by the movement of the corresponding UE; and adjusting the multi-user loss for each UE based on the mobility weight factor associated with each UE.

[0028] Optionally, for each UE, the step of determining the channel correlation of the next SRS reporting time includes: for each UE, determining the channel correlation of the next SRS reporting time based on the first channel matrix and the second channel matrix of the two preceding SRS reporting times immediately adjacent to the next SRS reporting time, wherein the first channel matrix is ​​determined based on the SRS reported by the corresponding UE at the first SRS reporting time among the two preceding SRS reporting times, and the second channel matrix is ​​determined based on the SRS reported by the corresponding UE at the second SRS reporting time among the two preceding SRS reporting times.

[0029] According to a second aspect of the embodiments of this application, a network node is provided, comprising: a transceiver for transmitting and receiving signals; and a processor coupled to the transceiver and configured to perform the methods described above.

[0030] According to a third aspect of the present application, a computer-readable storage medium for storing instructions is provided, wherein when the instructions are executed by at least one processor, they cause the at least one processor to perform the method described above.

[0031] The beneficial effects of the technical solutions provided in this application will be explained in the following text in conjunction with specific optional embodiments, or can be learned from the description of the embodiments, or can be learned through the implementation of the embodiments. Attached Figure Description

[0032] To more clearly and easily illustrate and understand the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments of this application will be briefly introduced below.

[0033] Figure 1 An example wireless network according to an embodiment of this disclosure is shown.

[0034] Figure 2 An example base station according to an embodiment of the present disclosure is shown.

[0035] Figure 3 An example user equipment according to an embodiment of the present disclosure is shown.

[0036] Figure 4 This is a schematic diagram illustrating the process of the MU-PDCCH link adaptive method.

[0037] Figure 5A This is a flowchart illustrating a method performed by a network node according to an exemplary embodiment of this application.

[0038] Figure 5B This is a schematic diagram illustrating a method performed by a network node according to an exemplary embodiment of this application.

[0039] Figure 6A This is a schematic diagram illustrating a method performed by a network node according to an exemplary embodiment of this application.

[0040] Figure 6B This is a schematic diagram illustrating a method performed by a network node according to another exemplary embodiment of this application.

[0041] Figure 6C This is a schematic diagram illustrating a method performed by a network node according to another exemplary embodiment of this application.

[0042] Figure 6D This is a schematic diagram illustrating a method performed by a network node according to another exemplary embodiment of this application.

[0043] Figures 7A to 7D This is a diagram illustrating an example of power adjustment according to an exemplary embodiment of this application.

[0044] Figure 8 This is a flowchart illustrating the process of determining the first SINR for each UE in each MU pairing group according to an exemplary embodiment of this application.

[0045] Figure 9A This is a flowchart illustrating the process of determining the second SINR for each UE's PDCCH according to an exemplary embodiment of this application.

[0046] Figure 9B This is a schematic diagram illustrating the process of determining the second SINR for each UE's PDCCH according to an exemplary embodiment of this application.

[0047] Figure 10 This is a schematic diagram illustrating a process related to DTX prediction of PDCCH according to an exemplary embodiment of this application.

[0048] Figure 11 The diagram illustrates the impact of UE movement on SRS and PIM during the reporting period.

[0049] Figure 12This is a flowchart illustrating the process of determining the multi-user loss of each UE according to an exemplary embodiment of this application.

[0050] Figure 13 This is a schematic diagram illustrating the process of calculating the mobility weighting factor according to an exemplary embodiment of this application.

[0051] Figure 14 This is a block diagram illustrating an electronic device according to exemplary embodiments of the present disclosure. Detailed Implementation

[0052] Before proceeding with the following detailed description, it may be advantageous to define certain words and phrases used throughout the patent literature. The term “connection” and its derivatives refer to any direct or indirect communication between two or more elements, regardless of whether those elements are physically in contact with each other. The terms “transmit,” “receive,” and “transmit,” and their derivatives encompass both direct and indirect communication. The terms “comprise” and “include,” and their derivatives mean inclusion without limitation. The term “or” is concurrent, meaning both and / or. The phrase “associated with,” and its derivatives mean including, being included in, interconnected with, containing, being contained within, connected to or connected with, coupled to or coupled with, able to communicate with, cooperate with, intertwine, juxtapose, proximate, bound to or bound with, having, possessing attributes, having a relationship with, or having a relationship with, etc. The term “controller” means any device, system, or part thereof that controls at least one operation. Such a controller may be implemented in hardware or in a combination of hardware and software and / or firmware. The functionality associated with any particular controller, whether local or remote, can be centralized or distributed. The phrase "at least one" when used to list items means that different combinations of one or more of the listed items can be used, and it is possible that only one item in the list is needed. For example, "at least one of A, B, and C" includes any of the following combinations: A, B, C; A and B; A and C; B and C; and only A, only B, and only C. Similarly, the term "set" means one or more. Therefore, a set of items can be a single item or a set of two or more items.

[0053] Furthermore, the various functions described below can be implemented or supported by one or more computer programs, each function being formed by computer-readable program code and embodied in a computer-readable medium. The terms "application" and "program" refer to one or more computer programs, software components, instruction sets, procedures, functions, objects, classes, instances, associated data, or portions thereof suitable for implementation in appropriate computer-readable program code. The phrase "computer-readable program code" includes any type of computer code, including source code, object code, and executable code. The phrase "computer-readable medium" includes any type of medium accessible by a computer, such as read-only memory (ROM), random access memory (RAM), hard disk drive, compact disc (CD), digital video disc (DVD), or any other type of storage. "Non-transitory" computer-readable media excludes wired, wireless, optical, or other communication links that transmit transient electrical or other signals. Non-transitory computer-readable media includes media in which data can be permanently stored and media such as rewritable optical discs or erasable memory devices in which data can be stored and later rewritten.

[0054] Definitions for certain other words and phrases are provided throughout this patent document. Those skilled in the art will understand that, in many, if not the most, instances, such definitions apply to both prior and future use of the words and phrases defined in this way.

[0055] The figures and various embodiments included herein, used to illustrate the principles of this disclosure, are merely illustrative and should not be construed in any way as limiting the scope of this disclosure. Furthermore, those skilled in the art will understand that the principles of this disclosure can be implemented in any suitably arranged wireless communication system.

[0056] The following Figures 1 to 3 Various embodiments of this disclosure implemented in wireless communication systems are described. Figures 1 to 3 The description does not imply any physical or architectural limitations on the ways in which different embodiments can be implemented. Different embodiments of this disclosure can be implemented in any suitably arranged communication system.

[0057] Figure 1 An example wireless network according to an embodiment of this disclosure is shown. Figure 1 The embodiments of the wireless network shown are for illustrative purposes only. Other embodiments of the wireless network 100 may be used without departing from the scope of this disclosure.

[0058] like Figure 1As shown, the wireless network includes a base station (next generation nodeB, gNB or gNodeB) 101, gNB 102, and gNB 103. gNB 101 communicates with gNB 102 and gNB 103. gNB 101 also communicates with at least one network 130 such as the Internet, Internet Protocol (IP) networks, or other data networks.

[0059] gNB 102 provides wireless broadband access to network 130 to multiple first user equipments (UEs) within coverage area 120 of gNB 102. The multiple first UEs include UE 111, which may be located in a small business (SB); UE 112, which may be located in an enterprise (E); UE 113, which may be located in a WiFi hotspot (HS); UE 114, which may be located in a first residence (R1); UE 115, which may be located in a second residence (R2); and UE 116, which may be a mobile device (M) such as a cellular phone, wireless laptop, or wireless personal digital assistant (PDA). gNB 103 provides wireless broadband access to network 130 to multiple second UEs within coverage area 125 of gNB 103. The multiple second UEs include UE 115 and UE 116, and subscriber stations (SS, such as UEs) 117, 118, and 119. In some embodiments, one or more of gNBs 101-103 may communicate with each other and UEs 111-116 using existing wireless communication technologies, and one or more of UEs 111-119 may communicate directly with each other (e.g., UEs 117-119) using other existing or proposed wireless communication technologies.

[0060] Depending on the network type, the term "base station" or "BS" can refer to any component (or set of components) configured to provide wireless access to a network, such as a transmit point (TP), transmit-receive point (TRP), enhanced (or "evolved") base station (eNodeB or eNB), 5G base station (gNB), macro cell, femtocell, wireless fidelity (WiFi) access point (AP), or other wireless-capable devices. A base station can provide wireless access according to one or more wireless communication protocols, such as 3GPP 5G new radio (NR), Long Term Evolution (LTE), LTE-Advanced (LTE-A), high-speed packet access (HSPA), Wi-Fi 802.11a / b / g / n / ac, etc. For convenience, various names for base station type devices and functions may be used interchangeably in this patent document to refer to network infrastructure components that provide wireless access to remote terminals. Furthermore, depending on the network type, the term "User Equipment" (UE) can refer to any component such as a mobile station (MS), user station (SS), remote terminal, wireless terminal, receiving point, or user device. For convenience, various names for user equipment type devices and functions may be used interchangeably in this patent document to refer to remote wireless devices that wirelessly access the BS regardless of whether the UE is a mobile device (such as a mobile phone or smartphone) or is generally considered a fixed device (such as a desktop computer or vending machine).

[0061] The dashed lines indicate the approximate extent of coverage areas 120 and 125, which are shown as roughly circular for illustrative and explanatory purposes only. It should be clearly understood that coverage areas such as 120 and 125 associated with the gNB can have other shapes, including irregular shapes, depending on the configuration of the gNB and variations in the wireless environment associated with natural and man-made obstacles.

[0062] As described in more detail below, one or more of UEs 111-119 include circuitry, programming, or a combination thereof. In some embodiments, one or more of gNBs 101-103 include circuitry, programming, or a combination thereof.

[0063] although Figure 1 An example of a wireless network is shown, but more can be found on... Figure 1Various modifications can be made. For example, wireless network 100 can include any number of gNBs and any number of UEs in any suitable arrangement. Furthermore, gNB 101 can communicate directly with any number of UEs and provide those UEs with wireless broadband access to network 130. Similarly, each gNB 102-103 can communicate directly with network 130 and provide UEs with direct wireless broadband access to network 130. Additionally, gNBs 101, 102, and / or 103 can provide access to other or additional external networks, such as external telephone networks or other types of data networks.

[0064] Figure 2 An example base station according to an embodiment of the present disclosure is shown. Figure 2 The embodiment of gNB 102 shown is for illustrative purposes only, and Figure 1 gNBs 101 and 103 can have the same or similar configurations. However, gNBs come in a variety of configurations, and Figure 2 This disclosure is not intended to limit the scope to any particular implementation of gNB.

[0065] like Figure 2 As shown, gNB 102 includes multiple antennas 200a-200n, multiple radio frequency (RF) transceivers 201a-201n, transmit (TX) processing circuitry 203, and receive (RX) processing circuitry 204. gNB 102 also includes a controller / processor 205, a memory 206, and a backhaul or network interface (IF) 207.

[0066] RF transceivers 201a-201n receive incoming RF signals from antennas 200a-200n, such as signals transmitted by the UE in network 100. RF transceivers 201a-201n down-convert the incoming RF signals to generate intermediate frequency (IF) or baseband signals. The IF or baseband signal is sent to RX processing circuitry 204, which generates a processed baseband signal by filtering, decoding, and / or digitizing the baseband or IF signal. RX processing circuitry 204 sends the processed baseband signal to controller / processor 205 for further processing.

[0067] The TX processing circuit 203 receives analog or digital data (such as voice data, web data, email, or interactive video game data) from the controller / processor 205. The TX processing circuit 203 encodes, multiplexes, and / or digitizes the outgoing baseband data to generate a processed baseband or IF signal. RF transceivers 201a-201n receive the processed baseband or IF signal from the TX processing circuit 203 and up-convert the baseband or IF signal into an RF signal transmitted via antennas 201a-201n.

[0068] The controller / processor 205 may include one or more processors or other processing devices that control the overall operation of the gNB 102. For example, the controller / processor 205 may control the reception of forward channel signals and the transmission of reverse channel signals by the RF transceivers 201a-201n, the RX processing circuit 204, and the TX processing circuit 203, according to known principles. The controller / processor 205 may also support additional functions, such as more advanced wireless communication functions.

[0069] For example, the controller / processor 205 can support beamforming or directional routing operations, where signals emitted from multiple antennas 200a-200n are weighted differently to effectively redirect the emitted signals in the desired direction. Any of a variety of other functions can be supported in the gNB 102 via the controller / processor 205.

[0070] The controller / processor 205 is also capable of executing programs and other processes located in the memory 206, such as the operating system (OS). The controller / processor 205 can move data into or out of the memory 206 as needed by the executing process.

[0071] The controller / processor 205 is also connected to a backhaul or network interface 207. The backhaul or network interface 207 allows the gNB 102 to communicate with other devices or systems via a backhaul connection or over a network. Interface 207 can support communication via any suitable wired or wireless connection(s). For example, when the gNB 102 is implemented as part of a cellular communication system (such as a cellular communication system supporting 5G, LTE, or LTE-A), interface 207 can allow the gNB 102 to communicate with other gNBs via a wired or wireless backhaul connection. When the gNB 102 is implemented as an access point, interface 207 can allow the gNB 102 to communicate via a wired or wireless local area network or via a wired or wireless connection to a larger network (such as the Internet). Interface 207 includes any suitable structure that supports communication via wired or wireless connections such as Ethernet or RF transceivers.

[0072] Memory 206 is connected to controller / processor 205. A portion of memory 206 may include random access memory (RAM), and another portion of memory 206 may include flash memory or other read-only memory (ROM).

[0073] although Figure 2 An example of gNB 102 is shown, but it is possible to see more. Figure 2 Various changes can be made. For example, gNB 102 can include any number of Figure 2 Each component is shown in the diagram. As a specific example, an access point may include multiple interfaces 207, and the controller / processor 205 may support routing functionality to route data between different network addresses. As another specific example, although shown as a single instance of TX processing circuitry 203 and a single instance of RX processing circuitry 204, gNB102 may include multiple instances of each (such as one per RF transceiver). For example, Figure 2 The various components can be combined, further subdivided, or omitted, and additional components can be added as needed.

[0074] Figure 3 An example user equipment according to an embodiment of the present disclosure is shown. Figure 3 The embodiment of UE 116 shown is for illustrative purposes only, and Figure 1 UEs 111-115 and 117-119 can have the same or similar configurations. However, UEs appear in multiple configurations, and Figure 3 This disclosure is not intended to limit the scope to any particular implementation of the UE.

[0075] like Figure 3 As shown, UE 116 includes an antenna 301, a radio frequency (RF) transceiver 302, a TX processing circuit 303, a microphone 304, and a receive (RX) processing circuit 305. UE 116 also includes a speaker 306, a controller or processor 307, an input / output (I / O) interface (IF) 308, an input device 309, a touchscreen display 310, and memory 311. Memory 311 includes an OS 312 and one or more applications 313.

[0076] RF transceiver 302 receives incoming RF signals transmitted by gNB of network 100 from antenna 301. RF transceiver 302 down-converts the incoming RF signals to generate IF or baseband signals. The IF or baseband signals are sent to RX processing circuitry 305, which generates processed baseband signals by filtering, decoding, and / or digitizing the baseband or IF signals. RX processing circuitry 305 sends the processed baseband signals to speaker 306 (e.g., for voice data) or processor 307 for further processing (e.g., for web browsing data).

[0077] TX processing circuit 303 receives analog or digital voice data from microphone 304 or other outgoing baseband data (such as web data, email, or interactive video game data) from processor 307. TX processing circuit 303 encodes, multiplexes, and / or digitizes the outgoing baseband data to generate a processed baseband or IF signal. RF transceiver 302 receives the processed baseband or IF signal from TX processing circuit 303 and up-converts the baseband or IF signal into an RF signal transmitted via antenna 301.

[0078] Processor 307 may include one or more processors or other processing devices and executes OS 312 stored in memory 311 to control the overall operation of UE 116. For example, processor 307 may control the reception of forward channel signals and the transmission of reverse channel signals by RF transceiver 302, RX processing circuitry 305, and TX processing circuitry 303 according to known principles. In some embodiments, processor 307 includes at least one microprocessor or microcontroller.

[0079] Processor 307 is also capable of executing other processes and programs located in memory 311, such as processes for CSI (Channel State Information) reporting on the uplink channel. Processor 307 can move data into or out of memory 311 as needed for executing processes. In some embodiments, processor 307 is configured to execute application 313 based on OS 312 or in response to signals received from gNB or operator. Processor 307 is also coupled to I / O interface 308, which provides UE 116 with the ability to connect to other devices such as laptops and laptops. I / O interface 308 is the communication path between these accessories and processor 307.

[0080] The processor 307 is also connected to the touchscreen display 310. The user of the UE 116 can use the touchscreen display 310 to input data into the UE 116. The touchscreen display 310 can be a liquid crystal display, a light-emitting diode display, or other display capable of rendering text and / or at least limited graphics such as those from a website.

[0081] Memory 311 is connected to processor 307. A portion of memory 311 may include RAM, and another portion of memory 311 may include flash memory or other ROM.

[0082] although Figure 3 An example of UE 116 is shown, but it is possible to modify it. Figure 3 Make various changes. For example, Figure 3 The various components can be combined, further subdivided, or omitted, and additional components can be added as needed. As a specific example, processor 307 can be divided into multiple processors, such as one or more central processing units (CPUs) and one or more graphics processing units (GPUs). Moreover, although... Figure 3 The UE 116 is shown configured as a mobile phone or smartphone, but the UE can be configured to operate as other types of mobile or fixed devices.

[0083] The Physical Downlink Control Channel (PDCCH) is a physical channel in a wireless network used to carry downlink control information (DCI). DCI includes scheduling information for uplink or downlink data channels, power control, and other user equipment (UE) control information.

[0084] With the continuous development of wireless communication networks, users have increasingly higher requirements for service transmission rates. Multiple-Input Multiple-Output (MIMO) technology utilizes multiple transmit antennas and multiple receive antennas to create multiple parallel spatial transmission channels on the same time-frequency resources. These transmission channels are independent of each other and can transmit data from different users simultaneously, thereby greatly improving the system's data transmission capacity and allowing support for more users.

[0085] As the number of base station antennas increases, more Physical Downlink Shared Channel (PDSCH) resources can be allocated to more users. However, the number of UEs that can be scheduled simultaneously is limited by PDCCH resources. The physical resource unit of PDCCH carrying DCI information is the Control Channel Element (CCE). For the same CCE resource, Single User-PDCCH (SU-PDCCH) technology can only allocate it to a single user to transmit control information. Therefore, SU-PDCCH technology suffers from poor scheduling flexibility, low resource allocation efficiency, and difficulty in improving cell capacity. Multi-User-PDCCH (MU-PDCCH) technology can transmit control information to multiple users on the same CCE resource, improving the flexibility of multi-user scheduling and resource utilization, and increasing the overall cell capacity. Therefore, MU-PDCCH technology is an inevitable trend in network development.

[0086] In wireless communication systems, the channel environment is complex and variable. To ensure transmission reliability, Link Adaptation (LA), one of the core technologies of wireless communication, is employed. For example, PDCCH LA can dynamically allocate control channel resources based on real-time channel conditions. When channel conditions are good, PDCCH LA can allocate fewer Control Channel Encoders (CCEs) to the UE to improve resource utilization; when channel conditions deteriorate, PDCCH LA can increase the number of CCEs allocated to the UE, allowing for lower coding rates and stronger error correction coding to ensure reliable transmission of control information. The number of allocated CCEs is typically represented by the CCE Aggregation Level (CCE AL), as shown in Table 1, which illustrates the AL definition provided by the protocol.

[0087] Table 1

[0088] AL Number of CCEs 1 1 2 2 4 4 8 8 16 16

[0089] In the MU scenario, link adaptation of the MU-PDCCH needs to be enhanced to effectively improve cell scheduling capabilities and increase cell capacity. For example, since multiple UEs share the same control channel resources, the accuracy of channel state assessment for each UE and / or the rationality of CCE resource allocation pose greater challenges.

[0090] Figure 4 This is a schematic diagram illustrating the process of the MU-PDCCH link adaptive method.

[0091] like Figure 4 As shown in step 410, the base station calculates the signal-to-interference plus noise ratio (SINR) of the PDSCH for the UE using the Channel Quality Indicator (CQI), Rank Indicator (RI) carried in the Channel Status Information (CSI) reported by the UE, and the Hybrid Automatic Repeat Request (HARQ) information fed back by the PDSCH. 。

[0092] In step 420, based on the discontinuous transmission (DTX) results of the Physical Uplink Shared Channel (PUSCH), the base station calculates the SINR offset of the PDCCH for the UE using the Outer Loop Rate Control (OLRC) algorithm.

[0093] In step 430, the base station calculates the SINR of the PDCCH for the UE based on the SINR of the PDSCH for the UE, the SINR offset of the PDCCH, and the Multiple Users Loss (MU_Loss) information. Specifically, the transmit power used by the base station when transmitting signals on the PDCCH (i.e., the base station's PDCCH transmit power) is evenly distributed across all CCE resources. When the same CCE resource is shared by multiple paired UEs, the transmit power on the same CCE resource is again evenly distributed among the multiple paired UEs. Since MU_Loss contains information about the number of paired UEs, it can be used to obtain the transmit power for each paired UE and calculate the SINR of the PDCCH for each UE.

[0094] In step 440, the base station determines the corresponding CCE AL for each UE based on the SINR of the PDCCH for each UE using the mapping relationship between CCE AL and the SINR of the PDCCH. The base station defines the mapping relationship between CCE AL and the SINR of the PDCCH using a fixed SINR threshold of the PDCCH.

[0095] Figure 5A This is a flowchart illustrating a method performed by a network node according to an exemplary embodiment of this application. Figure 5BThis is a schematic diagram illustrating a method performed by a network node according to an exemplary embodiment of this application. Figure 6A This is a schematic diagram illustrating a method performed by a network node according to an exemplary embodiment of this application. In this application, a network node may be a base station, a component of a base station (e.g., a centralized unit (CU), a distributed unit (DU), etc.), or other network servers operating independently of the base station; this application does not specifically limit this.

[0096] like Figure 5A As shown, in step S501, based on the MU pairing information of each MU pairing group and the first SINR of each UE in each MU pairing group regarding PDCCH, MU pairing groups that have CCE resource conflicts with each other are determined.

[0097] Specifically, the MU pairing information of the MU pairing group includes the identification (ID) information of each UE in the MU pairing group and the CCE resource start position information, which indicates the start position of the CCE resource occupied by the corresponding UE.

[0098] In this application, the step of determining MU pairing groups with CCE resource conflicts based on MU pairing information of each MU pairing group and the first SINR of each UE in each MU pairing group regarding the PDCCH includes: determining first CCE resource occupancy information for each UE based on the MU pairing information of each MU pairing group and the first SINR of each UE in each MU pairing group; and determining MU pairing groups with CCE resource conflicts based on the first CCE resource occupancy information for each UE. Specifically, the CCE resource occupancy information for a UE (e.g., first CCE resource occupancy information, second CCE resource occupancy information, etc.) may include the UE's CCE resource start position information and CCE AL. For example, for a MU pairing group (e.g., the first MU pairing group), the CCE AL of each UE in the MU pairing group can be determined by a lookup table method based on a comparison between the first SINR of each UE in the MU pairing group and a predetermined threshold. Subsequently, the CCE resource occupancy information for each UE can be determined based on the CCE resource start position information of each UE in the MU pairing information of the MU pairing group and the CCE AL of each UE. Based on this, it can be determined whether the MU pairing group to which each UE belongs has a CCE resource conflict with other MU pairing groups by using the CCE resource occupancy information for each UE.

[0099] For example, such as Figure 6AAs shown in the diagram, assume there are N MU pairing groups, group 1 includes two UEs (UE1 and UE2), group 2 includes three UEs (UE3, UE4, and UE5), ..., group N includes two UEs (UEm and UEn). Figure 6A As shown, in operation 611, the first CCE resource occupancy information for each UE can be determined based on the MU pairing information of each MU pairing group in these N MU pairing groups and the first SINR of each UE. Then, MU pairing groups that have CCE resource conflicts with each other are determined based on the first CCE resource occupancy information for each UE. In some embodiments of this application, some MU pairing groups may not have other MU pairing groups that have CCE resource conflicts with them.

[0100] In step S502, the following operations are performed for each MU pairing group: based on the MU pairing information including the MU pairing group and the first information of the first SINR for each UE in the MU pairing group, the first transmit power for each UE in the MU pairing group is adjusted through the first AI model, and the first SINR for each UE in the MU pairing group is updated. If there are other MU pairing groups that have CCE resource conflicts with the MU pairing group, the first information also includes the MU pairing information of the other MU pairing groups and the first SINR of each UE in the other MU pairing groups regarding the PDCCH.

[0101] Specifically, such as Figure 6A As shown, in operation 612, the first AI model can process N MU pairing groups in parallel, that is, the first AI model can process the information input for N MU pairing groups simultaneously. For example, first information including MU pairing information for group 1 and the first SINR for each UE (i.e., UE1 and UE2) in group 1 can be input into the first AI model. In addition, if there are other MU pairing groups (which may be referred to as conflicting groups) that have CCE resource conflicts with group 1, i.e., group 2, the first information input into the first AI model also includes MU pairing group information for group 2 and the first SINR for each UE in group 2 regarding the PDCCH. Accordingly, the first AI model can adjust the first transmit power of each UE in group 1 and update the first SINR for each UE. In this application, the first transmit power of each UE can be determined by an average allocation method, for example, as referred to above. Figure 4In the described method, the transmit power used by the base station when transmitting signals on the PDCCH (i.e., the base station's PDCCH transmit power) can be evenly distributed across all CCE resources. When the same CCE resource is shared by multiple UEs in a MU pairing group, the transmit power on the same CCE resource is again evenly distributed among the multiple UEs. At this point, the transmit power for each UE is the first transmit power. Specifically, for group 1, the first AI model can adjust the first transmit power for each UE in group 1 to minimize the total transmit power for group 1 and the CCE resource conflicts between group 1 and other MU pairing groups. After adjusting the transmit power for each UE in group 1, the first AI model updates the first SINR for each UE accordingly. In this case, the first AI model can output the adjusted transmit power and updated SINR for each UE in group 1. Similarly, the first AI model can adjust the first transmit power for each UE in each MU pairing group and update the first SINR for each UE using the first AI model. For example, as... Figure 6A As shown, the first AI model can output the adjusted transmit power and updated SINR for each UE in each MU pair. Furthermore, if a certain MU pair does not have other MU pairing groups that conflict with it in terms of CCE resources, then for that MU pairing group, the first information input to the first AI model includes the MU pairing information of that MU pairing group and the first SINR of each UE in that MU pairing group regarding the PDCCH, but does not include the MU pairing information of other MU pairing groups and the first SINR of each UE in those other MU pairing groups regarding the PDCCH. Based on this, the first AI model can also adjust the first transmit power for each UE in that MU pairing group and update the first SINR for each UE.

[0102] In step S503, based on the adjusted transmit power and updated SINR for each UE, the schedulable MU pairing group and the second CCE resource occupancy information and the second transmit power for each UE in each schedulable MU pairing group are determined, that is, the CCE resource occupancy information and transmit power that are finally applied to each UE are determined.

[0103] In one exemplary embodiment of this application, step S503 may include: updating the first CCE resource occupancy information for each UE based on the updated SINR for each UE in each MU pairing group; determining schedulable MU pairing groups based on the updated CCE resource occupancy information; and determining the transmit power for each UE based on the adjusted transmit power for each UE. Specifically, the CCE AL for each UE may be re-determined by looking up a table based on a comparison between the updated SINR and a predetermined threshold, thereby updating the CCE AL in the first CCE resource occupancy information for each UE. Then, it may be determined whether there is a CCE resource conflict between each MU pairing group and other MU pairing groups based on the updated CCE resource occupancy information for each UE in each MU pairing group. If there is no CCE resource conflict between each MU pairing group and other MU pairing groups, then all MU pairing groups are determined as schedulable MU pairing groups. If there are still MU pairing groups that conflict with each other for CCE resources (referred to as the first conflict group), then the schedulable MU pairing groups in these first conflict groups can be determined based on the scheduling priority of each UE in these first conflict groups. These schedulable MU pairing groups, along with all MU pairing groups excluding the first conflict groups, are then determined as the final schedulable MU pairing groups. For example, such as... Figure 6A As shown, in operation 613, the first CCE resource occupancy information for each UE can be updated according to the updated SINR for each UE. Based on the updated CCE resource occupancy information for each UE, it is determined that there is still a CCE resource conflict between group 1 and group 2. If UE1 has the highest priority 1 in group 1, then the priority 1 of UE1 can be determined as the priority of group 1. If UE3 has the highest priority 2 in group 2, then the priority 2 of UE3 can be determined as the priority of group 2. Therefore, in the case of a CCE resource conflict between group 1 and group 2, group 1 can be determined as a schedulable MU pairing group because the priority of group 1 is higher than the priority of group 2. On this basis, the MU pairing groups other than group 1 and group 2 in N groups, as well as group 1, can be determined as schedulable MU pairing groups. In other words, the MU pairing groups other than group 2 in N groups can be determined as schedulable MU pairing groups. After determining the schedulable MU pairing groups, the updated CCE resource occupancy information for each UE in each schedulable MU pairing group can be determined as the second CCE resource occupancy information for the corresponding UE, and the adjusted transmit power for each UE in each schedulable MU pairing group can be determined as the second transmit power for the corresponding UE. For example... Figure 6AAs shown, the schedulable MU pairing groups and the second CCE resource occupancy information and second transmit power for each UE in each schedulable MU pairing group can be determined. In addition, the SINR for each UE in each schedulable MU pairing group can also be determined.

[0104] In another exemplary embodiment of this application, after the above step S502, it can be determined whether to further adjust the transmit power for at least one UE in these MU pairing groups through the second AI model based on whether there are still MU pairing groups in all MU pairing groups that have CCE resource conflicts with each other.

[0105] Specifically, step S503 may include: updating the first CCE resource occupancy information for each UE based on the updated SINR for each UE in each MU pairing group; determining whether there is still a first conflict group in the MU pairing group that has CCE resource conflicts with each other based on the updated CCE resource occupancy information for each UE in each MU pairing group; if there is no first conflict group, then determining all MU pairing groups as schedulable MU pairing groups; or, if there is still a first conflict group, then adjusting the transmission power for at least one UE in the first conflict group and updating the updated SINR for that at least one UE based on the transmit power margin for each MU pairing group other than the first conflict group, the MU pairing information of the first conflict group, the updated SINR for each UE in the first conflict group, and the adjusted transmit power through a second AI model; updating the updated CCE resource occupancy information for each UE based on the updated SINR for each UE in all MU pairing groups, and determining the schedulable MU pairing group. (Refer to the following...) Figure 6B This will be described in detail.

[0106] Figure 6B This is a schematic diagram illustrating a method performed by a network node according to an exemplary embodiment of this application.

[0107] like Figure 6B As shown, due to Figure 6B Operations 611 and 612 in the middle are related to Figure 6A Operations 611 and 612 are the same, so they will not be described again here. Figure 6BOperation 613 can update the first CCE resource occupancy information for each UE based on the updated SINR for each UE in each MU pairing group, and then determine whether there are still MU pairing groups in each MU pairing group that have CCE resource conflicts with each other (hereinafter referred to as the "first conflict group" for ease of description) based on the updated CCE resource occupancy information for each UE in each MU pairing group.

[0108] If there is no first conflict group that has CCE resource conflicts with each other (i.e. Figure 6B If operation 613 is set to "No", then all MU pairing groups can be identified as schedulable MU pairing groups. Accordingly, the updated CCE resource occupancy information and adjusted transmit power for each UE in each schedulable MU pairing group can be identified as the second CCE resource occupancy information and second transmit power for that UE.

[0109] If there still exists a first conflict group that has CCE resource conflicts with each other (i.e. Figure 6B If the "yes" is selected in operation 613, then in operation 614, these first conflict groups can be filtered out from all MU pairing groups. Based on the transmit power margin for each MU pairing group (i.e., the first non-conflicting group) other than the first conflict group in all MU pairing groups, the MU pairing information of the first conflict group, the updated SINR and the adjusted transmit power for each UE in the first conflict group, the transmit power for at least one UE in the first conflict group is adjusted and the updated SINR for the at least one UE is updated through the second AI model.

[0110] For example, in this application, the transmit power margin for each MU pairing group other than the first conflict group is determined by the following operation: calculating the transmit power margin for each MU pairing group based on the adjusted transmit power of each UE in each MU pairing group other than the first conflict group. Figure 6BAs shown, the calculated transmit power margin for each MU pairing group (i.e., the first non-conflicting group) excluding the first conflicting group can be input into the second AI model. The MU pairing information of the first conflicting group, the updated SINR for each UE in the first conflicting group, and the adjusted transmit power can also be input into the second AI model. In operation 615, the second AI model adjusts the transmit power of at least one UE in the first conflicting group based on this input information to minimize CCE resource conflicts between the first conflicting groups, and updates the SINR of that at least one UE accordingly. After adjustment by the second AI model, if some or all of the first conflicting groups that previously had CCE resource conflicts no longer have CCE resource conflicts, these first conflicting groups become non-conflicting groups and can be referred to as second non-conflicting groups; if some or all of the first conflicting groups that previously had CCE resource conflicts still have CCE resource conflicts, these first conflicting groups can be referred to as second conflicting groups. Figure 6B As shown, the second AI model outputs MU pairing information for the second conflict group and / or the second non-conflict group, as well as the adjusted transmit power and updated SINR for each UE in the second conflict group and / or the second non-conflict group.

[0111] After adjusting the transmit power for at least one UE in the first collision group and updating the SINR for that at least one UE using the second AI model, as follows Figure 6B As shown, in operation 616, the updated CCE resource occupancy information for each UE is updated based on the updated SINR for each UE in all MU pairing groups, and the schedulable MU pairing groups among all MU pairing groups can be determined.

[0112] Specifically, after adjusting the transmit power for at least one UE in the first conflict group using the second AI model, the step of determining the schedulable MU pairing group includes: determining whether a second conflict group still exists after the first conflict group has undergone transmit power adjustment using the second AI model and has CCE resource conflicts with each other; if no second conflict group exists, then all MU pairing groups are determined as schedulable MU pairing groups; or if a second conflict group exists, then the schedulable MU pairing groups in the second conflict group determined based on the scheduling priority of each UE in the second conflict group, and the MU pairing groups in all MU pairing groups other than the second conflict group are determined as schedulable MU pairing groups.

[0113] For example, such as Figure 6BAs shown in the diagram, assuming that only group 1 and group 2 are the first conflict groups among the N MU pairing groups, after adjusting the transmit power for at least one UE in group 1 and group 2 using the second AI model and updating the SINR of that at least one UE, the updated CCE resource occupancy information for each UE is updated based on the updated SINR of each UE in group 1 and group 2. Then, based on the updated CCE resource occupancy information for each UE in group 1 and group 2, it is determined whether there is still a CCE resource conflict between group 1 and group 2. If it is determined that there is no longer a CCE resource conflict between group 1 and group 2, then the N MU pairing groups are determined as schedulable MU pairings. If it is determined that there is still a CCE resource conflict between Group 1 and Group 2 (at this time, both Group 1 and Group 2 can be called the second conflict group), assuming that UE1 has the highest priority 1 in Group 1 and UE3 has the highest priority 2 in Group 2, then the priority 1 of UE1 can be determined as the priority of Group 1, and the priority 2 of UE3 can be determined as the priority of Group 2. Therefore, in the case of a CCE resource conflict between Group 1 and Group 2, Group 1 can be determined as a schedulable MU pairing group based on the fact that the priority of Group 1 is higher than the priority of Group 2. On this basis, all MU pairing groups in N groups except Group 2 can be determined as schedulable MU pairing groups.

[0114] Once a schedulable MU pairing group is determined, the updated CCE resource occupancy information for each UE in each schedulable MU pairing group can be determined as the second CCE resource occupancy information for the corresponding UE, and the adjusted transmit power for each UE in each schedulable MU pairing group can be determined as the second transmit power for the corresponding UE. For example... Figure 6B As shown, through operation 616, the schedulable MU pairing groups and the second CCE resource occupancy information and second transmit power for each UE in each schedulable MU pairing group can be determined. In addition, the SINR for each UE in each schedulable MU pairing group can also be determined.

[0115] In yet another exemplary embodiment of this application, with reference to the above... Figure 6B Based on the described example, it can be further determined whether the total transmit power for all schedulable MU pairing groups is less than the maximum transmit power of the base station, that is, whether the transmit power of the base station is fully utilized. If the total transmit power for all schedulable MU pairing groups is less than the maximum transmit power of the base station, the remaining transmit power of the base station can be further allocated to the UE in each schedulable MU pairing group.

[0116] Specifically, step S503 further includes: determining whether the total transmit power for all schedulable MU pairing groups is less than the maximum transmit power of the base station; if the total transmit power is less than the maximum transmit power of the base station, then the remaining transmit power of the base station is allocated to at least one UE in all schedulable MU pairing groups to adjust the transmit power for that at least one UE, while keeping the updated CCE resource occupancy information and updated SINR unchanged for that at least one UE. Furthermore, if the total transmit power is not less than the maximum transmit power of the base station, then the adjusted transmit power for each UE in each schedulable MU pairing group is no longer adjusted. See below for further details. Figure 6C This will be described in detail.

[0117] Figure 6C This is a schematic diagram illustrating a method performed by a network node according to an exemplary embodiment of this application.

[0118] like Figure 6C As shown, Figure 6C Operations 611 to 616 in the middle Figure 6B Operations 611 to 616 are the same, so they will not be repeated here. Figure 6CIf operation 613 determines that there are no longer any first conflict groups with CCE resource conflicts after operation 612, then proceed to operation 617. Alternatively, if operation 613 determines that there are first conflict groups with CCE resource conflicts after operation 612, then operations 614 to 616 are executed, and then operation 617 is performed. In operation 617, it can be determined whether the total transmit power for all schedulable MU pairing groups is less than the maximum transmit power of the base station. That is, the total transmit power for all schedulable MU pairing groups can be determined based on the adjusted transmit power for each UE in all schedulable MU pairing groups, and then it is determined whether the total transmit power is less than the maximum transmit power of the base station. If the total transmit power is not less than the maximum transmit power of the base station, then the adjusted transmit power for the UEs in the MU pairing groups is no longer adjusted. If the total transmit power is less than the maximum transmit power of the base station, in operation 618, the remaining transmit power of the base station can be additionally allocated to all UEs in all schedulable MU pairing groups to improve transmission reliability. For example, the remaining transmit power of the base station can be additionally allocated to all UEs in all schedulable MU pairing groups according to the criterion of average allocation. However, this application is not limited to this and other criteria are also used to allocate the remaining transmit power of the base station to each UE in each schedulable MU pairing group. For example, the allocation ratio of the remaining transmit power of the base station can be determined according to the scheduling priority of the UEs in the schedulable MU pairing group, and the remaining transmit power of the base station can be additionally allocated to the UEs in the schedulable MU pairing group according to the allocation ratio. In addition, although the transmit power of the UEs in the schedulable MU pairing group is further adjusted using the remaining transmit power of the base station, the updated CCE resource occupancy information and the updated SINR for the at least one UE are not updated accordingly and remain unchanged.

[0119] In another exemplary embodiment of this application, the above references are made to... Figure 6A , Figure 6B or Figure 6CThe process of determining schedulable MU pairing groups and the second CCE resource occupancy information and second transmit power for each UE in each schedulable MU pairing group may include: determining whether a first condition is met based on the adjusted transmit power, the updated SINR, and the CCE resource occupancy information updated based on the updated SINR for each UE in each schedulable MU pairing group; if the first condition is met, determining the adjusted transmit power and the updated CCE resource occupancy information for each UE in each schedulable MU pairing group as the second transmit power and second CCE resource occupancy information for that UE; or, if the predetermined condition is not met, determining schedulable MU pairing groups in all MU pairing groups based on the scheduling priority of each UE in all MU pairing groups, and determining the first transmit power and the first CCE resource occupancy information associated with the first transmit power for each UE in each schedulable MU pairing group as the second transmit power and second CCE resource occupancy information for that UE.

[0120] For example, such as Figure 6D As shown, in operation 619, it can be determined whether the first condition is met, i.e., result verification, based on the adjusted transmit power, updated SINR, and CCE resource occupancy information updated according to the updated SINR for each UE in each schedulable MU pairing group. In one example, the first condition is met when the following three conditions are met simultaneously: the sum of the adjusted transmit powers for each UE in all schedulable MU pairing groups meets the power constraint; the sum of the CCE resource occupancy of all schedulable MU pairing groups meets the CCE resource constraint; and the updated SINR for each UE in all schedulable MU pairing groups meets the SINR constraint.

[0121] Specifically, as shown in formula (1) below, when the sum of the adjusted transmit power for each UE in all schedulable MU pairing groups is less than or equal to the maximum transmit power of the base station, it can be determined that the sum of the adjusted transmit power for each UE in all schedulable MU pairing groups satisfies the power constraint condition.

[0122] ∑ All_UE (Power[i]*AL[i])≤Pmax (1)

[0123] Where ALL_UE represents the number of UEs in all schedulable MU pairing groups, Power[i] represents the transmit power for the i-th UE in all schedulable MU pairing groups, AL[i] represents the CCE AL for the i-th UE in all schedulable MU pairing groups, and Pmax represents the maximum transmit power of the base station.

[0124] As shown in formula (2) below, when the sum of the CCE resource occupancy of all schedulable MU pairings is less than or equal to the total CCE resource, it can be determined that the sum of the CCE resource occupancy of all schedulable MU pairings satisfies the CCE resource constraint condition.

[0125] ∑ Group (maxG_AL[j])≤N CCE (2)

[0126] Where Group represents the number of all schedulable MU pairings, maxG_AL[j] represents the CCE AL of the UE with the maximum CCE AL in the j-th schedulable MU pairing, and N CCE This represents the total amount of CCE resources.

[0127] As shown in formula (3) below, when the updated SINR for each UE in all schedulable MU pairings is greater than a predetermined threshold (e.g., greater than the threshold thr_AL16 corresponding to CCE AL16), it can be determined that the updated SINR for each UE in each schedulable MU pairing satisfies the SINR constraint.

[0128] SINR[i]≥thr_AL16 (3)

[0129] Where SINR[i] represents the SINR of the i-th UE in all schedulable MU pairings, and thr_AL16 represents the threshold corresponding to CCE AL16. That is, the SINR of each UE in all schedulable MU pairings should be greater than the threshold thr_AL16 corresponding to CCE AL16, so that the Block Error Ratio (BLER) is less than 1%.

[0130] Furthermore, in another exemplary embodiment of this application, in Figure 6A Based on the example above, after determining the schedulable MU pairing groups according to the output of operation 613, it is also possible to further determine whether the total transmit power for all schedulable MU pairing groups is less than the maximum transmit power of the base station, that is, to determine whether the base station's transmit power is being fully utilized. If the total transmit power for all schedulable MU pairing groups is less than the maximum transmit power of the base station, then the remaining transmit power of the base station can be further allocated to the UEs in each schedulable MU pairing group. This operation is consistent with the above reference. Figure 6D Operations 617 and 618 describe the same operations, so they will not be repeated here.

[0131] The following reference Figures 7A to 7D For the above reference Figures 5A to 6D The methods described are illustrated with examples.

[0132] First, based on the MU pairing information for each MU pairing group and the first SINR for each UE in each MU pairing group regarding the PDCCH, MU pairing groups with CCE resource conflicts can be identified. The first SINR for each UE regarding the PDCCH is determined as follows: the base station's transmit power is evenly distributed across all CCE resources. When the same CCE resource is shared by multiple paired UEs in a MU pairing group, the transmit power allocated to that same CCE resource is again evenly distributed among the multiple paired UEs. Then, the first SINR is determined based on the transmit power for each UE. Assume the transmit power evenly distributed across each CCE is P.

[0133] like Figure 7A As shown in the figure, assuming there are 6 MU pairing groups, only 3 MU pairing groups ({UE1,UE2},{UE3,UE4,UE5},{UE6,UE7,UE8}) can be scheduled, that is, can be allocated CCE resources, based on the scheduling priority of each MU pairing group determined by the highest scheduling priority of the UE in each MU pairing group. The other three MU pairing groups ({UEh,UEi},{UEj,UEk},{UEm,UEn}) have CCE resource conflicts with MU pairing groups {UE1,UE2}, {UE3,UE4,UE5}, or {UE6,UE7,UE8} (i.e., there is a CCE resource conflict between {UE1,UE2} and {UEh,UEi}, between {UE3,UE4,UE5} and {UEj,UEk}, and between {UE6,UE7,UE8} and {UEm,UEn}), and their scheduling priority is lower than that of MU pairing groups {UE1,UE2}, {UE3,UE4,UE5}, and {UE6,UE7,UE8}, so they cannot be scheduled.

[0134] Subsequently, the following operations are performed for each MU pairing group: Based on the MU pairing information of the MU pairing group and the first information including the first SINR of each UE in the MU pairing group, the first transmit power of each UE in the MU pairing group is adjusted through the first AI model, and the first SINR of each UE in the MU pairing group is updated. If there are other MU pairing groups that have CCE resource conflicts with the MU pairing group, the first information also includes the MU pairing information of the other MU pairing groups and the first SINR of each UE in the other MU pairing groups regarding the PDCCH. That is, the transmit power of each UE in each MU pairing group is adjusted independently through the first AI model to minimize CCE resource conflicts between MU pairing groups and the total power used within the MU pairing group. Furthermore, the first AI model can update the first SINR of each UE based on the adjusted transmit power for each UE. Additionally, the first CCE resource occupancy information of each UE can be updated based on the updated SINR. Figure 7B As shown, the CCE resources indicated by 117 are the CCE resources saved after power adjustment within the MU pairing group. These saved CCE resources can be allocated to other groups that have CCE resource conflicts with this MU pairing group. SP can represent the transmit power further saved within the MU pairing group after power adjustment within the MU pairing group through the first AI model (which can be called "transmit power margin"). Even if this part of the transmit power is allocated to the UE in the current MU pairing group, it cannot further reduce the CCE resource occupation of the current MU pairing group. Therefore, this part of the transmit power can be reserved for subsequent inter-group power adjustment, that is, for power adjustment through the second AI model.

[0135] from Figure 7BAs can be seen, after power adjustment within the MU pairing groups using the first AI model, there are no longer CCE resource conflicts between MU pairing groups {UE1,UE2} and {UEh,UEi}, and between MU pairing groups {UE3,UE4,UE5} and {UEj,UEk}. Furthermore, after power adjustment within the MU pairing groups using the first AI model, MU pairing group {UE1,UE2} can save 0.16P of power, MU pairing group {UE3,UE4,UE5} can save 0.04P of power, and MU pairing group {UE6,UE7,UE8} can save 1P of power. At this point, the number of schedulable MU pairing groups has increased from 3 to 5. However, after adjusting the power within the MU pairing group using the first AI model, the CCE resource occupancy of the MU pairing group {UE6, UE7, UE8} cannot be reduced. Even if all the 1P power saved within the MU pairing group is allocated to UE8, the CCE resource occupancy of the MU pairing group cannot be reduced (i.e., the CCE resource occupancy of UE8 cannot be reduced). This is because UE8's current average transmit power on each CCE is 0.75P. If the 1P power saved within the MU pairing group is allocated to UE8, and the CCE resource occupancy is simultaneously reduced from 8 to 4, UE8's average transmit power on each CCE remains 0.75P. In other words, the average transmit power on each CCE is not improved. Therefore, considering that the transmission performance is not improved, the CCE resource occupancy cannot be reduced. At this point, a CCE resource conflict still exists between the MU pairing groups {UE6, UE7, UE8} and {UEm, UEn}.

[0136] In other words, if, based on the updated CCE resource occupancy information for each UE, it is determined that after power adjustment via the first AI model, there still exists a first conflict group among all MU pairing groups that has CCE resource conflicts with each other, then based on the transmit power margin of each MU pairing group other than the first conflict group, the MU pairing information of the first conflict group, the updated SINR and adjusted transmit power for each UE in the first conflict group, the transmit power for at least one UE in the first conflict group is adjusted via the second AI model, and the updated SINR of that at least one UE is updated.

[0137] Specifically, by filtering the CCE resource conflicts between MU pairing groups based on the updated CCE resource occupancy information for each UE, a first non-conflict group (e.g., {UE1,UE2}, {UE3,UE4,UE5}, {UEh,UEi}, and {UEj,UEk}) and a first conflict group (e.g., {UE6,UE7,UE8} and {UEm,UEn}) with CCE resource conflicts can be identified. In this case, the CCE resource occupancy of the first non-conflict group is fixed and will not change. The MU pairing information of the first conflict group, the adjusted transmit power and updated SINR for each UE in the first conflict group, and the transmit power margin SP for each MU pairing group other than the first conflict group can be input into the second AI model for power adjustment and SINR update.

[0138] like Figure 7C As shown, there is no longer any CCE resource conflict between MU pairing group {UE1,UE2} and MU pairing group {UEh,UEi}, and there is no longer any CCE resource conflict between {UE3,UE4,UE5} and {UEj,UEk}. Therefore, the CCE resource occupancy information of these four groups can be fixed. Furthermore, the 0.2P transmit power saved within MU pairing groups {UE1,UE2} and {UE3,UE4,UE5} can be allocated to MU pairing group {UE6,UE7,UE8}. In this case, the transmit power margin for MU pairing groups {UE6,UE7,UE8} (i.e., the transmit power used to enhance transmission performance) becomes 1.2P. If this 1.2P transmit power is allocated to UE8, the number of CCE resources occupied by UE8 can be reduced from 8 to 4 (because the average power of each CCE for UE8 increases from 0.75P to 0.8P, thus improving UE8's transmission performance). Therefore, there is no longer a CCE resource conflict between MU pairing groups {UE6,UE7,UE8} and MU pairing groups {UEm,UEn}. The above describes, with a simple example, the process of adjusting the power of at least one UE in the first conflict group using the power margin saved within the MU pairing groups. In reality, the above power adjustment operation is implemented through the second AI model.

[0139] Furthermore, after power adjustment and SINR update via the second AI model, the CCE resource occupancy information for each UE can be updated again based on the updated SINR of each UE in all MU pairing groups. Subsequently, the schedulable MU pairing groups among all MU pairing groups can be determined.

[0140] Specifically, such as Figure 7DAs shown, since there are no CCE resource conflicts between the six MU pairing groups, these six MU pairing groups can be identified as schedulable MU pairing groups. Then, it can be determined whether the total transmit power for these six MU pairing groups is less than the maximum transmit power of the base station, i.e., whether the base station's transmit power is fully utilized. Since the total transmit power for these six MU pairing groups is not less than the maximum transmit power of the base station, i.e., the base station's transmit power is fully utilized, the transmit power for each UE in the six MU pairing groups is no longer adjusted. In this case, it can be determined whether the first condition is met. Assuming that the sum of the adjusted transmit power for each UE in the six MU pairing groups meets the power constraint condition, the sum of the CCE resource occupancy of the six MU pairing groups meets the CCE resource constraint condition, and the updated SINR for each UE in the six MU pairing groups meets the SINR constraint condition, then it can be determined that the first condition is met. At this time, the MU pairing information of the six MU pairing groups, the CCE resource occupancy information for each UE in the six MU pairing groups, the SINR, and the transmit power determined through the above operations can be used as the final output results. This example demonstrates that, in the current scheduling time unit, only 3 MU pairing groups (a total of 8 UEs) could originally be scheduled, but by using the method proposed in this application, 6 MU pairing groups (a total of 14 UEs) can be scheduled, thus enhancing the cell's scheduling capability and increasing cell capacity.

[0141] Existing methods distribute the base station's PDCCH transmit power evenly across all CCEs and then evenly distribute the transmit power allocated to the same CCE among UEs in a shared MU pairing group. This even distribution leads to a mismatch between the allocated transmit power and the UE's channel quality. For UEs with good channel conditions, excessive power may be allocated, resulting in wasted transmit power. For UEs with poor channel conditions, insufficient allocated power requires more CCE resources to ensure transmission reliability, causing these UEs to occupy more CCEs, thus reducing the number of UEs that can be simultaneously scheduled and lowering CCE resource utilization. The method proposed in this application dynamically adjusts the PDCCH transmit power for each UE in each MU pairing group, scheduling as many MU pairing groups as possible while ensuring PDCCH transmission reliability, thereby improving cell capacity and avoiding the CCE resource waste problem caused by the even distribution of PDCCH transmit power in existing methods.

[0142] Reference above Figure 5A Steps S501 to S503 described herein can be derived from Figure 5B The CCE AL decision module shown is used for execution.

[0143] Return to reference Figure 5AIn step S501, when determining MU pairing groups that have CCE resource conflicts with each other, a first SINR for each UE with respect to the PDCCH is used. The first SINR can be determined by any existing method or by the method proposed in this application. The method for determining the first SINR proposed in this application is described in detail below.

[0144] Figure 8 This is a flowchart illustrating the process of determining the first SINR for each UE in each MU pairing group according to an exemplary embodiment of this application.

[0145] like Figure 8 As shown, in step S801, a second SINR for each UE is determined based on the Sounding Reference Signal (SRS) and CSI reported by each UE. See below for further details. Figure 5B , Figure 9A and Figure 9B Step S801 is described in detail.

[0146] Figure 9A This is a flowchart illustrating the process of determining a second SINR for each UE with respect to the PDCCH according to an exemplary embodiment of this application. Figure 9B This is a schematic diagram illustrating the process of determining a second SINR for each UE with respect to the PDCCH according to an exemplary embodiment of this application.

[0147] like Figure 9A As shown, in step S901, the first demodulation SINR for each UE and the second demodulation SINR for each UE are calculated based on the SRS and CSI reported by each UE.

[0148] Specifically, such as Figure 5B and Figure 9B As shown, the PDCCH SINR evaluation module can calculate the channel matrix H of PDSCH for each UE based on the SRS reported by each UE. PDSCH And calculate the beamforming weight matrix W for each UE's PDSCH based on the CSI (i.e., PMI) reported by each UE. PDSCH Then, the PDCCH SINR evaluation module can evaluate the channel matrix H of the PDSCH for each UE. PDSCH and beamforming weight matrix W PDSCH The first demodulation SINR for each UE with respect to the PDSCH is calculated using, for example, the Minimum Mean Square Error (MMSE) algorithm. de,PDSCH (HPDSCH W PDSCH For example, as shown in formula (4) below.

[0149]

[0150] Where f represents the MMSE algorithm (i.e., the MMSE channel evaluation algorithm); ||H PDSCH W PDSCH,i || 2 Indicates signal power; W PDSCH,i σ represents the beamforming weight matrix for the i-th layer spatial flow of the PDSCH; 2 Indicates system thermal noise (fixed value); I neighbor cell This indicates interference from neighboring cells; M represents the number of layers in the PDSCH multi-layer spatial flow. This indicates interference between PDSCH multilayer spatial flows.

[0151] Similarly, the PDCCH SINR evaluation module can calculate the channel matrix H for each UE's PDCCH based on the SRS reported by each UE. PDCCH And calculate the beamforming weight matrix W for each UE's PDCCH based on the CSI (i.e., PMI) reported by each UE. PDCCH Then, the PDCCH SINR evaluation module can evaluate the PDCCH based on the channel matrix H for each UE. PDCCH and beamforming weight matrix W PDCCH The second demodulation SINR is calculated for each UE using the MMSE algorithm with respect to the PDCCH. de,PDCCH (H PDCCH W PDCCH For example, as shown in formula (5) below.

[0152]

[0153] In step S902, the SINR difference between the first demodulation SINR and the second demodulation SINR for each UE is calculated.

[0154] Specifically, such as Figure 9B As shown, for each UE, the PDCCH SINR evaluation module can calculate the difference G between the first demodulation SINR and the second demodulation SINR for the UE. PDSCH,PDCCH The difference G PDSCH,PDCCH This refers to the SINR difference for this UE. This difference G PDSCH,PDCCH This reflects the SINR difference caused by the different precoding methods used in PDSCH and PDCCH.

[0155] For example, it can be assumed that neighboring cell interference is small enough to be ignored. Therefore, the difference G between the first demodulated SINR and the second demodulated SINR for the UE can be calculated using the following formula (6). PDSCH,PDCCH :

[0156] G PDSCH,PDCCH =SINR de,PDCCH (H PDCCH W PDCCH )-SINR de,PDSCH (H PDSCH W PDSCH (6)

[0157] In step S903, a third SINR for each UE is calculated based on the CSI reported by each UE regarding the PDSCH. Specifically, as follows: Figure 5B and Figure 9B As shown, the PDSCH SINR calculation module can calculate the SINR for each UE based on the RI and CQI included in the CSI reported by each UE. This operation S903 can be implemented using various methods currently known, and this application does not specifically limit it.

[0158] In step S904, the second SINR for each UE with respect to the PDCCH is calculated based on the SINR difference for each UE and the third SINR.

[0159] Specifically, such as Figure 5B and Figure 9B As shown, the PDCCH SINR evaluation module can evaluate the SINR difference G for each UE. PDSCH,PDCCH The second SINR for each UE is obtained by summing the third SINR (i.e., the SINR for each UE with respect to the PDSCH) and the third SINR.

[0160] For example, the second SINR for each UE with respect to the PDCCH can be calculated using the following formula (7). PDCCH .

[0161] SINR PDCCH =SINR PDSCH +G PDSCH,PDCCH (7)

[0162] Based on the above references Figure 9A and Figure 9BThe described operation obtains a second SINR for each UE regarding the PDCCH, which can also be referred to as the basic SINR for each UE regarding the PDCCH. Compared to existing methods, step S801 above can accurately obtain the second SINR regarding the PDCCH. Specifically, in the prior art, the SINR regarding the PDSCH is calculated through the CSI information fed back by the UE, and this SINR regarding the PDSCH represents the basic SINR regarding the PDCCH. Although the PDCCH and PDSCH occupy different symbols within the same Transmission Time Interval (TTI) and their channels are similar, there is a significant difference between the SINR regarding the PDSCH and the SINR regarding the PDCCH. This difference largely depends on the difference in the number of transmission layers and the MIMO method. Specifically, the PDSCH can transmit multiple layers and adopts a method based on SRS / PMI / CoMP (Coordinated Multi-Layered ... Multi-Point (MIMO) transmission is used, but PDCCH only transmits at Layer 1 and is usually based on PMI transmission. In addition, the SINR of PDSCH and the SINR of PDCCH are also related to the deployment scenario and channel fading. These differences make it impossible for the SINR of PDSCH to reflect the true SINR of PDCCH. However, this application can solve the problem of inaccurate basic SINR of PDSCH determined by existing methods through the above methods.

[0163] Return to reference Figure 8 In step S802, the SINR offset with respect to the PDCCH for each UE is determined.

[0164] In one exemplary embodiment of this application, it may be as follows Figure 4 In step S420, the SINR offset for each UE with respect to the PDCCH is calculated using the OLRC algorithm based on the PUSCH DTX result. That is, the PUSCH DTX result is regarded as the PDCCH DTX result, and then the SINR offset for each UE with respect to the PDCCH is calculated based on the PUSCH DTX result.

[0165] In another exemplary embodiment of this application, the DTX result of the PDCCH for each UE can be predicted using an AI method based on historical scheduling information, and then the SINR offset of the PDCCH for each UE can be calculated based on the predicted DTX result of the PDCCH. Accordingly, step S802 may include: predicting the DTX result of the PDCCH for each UE based on historical scheduling information for a preset time; and calculating the SINR offset value of the PDCCH for each UE based on the DTX result of the PDCCH for each UE. The step of predicting the DTX result of the PDCCH for each UE based on historical scheduling information for a preset time includes: performing conversion and padding processing on the historical scheduling information for the preset time to obtain continuous scheduling information in time units; and predicting the DTX result of the PDCCH for the current scheduling time unit for each UE using a third AI model based on the continuous scheduling information in time units. The continuous scheduling information in time units includes continuous CCE AL, continuous MU pairing information, SINR of the PDCCH, continuous SRS flag, and continuous CSI flag associated with each UE within the preset time period. By utilizing AI models to predict the DTX result of PDCCH, the following situation can be avoided: when the UE fails to receive PDCCH information correctly or PUSCH demodulation fails due to poor channel quality, the base station detects the DTX of PUSCH, leading to an increase in the number of evaluated PDCCH DTX results when using the DTX of PUSCH to reflect the DTX of PDCCH. In other words, this avoids the inaccuracy caused by using the DTX result of PUSCH to reflect the DTX result of PDCCH in existing methods due to the lack of a feedback mechanism for PDCCH. Furthermore, the "time unit" mentioned in this document can be, for example, a "time slot," a "subframe," etc., and this application does not specifically limit it. See below for reference. Figure 5B and Figure 10 The process of predicting the DTX result of PDCCH using an AI model and calculating the SINR offset of PDCCH for each UE based on this DTX result is described in detail.

[0166] Figure 10 This is a schematic diagram illustrating a process related to DTX prediction of PDCCH according to an exemplary embodiment of this application.

[0167] First, in S1010, historical scheduling information for a preset time period is transformed and populated to obtain continuous scheduling information in time units. For example, it can be obtained by... Figure 5B The PDCCH DTX prediction module in the system performs this operation. Figure 10 As shown, it is assumed that the preset time is a time unit t. n-w To time unit t n-1The historical scheduling information for the preset time period may include CCE AL and MU pairing information associated with each UE, SINR regarding PDCCH, and SRS and CSI flags (not shown) within the preset time period. The CCE AL and MU pairing information associated with each UE, as well as the SRS and CSI flags, in this historical scheduling information are discrete in time units (i.e., discontinuous in time units). To enable the AI ​​model to identify relevant information in the historical scheduling information and invalid information corresponding to non-scheduled time units, this historical scheduling information needs to be converted and filled in. Specifically, during information conversion, for MU pairing information, flag 0 can be set to represent SU mode, and flag 1 can be set to represent MU mode; for SRS and CSI (specifically PMI), flag 0 can be set to represent SRS, and flag 1 can be set to represent PMI. During information filling, for non-scheduled time units within the preset time period, invalid values ​​(e.g., 0) are filled into the flags for CCEAL and MU modes. This allows the AI ​​model to identify these CCEAL and MU modes as invalid values ​​and correspondingly identify the SINR, SRS, and PMI flags for each UE related to the PDCCH in the historical scheduling information corresponding to these invalid CCEAL and MU modes. This information is then not used during prediction. Furthermore, in S1020, dataset management can be performed, allowing the continuous historical scheduling information within time units after the conversion and filling operations to be saved as a dataset for time unit t. n In the dataset, the continuous scheduling information in time units may include continuous CCE AL associated with each UE, continuous MU pairing information, SINR with respect to PDCCH, continuous SRS flag and continuous CSI flag within the preset time period.

[0168] Then, in S1030, for each UE, the DTX result of the PDCCH for the current scheduling time unit is predicted using the third AI model based on the continuous scheduling information in the time unit. Specifically, this operation may include: for each UE, obtaining the PDCCH channel state-related features of the current scheduling time unit using the first sub-AI model in the third AI model based on the continuous scheduling information in the time unit; and for each UE, determining the PDCCH DTX result of the current scheduling time unit using the second sub-AI model in the third AI model based on the PDCCH channel state-related features of the current scheduling time unit. Furthermore, the PDCCH DTX result predicted by the third AI model can also simultaneously reflect the actual neighboring cell interference.

[0169] like Figure 10 As shown, the preset time (i.e., time unit t) obtained by the conversion and filling operation in S1010 is continuous in time unit.n-w To time unit t n-1 The scheduling information is input into the third AI model. In one example, the first sub-AI model in the third AI model can be a Long Short-Term Memory (LSTM) network, and the second sub-AI model in the third AI model can be a Naive Bayes classifier. BayesClassifier (NB Classifier). The first sub-AI model can predict the current scheduling time unit t based on the continuous scheduling information in time units of the input. n The PDCCH channel state is then used to output the current scheduling time unit t. n The PDCCH channel state-related characteristics. The second sub-AI model can be based on the input current scheduling time unit t. n The conditional probability of each possible classification is calculated based on the PDCCH channel state-related features, and the DTX result of the PDCCH is obtained based on the calculated conditional probability. Since the DTX of the PDCCH has only two states, namely DTX and non-DTX, the second sub-AI model can calculate the conditional probability of each possible classification based on the current scheduling time unit t. n The probability of DTX for PDCCH is calculated based on the channel state-related features of PDCCH, and the DTX result of PDCCH is obtained based on the calculated probability. However, this application is not limited to this, and other models can be used to implement the third AI model. In addition, updates can be made for time unit t. n The dataset can be used to predict the current scheduling time unit t. n The DTX result of the PDCCH (also known as the DTX prediction result) and the preset time (i.e., time unit t) that are continuous in time unit. n-w To time unit t n-1 The scheduling information is saved together with the time unit t. n The dataset.

[0170] In S1040, based on the DTX results of the PDCCH for each UE, the SINR offset with respect to the PDCCH is calculated for each UE. For example, it can be calculated by... Figure 5B This operation is performed by the SINR offset calculation module within the system. For example, the SINR offset for each UE with respect to the PDCCH can be calculated using the OLRC algorithm based on the DTX results of the PDCCH for each UE.

[0171] The third AI model described above can be obtained through offline training before deployment. Furthermore, if the third AI model is deployed and used to predict the DTX results of the PDCCH for the UE, the decision to update the third AI model online can be based on the DTX prediction results. Therefore, in reference to... Figure 8 The described method may further include: when receiving HARQ feedback from the UE associated with a PDSCH scheduled by a first PDCCH, determining whether to update the third AI model. The step of determining whether to update the third AI model includes: if the non-DTX corresponding to the HARQ feedback is inconsistent with the first DTX result of the first PDCCH predicted in the scheduling time unit before receiving the HARQ feedback, determining to update the third AI model; or, if the non-DTX corresponding to the HARQ feedback is consistent with the first DTX result, determining not to update the third AI model.

[0172] Specifically, such as Figure 10 As shown, in S1050, when in time unit t n+k When a UE receives HARQ feedback associated with a PDSCH scheduled by the first PDCCH, it verifies the scheduling time unit (e.g., time unit t) prior to receiving the HARQ feedback. n This refers to the first DTX result of the first PDCCH predicted for the UE. Specifically, since the base station can receive HARQ feedback, whether the HARQ feedback is ACK or NACK, it indicates that the UE correctly received the PDCCH information previously. Therefore, the true DTX result of the PDCCH used to schedule the PDSCH corresponding to the HARQ feedback should be non-DTX. In this case, non-DTX can be used to replace the result for time unit t. n The first DTX result in the dataset is used to form a time unit t n The verification dataset.

[0173] Subsequently, in S1060, it is determined whether the non-DTX corresponding to the HARQ feedback is related to the scheduling time unit (e.g., time unit t) prior to receiving the HARQ feedback. n If the first DTX result of the first PDCCH predicted by the UE is consistent with the first DTX result (i.e., whether the actual DTX result is consistent with the DTX prediction result), and if the non-DTX result is consistent with the DTX prediction result, then the third AI model is determined to be in time unit t. n Since the first DTX result (i.e., the DTX prediction result) of the first PDCCH predicted by the UE is correct, it is determined that the third AI model will not be updated. Accordingly, the previously stored data for time unit t can be cleared in S1020. n The dataset. If the non-DTX and DTX predictions are inconsistent, then the third AI model can be determined to be at time unit t. n The first DTX prediction result of the first PDCCH predicted by the UE is incorrect, therefore it is determined to update the third AI model, for example, by performing an online update.

[0174] When it is determined that the third AI model needs to be updated, the third AI model can be updated (e.g., trained) based on the first scheduling information used to predict the first DTX result in the non-DTX and the scheduling information that is continuous in time units.

[0175] Specifically, such as Figure 10 As shown, in S1070, it can be determined whether to perform data expansion on the non-DTX and the first scheduling information. If the non-DTX and DTX prediction results are consistent, then using a higher CCE AL than the CCE AL in the first scheduling information used to predict the first DTX result will certainly not cause the DTX of PDCCH to occur. Therefore, data expansion can be performed to provide more explicit information for the third AI model.

[0176] In one exemplary embodiment of this application, when HARQ feedback associated with the PDSCH scheduled by the first PDCCH is received from the UE, if the CCE AL in the first scheduling information is the highest CCE AL, then since the CCE AL in the first scheduling information is already the highest CCE AL, no further data expansion is performed on the non-DTX and the first scheduling information. In this case, the non-DTX and the first scheduling information (i.e., for time unit t) can be extended. n The validation dataset is used as the training dataset to update the third AI model (e.g., for training).

[0177] In another exemplary embodiment of this application, upon receiving HARQ feedback from the UE associated with the PDSCH scheduled by the first PDCCH, if the CCE AL in the first scheduling information is not the highest CCE AL, then it is determined that data expansion should be performed on the non-DTX and the first scheduling information. Therefore, as Figure 10 As shown in S1080, this can be achieved by processing non-DTX and the first scheduling information (i.e., for time unit t). nThe training dataset is obtained by expanding the data of the verification dataset. Specifically, the steps of obtaining the training dataset by expanding the non-DTX and the first scheduling information include: obtaining at least one scheduling information by adjusting the CCE AL in the first scheduling information to at least one higher CCE AL; and using the at least one scheduling information, the first scheduling information, and the non-DTX to form the training dataset. For example, if the CCE AL in the first scheduling information is 4, the CCE AL in the first scheduling information can be changed to 8 and 16 respectively to obtain two scheduling information. That is, only the CCE AL in the first scheduling information is changed, without changing other information. In this case, two additional scheduling information can be obtained, and the label (i.e., the true result) used when updating the third AI model using each of these two scheduling information is the non-DTX. Therefore, the two additional scheduling information, the first scheduling information, and the non-DTX can be used to form the training dataset to update the third AI model, thereby improving the accuracy of the third AI model.

[0178] Return to reference Figure 8 In step S803, the multi-user loss for each UE is determined.

[0179] In one exemplary embodiment of this application, multi-user loss for each UE can be calculated based on periodic SRS or PMI. This application does not specifically limit this method, and other methods may also be used to calculate multi-user loss for each UE.

[0180] In another exemplary embodiment of this application, during the SRS reporting period, the channel conditions change as the UE moves, for example, Figure 11 This application addresses the impact of UE movement on SRS and PIM during the reporting period. By considering UE movement, this application determines the multi-user loss for each UE, ensuring that changes in channel conditions due to UE movement are reflected in the multi-user loss, thus obtaining a more accurate multi-user loss. Specifically, the steps for determining the multi-user loss for each UE include: determining the channel correlation for each UE at the next SRS reporting time; determining a mobility weighting factor associated with each UE based on the channel correlation, where the mobility weighting factor represents the degree of channel change caused by the movement of the corresponding UE; and adjusting the multi-user loss for each UE based on the mobility weighting factor associated with each UE. (See below for reference.) Figure 12 This will be described in detail.

[0181] Figure 12This is a flowchart illustrating the process of determining multi-user loss for each UE according to an exemplary embodiment of this application.

[0182] like Figure 12 As shown, in step S1201, the channel correlation for the next SRS reporting time is determined for each UE. In this application, for each UE, the channel correlation for the next SRS reporting time is determined based on the first channel matrix and the second channel matrix of the two preceding SRS reporting times immediately adjacent to the next SRS reporting time. The first channel matrix is ​​determined based on the SRS reported by the corresponding UE at the first SRS reporting time of the two preceding SRS reporting times, and the second channel matrix is ​​determined based on the SRS reported by the corresponding UE at the second SRS reporting time of the two preceding SRS reporting times.

[0183] For example, assuming the SRS reporting period is RP (Reporting Period), such as Figure 13 As shown, the time T is the time of the next SRS report. n+RP The immediately following first SRS reporting time T n The first channel matrix is ​​H n The time T is the next SRS reporting time. n+RP The immediately following second SRS reporting time T n-RP The second channel matrix is ​​H n-RP Based on this first channel matrix H n Second channel matrix H n-RP Determine the channel correlation R for the next SRS reporting time. n+RP For example, the channel correlation R at the next SRS reporting time can be calculated using the following formula (8). n+RP .

[0184]

[0185] in, It is the first SRS reporting time T n The first channel matrix H n The conjugate transpose of .

[0186] Then, in step S1202, based on the channel correlation for each UE, a mobility weight factor associated with each UE is determined, wherein the mobility weight factor represents the degree of channel change caused by the movement of the corresponding UE.

[0187] Specifically, over time, the mobility of the UE leads to changes in the channel. For example... Figure 13 As shown, during the SRS reporting period, the channel correlation decreases linearly with time, and the mobility weight factor β associated with the UE can be calculated by the following formula (9).

[0188]

[0189] Wherein, the mobility weighting factor β represents the degree of channel change caused by the movement of the corresponding UE, specifically, it represents the change in channel performance at the current time T caused by the movement of the corresponding UE. current The degree of channel variation.

[0190] In step S1203, the multi-user loss for each UE is adjusted based on the mobility weight factor associated with each UE. For example, the multi-user loss for the corresponding UE can be adjusted using the following formula (10).

[0191] MU_Loss′=β*MU_Loss (10)

[0192] Wherein, MU_Loss represents the multi-user loss for the UE, and MU_Loss′ represents the adjusted multi-user loss for the UE. Figure 12 The operation shown can be performed by Figure 5B The multi-user loss adjustment module in the system is used to perform this.

[0193] Return to reference Figure 8 In step S804, based on the second SINR for each UE, the SINR offset, and the multi-user loss, the first SINR with respect to the PDCCH is calculated for each UE. This operation can be performed by... Figure 5B The PDCCH SINR calculation module in the application performs the calculation. In this application, existing methods can be used to calculate the first SINR for each UE based on the second SINR, SINR offset, and multi-user loss for each UE. This application does not limit the specific calculation method.

[0194] The method proposed in this application can dynamically allocate PDCCH transmit power within and between MU pairing groups, maximizing CCE resource utilization and increasing cell capacity. Furthermore, the method can apply the demodulation algorithm used by the receiver to the base station, estimating the demodulation SINR of PDSCH and PDCCH based on the CSI reported by the UE, obtaining the SINR difference between the two, and evaluating the SINR of PDCCH based on this SINR difference and the actually calculated SINR of PDSCH, thus obtaining an accurate SINR for PDCCH. In addition, the method can predict the current scheduling time unit t using historical scheduling information. nThe proposed method uses the DTX results of the PDCCH to avoid the inaccuracies caused by using the DTX results of the PUSCH to reflect the DTX results of the PDCCH in existing methods due to the lack of a feedback mechanism in the PDCCH. Furthermore, the proposed method adjusts the multi-user loss for the UE by introducing a mobility weighting factor associated with the UE, ensuring that changes in channel conditions due to UE movement are reflected in the multi-user loss, thus obtaining a more accurate multi-user loss.

[0195] Figure 14 This is a block diagram illustrating an electronic device 2500 according to an exemplary embodiment of the present disclosure.

[0196] like Figure 14 As shown, the electronic device 2500 includes a transceiver 2510 and a processor 2520, wherein the processor 2520 is coupled to the transceiver 2510 and configured to perform the above-mentioned functions. Figures 5A to 13 The method described above. For details on the operation of the above method, please refer to [link / reference]. Figures 5A to 13 The descriptions will not be repeated here.

[0197] Furthermore, according to embodiments of this application, an electronic device may also be provided, comprising: at least one processor; and at least one memory storing computer-executable instructions, wherein the computer-executable instructions, when executed by the at least one processor, cause the at least one processor to perform the method described above.

[0198] As an example, an electronic device can be a PC, tablet, personal digital assistant, smartphone, or other device capable of executing the aforementioned set of instructions. Here, the electronic device is not necessarily a single device; it can be any collection of devices or circuits capable of executing the aforementioned instructions (or instruction sets) individually or in combination. The electronic device can also be part of an integrated control system or system manager, or can be configured to interconnect locally or remotely (e.g., via wireless transmission) through an interface.

[0199] In electronic devices, processors may include central processing units (CPUs), graphics processing units (GPUs), programmable logic devices, dedicated processor systems, microcontrollers, or microprocessors. By way of example and not limitation, processors may also include analog processors, digital processors, microprocessors, multi-core processors, processor arrays, network processors, etc.

[0200] The processor can execute instructions or code stored in memory, which can also store data. Instructions and data can also be sent and received over a network via a network interface device, which can employ any known transport protocol.

[0201] Memory can be integrated with the processor; for example, RAM or flash memory can be housed within an integrated circuit microprocessor. Alternatively, memory can comprise a separate device, such as an external disk drive, storage array, or other storage device that can be used by any database system. Memory and processor can be operatively coupled, or can communicate with each other, for example, via I / O ports, network connections, etc., enabling the processor to read files stored in the memory.

[0202] In addition, electronic devices may include video displays (such as liquid crystal displays) and user interaction interfaces (such as keyboards, mice, touch input devices, etc.). All components of the electronic device may be interconnected via buses and / or networks.

[0203] According to embodiments of this application, a computer-readable storage medium storing instructions may also be provided, wherein when the instructions are executed by at least one processor, they cause the at least one processor to perform the method described above according to exemplary embodiments of this application. Examples of computer-readable storage media include: read-only memory (ROM), random access programmable read-only memory (PROM), electrically erasable programmable read-only memory (EEPROM), random access memory (RAM), dynamic random access memory (DRAM), static random access memory (SRAM), flash memory, non-volatile memory, CD-ROM, CD-R, CD+R, CD-RW, CD+RW, DVD-ROM, DVD-R, DVD+R, DVD-RW, DVD+RW, DVD-RAM, BD-ROM, BD-R, BD-R, BD-R BD-RE, Blu-ray or optical disc storage, hard disk drive (HDD), solid-state drive (SSD), card storage (such as multimedia cards, secure digital (SD) cards, or ultra-fast digital (XD) cards), magnetic tape, floppy disk, magneto-optical data storage device, optical data storage device, hard disk, solid-state drive, and any other device configured to store a computer program and any associated data, data files, and data structures in a non-transitory manner and to provide the computer program and any associated data, data files, and data structures to a processor or computer so that the processor or computer can execute the computer program. The instructions or computer program in the aforementioned computer-readable storage medium can run in an environment deployed in computer devices such as clients, hosts, agent devices, servers, etc. Furthermore, in one example, the computer program and any associated data, data files, and data structures are distributed across a networked computer system, such that the computer program and any associated data, data files, and data structures are stored, accessed, and executed in a distributed manner through one or more processors or computers.

[0204] It should be noted that the terms "first," "second," "third," "fourth," "1," "2," etc. (if present) in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in a sequence other than that shown in the figures or text.

[0205] It should be understood that although arrows indicate various operation steps in the flowcharts of this application's embodiments, the order in which these steps are implemented is not limited to the order indicated by the arrows. Unless explicitly stated herein, in some implementation scenarios of this application's embodiments, the implementation steps in each flowchart can be executed in other orders as required. Furthermore, some or all steps in each flowchart, based on the actual implementation scenario, may include multiple sub-steps or multiple stages. Some or all of these sub-steps or stages can be executed at the same time, and each sub-step or stage can also be executed at different times. In scenarios where execution times differ, the execution order of these sub-steps or stages can be flexibly configured according to requirements, and this application's embodiments do not limit this.

[0206] The above description is only an optional implementation method for some implementation scenarios of this application. It should be noted that for those skilled in the art, other similar implementation methods based on the technical concept of this application without departing from the technical concept of this application also fall within the protection scope of the embodiments of this application.

Claims

1. A method executed by a network node, comprising: Based on the MU pairing information of each multi-user MU pairing group and the first signal-to-interference-plus-noise ratio (SINR) of each UE in each MU pairing group with respect to the physical downlink control channel (PDCCH), MU pairing groups that have control channel element (CCE) resource conflicts with each other are determined. For each MU pairing group, the following operations are performed: Based on the MU pairing information including the MU pairing group and the first information of the first SINR for each UE in the MU pairing group, the first transmit power for each UE in the MU pairing group is adjusted through the first AI model, and the first SINR for each UE in the MU pairing group is updated. If there are other MU pairing groups that have CCE resource conflicts with the MU pairing group, the first information also includes the MU pairing information of the other MU pairing groups and the first SINR of each UE in the other MU pairing groups regarding the PDCCH. Based on the adjusted transmit power and updated SINR for each UE, determine the schedulable MU pairing group and the second CCE resource occupancy information and second transmit power for each UE in each schedulable MU pairing group.

2. The method according to claim 1, wherein, The steps for determining MU pairing groups that have CCE resource conflicts with each other, based on the MU pairing information of each MU pairing group and the first SINR of each UE in each MU pairing group regarding the PDCCH, include: Based on the MU pairing information of each MU pairing group and the first SINR for each UE in each MU pairing group, determine the first CCE resource occupancy information for each UE; Based on the first CCE resource occupancy information for each UE, determine the MU pairing groups that have CCE resource conflicts with each other.

3. The method according to claim 2, wherein, The steps for determining schedulable MU pairing groups and, for each UE in each schedulable MU pairing group, the second CCE resource occupancy information and the second transmit power based on the adjusted transmit power and updated SINR for each UE include: Update the first CCE resource occupancy information for each UE based on the updated SINR for each UE in each MU pairing group; Based on the updated CCE resource occupancy information for each UE in each MU pairing group, determine whether there is still a first conflict group in the MU pairing group that has CCE resource conflicts with each other; If the first conflict group does not exist, then all MU pairing groups are determined as schedulable MU pairing groups; or If the first conflict group still exists, then based on the transmit power margin for each MU pairing group other than the first conflict group in all MU pairing groups, the MU pairing information of the first conflict group, the updated SINR and adjusted transmit power for each UE in the first conflict group, the transmit power for at least one UE in the first conflict group is adjusted by the second AI model and the updated SINR for that at least one UE is updated; the updated CCE resource occupancy information for each UE is updated according to the updated SINR for each UE in all MU pairing groups, and the schedulable MU pairing group is determined.

4. The method according to claim 3, wherein, After adjusting the transmit power for at least one UE in the first conflict group using a second AI model, the step of determining the schedulable MU pairing group includes: Determine whether a second conflict group still exists after the first conflict group has its CCE resource conflicted with each other, after the first conflict group has its transmit power adjusted by the second AI model; If the second conflict group does not exist, then all MU pairing groups are determined as schedulable MU pairing groups; or If the second conflict group exists, the schedulable MU pairing group in the second conflict group, determined based on the scheduling priority of each UE in the second conflict group, and the MU pairing groups other than the second conflict group in all MU pairing groups are determined as schedulable MU pairing groups.

5. The method according to claim 3, wherein, The transmit power margin for each MU pairing group, excluding the first conflict group, is determined by the following operation: Calculate the transmit power margin for each MU pairing group based on the adjusted transmit power of each UE in each MU pairing group other than the first conflict group.

6. The method according to claim 1 or 3, wherein, The steps of determining schedulable MU pairing groups and, for each UE in each schedulable MU pairing group, the second CCE resource occupancy information and the second transmit power based on the adjusted transmit power and updated SINR for each UE further include: Determine whether the total transmit power for all schedulable MU pairing groups is less than the base station's maximum transmit power; If the total transmit power is less than the maximum transmit power of the base station, the remaining transmit power of the base station is allocated to at least one UE in all schedulable MU pairing groups to adjust the transmit power for the at least one UE, while keeping the updated CCE resource occupancy information and the updated SINR for the at least one UE unchanged.

7. The method according to any one of claims 1 to 6, wherein, The steps for determining schedulable MU pairing groups and, for each UE in each schedulable MU pairing group, the second CCE resource occupancy information and the second transmit power based on the adjusted transmit power and updated SINR for each UE include: Based on the adjusted transmit power for each UE in each schedulable MU pairing group, the updated SINR, and the CCE resource occupancy information updated according to the updated SINR, it is determined whether the first condition is met; If the first condition is met, the adjusted transmit power and updated CCE resource occupancy information for each UE in each schedulable MU pairing group will be determined as the second transmit power and second CCE resource occupancy information for that UE; or If the predetermined conditions are not met, based on the scheduling priority of each UE in all MU pairing groups, schedulable MU pairing groups are determined, and the first transmit power of each UE in each schedulable MU pairing group and the first CCE resource occupancy information associated with the first transmit power are determined as the second transmit power and the second CCE resource occupancy information for each UE.

8. The method according to claim 7, wherein, The predetermined condition is satisfied when all three of the following conditions are met simultaneously: The sum of the adjusted transmit power for each UE in all schedulable MU pairing groups satisfies the power constraint condition; The sum of the CCE resource occupancy of all schedulable MU pairing groups satisfies the CCE resource constraint. as well as The updated SINR for each UE in all schedulable MU pairing groups satisfies the SINR constraint.

9. The method according to claim 1, wherein, The first SINR for each UE is obtained through the following operation: Based on the detection reference signal (SRS) and channel state information (CSI) reported by each UE, determine the second SINR for each UE regarding the PDCCH; Determine the SINR offset with respect to the PDCCH for each UE; Determine the multi-user loss for each UE; The first SINR is calculated for each UE based on the second SINR for each UE, the SINR offset, and the multi-user loss.

10. The method according to claim 9, wherein, The steps for determining the second SINR for each UE regarding the PDCCH, based on the Sounding Reference Signal (SRS) and Channel State Information (CSI) reported by each UE, include: Calculate the first demodulation SINR for PDSCH and the second demodulation SINR for PDCCH for each UE based on the SRS and CSI reported by each UE; Calculate the SINR difference between the first demodulation SINR and the second demodulation SINR for each UE; Calculate the third SINR for each UE based on the CSI reported by each UE; The second SINR for each UE is calculated based on the SINR difference for each UE and the third SINR.

11. The method according to claim 9, wherein, The steps for determining the SINR offset value for each UE with respect to the PDCCH include: For each UE, predict the discontinuous transmission DTX result of PDCCH based on historical scheduling information over a preset time. Based on the DTX results of the PDCCH for each UE, calculate the SINR offset value for the PDCCH for each UE.

12. The method according to claim 11, wherein, For each UE, the steps for predicting the discontinuous transmission DTX result of PDCCH based on historical scheduling information over a preset time include: The historical scheduling information for the preset time period is transformed and filled to obtain continuous scheduling information in time units; For each UE, based on the continuous scheduling information in time units, the DTX result of the PDCCH for the current scheduling time unit is predicted by the third AI model. The continuous scheduling information in time units includes continuous CCE AL associated with each UE, continuous MU pairing information, SINR about PDCCH, continuous SRS flag, and continuous CSI flag within the preset time period.

13. The method according to claim 12, wherein, For each UE, the step of predicting the DTX result of the PDCCH for the current scheduling time unit using a third AI model based on the continuous scheduling information in the time unit includes: For each UE, based on the continuous scheduling information in the time unit, the PDCCH channel state related features of the current scheduling time unit are obtained through the first sub-AI model in the third AI model; For each UE, the DTX result of the PDCCH for the current scheduling time unit is determined by the second sub-AI model in the third AI model based on the PDCCH channel state-related characteristics of the current scheduling time unit.

14. The method of claim 12, further comprising: When the UE receives a Hybrid Automatic Repeat Request (HARQ) feedback associated with the PDSCH scheduled by the first PDCCH, it determines whether to update the third AI model.

15. The method according to claim 14, wherein, The steps to determine whether to update the third AI model include: If the non-DTX corresponding to the HARQ feedback is inconsistent with the first DTX result of the first PDCCH predicted by the scheduling time unit before receiving the HARQ feedback, it is determined that the third AI model should be updated; or If the non-DTX corresponding to the HARQ feedback is consistent with the first DTX result, it is determined that the third AI model will not be updated.

16. The method of claim 14, wherein, When it is determined that the third AI model needs to be updated, the third AI model is updated based on the non-DTX and the first scheduling information used to predict the first DTX result in the continuous scheduling information in the time unit.

17. The method according to claim 16, wherein, The steps for updating the third AI model based on the non-DTX and the first scheduling information used to predict the first DTX result in the continuous scheduling information over time units include: If the CCE AL in the first scheduling information is not the highest CCE AL, then a training dataset is obtained by expanding the non-DTX and the first scheduling information, and the third AI model is updated based on the training dataset; or If the CCE AL in the first scheduling information is the highest CCE AL, then the non-DTX and the first scheduling information are used as the training dataset to update the third AI model.

18. The method according to claim 17, wherein, The step of obtaining the training dataset by expanding the non-DTX and the first scheduling information includes: At least one scheduling message is obtained by adjusting the CCE AL in the first scheduling message to at least one CCE AL that is higher than the CCE AL. The training dataset is composed of the at least one scheduling information, the first scheduling information, and the non-DTX.

19. The method according to claim 9, wherein, The steps to determine multi-user loss for each UE include: For each UE, determine the channel correlation for the next SRS reporting time; Based on the channel correlation for each UE, a mobility weighting factor associated with each UE is determined, wherein the mobility weighting factor represents the degree of channel change caused by the movement of the corresponding UE; The multi-user loss for each UE is adjusted based on the mobility weight factor associated with each UE.

20. A network node, comprising A transceiver is used to send and receive signals; and A processor, coupled to the transceiver, is configured to perform the method described in any one of claims 1 to 19.

Images