User selection method and node for performing the method

Abstract

A user selection method performed by a first node and the first node performing the method are disclosed. According to an exemplary implementation method, the user selection method executed by a first node comprises the following steps: arranging a plurality of pieces of user equipment to obtain a first arrangement; rearranging part of the user equipment in the first arrangement to obtain a second arrangement; and determining the scheduled user equipment based on the first arrangement and the second arrangement.

Description

Technical Field

[0001] The present application relates to a user selection method in a wireless communication system and a node for executing the method. Background Art

[0002] Considering the development of wireless communication from generation to generation, these technologies are mainly developed for services targeting people, such as voice calls, multimedia services and data services. With the commercialization of the fifth generation (5G) communication system, the number of connected devices is expected to grow exponentially. These will be increasingly connected to the communication network. Examples of the Internet of Things can include vehicles, robots, drones, home appliances, displays, smart sensors connected to various infrastructures, construction machinery and factory equipment. Mobile devices are expected to develop in various forms (such as augmented reality glasses, virtual reality headsets and holographic devices). Efforts have been made to develop improved 6G communication systems in order to provide various services by connecting hundreds of billions of devices and things in the sixth generation (6G) era. For these reasons, 6G communication systems are called super 5G systems.

[0003] The 6G communication system, which is expected to be commercialized around 2030, will have a peak data rate of tera (1,000 gigabits) bps and a radio latency of less than 100 μsec, thus being 50 times the data rate of the 5G communication system and having 1 / 10 of its radio latency.

[0004] In order to achieve such high data rates and ultra-low latency, the implementation of 6G communication systems in terahertz (e.g., 95GHz to 3THz bands) has been considered. It is expected that since the path loss and atmospheric absorption in the terahertz band are more serious than those in the millimeter wave (mmWave) band introduced in 5G, technologies that can ensure the signal transmission distance (i.e., coverage) will become more critical. As the main technology to ensure coverage, it is necessary to develop radio frequency (RF) elements, antennas, new waveforms with better coverage than orthogonal frequency division multiplexing (OFDM), beamforming and massive multiple input multiple output (MIMO), full-dimensional MIMO (FD-MIMO), array antennas, and multi-antenna transmission technologies such as massive antennas. In addition, new technologies for improving terahertz band signal coverage have been discussed, such as metamaterial-based lenses and antennas, orbital angular momentum (OAM), and reconfigurable smart surfaces (RIS).

[0005] In addition, in order to improve spectrum efficiency and overall network performance, the following technologies have been developed for 6G communication systems: full-duplex technology for enabling uplink transmission and downlink transmission to use the same frequency resources at the same time; network technology that utilizes satellites, high altitude platform stations (HAPS), etc. in an integrated manner; improved network structure for supporting mobile base stations, etc., and enabling network operation optimization and automation, etc.; dynamic spectrum sharing technology via conflict avoidance based on spectrum usage prediction: using artificial intelligence (AI) in wireless communication to improve overall network operation by utilizing AI from the design stage of developing 6G and internalizing end-to-end AI support functions; and next-generation distributed computing technology that overcomes the computing power limitations of user equipment (UE) through ultra-high performance communication and computing resources (such as mobile edge computing (MEC), cloud, etc.) that can be realized on the network. In addition, attempts are continuing to strengthen connectivity between devices, optimize networks, promote softwareization of network entities, and increase openness of wireless communications by designing new protocols to be used in 6G communication systems, developing mechanisms for realizing hardware-based security environments and secure use of data, and developing technologies for maintaining privacy.

[0006] Research and development of 6G communication systems, including hyperconnectivity of human-to-machine (P2M) and machine-to-machine (M2M), are expected to bring about the next hyperconnectivity experience. In particular, services such as truly immersive extended reality (XR), high-fidelity mobile holograms, and digital replicas are expected to be provided through 6G communication systems. In addition, services such as remote surgery, industrial automation, and emergency response for enhanced safety and reliability will be provided through 6G communication systems, making it possible for the technology to be applied to various fields such as industry, healthcare, automobiles, and home appliances. Summary of the invention

[0007] According to one aspect of the present disclosure, there is provided a user selection method performed by a first node, comprising: arranging a plurality of user devices to obtain a first arrangement; rearranging some of the user devices in the first arrangement to obtain a second arrangement; and determining a scheduled user device based on the first arrangement and the second arrangement.

[0008] In an exemplary embodiment, determining the scheduled user equipment based on the first arrangement and the second arrangement includes: determining the scheduled first user equipment based on the first arrangement; and determining the scheduled second user equipment based on the second arrangement.

[0009] In an exemplary embodiment, the rearranging of some user equipments in the first arrangement includes: performing the following processing on the first arrangement at least once: selecting a sub-arrangement in the current arrangement, and rearranging the user equipments in the sub-arrangement.

[0010] In an exemplary embodiment, based on the second arrangement, determining the second user equipment to be scheduled includes performing the following steps at least once: for each current arrangement, taking the user equipment located in front of the user equipment in the sub-arrangement as the second user equipment to be scheduled.

[0011] In an exemplary embodiment, arranging multiple user devices to obtain a first arrangement includes: arranging multiple user devices based on information of each user device to obtain a first arrangement; the information of the user device includes at least one of the following items: a historical rate of the user device, current channel estimation information and related information of the user device, a signal to interference plus noise ratio SINR of the user device, a maximum transmission rate of the user device, and a fairness weight of the user device.

[0012] In an exemplary embodiment, selecting a sub-permutation in a current arrangement and rearranging the sub-permutation includes: selecting a sub-permutation in the current arrangement, obtaining a scheduling value or probability of user equipment in the sub-permutation based on a permutation function according to state information of user equipment in the current arrangement; and performing an arrangement based on the scheduling value or probability of user equipment in the sub-permutation.

[0013] In an exemplary embodiment, the number of user equipments in the sub-array is determined based on at least one of computing resources available for scheduling, a maximum number of user equipments that can be scheduled or a number of user equipments expected to be scheduled, and a maximum coverage range of a base station.

[0014] In an exemplary embodiment, the status information of the user equipment includes at least one of the following items: the historical rate of the user equipment, the current channel estimation information and related information of the user equipment, the signal to interference plus noise ratio SINR estimated by the current channel estimation related information of the user equipment, the user rate estimated by the current channel estimation related information of the user equipment, the SINR obtained by user feedback, or the SINR estimated by the user's uplink reference signal.

[0015] In an exemplary embodiment, the arrangement function includes at least one of the following: directly mapping the state information of the user device to a lookup table of the arrangement order of the user device, mapping the state information of the user device to a function of the scheduled value or probability of the user device, or mapping the state information of the user to a neural network of the user's scheduled value or probability.

[0016] According to another aspect of the present disclosure, a first node for executing the above-mentioned user selection method is provided, comprising a transceiver and a processor, wherein the transceiver is configured to send and receive signals, and the processor is coupled to the transceiver and configured to execute the above-mentioned user selection method.

[0017] According to another aspect of the present disclosure, a computer-readable storage medium is provided, storing computer-executable instructions. When the computer-executable instructions are executed by a processor, the processor executes the above-mentioned user selection method. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 An example wireless network according to an embodiment of the present disclosure is shown.

[0019] Figure 2 An example base station according to an embodiment of the present disclosure is shown.

[0020] Figure 3 An example user device according to an embodiment of the present disclosure is shown.

[0021] Figure 4 A user equipment selection method according to an exemplary embodiment of the present disclosure is shown.

[0022] Figure 5 A user equipment selection method according to an exemplary embodiment of the present disclosure is shown.

[0023] Figure 6 The architecture of a user equipment ranking function according to an exemplary embodiment of the present disclosure is shown.

[0024] Figure 7 A method for selecting a second arrangement of user equipment according to an exemplary embodiment of the present disclosure is shown.

[0025] Figure 8 A method for training a user equipment ranking function according to an exemplary embodiment of the present disclosure is shown.

[0026] Fig. 9 A user equipment selection method according to an exemplary embodiment of the present disclosure is shown.

[0027] Fig.10 The user equipment included in each arrangement in an exemplary embodiment according to the present disclosure is shown.

[0028] Fig.11 An exemplary structure of a base station according to the present disclosure is shown. DETAILED DESCRIPTION

[0029] Before carrying out the following specific embodiments, it may be advantageous to set forth the definitions of certain words and phrases used throughout the patent document. The term "connection" and its derivatives refer to any direct or indirect communication between two or more elements, regardless of whether those elements are in physical contact with each other. The terms "send", "receive" and "communicate" and their derivatives include both direct and indirect communication. The terms "include" and "include" and their derivatives mean unrestricted inclusion. The term "or" is compatible, meaning and / or. The phrase "associated with" and its derivatives mean including, included, interconnected with it, including, included, connected to or connected with it, coupled to or coupled with it, can communicate with it, collaborate with it, interweave, juxtapose, approach, be bound to or bound with it, have, have the property of, have to ... or have a relationship with ... etc. The term "controller" means any device, system or part thereof that controls at least one operation. Such a controller can be implemented in a hardware manner or in a combination of hardware and software and / or firmware. The functionality associated with any particular controller, whether local or remote, may be centralized or distributed. The phrase "at least one of" when used with a list of items means that different combinations of one or more of the listed items may be used, and only one item in the list may be required. 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, only C. Likewise, the term "set" means one or more. Thus, a set of items may be a single item or a set of two or more items.

[0030] Moreover, various functions as described below can be implemented or supported by one or more computer programs, each of which is formed by a 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, processes, functions, objects, categories, instances, related data, or a part thereof that are suitable for being implemented in a suitable 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 that can be accessed by a computer, such as a read-only memory (ROM), a random access memory (RAM), a hard drive, a compact disc (CD), a digital video disc (DVD), or any other type of memory. "Non-transient" computer-readable media excludes wired, wireless, optical, or other communication links that convey instantaneous electrical signals or other signals. Non-transient computer-readable media include media in which data can be permanently stored and media in which data can be stored and rewritten later, such as rewritable optical discs or erasable memory devices.

[0031] Definitions for certain other words and phrases are provided throughout this patent document. Those of skill in the art should understand that in many, if not most instances, such definitions apply to prior, as well as future uses of such defined words and phrases.

[0032] The figures and various embodiments used to describe the principles of the present disclosure are included herein for illustration only and should not be construed in any way as limiting the scope of the present disclosure. In addition, those skilled in the art will appreciate that the principles of the present disclosure can be implemented in any appropriately arranged wireless communication system.

[0033] The following Figures 1 to 3 Various embodiments of the present disclosure are described as being implemented in a wireless communication system. Figures 1 to 3 The description is not meant to imply physical or architectural limitations to the manner in which different embodiments may be implemented. Different embodiments of the present disclosure may be implemented in any suitably arranged communications system.

[0034] Figure 1 An example wireless network according to an embodiment of the present disclosure is shown. Figure 1 The embodiment of the wireless network shown in FIG. 1 is for illustration only. Other embodiments of the wireless network 100 may be used without departing from the scope of the present disclosure.

[0035] like Figure 1 As shown, the wireless network includes base station (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, a proprietary Internet Protocol (IP) network, or other data network.

[0036] The gNB 102 provides wireless broadband access to a network 130 for a plurality of first user equipments (UEs) within a coverage area 120 of the gNB 102. The plurality of first UEs include a UE 111 that may be located at a small business (SB); a UE 112 that may be located at an enterprise (E); a UE 113 that may be located at a WiFi hotspot (HS); a UE 114 that may be located at a first residence (R1); a UE 115 that may be located at a second residence (R2); and a UE 116 that may be a mobile device (M) such as a cellular phone, a wireless laptop, a wireless personal digital assistant (PDA), etc. The gNB 103 provides wireless broadband access to the network 130 for a plurality of second UEs within a coverage area 125 of the gNB 103. The plurality of second UEs include UE 115 and UE 116 and subscriber stations (SS, e.g., UEs) 117, 118, and 119. In some embodiments, one or more of gNBs 101 103 may communicate with each other and UE 111 116 using existing wireless communication technologies, and one or more of UE 111 119 may communicate directly with each other (e.g., UE 117 119) using other existing or proposed wireless communication technologies.

[0037] Depending on the network type, the term "base station" or "BS" may refer to any component (or collection of components) configured to provide wireless access to a network, such as a transmission point (TP), a transceiver point (TRP), an enhanced (or "evolved") base station (eNodeB or eNB), a 5G base station (gNB), a macro cell, a femto cell, a wireless fidelity (WiFi) access point (AP), or other wireless-capable device. A base station may provide wireless access according to one or more wireless communication protocols, such as 3GPP 5G New Radio (NR), Long Term Evolution (LTE), Advanced LTE (LTE A), High Speed ​​Packet Access (HSPA), Wi Fi 802.11a / b / g / n / ac, etc. For convenience, various names of base station type devices and functions are used interchangeably in this patent document to refer to network infrastructure components that provide wireless access to remote terminals. Moreover, depending on the network type, the term "user equipment" (UE) may refer to any component such as a mobile station (MS), a subscriber station (SS), a remote terminal, a wireless terminal, a receiving point, or a user device. For convenience, various names of user equipment type devices and functions are used interchangeably in this patent document to refer to a remote wireless device that wirelessly accesses a BS, regardless of whether the UE is a mobile device (such as a mobile phone or smart phone) or a device generally considered to be a fixed device (such as a desktop computer or a vending machine).

[0038] Dashed lines illustrate the approximate extents of coverage areas 120 and 125, which are shown as generally circular for purposes of illustration and explanation only. It should be clearly understood that coverage areas associated with a gNB, such as coverage areas 120 and 125, may have other shapes, including irregular shapes, depending on the configuration of the gNB and variations in the wireless environment associated with natural and artificial obstacles.

[0039] As described in more detail below, one or more of the UEs 111 119 include circuitry, programming, or a combination thereof. In certain embodiments, one or more of the gNBs 101 103 include circuitry, programming, or a combination thereof.

[0040] although Figure 1 An example of a wireless network is shown, but Figure 1 Various changes may be made. For example, wireless network 100 may include any number of gNBs and any number of UEs in any suitable arrangement. Moreover, gNB 101 may communicate directly with any number of UEs and provide those UEs with wireless broadband access to network 130. Similarly, each gNB 102 103 may communicate directly with network 130 and provide UEs with direct wireless broadband access to network 130. In addition, gNBs 101, 102, and / or 103 may provide access to other or additional external networks such as an external telephone network or other types of data networks.

[0041] Figure 2 An example base station according to an embodiment of the present disclosure is shown. Figure 2 The embodiment of the gNB 102 shown in FIG. is for illustration only, and Figure 1 gNBs 101 and 103 may have the same or similar configurations. However, gNBs appear in a variety of configurations, and Figure 2 The scope of the present disclosure is not limited to any particular implementation of the gNB.

[0042] like Figure 2 As shown in FIG. 1 , 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 207.

[0043] The RF transceiver 201a 201n receives incoming RF signals from the antenna 200a 200n, such as signals sent by a UE in the network 100. The RF transceiver 201a 201n down-converts the incoming RF signals to generate an intermediate frequency (IF) or baseband signal. The IF or baseband signal is sent to the RX processing circuit 204, which generates a processed baseband signal by filtering, decoding and / or digitizing the baseband or IF signal. The RX processing circuit 204 sends the processed baseband signal to the controller / processor 205 for further processing.

[0044] 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. The RF transceiver 201a 201n receives the outgoing processed baseband or IF signal from the TX processing circuit 203 and up-converts the baseband or IF signal to an RF signal that is transmitted via the antenna 201a 201n.

[0045] Controller / processor 205 may include one or more processors or other processing devices that control the overall operation of gNB 102. For example, controller / processor 205 may control the reception of forward channel signals and the transmission of reverse channel signals by RF transceivers 201a 201n, RX processing circuitry 204, and TX processing circuitry 203 in accordance with well-known principles. Controller / processor 205 may also support additional functionality, such as more advanced wireless communication functionality.

[0046] For example, the controller / processor 205 may support beamforming or directional routing operations, in which outgoing signals from multiple antennas 200a-200n are weighted differently to effectively steer the outgoing signals in a desired direction. Any of a variety of other functions may be supported in the gNB 102 by the controller / processor 205.

[0047] Controller / processor 205 is also capable of executing programs and other processes, such as an operating system (OS), located in memory 206. Controller / processor 205 may move data into or out of memory 206 as required by the executing processes.

[0048] 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 via a network. The interface 207 may support communication over any appropriate (one or more) wired or wireless connections. 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), the interface 207 may 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, the interface 207 may allow the gNB 102 to communicate over a wired or wireless local area network or over a wired or wireless connection to a larger network (such as the Internet). The interface 207 includes any appropriate structure that supports communication over a wired or wireless connection such as an Ethernet or RF transceiver.

[0049] 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).

[0050] although Figure 2 An example of gNB 102 is shown, but the Figure 2 For example, gNB 102 may include any number of Figure 2 As a specific example, the access point may include multiple interfaces 207, and the controller / processor 205 may support routing functions to route data between different network addresses. As another specific example, although shown as including a single instance of TX processing circuitry 203 and a single instance of RX processing circuitry 204, the gNB 102 may include multiple instances of each (such as one for each RF transceiver). For example, Figure 2 The various components in may be combined, further subdivided, or omitted, and additional components may be added according to specific needs.

[0051] Figure 3 An example user device according to an embodiment of the present disclosure is shown. Figure 3 The embodiment of UE 116 shown in FIG. 1 is for illustration only, and Figure 1 UEs 111 115 and 117 119 may have the same or similar configurations. However, UEs may appear in a variety of configurations, and Figure 3 The scope of the present disclosure is not limited to any particular implementation of the UE.

[0052] like Figure 3As shown in FIG. 1 , 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, a touch screen display 310, and a memory 311. The memory 311 includes an OS 312 and one or more applications 313.

[0053] RF transceiver 302 receives incoming RF signals transmitted by a gNB of network 100 from antenna 301. RF transceiver 302 downconverts the incoming RF signals to generate an IF or baseband signal. The IF or baseband signal is sent to RX processing circuitry 305, which generates a processed baseband signal by filtering, decoding, and / or digitizing the baseband or IF signal. RX processing circuitry 305 sends the processed baseband signal to speaker 306 (such as for voice data) or processor 307 for further processing (such as for web browsing data).

[0054] The TX processing circuit 303 receives analog or digital voice data from the microphone 304 or other outgoing baseband data (such as web data, email, or interactive video game data) from the processor 307. The TX processing circuit 303 encodes, multiplexes, and / or digitizes the outgoing baseband data to generate a processed baseband or IF signal. The RF transceiver 302 receives the outgoing processed baseband or IF signal from the TX processing circuit 303 and up-converts the baseband or IF signal to an RF signal that is transmitted via the antenna 301.

[0055] The processor 307 may include one or more processors or other processing devices and executes the OS 312 stored in the memory 311 to control the overall operation of the UE 116. For example, the processor 307 may control the reception of forward channel signals and the transmission of reverse channel signals by the RF transceiver 302, the RX processing circuit 305, and the TX processing circuit 303 according to well-known principles. In some embodiments, the processor 307 includes at least one microprocessor or microcontroller.

[0056] The processor 307 is also capable of executing other processes and programs located in the memory 311, such as a process for CSI reporting on the uplink channel. The processor 307 can move data into or out of the memory 311 as needed to execute the process. In some embodiments, the processor 307 is configured to execute the application 313 based on the OS 312 or in response to a signal received from the gNB or operator. The processor 307 is also coupled to the I / O interface 309, which provides the UE 116 with the ability to connect to other devices such as laptops and portable computers. The I / O interface 309 is the communication path between these accessories and the processor 307.

[0057] Processor 307 is also connected to touch screen display 310. A user of UE 116 may use touch screen display 310 to enter data into UE 116. Touch screen display 310 may be a liquid crystal display, light emitting diode display, or other display capable of rendering text and / or at least limited graphics, such as from a website.

[0058] The memory 311 is connected to the processor 307. A portion of the memory 311 may include RAM, and another portion of the memory 311 may include flash memory or other ROM.

[0059] although Figure 3 An example of UE 116 is shown, but the Figure 3 Make various changes. For example, Figure 3 The various components in the embodiment may be combined, further subdivided, or omitted, and additional components may be added as required. As a specific example, processor 307 may be divided into multiple processors, such as one or more central processing units (CPUs) and one or more graphics processing units (GPUs). Furthermore, although Figure 3 The UE 116 is shown configured as a mobile phone or smart phone, but the UE may be configured to operate as other types of mobile or stationary devices.

[0060] In order to improve the total capacity of the system and the ability to serve multiple users at the same time, the 4G communication system uses Multi-User Multiple-Input Multiple-Output (MU-MIMO) technology. Based on MU-MIMO technology, the base station can use multiple layers of data streams to provide services to multiple users (UE) at the same time, and establish at least one communication link with each UE. Among them, the base station establishes communication links simultaneously by assigning different communication layers to multiple different UEs. The principle of MU-MIMO implementation is to maximize the spatial multiplexing capability of the multiple-input multiple-output communication system, and to enable multiple users to use the same time-frequency resources by finding multiple mutually quasi-orthogonal channels in space. MU-MIMO technology increases the total capacity of the system by accommodating more users in each cell.

[0061] Using MU-MIMO technology to improve the total capacity of the system requires the base station to find an optimal spatial multiplexing method in the environment at any time. The spatial multiplexing method is a method that allows different users to transmit on the same frequency and channel resources at the same time and minimize interference. Dirty paper coding in the prior art is a method that can theoretically optimize throughput. However, the complexity of its multi-user coding strategy based on interference prediction is extremely high, which makes this method unsuitable for actual systems. Precoding technology (also known as beamforming, beamforming, etc.) is a suboptimal method for achieving multi-user spatial multiplexing. This method does not consider the state of the channel during encoding, but encodes the sequence of each UE independently, and then multiplies the encoded sequences of all UEs with a precoding matrix to achieve multi-antenna transmission. Among them, how to find the precoding matrix is ​​a major problem in implementing MU-MIMO using the precoding method. Selecting a suitable precoding matrix can achieve separation of spatial dimensions between users, thereby reducing mutual interference between different data streams, thereby improving the throughput of each user. However, finding the optimal precoding matrix is ​​a high-dimensional non-convex optimization problem. Solving it requires a lot of computing resources and extremely high latency, so this method is still not accepted by existing systems. The method widely used by existing systems is zero-forcing precoding, also known as null-steering precoding, zero-forcing beamforming, and zero-forcing beamforming. Zero-forcing precoding is a suboptimal precoding method that directly finds the precoding matrix by inverting the channel state matrix. Since this method has extremely low complexity, it is widely used by existing systems.

[0062] The advantage of zero-forcing precoding technology is its low complexity. In addition, when the environment in which the MU-MIMO system is located satisfies that the number of user devices that need to transmit data is much larger than the maximum number of user devices supported by the base station (for one time-frequency resource unit), the theoretical optimal sum rate of transmission using zero-forcing precoding technology is close to the sum rate of transmission using dirty paper coding. This is because when the number of user devices that need to transmit data is large enough, the base station can improve the efficiency of zero-forcing precoding by selecting a suitable subset of user devices from all user devices that need to transmit data, thereby improving the sum rate of the system. This subset should satisfy that the user devices in it are user devices with good channel fading conditions (that is, user devices with high channel amplitude are selected), and that the channels experienced by each user device in the subset are close to quasi-orthogonal. The reason why such a subset of user devices can be found to maximize the efficiency of zero-forcing precoding is that in the MU-MIMO system, since different user devices may be located at different physical locations, there will be a diversity effect in the physical space between each user device (the diversity effect refers to the fading experienced by the signals sent at different locations presenting a characteristic that is close to being independent of each other). However, how to find a group of user devices that meet the above conditions is a complex combinatorial optimization problem.

[0063] The technical solution of the present disclosure is described below in conjunction with embodiments.

[0064] Figure 4 The user equipment selection method according to an embodiment of the present disclosure is shown. In step S41, the first node arranges multiple user equipments to obtain a first arrangement. In step S42, the first node rearranges some users in the first arrangement to obtain a second arrangement. In step S43, based on the first arrangement and the second arrangement, the scheduled user equipment is determined. The above-mentioned first node is, for example, a base station, but is not limited thereto. The first node that executes the user selection method of the present disclosure may also be other network nodes in the wireless communication system.

[0065] The first and second arrangements described above may be arrangements based on scheduling priorities, for example. For the sake of simplicity, the first and second arrangements based on scheduling priorities will be introduced as examples below. It should be understood that the first and second arrangements in the user selection method disclosed in the present invention may also be arrangements based on other factors.

[0066] In an exemplary embodiment, arranging a plurality of user devices to obtain a first arrangement may include: arranging a plurality of user devices based on information of each user device to obtain a first arrangement. The information of the user device may include at least one of the following: a historical rate of the user device, current channel estimation information and related information of the user device, a signal to interference plus noise ratio SINR of the user device, a maximum transmission rate of the user device, and a fairness weight of the user device. The related information of the channel estimation information of the user device may be, for example, a singular value obtained by performing a singular value decomposition on a channel estimate of a current channel obtained by the user device. The signal to interference plus noise ratio SINR and the maximum transmission rate of the user device may be estimated using the current channel state information (Channel State Information, CSI).

[0067] In an exemplary embodiment, rearranging some of the user equipments in the first arrangement includes performing the following processing on the first arrangement at least once: selecting a sub-arrangement in the current arrangement, and rearranging the user equipments in the sub-arrangement. For example, selecting a sub-arrangement in the current arrangement, and rearranging the sub-arrangement may include: selecting a sub-arrangement in the current arrangement, obtaining the scheduling value or probability of the user equipment in the sub-arrangement based on the arrangement function according to the state information of the user equipment in the current arrangement; and performing the arrangement based on the scheduling value or probability of the user equipment in the sub-arrangement. For example, the number of user equipments in the sub-arrangement is determined based on at least one of the computing resources that can be used for scheduling, the maximum number of users that can be scheduled or the number of users expected to be scheduled, and the maximum coverage range of the base station. The state information of the user equipment may include at least one of the following items: the historical rate of the user equipment, the current channel estimation information and related information of the user equipment, the signal to interference plus noise ratio SINR estimated by the current channel estimation related information of the user equipment (for example, the eigenvector and eigenvalue of the current channel of the user), the user rate estimated by the current channel estimation related information of the user equipment (for example, the eigenvector and eigenvalue of the current channel of the user), the SINR obtained by user feedback, or the SINR estimated by the uplink reference signal of the user. The arrangement function may include at least one of the following: a lookup table that directly maps the user's state information to the user's arrangement order, a function that maps the user's state information to the user's scheduled value or probability, or a neural network that maps the user's state information to the user's scheduled value or probability.

[0068] In an exemplary embodiment, determining the scheduled user equipment based on the first arrangement and the second arrangement may include: determining the scheduled first user equipment based on the first arrangement; and determining the scheduled second user equipment based on the second arrangement. In an exemplary embodiment, determining the scheduled second user equipment based on the second arrangement includes performing the following steps at least once: for each current arrangement, taking the user equipment located in front of the user equipment in the sub-arrangement as the scheduled second user equipment.

[0069] According to the user selection method proposed in the present disclosure, a better combination of scheduled user equipment can be selected to improve system performance.

[0070] The following is a detailed description with reference to exemplary embodiments.

[0071] Embodiment 1

[0072] Figure 5 The user equipment selection method according to an embodiment of the present disclosure is shown. In step S51, the base station arranges the scheduling priorities of all the user equipment to be scheduled based on the user equipment information to obtain a first scheduling priority arrangement. In step S52, the base station arranges the scheduling priorities of some of the user equipment to be scheduled by using the user equipment arrangement function to obtain a second scheduling priority arrangement. In step S53, the base station selects some of the user equipment in the first scheduling priority arrangement and the second scheduling priority arrangement as a scheduling user equipment set.

[0073] How to get the first permutation

[0074] In some examples, the "user equipment information" described in "the base station arranges the scheduling priorities of the user equipment based on the user equipment information to obtain a first arrangement of scheduling priorities" includes at least one of the following information: 1) the historical rate of each user equipment to be scheduled, 2) the singular value obtained by performing singular value decomposition on the channel estimate of the current channel obtained by each user equipment to be scheduled, 3) the signal to interference plus noise ratio (SINR) of each user equipment to be scheduled estimated using the current channel state information (CSI), 4) the maximum transmission rate that can be achieved by each user equipment to be scheduled estimated using the current channel state information, 5) the fairness weight of the user equipment, 6) the order of user equipment selection after a semi-orthogonal user selection (SUS) algorithm is used to select an SUS user equipment using the current channel information of the user equipment, and 7) the order of user equipment selection after a user equipment selection is performed using any greedy algorithm using the current channel information of the user equipment.

[0075] SUS and its variants are algorithms used for the user equipment selection problem in zero-forcing precoding. SUS is a heuristic iterative algorithm based on the idea of ​​a greedy algorithm, which searches for the user equipment that best meets the above conditions through multiple rounds. In short, SUS calculates the quasi-orthogonal function of each user equipment that is not included in the scheduled user equipment set and all user equipment in the current scheduled user equipment set in each round. The calculation result of this function represents the scheduling value of each user equipment that is not included in the scheduled user equipment set, and selects a user equipment with the best value to add to the scheduled user equipment set (keep the user equipment added to the scheduled user equipment set in each round quasi-orthogonal with all the user equipment added previously). SUS repeats the above iterative process until the number of user equipment in the scheduled user equipment set meets the system requirements.

[0076] Specifically, the method for the base station to obtain the first arrangement is that when the "user equipment information" includes the information in 1), 2), 3), 4), and 5) above, a value indicating the scheduled value of each user equipment to be scheduled can be determined based on the user equipment information. The first arrangement is obtained by arranging the values ​​indicating the scheduled value of the user equipment from large to small. For example, one of the above user equipment information of N scheduled user equipment can be represented as a user equipment value vector, each value in the user equipment value vector indicates the scheduled value of the corresponding user equipment, and the first arrangement is obtained by arranging the values ​​in the user equipment value vector. For example, it is also possible to obtain a user equipment value vector by weighted averaging at least one of the above user equipment information, and to obtain the first arrangement by arranging the values ​​of this vector from large to small. Among them, the value of the user equipment value vector represents the user equipment scheduling value of each type of user equipment information. Because the priority of the user equipment to be scheduled may be related to all the above user equipment information, the advantage of weighted averaging of multiple user equipment information is that it can balance the influence of each type of user equipment information on the first arrangement, and obtain a better arrangement than arranging using a single user equipment information. For example, the base station obtains first user equipment information and second user equipment information of N user equipments to be scheduled, which are represented as vector A and vector B respectively. The base station calculates ρ 1 A+ρ 2 B obtains the user device value vector and arranges the values ​​in the user device value vector to obtain the first arrangement, and the weighted average coefficient ρ 1 and ρ 2 Is a constant. When the "user equipment information" includes the historical rate of the user equipment to be scheduled, the weighted average coefficient can be determined according to the period of reference signal transmission in the system. The channel state information described in 3) and 4) is at least one of the following information: channel state matrix, channel eigenvalues ​​obtained by singular value decomposition of the channel state matrix, channel eigenvectors obtained by singular value decomposition of the channel state matrix, precoding matrix indicator (Precoding Matrix Indicator, PMI), channel quality indicator (Channel Quality Indicator, CQI). The fairness weights described here are weights calculated using any one of the methods such as proportional fairness, polling, maximum weighted delay priority, etc. For example, when the proportional fairness method is used, the method for calculating the fairness weight p for any user equipment is Where s is the estimated maximum transmission rate that the user equipment can achieve, o is the historical average rate of the user equipment, and σ and ψ are constants representing the fairness coefficients.

[0077] The user equipment information may also be a pre-selected or pre-determined user equipment sequence, such as the information in 6) or 7) above. When the "user equipment information" is the information in 6) or 7) above, the system directly uses the user equipment selection sequence provided in 6) or 7) as the first arrangement of the user equipment scheduling priority.

[0078] Taking the “user equipment information” including the historical rate and channel characteristic value of each user equipment as an example, the historical rates of the N user equipments to be scheduled in the system can be expressed as a vector And the channel eigenvalue of the user equipment can be expressed as a vector where t n and e n They respectively express the historical rate and characteristic value of user equipment n. The method for the base station to obtain the first arrangement may be, for example, to calculate And sort the user devices according to the calculation results, where the weighted average coefficient ρ 1 and ρ 2 is a constant and can be determined according to the period of reference signal sending in the system.

[0079] How to get the second permutation

[0080] In some examples, the feature of "the base station arranges the scheduling priorities of some user equipments in the first arrangement by the user equipment arrangement function to obtain the second arrangement" includes: obtaining a value indicating the scheduling value or probability of some user equipments in the first arrangement based on the user equipment arrangement function, and sorting the value to obtain the second arrangement. Specifically, the above process involves the following aspects: 1) selecting some user equipments in the first arrangement, 2) constructing a user equipment arrangement function that can reflect the priority of each user equipment, and 3) determining the second arrangement using the user equipment arrangement function.

[0081] Select some user devices in the first row

[0082] In some examples, "selecting some user devices in the first arrangement" may be to add the Mth user device in the first arrangement to the target user device set of the second arrangement, and add the user devices to the target user device set of the second arrangement in descending order of similarity according to the degree of similarity between other user devices and the Mth user device in the first arrangement, until the number of user devices in the target user device set of the second arrangement reaches the predetermined number of user devices in the second arrangement. Wherein, M represents the maximum number of scheduled user devices of the system or the number of user devices expected to be scheduled, which is determined by high-level signaling. It is known that the first arrangement is a suboptimal arrangement of user device scheduling priorities, and the probability of user devices in the first arrangement being finally scheduled decreases as the priority decreases, wherein the closer the user devices are to the maximum number of scheduled user devices or the number of user devices expected to be scheduled M, the more similar the probability of being finally scheduled is (it can be understood that the M-1, M, and M+1th are priority adjacent user devices, and the probability of being scheduled is also close). The reason for selecting the Mth user equipment and the user equipment close to the Mth user equipment in the first arrangement as the target user equipment of the second arrangement is that these user equipments have a higher probability of being wrongly determined as user equipments according to the first arrangement (i.e., they should be scheduled but are not scheduled, or vice versa). Among them, the number of user equipments in the second arrangement is related to at least one of the following system variables: the computing resources that the system can use for scheduling, the maximum number of user equipments scheduled by the system or the number of user equipments M expected to be scheduled, and the maximum coverage of the base station. The computing resources described here are the available floating-point calculation amount allocated by the system for neural network reasoning. The system determines the threshold value of the number of user equipments in the second arrangement according to the computing resources allocated to the scheduling, and makes the number of user equipments in the second arrangement less than this threshold. When the number of user equipments in the second arrangement is related to the maximum number of user equipments scheduled by the system or the number of user equipments M expected to be scheduled, the number of user equipments in the second arrangement increases with the increase of the maximum number of user equipments or the number of user equipments M expected to be scheduled. When the number of user equipments in the second arrangement is related to the maximum coverage of the base station, the number of user equipments in the second arrangement increases with the increase of the coverage of the base station.

[0083] As an example, taking the system goal as an example of selecting M user equipments from a total of N user equipments for scheduling (N>=M), the arrangement order of the user equipments in the first arrangement obtained is Ω 1 = {u 1 ,u 2 ,…,u M ,…,u N}. Select Ω 1 The M-x+1th to M+yth user equipment {u M-x+1 ,…,u M ,…,u M+y}=Ψ1 As the target user equipment of the second arrangement, the sum of x and y is equal to the number of user equipments in the second arrangement, and x and y can be any integers that meet this condition. Preferably, when the number of user equipments in the second arrangement is an even number, let x=y, and when the number of user equipments in the second arrangement is an odd number, let x=y-1 or x=y+1. Optionally, the system parameters x and y can be set to satisfy ∈(x+y)=M,∈>1, where ∈ is a coefficient that decreases with the increase of the maximum coverage range of the base station.

[0084] Construct the user device ranking function required for ranking

[0085] In some examples, "constructing a user equipment ranking function that can reflect the priority of each user equipment" can be to construct a function whose input is the status of some user equipment to be scheduled, and whose output is the scheduling value or scheduling probability of some user equipment to be scheduled. For example, when the output is the scheduling value of the user equipment, the output value is a vector composed of floating point numbers, and the values ​​in the vector represent the scheduling value of the corresponding user equipment relative to other user equipment to be scheduled that are output. For example, when the output is the scheduling probability of the user equipment, the output value is a vector composed of probabilities, and the probability values ​​in the vector represent the scheduling probability of the corresponding user equipment relative to other user equipment to be scheduled that are output.

[0086] Specifically, the "status of some user equipment to be scheduled" includes at least one of the following information: the historical rate of the user equipment, the estimated value of the current full channel information of the user equipment, the eigenvector of the current channel of the user equipment, the eigenvalue of the current channel of the user equipment, the user equipment signal to interference plus noise ratio SINR estimated by the eigenvector and eigenvalue of the current channel of the user equipment, the user equipment rate estimated by the eigenvector and eigenvalue of the current channel of the user equipment, the SINR obtained through feedback from the user equipment, the SINR estimated by the uplink reference signal of the user equipment, etc.

[0087] Specifically, the carrier of the "user device arrangement function" can be one of the following forms: a lookup table that directly maps the state to the arrangement order of the user devices, a polynomial that maps the state to the value or probability of each user device being scheduled, and a neural network that maps the state to the value or probability of each user device being scheduled. The structure of the neural network includes but is not limited to a multilayer perceptron (Multilayer Perceptron, MLP), a convolutional neural network (Convolutional Neural Network, CNN), a deep neural network (Deep Neural Network, DNN), a recurrent neural network (Recurrent Neural Network, RNN), a restricted Boltzmann machine (Restricted Boltzmann machine, RBM), a graph neural network (Graph Neural Network, GNN), a deep belief network (Deep Belief Network, DBN), a bidirectional recurrent deep neural network (Bi-directional Recurrent Deep Neural Network, BRDNN), a Transformer network, etc. When the user device arrangement function is a lookup table, the method for obtaining the user device arrangement is to find the user device arrangement order corresponding to the current state by a table lookup method. When the user device ranking function is a polynomial, the value or probability of each user device being scheduled is calculated by substituting the current state into the polynomial. When the user device ranking function is a neural network, the current state is input into the neural network, and the output is the value or probability of the user device being scheduled.

[0088] Taking the system goal as an example, where M user equipments are selected from a total of N user equipments for scheduling (N>=M), the arrangement order of the N user equipments obtained by the system according to the first arrangement is Ω 1 = {u 1 ,u 2 ,…,u M ,…,u N}, the second ranked target user equipment Ψ 1 = {u M-x+1 ,…,u M ,…,u M+y} is to select Ω 1 The structure of the user equipment arrangement function is as follows: Figure 6 Specifically, the input of the user equipment ranking function is the status information of M+y user equipments (M+y<=N), and the output of the user equipment ranking function is x+y (x<=M) outputs. The input information is the first ranking Ω of the user equipment scheduling priority. 1The state information of the first M+y user equipments in the output is the target user equipment Ω of the second arrangement 2 The value or probability of the user equipment in the first arrangement being scheduled (that is, the value or probability of the M-x+1th to M+yth user equipment in the first arrangement being scheduled).

[0089] Determine the second arrangement using the user equipment arrangement function

[0090] In some examples, the process of "determining the second ranking using the user equipment ranking function" is to rank the value or probability of each user equipment being scheduled output by the user equipment ranking function from large to small to obtain a second ranking of user equipment scheduling priorities.

[0091] Taking the system goal of selecting M user equipments from a total of N user equipments for scheduling as an example (N>=M), the process of obtaining the second arrangement of user equipment scheduling priorities is as follows: Figure 7 Specifically, the process includes: 1) First, in step S71, the user equipment information is used to obtain the first ranking Ω of the user equipment scheduling priority. 1 = {u 1 ,u 2 ,…,u M ,…,u N}; 2) In step S72, the first M+y user equipments {u 1 ,u 2 ,…,u M-x+1 ,…,u M ,…,u M+y} is input into the user equipment ranking function to obtain x+y outputs, and the obtained x+y outputs are the values ​​or probabilities of the M-x+1th to M+yth user equipments being scheduled in the first ranking of user equipment scheduling priority; 3) in step S73, the obtained values ​​or probabilities are ranked from large to small to obtain the second ranking of user equipment scheduling priority Ω 2 = {u 1 ,u 2 ,…,u x+y}.

[0092] Method for obtaining scheduled user equipment set

[0093] In some examples, the feature of "the base station selects some user equipment in the first arrangement and the second arrangement as the scheduled user equipment set" is that the first Mx user equipment in the first arrangement of user equipment scheduling priority are selected to obtain user equipment set a, and the first x user equipment in the second arrangement of user equipment scheduling priority are selected to obtain user equipment set b, and the scheduled user equipment set is the union of the two sets, that is, a∪b.

[0094] In the above, it is introduced that the second arrangement is determined by using the user equipment arrangement function. The following describes how the user equipment arrangement function is determined by an example.

[0095] In some examples, the user equipment ranking function for obtaining the second ranking of user equipment scheduling priorities can be obtained by a reinforcement learning method. Specifically, the method for obtaining the user ranking function can be to train an initialized user ranking function according to a reward function using a reinforcement learning algorithm.

[0096] Specifically, the "reinforcement learning algorithm" can be one of the following methods, including but not limited to, multi-armed bandit algorithm, Monte Carlo algorithm, Q learning algorithm, SARSA algorithm, deep Q network (DQN) algorithm, dual deep Q network algorithm (Duelling DQN), rainbow algorithm, policy gradient algorithm, action-critic joint algorithm (Actor-Critic), proximal policy optimization (PPO) algorithm, soft action-critic joint algorithm (Soft Actor Critic), etc.

[0097] Specifically, the performance may be one of the following performance indicators: a reward obtained by using a user equipment permutation function, a sum rate estimated by using a user equipment permutation function, and an average SINR of all scheduled user equipments estimated by using a user equipment permutation function.

[0098] Specifically, the process of “training” an initialized user device ranking function is as follows: Figure 8As shown. First, in step S81, the user device arrangement function is initialized. For example, the initialization method is that when the user device arrangement function is a lookup table, all values ​​in the table are set to zero; when the user device arrangement function is a polynomial, the coefficients of the polynomial are randomly generated; when the user device arrangement function is a neural network, the weights of the neural network are randomly generated. After that, multiple rounds of training are performed to converge the user device arrangement function to the optimal, and each round of training includes: 1) In step S82, a user device is selected from the target user devices (x+y user devices) of the second arrangement according to the exploration strategy, wherein the exploration strategy includes but is not limited to the epsilon-greedy strategy (epsilon greedy), the random exploration strategy, etc.; 2) In step S83, the rewards corresponding to the selected user devices are calculated according to the first Mx user devices obtained from the first arrangement of the user device scheduling priority and the user devices selected by the current exploration strategy; 3) In step S84, the user device arrangement function is updated according to the selected reinforcement learning algorithm according to the user device selection and its corresponding reward; 4) In step S85, the performance of the current user device arrangement function is tested; 5) In step S86, it is determined whether to continue training. Optionally, whether the system continues training can be determined by judging whether the performance of the user equipment arrangement function training meets a predetermined condition (for example, whether it reaches a certain threshold). Optionally, whether the system continues training can be determined by judging whether the performance of the user equipment arrangement function on the test data set is improved after the first K rounds of training. Specifically, the system initializes the optimal test performance as a randomly selected performance at the beginning of training, and tests the user equipment arrangement function after each round of training. If the test performance exceeds the previous optimal test performance, the current test performance is recorded as the optimal test performance. If the optimal test performance does not improve after the first K rounds of training, the training is stopped. The performance can be one of the following performance indicators: the reward obtained by using the user equipment arrangement function, the sum rate estimated by using the user equipment arrangement function, and the average SINR of all scheduled user equipment estimated by the user equipment arrangement function.

[0099] Specifically, the "reward function" used to update the user device ranking function for any round of training can be calculated by the following method:

[0100] R = α(SS ref -P-β),

[0101] Among them, R represents reward, S refis the sum rate of the first Mx user devices obtained according to the first ranking of user device scheduling priority, S is the sum rate of the first Mx user devices obtained according to the first ranking of user device scheduling priority plus a user device selected from a total of x+y user devices (i.e., the M-x+1th to the M+yth user devices) according to the exploration strategy, P is the fairness weight of the selected user device, and α and β are both constants. When the optimization target selected by the user device only considers the sum rate, let P=0. When the optimization target selected by the user device is the sum rate under the constraint of the fairness principle, P is calculated according to the maximum priority function of the traditional fairness principle. For example, when the fairness principle is proportional fairness, P can be calculated by the following formula:

[0102]

[0103] Wherein, s is the estimated maximum transmission rate that the selected user equipment can achieve, o is the historical average rate of the selected user equipment, and σ and ψ are fairness coefficients. Thus, the user selection method according to the present disclosure can improve the system sum rate or the sum rate based on the fairness principle.

[0104] Embodiment 2

[0105] In the first embodiment, the base station obtains the second arrangement of user equipment scheduling priorities by a reinforcement learning method, wherein the target user equipment of the second arrangement is the M-x+1th to M+yth user equipment of the first arrangement, wherein x and y are system parameters, and the size of x and y increases with the increase of the maximum number of user equipment M scheduled by the system and the maximum coverage range of the base station. When x+y is less than a certain threshold value γ, the performance of the base station using reinforcement learning to obtain the second arrangement will not be affected by the increase in the number of x+y. When x+y is greater than a certain threshold value γ, the performance of the base station using reinforcement learning to obtain the second arrangement will decrease slightly with the increase in the number of x+y. The reason for the slight decrease in performance is that the increase in x+y leads to an increase in the output dimension of reinforcement learning and an increase in the complexity of the optimized problem, which increases the difficulty of reinforcement learning convergence, resulting in an increase in the difficulty of obtaining the optimal user equipment arrangement function, and the user equipment arrangement function obtained using limited computing resources may be slightly worse than the optimal user equipment arrangement function.

[0106] This embodiment proposes a user equipment selection method for multi-user equipment multi-input multi-output system scheduling based on multi-round reinforcement learning. This method can enable the base station to more accurately arrange the scheduling priority of the user equipment, thereby obtaining higher scheduling efficiency and higher system and rate.

[0107] According to this embodiment, the base station obtains the first arrangement of the scheduling priority of the user equipment based on the user equipment information, and obtains L arrangements (L>1) using L functions, including the second arrangement to the L+1th arrangement, wherein the l+1th arrangement is obtained by arranging the scheduling priorities of some user equipment in the lth arrangement through the lth function, and selects some user equipment in each arrangement of the total L+1 arrangements from the 1st arrangement to the L+1th arrangement as the scheduled user equipment set. That is, for each current arrangement, a sub-arrangement is selected, and the user equipment in the sub-arrangement is rearranged. For each current arrangement, the user equipment located in front of the user equipment in the selected sub-arrangement is selected as the scheduled user equipment. Rearranging the user equipment in the sub-arrangement includes: obtaining the scheduling value or probability of the user equipment in the sub-arrangement based on the arrangement function according to the status information of the user equipment in the current arrangement; and arranging based on the scheduling value or probability of the user equipment in the sub-arrangement. This process is as follows Fig. 9 shown.

[0108] The number of user devices in the sub-arrangement can be determined based on at least one of the computing resources that can be used for scheduling, the maximum number of users that can be scheduled or the number of users expected to be scheduled, and the maximum coverage of the base station. The state information of the user device may include at least one of the following: the historical rate of the user device, the relevant information of the current channel information of the user device, the signal to interference plus noise ratio SINR estimated by the eigenvector and eigenvalue of the user's current channel, the user rate estimated by the eigenvector and eigenvalue of the user's current channel, the SINR obtained by user feedback, or the SINR estimated by the user's uplink reference signal. The arrangement function may include at least one of the following: a lookup table that directly maps the user's state information to the user's arrangement order, a function that maps the user's state information to the user's scheduled value or probability, or a neural network that maps the user's state information to the user's scheduled value or probability.

[0109] Hereinafter, the “lth (or L) arrangement of scheduling priorities” will be referred to as the “lth (or L) arrangement”, and the “lth (or L) user equipment arrangement function” will be referred to as the “lth (or L) function”.

[0110] Fig. 9 The user equipment selection method according to the embodiment of the present disclosure is shown. In step S91, the base station arranges the scheduling priorities of the user equipment based on the user equipment information to obtain the first arrangement, and initializes l to 1. In step S92, the l+1th arrangement is obtained according to the lth arrangement function. Then in step S93, it is determined whether l is equal to L. If not, l is increased by one in step S94; if yes, some of the user equipment in each arrangement obtained is used as a scheduled user equipment set in step S95.

[0111] Taking the system including L=2 functions as an example, the base station arranges the scheduling priorities of the user equipment based on the user equipment information to obtain the first arrangement, arranges the scheduling priorities of some user equipment in the first arrangement by the first function to obtain the second arrangement, arranges the scheduling priorities of some user equipment in the second arrangement by the second function to obtain the third arrangement, and selects some user equipment in each arrangement as the scheduled user equipment set.

[0112] In some examples, the method of "the base station obtains the first arrangement of the user equipment scheduling priority based on the user equipment information" is obtained by the method proposed in Example 1.

[0113] In some examples, the method for selecting the “user equipment in the lth arrangement” may be to select the mth user equipment in the l-1th arrangement. l-1 The user equipment is added to the target user equipment set of the lth arrangement, and the other user equipment is added to the target user equipment set of the mth arrangement according to the l-1 According to the similarity of the user devices in the arrangement, the user devices are added to the target user device set of the lth arrangement in descending order of similarity until the number of user devices in the target user device set of the lth arrangement is consistent with the output dimension of the preset user device arrangement function. Specifically, when l=1, m 0 =M, when l>1 where x l-1 +y l-1 It represents the dimension of the l-1th arrangement, and int(*) means rounding *.

[0114] In some examples, the “first function” may be a function whose input is the state of some user devices and whose output is the value or probability of some user devices being scheduled. Specifically, when l=1, the input dimension and output dimension of the first function are M+y 1 and x 1 +y 1 When l>1, the input dimension of the lth function is m l-1 +y l , the output dimension is x l +y l The target user equipment of the lth function is the arrangement obtained by the l-1th function The mth l-1 -x l +1 user device to the mth l-1 +y l User equipment, that is Among them, x l and l is a system parameter, which can be determined by the method in the first embodiment. The user equipment included in each arrangement is as follows Fig.10 shown.

[0115] In some examples, the process of determining the l+1th arrangement using the lth function is to arrange the scheduling value or scheduling probability of each user equipment output by the lth function from large to small to obtain the l+1th arrangement of the user equipment scheduling priority. The user equipment status information input to the lth function includes: 1) the first Mx of the first arrangement 1 Status information of user equipment; 2) In the 2nd to l-1th arrangement, the first m of each arrangement l-1 -x l Status information of user equipment; 3) the first y l Input the user device status information to the first function to obtain x l +y l outputs, and arrange the obtained outputs from large to small to obtain the l+1th arrangement of the user equipment scheduling priority

[0116] In some examples, the feature of “selecting a portion of user equipment in each of the L+1 user equipment scheduling priority rankings” is to select the first Mx user equipments in the first ranking of the user equipment scheduling priority. 1 UEs obtain UE set a, let l = {2, ..., L + 1}, select the first m UEs in each ranking l in the scheduling priority rankings of all 2 to L + 1 UEs, l-1 -x l The user equipment obtains the user equipment set b l , the scheduled user equipment set is the union of L+1 sets, that is, a∪b 1 ∪…∪b L .

[0117] Taking the system including L=2 functions as an example, the second arrangement of the user equipment scheduling priority is The third ranking Ω of the user equipment scheduling priority is obtained through the first function. 3 It is obtained through the second function. Specifically, the input dimension of the second function is M+y 2 , the output dimension is x 2 +y 2 The target user device of the second function is the arrangement obtained by the first function. The mth 1 -x 2 +1 user device to the mth 1 +y 2 User equipment, that is The method for determining the third arrangement by using the second function is to input part of the user equipment status information in the second arrangement into the second function. Specifically, the input user equipment status information includes: 1) the first Mx of the first arrangement1 Status information of user equipment; 2) The first m in the second row 1 +y 2 The status information of the user device. Input the user device status information to the second function to obtain x 2 +y 2 outputs, and the obtained outputs are arranged from large to small to obtain the third arrangement of the user equipment scheduling priority Specifically, the characteristics of the scheduled user equipment set are obtained by selecting the first Mx of the user equipment scheduling priorities. 1 The user equipment obtains the user equipment set a, selects the first m in the second user equipment scheduling priority ranking 1 -x 2 The user equipment obtains the user equipment set b 1 , select the first m in the third user equipment scheduling priority ranking 2 -x 3 The user equipment obtains the user equipment set b 2 , the scheduled user equipment set is the union of the three sets, that is, a∪b 1 ∪b 2 .

[0118] In some examples, the l-1th function for obtaining the lth arrangement (l>1) of the user equipment scheduling priority can be obtained by sequential training through a reinforcement learning method. Specifically, the feature of "sequential training" is to train the lth function in order from 1 to L, wherein the training method for any lth function is the training method proposed in the first embodiment. Among them, the reward function R required for the lth function to update l The method is:

[0119] R l =α(S l -S l,ref -P-β),

[0120] Among them, S l,ref The first Mx of the input to the lth function l The sum rate of user equipments, S l The first Mx of the input to the lth function l The user equipment plus the exploration strategy from a total of x l +y l The sum rate of a user equipment selected from the user equipments, P is the fairness weight of the selected user equipment, and α and β are both constants.

[0121] The above method described in the present disclosure may be executed by a base station including a transceiver and a processor. Fig.11 FIG. 4 shows an exemplary structure of a base station according to the present disclosure. Fig.11 As shown, the base station includes a transceiver 1110 and a processor 1120 coupled to the transceiver 1110. The transceiver 1110 is configured to send and receive signals. The processor 1120 is configured to execute the user selection method described in the present disclosure. The present disclosure can also be implemented as a computer storage medium. The computer storage medium stores computer executable instructions. When the stored computer executable instructions are executed by the processor, the processor executes the user selection method described in the present disclosure.

[0122] It can be understood that “at least one of / at least one” described in the present disclosure includes any and / or all possible combinations of the listed items, the various embodiments described in the present disclosure and the various examples in the embodiments can be changed and combined in any appropriate form, and the “ / ” described in the present disclosure means “and / or”.

[0123] The various illustrative logical blocks, modules, and circuits described in the present disclosure may be implemented or executed with a general purpose processor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components, or any combination thereof designed to perform the functions described herein. A general purpose processor may be a microprocessor, but in an alternative, the processor may be any conventional processor, controller, microcontroller, or state machine. The processor may also be implemented as a combination of computing devices, such as a combination of a DSP and a microprocessor, a plurality of microprocessors, one or more microprocessors cooperating with a DSP core, or any other such configuration.

[0124] The steps of the method or algorithm described in the present disclosure can be directly embodied in hardware, in a software module executed by a processor, or in a combination of the two. The software module can reside in a RAM memory, a flash memory, a ROM memory, an EPROM memory, an EEPROM memory, a register, a hard disk, a removable disk, or any other form of storage medium known in the art. An exemplary storage medium is coupled to a processor so that the processor can read and write information from / to the storage medium. In an alternative, a storage medium can be integrated into a processor. The processor and the storage medium can reside in an ASIC. The ASIC can reside in a user equipment terminal. In an alternative, the processor and the storage medium can reside in a user equipment terminal as discrete components.

[0125] In one or more exemplary designs, the functions may be implemented in hardware, software, firmware, or any combination thereof. If implemented in software, the functions may be stored on or transmitted as one or more instructions or codes on a computer-readable medium. Computer-readable media include both computer storage media and communication media, the latter including any media that facilitates the transfer of a computer program from one place to another. Storage media may be any available media that can be accessed by a general or special purpose computer.

[0126] The description set forth herein, in conjunction with the accompanying drawings, describes example methods and apparatus and does not represent all examples that may be implemented or within the scope of the claims. The term "example" as used herein means "used as an example, instance, or illustration," rather than "preferred" or "superior to other examples." The detailed description includes specific details for the purpose of providing an understanding of the described techniques. However, these techniques may be practiced without these specific details. In some cases, well-known structures and devices are shown in block diagram form to avoid obscuring the concepts of the described examples.

[0127] Although this specification contains a number of specific implementation details, these should not be interpreted as limitations on any invention or the scope of the claimed protection, but rather as descriptions of specific features of specific embodiments of specific inventions. Certain features described in this specification in the context of separate embodiments may also be implemented in combination in a single embodiment. On the contrary, the various features described in the context of a single embodiment may also be implemented separately in multiple embodiments or in any suitable sub-combination. In addition, although features may be described above as working in certain combinations, and even initially claimed as such, in some cases, one or more features from the claimed combination may be deleted from the combination, and the claimed combination may be directed to a sub-combination or a variation of the sub-combination.

[0128] It should be understood that the specific order or hierarchy of steps in the method of the present invention is an illustration of an exemplary process. Based on design preferences, it is understood that the specific order or hierarchy of steps in the method can be rearranged to achieve the functions and effects disclosed in the present invention. The attached method claims present the elements of various steps in an example order and are not meant to be limited to the specific order or hierarchy presented unless otherwise specifically stated. In addition, although elements can be described or claimed in the singular, the plural number is also contemplated unless a limitation to the singular is explicitly stated. Therefore, the present disclosure is not limited to the examples shown, and any device for performing the functions described herein is included in the various aspects of the present disclosure.

[0129] The text and drawings are provided as examples only to help readers understand the present disclosure. They are not intended and should not be interpreted as limiting the scope of the present disclosure in any way. Although certain embodiments and examples have been provided, it is obvious to those skilled in the art based on what is disclosed herein that the embodiments and examples shown may be changed without departing from the scope of the present disclosure.

Claims

1. A user selection method performed by a first node, comprising: Arranging a plurality of user devices to obtain a first arrangement; Rearranging some user equipments in the first arrangement to obtain a second arrangement; Based on the first arrangement and the second arrangement, a scheduled user equipment is determined.

2. The method of claim 1, wherein: Based on the first arrangement and the second arrangement, determining the scheduled user equipment includes: Determining a first user equipment to be scheduled based on the first arrangement; Based on the second arrangement, a second user equipment to be scheduled is determined.

3. The method according to claim 1 or 2, wherein: The rearranging of some user equipments in the first arrangement includes: Perform at least one of the following processes on the first arrangement: A sub-arrangement is selected in the current arrangement, and user equipments in the sub-arrangement are rearranged.

4. The method of claim 3, wherein: Based on the second arrangement, determining the scheduled second user equipment includes: Perform the following steps at least once: For each current arrangement, the user equipment located in front of the user equipment in the sub-arrangement is used as the second user equipment to be scheduled.

5. The method of claim 1, wherein: Arranging a plurality of user equipments to obtain a first arrangement includes: Arrange the plurality of user devices based on the information of each user device to obtain a first arrangement; The information of the user equipment includes at least one of the following: a historical rate of the user equipment, current channel estimation information and related information of the user equipment, a signal to interference plus noise ratio SINR of the user equipment, a maximum transmission rate of the user equipment, and a fairness weight of the user equipment.

6. The method of claim 3, wherein: Selecting a sub-arrangement in the current arrangement, and rearranging the sub-arrangement comprises: Select a sub-array in the current array. According to the state information of the user equipment in the current arrangement, obtaining the scheduling value or probability of the user equipment in the sub-arrangement based on the arrangement function; and The ranking is performed based on the scheduling value or probability of the user equipment in the sub-ranking.

7. The method of claim 6, wherein: The number of user equipments in the sub-array is determined based on at least one of computing resources available for scheduling, a maximum number of user equipments that can be scheduled or a number of user equipments expected to be scheduled, and a maximum coverage range of a base station.

8. The method of claim 6, wherein: The status information of the user equipment includes at least one of the following items: a historical rate of the user equipment, current channel estimation information and related information of the user equipment, a signal to interference plus noise ratio SINR estimated by current channel estimation related information of the user equipment, a user rate estimated by current channel estimation related information of the user equipment, an SINR obtained by user feedback, or an SINR estimated by an uplink reference signal of the user.

9. The method of claim 6, wherein: The arrangement function includes at least one of the following: directly mapping the state information of the user device to a lookup table of the arrangement order of the user device, mapping the state information of the user device to a function of the scheduled value or probability of the user device, or mapping the state information of the user device to a neural network of the scheduled value or probability of the user device.

10. A first node, comprising: a transceiver configured to transmit and receive signals; and A processor, coupled to the transceiver, and configured to execute the method according to any one of claims 1 to 9.

11. A computer-readable storage medium storing computer-executable instructions, wherein when the computer-executable instructions are executed by a processor, the processor executes the method according to any one of claims 1 to 9.

Images