Intelligent precoding method in real-time broadband communication scenario
Through the deep reinforcement learning network and traditional precoding cascade architecture, a precoding solution under multi-slot span is designed, which solves the problems of user capacity limitation and dynamically changing transmission requirements in broadband real-time interaction scenarios, and achieves global optimal solution and reception Frame rate increases.
Patent Information
- Application Number
- PCT/CN2024/090682
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Priority Date
- 2023-05-22
- Filing Date
- 2024-04-29
- Publication Date
- 2024-11-28
AI Technical Summary
In the existing broadband real-time interaction scenarios, traditional precoding technology cannot meet the needs of low latency and multi-users, resulting in limited user capacity and the single-slot optimal solution cannot adapt to the transmission needs of dynamic changes between users during time slots.
Using a deep reinforcement learning (DRL) network and traditional precoding cascade architecture, train adaptive regulatory precoding schemes through reinforcement learning methods, design precoding schemes under multiple time slot spans, and optimize the precoding matrix to improve user capacity and Meet dynamically changing transmission needs.
The global optimal solution under multiple time slots in broadband real-time interaction scenarios is realized, which improves user capacity and receive frame rate, and solves the problem that the single time slot optimal solution cannot meet the dynamically changing transmission needs.
Smart Images

Figure CN2024090682_28112024_PF_FP_ABST
Abstract
Description
An intelligent precoding method for broadband real-time interaction scenarios Technical Field
[0001] The present application relates to the field of communication technology, and in particular to an intelligent precoding method and device in a broadband real-time interaction scenario. Background Art
[0002] In wireless communication networks, extended reality (XR) technology has the advantages of multi-perspective and strong interactivity. It can provide users with a brand-new visual experience and has great application value and commercial potential.
[0003] Real-time broadband communication (RTBC) is one of the three new scenarios defined by the 5.5G vision. It primarily refers to multimedia transmission technologies, such as cloud extended reality (Cloud XR) and the tactile internet, that require real-time interaction between senders and receivers. RTBC features large data volumes, high reliability, low latency, and quasi-periodicity in service packet arrival. However, the low-latency requirements of these services reduce effective channel capacity, and the large data volumes significantly limit user capacity for these services. Traditional precoding technologies, which aim to maximize the transmission rate in the current time slot, are unable to meet the requirements for maximizing the long-term utility of RTBC service systems (combining multiple transmission time slots).
[0004] RTBC services require a precoding scheme that combines multiple transmission time slots to improve user data reception rates and, in turn, the system's user capacity. Therefore, designing an intelligent precoding method for broadband real-time interaction scenarios is an urgent problem to be solved.
[0005] Summary of the Invention
[0006] In a first aspect, embodiments of the present application provide a communication method. The method can be executed by a wireless access network device, or by a component of the wireless access network device (e.g., a processor, chip, or chip system), or by a logical node, logic module, or software that implements all or part of the wireless access network device's functions. The method includes: obtaining a precoding matrix for first data to be transmitted of at least one terminal, wherein the precoding matrix corresponds to a priority weight of the at least one terminal, the priority weight corresponds to a first factor, the first factor corresponds to first status information, and the first status information corresponds to the first data to be transmitted of the at least one terminal. Precoding the first data to be transmitted of the at least one terminal is performed based on the precoding matrix. Outputting first data, wherein the first data is the data after the precoding of the first data to be transmitted of the at least one terminal is performed.
[0007] Through the above method, the base station obtains a precoding matrix for precoding at least one terminal. The precoding matrix corresponds to the reception accuracy of the first data to be transmitted in the first time slot, the first state information of the first data to be transmitted in the first time slot, and the second state information of the second data to be transmitted in the second time slot. An adaptive control precoding scheme trained using a reinforcement learning method is employed. By combining a deep reinforcement learning (DRL) network with a traditional precoding cascade architecture, a global optimal solution for precoding over multiple time slots is obtained, addressing the problem that a single-time slot optimal solution cannot meet the dynamically changing transmission requirements of users between time slots.
[0008] In combination with the first aspect, in certain embodiments of the first aspect, the first data to be transmitted is single-mode data to be transmitted.
[0009] In combination with the first aspect, in certain embodiments of the first aspect, the first data to be transmitted is multimodal data to be transmitted.
[0010] In combination with the first aspect, in certain implementations of the first aspect, the first status information includes an activation status and an expected average transmission rate of the at least one terminal.
[0011] In combination with the first aspect, in certain embodiments of the first aspect, the first status information corresponds to the first data to be transmitted of the at least one terminal, including: determining the activation status of the at least one terminal according to the arrival time of the first data to be transmitted.
[0012] In combination with the first aspect, in certain embodiments of the first aspect, the above-mentioned first status information corresponds to the above-mentioned first data to be transmitted of the above-mentioned at least one terminal, including: determining the above-mentioned expected average transmission rate of the above-mentioned first terminal based on the data volume of the above-mentioned data to be transmitted of the first terminal and the remaining transmission time for the above-mentioned first terminal to transmit the above-mentioned data to be transmitted, the above-mentioned first terminal is one of the above-mentioned at least one terminal, and the above-mentioned first data to be transmitted includes the above-mentioned data to be transmitted.
[0013] In conjunction with the first aspect, in certain embodiments of the first aspect, the expected average transmission rate satisfies:
[0014] Among them, R k is the expected average transmission rate of one terminal k in the at least one terminal, q k is the total amount of data to be transmitted from the terminal k in the first data to be transmitted, τ k is the remaining transmission time for the terminal k to transmit the data to be transmitted of the terminal k.
[0015] In conjunction with the first aspect, in certain embodiments of the first aspect, the expected average transmission rate satisfies:
[0016] Among them, R k is the expected average transmission rate of one terminal k in the at least one terminal, q k,n is the total amount of data to be transmitted in the nth mode in the data to be transmitted of the terminal k in the first data to be transmitted, τ k,n The remaining transmission time for the terminal k to transmit the data to be transmitted in the nth mode, where n is a positive integer less than or equal to N.
[0017] In combination with the first aspect, in some implementations of the first aspect, there is a corresponding relationship between the first factor and the first state information, including: the DRL network determines the first factor according to the first state information.
[0018] In combination with the first aspect, in certain embodiments of the first aspect, the priority weight corresponds to the first factor, including: determining the priority weight according to the first factor and the expected average transmission rate.
[0019] In conjunction with the first aspect, in certain implementations of the first aspect, the priority weights satisfy:
[0020] Among them, α k is the priority weight of one terminal k in the at least one terminal, C is the first factor of the terminal k, R k is the expected average transmission rate of the terminal k, R max is the maximum value of the above-mentioned expected average transmission rates of the above-mentioned at least one terminal.
[0021] In combination with the first aspect, in certain embodiments of the first aspect, the above method also includes: obtaining a first ratio, the above first ratio corresponds to the above first data, and the above first ratio is the ratio of the amount of correctly received data in the above first data to the amount of data of the above first data.
[0022] In combination with the first aspect, in certain embodiments of the first aspect, the above-mentioned first ratio and second status information are used to update the above-mentioned DRL network, the above-mentioned second status information corresponds to the second data to be transmitted of the above-mentioned at least one terminal, and the above-mentioned second data to be transmitted is the next data to be transmitted after the above-mentioned first data to be transmitted is transmitted.
[0023] In combination with the first aspect, in certain embodiments of the first aspect, the first data to be transmitted is the data to be transmitted in the first time slot, the second data to be transmitted is the data to be transmitted in the second time slot, the first time slot and the second time slot are continuous in the time domain, and the second time slot is located after the first time slot.
[0024] In a second aspect, an embodiment of the present application provides a communication method, which can be executed by a terminal, or by a component of the terminal (such as a processor, chip, or chip system, etc.), or by a logical node, logic module, or software that can implement all or part of the terminal functions. The method includes: receiving second data, the first data includes the second data, the first data is the data after precoding the first data to be transmitted of at least one terminal, the precoding corresponds to the precoding matrix, the precoding matrix corresponds to the priority weight of the at least one terminal, the priority weight corresponds to the first factor, the first factor corresponds to the first state information, and the first state information corresponds to the first data to be transmitted of the at least one terminal. Determine a second ratio based on the second data, the second ratio corresponds to the second data, and the second ratio is the ratio of the amount of data correctly received in the second data to the amount of data of the second data. Send the second ratio.
[0025] In this way, the base station obtains a precoding matrix for precoding of at least one terminal, and there is a correspondence between the precoding matrix and the reception accuracy of the first data to be transmitted in the first time slot, the first state information of the first data to be transmitted in the first time slot, and the second state information of the second data to be transmitted in the second time slot. The adaptive control precoding scheme trained by the reinforcement learning method is used to obtain the global optimal solution of precoding under multiple time slot spans through the architecture of the DRL network and the traditional precoding cascade, so as to solve the problem that the optimal solution of a single time slot cannot meet the dynamically changing transmission requirements between user time slots.
[0026] In combination with the second aspect, in certain embodiments of the second aspect, the first data to be transmitted is single-mode data to be transmitted.
[0027] In combination with the second aspect, in certain embodiments of the second aspect, the first data to be transmitted is multimodal data to be transmitted.
[0028] In combination with the second aspect, in certain embodiments of the second aspect, the first status information includes the activation status and expected average transmission rate of the at least one terminal.
[0029] In combination with the second aspect, in certain embodiments of the second aspect, the first status information corresponds to the first data to be transmitted of the at least one terminal, including: determining the activation status of the at least one terminal according to the arrival time of the first data to be transmitted.
[0030] In combination with the second aspect, in certain embodiments of the second aspect, the above-mentioned first status information corresponds to the above-mentioned first data to be transmitted of the above-mentioned at least one terminal, including: determining the above-mentioned expected average transmission rate of the above-mentioned first terminal based on the data volume of the above-mentioned data to be transmitted of the first terminal and the remaining transmission time for the above-mentioned first terminal to transmit the above-mentioned data to be transmitted, the above-mentioned first terminal is one of the above-mentioned at least one terminal, and the above-mentioned first data to be transmitted includes the above-mentioned data to be transmitted.
[0031] In conjunction with the second aspect, in certain embodiments of the second aspect, the expected average transmission rate satisfies:
[0032] Among them, R k is the expected average transmission rate of one terminal k in the at least one terminal, q k is the total amount of data to be transmitted from the terminal k in the first data to be transmitted, τ k is the remaining transmission time for the terminal k to transmit the data to be transmitted of the terminal k.
[0033] In conjunction with the second aspect, in certain embodiments of the second aspect, the expected average transmission rate satisfies:
[0034] Among them, R k is the expected average transmission rate of one terminal k in the at least one terminal, q k,n is the total amount of data to be transmitted in the nth mode in the data to be transmitted of the terminal k in the first data to be transmitted, τ k,n The remaining transmission time for the terminal k to transmit the data to be transmitted in the nth mode, where n is a positive integer less than or equal to N.
[0035] In combination with the second aspect, in certain embodiments of the second aspect, there is a corresponding relationship between the above-mentioned first factor and the first state information, including: a deep reinforcement learning DRL network determines the above-mentioned first factor based on the above-mentioned first state information.
[0036] In combination with the second aspect, in certain embodiments of the second aspect, the above-mentioned second ratio and second status information are used to update the above-mentioned DRL network, the above-mentioned second status information corresponds to the second data to be transmitted of the above-mentioned at least one terminal, and the above-mentioned second data to be transmitted is the next data to be transmitted after the above-mentioned first data to be transmitted is transmitted.
[0037] In combination with the second aspect, in some embodiments of the second aspect, the first data to be transmitted is data to be transmitted in the first time slot, the second data to be transmitted is data to be transmitted in the second time slot, the first time slot and the second time slot are continuous in the time domain, and the second time slot is located after the first time slot.
[0038] In a third aspect, embodiments of the present application provide an apparatus that can implement the method of the first aspect or any possible implementation of the first aspect. The apparatus includes corresponding units or modules for executing the above-mentioned method. The units or modules included in the apparatus can be implemented in software and / or hardware. The apparatus can be, for example, a radio access network device, or a chip, chip system, or processor that supports the radio access network device in implementing the above-mentioned method. It can also be a logical node, logical module, or software that can implement all or part of the functions of the radio access network device.
[0039] In a fourth aspect, an embodiment of the present application provides a device that can implement the method of the second aspect or any possible implementation of the second aspect. The device includes corresponding units or modules for executing the above-mentioned method. The units or modules included in the device can be implemented through software and / or hardware. The device can be, for example, a terminal, or a chip, chip system, or processor that supports the terminal to implement the above-mentioned method. It can also be a logical node, logic module, or software that can implement all or part of the terminal functions.
[0040] In a fifth aspect, an embodiment of the present application provides a device comprising: a processor coupled to a memory, the memory being used to store instructions, and when the instructions are executed by the processor, the device implements the method in the above-mentioned first aspect, or any possible implementation of the first aspect.
[0041] In a sixth aspect, an embodiment of the present application provides a device comprising: a processor coupled to a memory, the memory being used to store instructions, and when the instructions are executed by the processor, the device implements the method in the above-mentioned second aspect, or any possible implementation of the second aspect.
[0042] In a seventh aspect, an embodiment of the present application provides a computer-readable storage medium having instructions stored thereon, which, when executed, enables a computer to execute the method in the above-mentioned first aspect or any possible implementation of the first aspect.
[0043] In an eighth aspect, an embodiment of the present application provides a computer-readable storage medium having instructions stored thereon, which, when executed, enables a computer to execute the method in the above-mentioned second aspect or any possible implementation of the second aspect.
[0044] In a ninth aspect, an embodiment of the present application provides a computer program product, which includes a computer program code. When the computer program code runs on a computer, it enables the computer to execute the method of the above-mentioned first aspect or any possible implementation method of the first aspect.
[0045] In a tenth aspect, an embodiment of the present application provides a computer program product, which includes a computer program code. When the computer program code runs on a computer, it enables the computer to execute the method of the above-mentioned second aspect or any possible implementation of the second aspect.
[0046] In the eleventh aspect, an embodiment of the present application provides a chip, comprising: a processor, the processor being coupled to a memory, the memory being used to store instructions, and when the instructions are executed by the processor, the chip implements the method of the above-mentioned first aspect, the second aspect, any possible implementation of the first aspect, or any possible implementation of the second aspect.
[0047] In the twelfth aspect, an embodiment of the present application provides a communication system, including: the device of the third aspect mentioned above and the device of the fourth aspect mentioned above.
[0048] In a thirteenth aspect, an embodiment of the present application provides a communication system, comprising: the apparatus of the fifth aspect and the apparatus of the sixth aspect. It is understood that for the beneficial effects of the features corresponding to the first and second aspects in aspects three through thirteen, please refer to the relevant descriptions of aspects one and two, and no further elaboration is required. BRIEF DESCRIPTION OF THE DRAWINGS
[0049] FIG1 is a schematic diagram of a communication system used in an embodiment of the present application;
[0050] Figures 2 to 5 show schematic diagrams of several system frameworks applicable to embodiments of the present application;
[0051] Figure 6 is a schematic diagram of video frame arrival;
[0052] FIG7 is a schematic diagram of a communication method provided in an embodiment of the present application;
[0053] FIG8 is a schematic structural diagram of a terminal provided in an embodiment of the present application;
[0054] FIG9 is a schematic structural diagram of a device provided in an embodiment of the present application;
[0055] FIG10 is a schematic diagram of another device provided in an embodiment of the present application. DETAILED DESCRIPTION
[0056] Figure 1 is a schematic diagram of the architecture of the communication system used in the embodiments of the present application. As shown in Figure 1, the communication system 10 includes a radio access network (RAN) 100 and a core network (CN) 130. Optionally, the communication system 10 may also include the Internet 140. The RAN 100 may include at least one RAN node (such as 110a and 110b in Figure 1, collectively referred to as 110) and at least one terminal (such as 120a-120j in Figure 1, collectively referred to as 120). The RAN 100 may also include other RAN nodes, such as wireless relay equipment and / or wireless backhaul equipment (not shown in Figure 1). The terminal 120 is connected to the RAN node 110 wirelessly. The RAN node 110 is connected to the core network 130 wirelessly or wiredly. The core network equipment in the core network 130 and the RAN node 110 in the RAN 100 can be separate, distinct physical devices, or they can be a single physical device integrating core network logical functions and radio access network logical functions, or a single device integrating some core network logical functions and some radio access network logical functions. Terminals and RAN nodes can be connected to each other via wired or wireless means. Figure 1 is merely a schematic diagram; the communication system may also include other network devices, such as relay equipment and backhaul equipment, which are not shown in Figure 1.
[0057] The methods and devices provided in the embodiments of the present application can be used in various communication systems, such as fourth generation (4G) communication systems, 4.5G communication systems, 5G communication systems, 5.5G communication systems, 6G communication systems, systems integrating multiple communication systems, or future evolved communication systems. For example, long term evolution (LTE) systems, new radio (NR) systems, open access networks (open RAN, O-RAN or ORAN) systems, cloud radio access networks (CRAN) systems, wireless-fidelity (WiFi) systems, and communication systems related to the third generation partnership project (3GPP), as well as other such communication systems, can also be communication systems integrating two or more of the above systems.
[0058] RAN nodes can also be expressed in different ways, such as radio access network devices. Unless otherwise specified in this application, radio access network devices are used for expression. Radio access network devices (sometimes also referred to as network devices in this application) can be base stations, evolved NodeBs (eNodeBs), transmission reception points (TRPs), next generation NodeBs (gNBs) in 5G mobile communication systems, next generation base stations in 6G mobile communication systems, base stations in future mobile communication systems, or access nodes in WiFi systems, etc.; they can also be modules or units that complete part of the functions of a base station, for example, they can be centralized units (CUs) or distributed units (DUs). Radio access network devices can be macro base stations (such as 110a in Figure 1), micro base stations or indoor stations (such as 110b in Figure 1), relay nodes or donor nodes, etc., or wireless controllers in CRAN scenarios. Optionally, radio access network devices can also be servers, wearable devices, vehicles or vehicle-mounted devices, etc. For example, the access network device in vehicle to everything (V2X) technology may be a road side unit (RSU). It is understood that all or part of the functions of the wireless access network device in this application may also be implemented by software functions running on hardware, or by virtualization functions instantiated on a platform (e.g., a cloud platform). The wireless access network device in this application may also be a logical node, logical module, or software that can implement all or part of the functions of the wireless access network device.
[0059] In another possible scenario, multiple radio access network devices collaborate to assist the terminal in achieving wireless access, and different radio access network devices respectively implement part of the functions of the base station. For example, the radio access network device can be a centralized unit (CU), a distributed unit (DU), a CU-control plane (CP), a CU-user plane (UP), or a radio unit (RU). The CU and DU can be set separately, or they can be included in the same network element, such as a baseband unit (BBU). The RU can be included in a radio frequency device or radio frequency unit, such as a remote radio unit (RRU), an active antenna unit (AAU), or a remote radio head (RRH).
[0060] In different systems, CU (or CU-CP and CU-UP), DU or RU may also have different names, but those skilled in the art can understand their meanings. For example, in the ORAN system, CU may also be called O-CU (Open CU), DU may also be called O-DU, CU-CP may also be called O-CU-CP, CU-UP may also be called O-CU-UP, and RU may also be called O-RU. For the convenience of description, this application uses CU, CU-CP, CU-UP, DU and RU as examples for description. Any unit of CU (or CU-CP, CU-UP), DU and RU in this application may be implemented by a software module, a hardware module, or a combination of a software module and a hardware module. The embodiments of this application do not limit the specific technology and specific device form adopted by the wireless access network device. For the convenience of description, the following description takes the base station as an example of the wireless access network device.
[0061] A terminal may also be referred to as a terminal device, user equipment (UE), mobile station, mobile terminal, etc. The terminal can be widely used in various scenarios, such as device-to-device (D2D), vehicle-to-everything (V2X) communication, machine-type communication (MTC), Internet of Things (IoT), virtual reality, augmented reality, industrial control, autonomous driving, telemedicine, smart grid, smart furniture, smart office, smart wearable, smart transportation, smart city, etc. The terminal can be a mobile phone, tablet computer, computer with wireless transceiver function, wearable device, vehicle, drone, helicopter, airplane, ship, robot, robotic arm, smart home device, etc. The embodiments of the present application do not limit the specific technology and specific device form adopted by the terminal.
[0062] The terminal in this application may also be a VR terminal, an AR terminal, or an MR terminal. VR terminals, AR terminals, and MR terminals may all be referred to as XR terminals. An XR terminal may be, for example, a head-mounted device (such as a helmet or glasses), an all-in-one machine, a TV, a monitor, a car, a vehicle-mounted device, a tablet or a smart screen, etc. The XR terminal can present XR data to the user, and the user can experience a variety of XR services by wearing or using the XR terminal. The XR terminal can access the network wirelessly or wired, for example, through WiFi, 5G or other systems.
[0063] Base stations and terminals can be fixed or mobile. They can be deployed on land, indoors or outdoors, handheld or vehicle-mounted; on water; or in the air on aircraft, balloons, and satellites. The embodiments of this application do not limit the application scenarios of base stations and terminals.
[0064] The roles of base stations and terminals can be relative. For example, the aircraft or drone 120i in Figure 1 can be configured as a mobile base station. To terminals 120j accessing the wireless access network 100 via 120i, terminal 120i is a base station. However, to base station 110a, 120i is a terminal, meaning that communication between 110a and 120i occurs via a wireless air interface protocol. Of course, communication between 110a and 120i can also occur via a base station-to-base station interface protocol. In this case, 120i is also a base station relative to 110a. Therefore, base stations and terminals can be collectively referred to as communication devices. 110a and 110b in Figure 1 can be referred to as communication devices with base station functionality, while 120a-120j in Figure 1 can be referred to as communication devices with terminal functionality.
[0065] Communication between base stations and terminals, between base stations, and between terminals can be carried out through authorized spectrum, unauthorized spectrum, or both; communication can be carried out through spectrum below 6 gigahertz (GHz), spectrum above 6 GHz, or spectrum below 6 GHz and spectrum above 6 GHz. The embodiments of the present application do not limit the spectrum resources used for wireless communication.
[0066] In the embodiments of the present application, the functions of the base station may also be performed by a module (such as a chip) in the base station, or by a control subsystem that includes the base station function. The control subsystem that includes the base station function here can be a control center in the application scenarios of the above-mentioned terminals such as smart grid, industrial control, intelligent transportation, and smart city. The functions of the terminal may also be performed by a module (such as a chip or a modem) in the terminal, or by a device that includes the terminal function.
[0067] In this application, a base station sends a downlink signal or downlink information to a terminal, and the downlink information is carried on a downlink channel; a terminal sends an uplink signal or uplink information to a base station, and the uplink information is carried on an uplink channel; a terminal sends a sidelink signal or sidelink information to another terminal, and the sidelink information is carried on a sidelink channel. The information can be either control information or data information.
[0068] XR technology offers advantages such as multi-perspective and strong interactivity, providing users with a completely new experience and possessing enormous application value and commercial potential. XR encompasses technologies such as VR, AR, and MR, and can be widely applied in a wide range of fields, including entertainment, gaming, healthcare, advertising, industry, online education, and engineering. VR technology primarily involves rendering visual and audio scenes to closely simulate the visual and audio stimulation of the real world. In VR, users typically wear an XR device (such as a head-mounted device) to simulate visual and / or auditory sensations. VR technology can also track user movements, allowing for timely updates to the simulated visual and / or auditory content. AR technology primarily involves providing additional visual and / or auditory information or artificially generated content within the user's perceived real environment. The user's understanding of the real environment can be direct (e.g., without sensing, processing, or rendering) or indirect (e.g., transmitted through sensors and other means), with further augmentation. MR technology involves inserting virtual elements into a physical scene, aiming to provide users with an immersive experience where these elements appear to be part of the real scene.
[0069] The embodiments provided in this application are applicable to a variety of different scenarios. Figures 2 to 5 show schematic diagrams of several system frameworks applicable to the embodiments of this application.
[0070] FIG2 shows a schematic diagram of a scenario applicable to an embodiment of the present application. FIG2 illustrates a system 200, which includes a server 210, a core network and an access network 220 (which may be referred to as a transmission network 220, such as an LTE, 5G, or 6G network), and a terminal 230. The server 210 may be used to encode, decode, and render XR source data, the transmission network 220 may be used to transmit XR data, and the terminal 230 may provide users with a diverse XR experience by processing XR data. It is understood that other devices may be included between the transmission network 220 and the terminal 230, such as other terminals (such as mobile phones, laptops, or vehicle-mounted terminals) and / or network devices (such as relay devices, integrated access backhaul (IAB) devices, WiFi routers, or WiFi access points). The terminal 230 obtains XR data from the transmission network 220 with the help of other terminals and / or network devices.
[0071] Figure 3 shows another schematic diagram of a scenario to which an embodiment of the present application is applicable. Figure 3 illustrates a system 300, comprising a terminal 320 and other terminals 310. Other terminals 310 are terminals other than terminal 320. Other terminals 310 can transmit XR data to terminal 320. For example, other terminals 310 can project XR data to terminal 320. For another example, other terminals 310 and terminal 320 are vehicle-mounted terminals, and XR data can be exchanged between vehicle-mounted terminals. It can be understood that other terminals 310 can also be connected to a transmission network (such as LTE, 5G or 6G network) to obtain XR data from the transmission network, or send data to the transmission network.
[0072] FIG4 shows another schematic diagram of a scenario applicable to an embodiment of the present application. FIG4 illustrates a system 400, comprising a terminal 430, a WiFi router or a WiFi access point 420 (which may be referred to as a WiFi device 420), and other terminals 410. Other terminals 410 are terminals other than terminal 430. Other terminals 410 can transmit XR data to terminal 430 with the aid of WiFi device 420. For example, other terminal 410 is a mobile phone device, WiFi device 420 is a WiFi router, a WiFi access point or a set-top box, and terminal 430 is a TV device, a smart screen device or an electronic tablet device. The mobile phone device can project XR data to a TV device, a smart screen device or an electronic tablet device through a WiFi router, a WiFi access point or a set-top box to present it to the user.
[0073] FIG5 shows another schematic diagram of a scenario applicable to an embodiment of the present application. FIG5 illustrates a system 500, comprising a server 510, a fixed network 520, a WiFi router or a WiFi access point 530 (which may be referred to as a WiFi device 530), and a terminal 540. The server 510 may be used to encode, decode, and render XR source data, and transmit XR data to the terminal 540 with the help of the fixed network 520 and the WiFi device 530. For example, the fixed network 520 is an operator network, and the WiFi device 530 is a WiFi router, a WiFi access point, or a set-top box. The server 510 transmits or projects XR data to the terminal 540 with the help of the operator network 520 and the WiFi device 530.
[0074] It can be understood that Figures 2 to 5 only provide illustrations of several scenarios to which the embodiments of the present application can be applied, and do not limit the applicable scenarios of the embodiments of the present application.
[0075] The technical solution of this application is described below with reference to the accompanying drawings.
[0076] XR services are widely used in multiple fields, such as entertainment, healthcare, education, retail, and advertising. For XR transmission services and video transmission services, service data usually arrives periodically based on the frame rate. As shown in Figure 6, for a video with a frame rate of 60 frames per second (FPS), ideally, a frame arrives every 16.67 milliseconds (ms) (which can also be expressed as a frame period of 16.67ms). The amount of data arriving in the frame may vary (the higher the arrow in the figure, the larger the data volume; the lower the arrow, the smaller the data volume). Common frame rates for video frames are 30, 60, 90, or 120 FPS, corresponding to frame periods of 33.33, 16.67, 11.11, or 8.33ms, respectively.
[0077] Compared with general video transmission services, XR transmission services require higher resolution, so they also have higher requirements for transmission rates. For example, the transmission rate of XR transmission services is 30 megabits per second (Mbps).
[0078] For XR transmission services and video transmission services, the transmitted video frame is generally composed of multiple IP packets after being compressed using a source compression standard (such as H.265 / HEVC). The above-mentioned transmitted video frame is subject to a cliff effect during transmission. The above-mentioned cliff effect means that the bit-level errors of the transmitted video frame during transmission will spread throughout the entire transmitted video frame. It can also be understood that the bit-level errors of the transmitted video frame during transmission will cause the quality of the entire video frame to drop sharply. Therefore, the normal transmission of video frames in XR transmission services and video transmission services requires the correct transmission of all data packets in the video frame.
[0079] Real-time broadband communication (RTBC) is one of the three new scenarios defined in the 5.5G communication system vision. It primarily refers to multimedia transmission technologies, such as cloud extended reality (Cloud XR) and the tactile internet, that require real-time interaction between senders and receivers. These services are characterized by large data volumes, high reliability, low latency, and quasi-periodicity in service packet arrival. While low-latency requirements reduce effective channel capacity, the high data volume significantly limits user capacity for these services. For example, a 100Mbps bandwidth for Cloud XR services can only support approximately five terminals. Furthermore, due to air interface channel fluctuations, 5G air interface RTBC services can suffer from unstable user experience.
[0080] To address the challenges of RTBC services, optimizing air interface precoding is a key technology. Unlike traditional services that prioritize maximizing the transmission rate in the current time slot, RTBC prioritizes maximizing the long-term utility of the system. Specifically, RTBC considers frame-level transmission. Data is valid only if it is fully transmitted within a specified timeframe. If part of a frame times out, the entire frame is discarded. This is the integrity constraint of real-time services. Therefore, for real-time interactive services, it is necessary to design a precoding scheme that combines multiple transmission time slots to improve user frame reception rates and ultimately increase system capacity. RTBC services are also multimodal, meaning the base station must simultaneously consider the transmission of video frames and haptic frames. The user experience of the terminal must be satisfied across both modalities. The bursty nature of haptic packets, coupled with their extremely low latency and high reliability, further complicates the problem. Modeling the precoding process as an optimization problem requires finding the optimal precoding scheme over the long term (i.e., across multiple time slots). This problem is NP-hard and cannot be solved directly using an optimization algorithm. Even if the problem is simplified by approximation, the algorithm complexity will be extremely high, and the solution obtained will not be the global optimal solution.
[0081] To address the aforementioned challenges faced by traditional algorithms, deep reinforcement learning (DRL) algorithms can be employed, leveraging the powerful data-driven power of artificial intelligence. This allows intelligent agents to learn environmental characteristics from a large amount of empirical data gained through interactions with the environment, ultimately acquiring the ability to predict precoding schemes over the long term. DRL-based algorithms also offer the advantages of adaptability and scalability. In dynamic environments, DRL can adaptively adjust its behavior based on the current scenario, thereby learning strategies that adapt to the dynamic environment. Furthermore, DRL has a universal network architecture and good transferability. In different scenarios, the data features or system model knowledge learned by DRL agents can be transferred, spliced, or deleted, significantly improving the scalability of communication systems. Therefore, designing a DRL-based intelligent precoding weight calculation method has become a key issue, which can improve system precoding performance while reducing algorithm complexity.
[0082] In a multi-user multiple-input multiple-output (MU-MIMO) system, the goal of calculating precoding weights is to maximize user capacity, which can also be approximated as maximizing the user signal-to-interference-plus-noise ratio. MU-MIMO precoding weight calculation methods include: zero forcing, block diagonalization, maximizing signal-to-leakage ratio, and weighted minimum mean square error (WMMSE). For example, the process of calculating precoding weights using the WMMSE algorithm with the goal of maximizing the sum rate is as follows:
[0083] 1) Initialize V k , making
[0084] 2) Repeat the following steps:
[0085] 3) Update U k
[0086] 4) Update W k
[0087] 5) Update V k
[0088] If the objective function If the increment compared to the previous iteration is less than a set threshold, the loop ends, otherwise return to 2).
[0089] Among them, V krepresents the issuance right, K represents the number of users, P T Indicates total power, U k Indicates the right to withdraw, W k represents the receiving weight matrix, E k represents mean square error (MSE), α k Represents the sum rate weighting coefficient for each user.
[0090] Deep-unfolding is a method for calculating precoding weights based on a deep learning network. The deep-unfolding method uses an iterative algorithm induced deep-unfolding neural network (IAIDNN) to approximate the inverse calculation process in the WMMSE algorithm, thereby reducing the complexity of the WMMSE algorithm in calculating precoding weights.
[0091] RTBC services require latency for air interface transmission. For example, an XR video frame in RTBC services must be transmitted over the air interface within 10ms. Multi-user precoding technologies, which aim to maximize the speed and throughput of a single time slot, cannot meet the latency requirements of RTBC services. This causes data transmitted over the air interface to violate integrity constraints and become invalid, wasting air interface resources. Therefore, designing a precoding scheme that combines multiple time slots is an urgent problem to be solved.
[0092] This application provides a method for calculating intelligent precoding weights in broadband real-time interactive scenarios. This method uses an adaptive precoding scheme trained using reinforcement learning. By combining a deep reinforcement learning (DRL) network with a traditional precoding cascade architecture, this method achieves a global optimal solution for precoding across multiple time slots. This solves the problem that a single-time slot optimal solution cannot meet the dynamically changing transmission requirements of users between time slots.
[0093] Figure 7 is an interactive diagram of a communication method 700 provided in an embodiment of the present application. In Figure 7, a wireless access network device and a terminal are used as examples to illustrate the method, but the present application does not limit the execution subjects of the interactive diagram. For example, the wireless access network device in Figure 7 can also be a module (such as a chip, a chip system, or a processor) applied to the wireless access network device, or a logical node, a logical module, or software that can implement all or part of the functions of the wireless access network device; the terminal in Figure 7 can also be a module (such as a chip, a chip system, or a processor) applied to the terminal to implement the method, or a logical node, a logical module, or software that can implement all or part of the terminal functions. As shown in Figure 7, the method 700 of this embodiment may include parts 710, 720, 730, and 740.
[0094] Part 710: The base station obtains a precoding matrix for first data to be transmitted of at least one terminal, where the precoding matrix corresponds to a priority weight of the at least one terminal, the priority weight corresponds to a first factor, the first factor corresponds to first state information, and the first state information corresponds to the first data to be transmitted of the at least one terminal. The first data to be transmitted may be data with a granularity of a frame, a transport block (TB), or a bit, which is not limited in this application.
[0095] Part 720: The base station completes precoding of the first data to be transmitted of the at least one terminal according to the precoding matrix.
[0096] Part 730: The base station outputs first data, the first data being the precoded data of the first to-be-transmitted data of the at least one terminal. Correspondingly, the terminal receives second data, the first data including the second data.
[0097] Part 740: The base station obtains a first ratio, and the above-mentioned first ratio corresponds to the above-mentioned first data, and the first ratio is the ratio of the amount of correctly received data in the first data to the amount of data in the first data. The above-mentioned first ratio and second state information are used to update the DRL network, and the above-mentioned second state information corresponds to the second data to be transmitted of the above-mentioned at least one terminal, and the above-mentioned second data to be transmitted is the next data to be transmitted after the above-mentioned first data to be transmitted is transmitted. For example, the first data to be transmitted is the data to be transmitted in the first time slot, and the second data to be transmitted is the data to be transmitted in the second time slot. The above-mentioned first time slot and the above-mentioned second time slot are continuous in the time domain, and the second time slot is located after the first time slot. Accordingly, the above-mentioned at least one terminal sends the above-mentioned first ratio to the base station. The above-mentioned second data to be transmitted can be data with a granularity of frame, transport block (TB) or bit, which is not limited in this application.
[0098] In method 700, the base station obtains a precoding matrix for precoding of at least one terminal, and there is a correspondence between the precoding matrix and the reception accuracy of the first data to be transmitted in the first time slot, the first state information of the first data to be transmitted in the first time slot, and the second state information of the second data to be transmitted in the second time slot. An adaptive control precoding scheme trained by a reinforcement learning method is used to obtain the global optimal solution for precoding under multiple time slot spans through the architecture of the DRL network and the traditional precoding cascade, thereby solving the problem that the optimal solution of a single time slot cannot meet the dynamically changing transmission requirements between user time slots.
[0099] In this application, "sending information to... (radio access network device)" can be understood as the destination of the information being the radio access network device. This can include sending information to the radio access network device directly or indirectly. "Receiving information... from (radio access network device)" can be understood as the source of the information being the radio access network device, which can include receiving information from the radio access network device directly or indirectly. The information may undergo necessary processing between the source and destination of the information, such as format changes, but the destination can understand the valid information from the source. Similar expressions in this application can be understood similarly and will not be repeated here.
[0100] In a possible implementation of the first data to be transmitted, the first data to be transmitted is single-modal data to be transmitted, for example, the first data to be transmitted is data to be transmitted comprising multiple transmission video frames, or the first data to be transmitted is data to be transmitted comprising multiple transmission tactile frames.
[0101] In another possible implementation of the first data to be transmitted, the first data to be transmitted is multimodal data to be transmitted. For example, the first data to be transmitted is data to be transmitted including multiple transmission video frames and transmission tactile frames. In this case, the modality number of the first data to be transmitted is 2.
[0102] In a possible implementation of the first state information, the first state information includes the activation state of at least one terminal, and the first state information corresponds to the first data to be transmitted of the at least one terminal, including: the base station determines the activation state of the at least one terminal according to the arrival time of the first data to be transmitted. For example, the first data to be transmitted is a video frame to be transmitted, the number of terminals included in the at least one terminal is K, and the maximum possible value of K is K. max, users are activated according to the arrival time of the video frame to be transmitted. The arrival time of the first packet of the video frame to be transmitted for each user follows a truncated Gaussian distribution. In the tth time slot, if a video frame arrives for user k, the user is in an activated state; if no video frame arrives for user k, the user is in an inactivated state. For another example, the first data to be transmitted is a video frame to be transmitted and a tactile frame to be transmitted. The number of terminals included in the at least one terminal is K, and the maximum possible value of K is K. max First, activate the user according to the arrival time of the video frame to be transmitted and each channel of the tactile frame to be transmitted. The arrival time of the first packet of the video frame to be transmitted for each user obeys the truncated Gaussian distribution, and the tactile frame to be transmitted is at the initial T initial Each real-time interactive user sets N possible tactile signals (i.e., the user has N touch points), and the arrival of each tactile signal obeys an independent generalized Pareto distribution. X is obtained as the interval time of the arrival of the tactile frame of this route. In the tth time slot, user k is in an active state if a video frame or a tactile frame arrives, and is in an inactive state if no video frame or tactile frame arrives. After the activation state of at least one of the above terminals is determined, the action network π(θ) and the value network Q(φ1), Q(φ2) of the DRL network are initialized. Among them, the value network Q(φ1), Q(φ2) is a fully connected structure composed of four layers of neurons. The first three layers of the action network π(θ) are also fully connected structures. The mean and variance of the Gaussian distribution used for action sampling are approximated by the neural network of the first three layers. The action finally output by the network is randomly sampled from the distribution.
[0103] In a possible implementation of the first state information, the above-mentioned first state information includes an expected average transmission rate, and the above-mentioned first state information corresponds to the first data to be transmitted of at least one terminal, including: the base station determines the above-mentioned expected average transmission rate of the above-mentioned first terminal based on the data volume of the data to be transmitted of the first terminal and the remaining transmission time for the above-mentioned first terminal to transmit the above-mentioned data to be transmitted, the above-mentioned first terminal is one of the above-mentioned at least one terminal, and the above-mentioned first data to be transmitted includes the above-mentioned data to be transmitted.
[0104] In a possible implementation of the expected average transmission rate, the expected average transmission rate satisfies:
[0105] Among them, R k is the expected average transmission rate of one terminal k in the at least one terminal, q k is the total amount of data to be transmitted from the terminal k in the first data to be transmitted, τ k is the remaining transmission time for the terminal k to transmit the data to be transmitted of the terminal k.
[0106] For example, in the tth time slot, the amount of video frames remaining to be transmitted by user k is q k,t , the remaining transmission delay of the video frame is τ k,t , the expected average transmission rate of user k in this time slot is Then the state vector s of all users t =R t , where R t is the expected average transmission rate vector of all users; the input dimension of the action network at the central end is K max , the network has good scalability, and its algorithm performance shows robustness under different numbers of interactive users. <K max When the state vector s t Pad with zeros to make its dimension K max .
[0107] In another possible implementation of the expected average transmission rate, the expected average transmission rate satisfies:
[0108] Among them, R k is the expected average transmission rate of one terminal k in the at least one terminal, q k,n is the total amount of data to be transmitted in the nth mode in the data to be transmitted of the terminal k in the first data to be transmitted, τ k,n The remaining transmission time for the terminal k to transmit the data to be transmitted in the nth mode, where n is a positive integer less than or equal to N.
[0109] For example, in the tth time slot, the amount of video frames remaining to be transmitted by user k is q k,t , the remaining transmission delay of the video frame is τ k,t The same is true for tactile frames, which will not be described here. The expected average transmission rate of user k in this time slot is n is the modality index, then the state vector s of all users t =R t , where R t is the expected average transmission rate vector of all users; the input dimension of the action network at the central end is K max , the network is scalable and its algorithm performance is robust under different numbers of interactive users. <K max When the state vector s t Pad with zeros to make its dimension K max .
[0110] In a possible implementation of the first factor, the first factor corresponds to the first state information, and the DRL network determines the first factor according to the first state information.t Input into the action network π(θ) of the DRL network, and output the action a of the tth time slot t , which is the factor C that controls the range of user priority weights.
[0111] In a possible implementation of the priority weight, the priority weight corresponds to the first factor, including: the base station determines the priority weight according to the first factor and the expected average transmission rate. The priority weight satisfies:
[0112] Among them, α k is the priority weight of one terminal k in the at least one terminal, C is the first factor of the terminal k, R k is the expected average transmission rate of the terminal k, R max is the maximum value of the above-mentioned expected average transmission rates of the above-mentioned at least one terminal.
[0113] For example, if the first factor is C, the priority weight of user k in the tth time slot satisfies:
[0114] Among them, α k,t is the priority weight of one terminal k in the at least one terminal in the tth time slot, C is the first factor of the terminal k, R k,t is the expected average transmission rate of the terminal k in the tth time slot, R t,max is the maximum value of the above-mentioned expected average transmission rates of the above-mentioned at least one terminal in the tth time slot.
[0115] Under the conditions of weight and power constraints, the multi-user precoding matrix is obtained by solving the WMMSE algorithm where N t The number of antennas at the transmitting end and the number of antennas at the receiving end is N r , d is the number of signal streams. The main process of the WMMSE algorithm is:
[0116] Initialize V k ,make sure P T Send power to the central end, and then repeat the following steps:
[0117] Update U k ,
[0118] Update W k ,
[0119] Update V k ,
[0120] If the objective function If the increment compared to the previous iteration is less than a given threshold, the loop ends; otherwise, the update continues.
[0121] Among them U k and W k is the intermediate variable introduced. Among them, V k represents the issuance right, K represents the number of users, P T Indicates total power, U k Indicates the right to withdraw, W k represents the receiving weight matrix, E k represents mean square error (MSE), α k Indicates the priority weight of each user.
[0122] The precoding matrix is used to precode first data to be transmitted from at least one terminal. After precoding is complete, the base station outputs first data, which is the precoded data of the first data to be transmitted from the at least one terminal. Accordingly, the terminal receives second data, which includes the first data. This enables real-time interaction between the base station and at least one terminal.
[0123] In a possible implementation of method 700, the method further includes: the base station obtaining a first ratio, the first ratio corresponding to the first data, the first ratio being a ratio of the amount of correctly received data in the first data to the amount of the first data. Accordingly, the terminal transmits the first ratio.
[0124] In a possible implementation of the first ratio, one of the first ratios satisfies: ξ k,t =U k,t / M k,t , where ξ k,t is the above ratio of one terminal k in the tth time slot of the at least one terminal, M k,t is the total amount of transmission data received by the terminal k before the t-th time slot, U k,t is the transmission utility function of the second data of the terminal k in the t-th time slot.
[0125] For example, the second data is data containing multiple video frames to be transmitted, and the ratio of the terminal k in the t-th time slot is satisfy: in is the total amount of data of the transmitted video frames received by the terminal k before the t-th time slot, is the transmission utility function of the multiple video frames to be transmitted by the terminal k in the t-th time slot.
[0126] In one possible implementation of the transmission utility function, based on a transmission integrity requirement, which can also be understood as requiring that the first data to be transmitted be completely transmitted within a specified time delay, the transmission utility function of the second data for one terminal k of the at least one terminal in the t-th time slot is defined as:
[0127] Where T1 is the set time slot length, the starting time of the above time slot length is the t0th time slot, the end time slot is the tth time slot, W is the system bandwidth, Q k,t is the total amount of the second data, c k,i is the data transmission rate at which the terminal k receives the second data in the i-th time slot.
[0128] For example, the second data is data including multiple video frames to be transmitted, and the transmission utility function of the second data of the terminal k in the t-th time slot is:
[0129] Wherein, T1 is the set time slot length, the starting time of the above time slot length is the t0th time slot, the end time slot is the tth time slot, W is the system bandwidth, is the total amount of data of the above-mentioned multiple video frames to be transmitted, c k,i A data transmission rate at which the terminal k receives the plurality of video frames to be transmitted in the i-th time slot.
[0130] In another possible implementation of the first ratio, one of the ratios in the group of ratios in the first ratio satisfies: ξ k,t,n =U k,t,n / M k,t,n , where ξ k,t,n is the ratio of the nth modal data in the second data received by one of the at least one terminals k in the tth time slot, M k,t,n is the total amount of the nth modal data in the transmission data received by the terminal k before the tth time slot, U k,t,n is the transmission utility function of the nth modal data in the second data of the terminal k in the tth time slot, where n is an integer greater than 1 and less than or equal to N, and N is the modal number of the second data.
[0131] For example, the second data is data including a plurality of video frames to be transmitted and a plurality of tactile frames to be transmitted, the modal number N of the second data is 2, and the terminal k receives the ratio of the plurality of video frames to be transmitted in the t-th time slot. (i.e. ξ k,t,1 )satisfy: in is the total amount of data of the transmitted video frames received by the terminal k before the t-th time slot, is the transmission utility function of the plurality of video frames to be transmitted by the terminal k in the t-th time slot; the ratio of the plurality of tactile frames to be transmitted received by the terminal k in the t-th time slot (i.e. ξ k,t,2 )satisfy: in is the total amount of data of the transmission tactile frame received by the terminal k before the t-th time slot, is the transmission utility function of the multiple tactile frames to be transmitted by the terminal k in the t-th time slot.
[0132] In another possible implementation of the transmission utility function, based on a transmission integrity requirement, which can also be understood as requiring that the first data to be transmitted be completely transmitted within a specified time delay, the transmission utility function of the nth modal data in the second data of one terminal k among the at least one terminal in the tth time slot is defined as:
[0133] Where T1 is the set time slot length, the starting time of the above time slot length is the t0th time slot, the end time slot is the tth time slot, W is the system bandwidth, Q k,t,n is the total value of the nth modal data in the second data, c k,i,n The data transmission rate of the nth modal data in the second data received by the terminal k in the i-th time slot.
[0134] For example, the second data is data including multiple video frames to be transmitted and multiple tactile frames to be transmitted, the modal number N of the second data is 2, and the transmission utility function of the multiple video frames to be transmitted by the terminal k in the t-th time slot is (i.e. U k,t,1 )for:
[0135] Wherein, T1 is the set time slot length, the starting time of the above time slot length is the t0th time slot, the end time slot is the tth time slot, W is the system bandwidth, is the total amount of data of the above-mentioned multiple video frames to be transmitted, ck,i,1 A data transmission rate at which the terminal k receives the plurality of video frames to be transmitted in the i-th time slot.
[0136] The transmission utility function of the plurality of tactile frames to be transmitted by the terminal k in the t-th time slot is: (i.e. U k,t,2 )for:
[0137] Wherein, T1 is the set time slot length, the starting time of the above time slot length is the t0th time slot, the end time slot is the tth time slot, W is the system bandwidth, is the total amount of data of the above multiple tactile frames to be transmitted, c k,i,2 The data transmission rate at which the terminal k receives the multiple tactile frames to be transmitted in the i-th time slot.
[0138] In a possible implementation manner of a data transmission rate at which one terminal k of the at least one terminal receives the second data in the t-th time slot, the data transmission rate satisfies:
[0139] Where W is the system bandwidth, I is the unit matrix, and H k is the channel matrix of one terminal k in the at least one terminal, V k is the precoding matrix of the terminal k, V m is the precoding matrix of one of the terminals other than the terminal k in the at least one terminal, m≠k, P T is the base station’s transmit power, is the noise variance of the terminal k, det(.) represents the determinant, (.) H represents the conjugate transpose, Tr(.) represents the sum of the diagonal elements, (.) -1 Indicates inversion.
[0140] For example, the second data is data including a plurality of video frames to be transmitted, and a data transmission rate at which a terminal k among the at least one terminal receives the second data in the t-th time slot satisfies:
[0141] Where W is the system bandwidth, I is the unit matrix, and H k,t is the channel matrix of the terminal k in the t-th time slot, V k,t is the precoding matrix of the terminal k in the t-th time slot, V m,t is the precoding matrix of one of the at least one terminal except the terminal k in the t-th time slot, m≠k, P Tis the base station’s transmit power, is the noise variance of the terminal k in the t-th time slot, det(.) represents the determinant, (.) H represents the conjugate transpose, Tr(.) represents the sum of the diagonal elements, (.) -1 Indicates inversion.
[0142] For another example, the second data includes multiple video frames to be transmitted and multiple tactile frames to be transmitted, and a data transmission rate at which a terminal k among the at least one terminal receives the second data in the tth time slot satisfies:
[0143] Where W is the system bandwidth, I is the unit matrix, and H k,t is the channel matrix of the terminal k in the t-th time slot, V k,t is the precoding matrix of the terminal k in the t-th time slot, V m,t is the precoding matrix of one of the at least one terminal except the terminal k in the t-th time slot, m≠k, P T is the base station’s transmit power, is the noise variance of the terminal k in the t-th time slot, det(.) represents the determinant, (.) H represents the conjugate transpose, Tr(.) represents the sum of the diagonal elements, (.) -1 Indicates inversion. Since the tactile frame has a higher priority, the above c k,t The data transmission rate is tactile frame, and the total data size of the multiple tactile frames to be transmitted in the t-th time slot is If the terminal k has The total amount of data at this moment is Bytes, where p haptic is the data size of each tactile signal, p head The remaining rate is reserved for the transmission of the above-mentioned multiple video frames to be transmitted. (i.e. the above c k,t,2 ).
[0144] The first ratio and the second status information are used to update the DRL network. The second status information corresponds to second data to be transmitted of the at least one terminal. The second data to be transmitted is the next data to be transmitted after the first data to be transmitted. The first data to be transmitted is data to be transmitted in the first time slot, and the second data to be transmitted is data to be transmitted in the second time slot. The first and second time slots are continuous in the time domain, and the second time slot is located after the first time slot.
[0145] In a possible implementation method for updating the above-mentioned DRL network, the base station re-acquires the status of the user's data frame to be transmitted, and calculates the reward value through the first ratio feedback from the user, and updates the action network and value network of the above-mentioned DRL network based on the collected experience (current state, action, next moment state, reward).
[0146] For example, the second data includes multiple video frames to be transmitted. Based on the first ratio, the following system long-term utility maximization problem can be modeled:
[0147] in The multi-user precoding process in a single-mode interaction scenario is modeled as a Markov decision process, and the above problem is solved with the help of a reinforcement learning algorithm. Based on the first ratio of user feedback, the reward value in the current transmission state is calculated as:
[0148] renew s t+1 =R t+1 , collect the experience of time slot t t ,a t ,s t+1 ,r t The experience is stored in a replay pool. When the experience stored in the replay pool exceeds the batch size B, the action network π(θ) and the value networks Q(φ1) and Q(φ2) are updated. The value networks Q(φ1) and Q(φ2) take the state and action as input and output a predicted value for each action. The value prediction is performed by selecting the lower output of the two networks to address overestimation of Q values. The replay pool stores experience on a first-in, first-out basis, and the size of the replay pool is set before training.
[0149] For another example, the second data includes multiple video frames to be transmitted and multiple tactile frames to be transmitted. Based on the first ratio, the following system long-term utility maximization problem can be modeled:
[0150] in The multi-user precoding process in a multimodal interaction scenario is modeled as a Markov decision process, and the above problem is solved with the help of a reinforcement learning algorithm. Based on the first ratio of user feedback, the reward value in the current transmission state is calculated as:
[0151] renew s t+1 =R t+1 , collect the experience of time slot t t ,a t ,s t+1 ,r t The experience is stored in a replay pool. When the experience stored in the replay pool exceeds the batch size B, the action network π(θ) and the value networks Q(φ1) and Q(φ2) are updated. The value networks Q(φ1) and Q(φ2) take the state and action as input and output a predicted value for each action. The value prediction is performed by selecting the lower output of the two networks to address overestimation of Q values. The replay pool stores experience on a first-in, first-out basis, and the size of the replay pool is set before training.
[0152] In this embodiment, the network update of the intelligent precoding algorithm follows the process of the Soft Actor-Critic (SAC) algorithm. By introducing the entropy maximization mechanism in the objective function, the intelligent agent can explore the state space more fully and avoid falling into the local optimum too early.
[0153] Update the DRL network. The convergence condition of the above DRL network is that the change in the above reward value is less than a certain threshold.
[0154] After the above-mentioned DRL network training is completed, the base station can directly use the above-mentioned trained DRL network to predict the priority weight of the above-mentioned at least one terminal based on the first status information of the first data to be transmitted of at least one terminal, combine the prediction results, output the precoding matrix, and complete the precoding of the first data to be transmitted.
[0155] The intelligent precoding method for broadband real-time interactive scenarios proposed in this application uses a precoding scheme with reinforcement learning adaptive control to obtain the global optimal solution under multiple time slots, solving the problem that the optimal solution of a single time slot cannot meet the dynamically changing transmission needs of users. In addition, it also solves the problems of existing intelligent wireless communication algorithms, such as large network architecture, poor generalization, and difficulty in application to actual communication scenarios. This solution realizes the use of a small-scale network architecture to efficiently complete the accurate prediction of the system's global precoding scheme. It achieves an improvement in the received frame rate and the number of users satisfied in real-time interactive scenarios.
[0156] Corresponding to the method provided in the above method embodiment, the present application embodiment also provides a corresponding device, including a module for executing the corresponding module of the above embodiment. The module can be software, hardware, or a combination of software and hardware.
[0157] Figure 8 provides a schematic structural diagram of a terminal. The terminal can be applied to the scenarios shown in Figures 1, 2, 3, 4 or 5. The terminal or components in the terminal can execute the aforementioned method 700 and various possible implementation methods. For ease of explanation, Figure 8 only shows the main components of the terminal. As shown in Figure 8, the terminal 800 includes a processor, a memory, a control circuit, an antenna, and input and output devices. The processor is mainly used to process communication protocols and communication data, as well as to control the entire terminal, execute software programs, and process data of software programs. The memory is mainly used to store software programs and data. The radio frequency circuit is mainly used to convert baseband signals into radio frequency signals and process radio frequency signals. The antenna is mainly used to transmit and receive radio frequency signals in the form of electromagnetic waves. Input and output devices, such as a touch screen, a display screen, a keyboard, etc., are mainly used to receive data input by the user and output data to the user.
[0158] When the terminal is powered on, the processor reads the software program from the storage unit, parses and executes the instructions of the software program, and processes the data of the software program. When data needs to be sent wirelessly, the processor performs baseband processing on the data to be sent and outputs the baseband signal to the RF circuit. The RF circuit processes the baseband signal to obtain an RF signal and transmits the RF signal to the outside in the form of electromagnetic waves via the antenna. When data is sent to the terminal, the RF circuit receives the RF signal via the antenna, which is further converted into a baseband signal and output to the processor. The processor converts the baseband signal into data and processes the data.
[0159] For ease of explanation, FIG8 shows only one memory and processor. In an actual terminal, there may be multiple processors and memories. The memory may also be referred to as a storage medium or storage device, etc., which is not limited in the present embodiment.
[0160] As an optional implementation, the processor may include a baseband processor and a central processing unit (CPU). The baseband processor is primarily responsible for processing communication protocols and communication data, while the CPU is primarily responsible for controlling the entire terminal device, executing software programs, and processing data from software programs. The processor in Figure 8 integrates the functions of both the baseband processor and the CPU. Those skilled in the art will appreciate that the baseband processor and the CPU may also be independent processors interconnected via a bus or other technology. Those skilled in the art will appreciate that a terminal may include multiple baseband processors to accommodate different network standards, multiple CPUs to enhance its processing capabilities, and that the various components of the terminal may be connected via various buses. The baseband processor may also be referred to as a baseband processing circuit or a baseband processing chip. The CPU may also be referred to as a central processing circuit or a central processing chip. The functionality for processing communication protocols and communication data may be built into the processor or stored as a software program in a storage unit, with the processor executing the software program to implement the baseband processing functionality.
[0161] In one example, the antenna and control circuitry with transceiver functions can be considered the transceiver unit 811 of terminal 800, and the processor with processing functions can be considered the processing unit 812 of terminal 800. As shown in Figure 8, terminal 800 includes a transceiver unit 811 and a processing unit 812. A transceiver unit may also be referred to as a transceiver, transceiver, or transceiver device. Optionally, the device in transceiver unit 811 that implements the receiving function may be considered a receiving unit, and the device in transceiver unit 811 that implements the transmitting function may be considered a transmitting unit, i.e., transceiver unit 811 includes a receiving unit and a transmitting unit. For example, the receiving unit may also be referred to as a receiver, a receiver, a receiving circuit, etc., and the transmitting unit may be referred to as a transmitter, a transmitter, or a transmitting circuit, etc. Optionally, the receiving unit and the transmitting unit may be a single integrated unit or multiple independent units. The receiving unit and the transmitting unit may be located in a single geographic location or dispersed across multiple geographic locations. As shown in Figure 9, another embodiment of the present application provides an apparatus 900. The apparatus may be a terminal or a component of a terminal (e.g., an integrated circuit, a chip, etc.). Alternatively, the apparatus may be a radio access network device, or a component of the radio access network device (e.g., an integrated circuit, a chip, etc.), or a logical node, a logical module, or software that implements all or part of the functions of the radio access network device. The apparatus may also be another communication module. For example, the apparatus 900 may implement the functions of the radio access network device in the method 700 and various possible implementations, or the apparatus 900 may implement the functions of the terminal in the method 700 and various possible implementations. The apparatus 900 may include: an interface module 901 (or referred to as an interface unit) and a processing module 902 (or referred to as a processing unit), and may further include a storage module 903 (or referred to as a storage unit).
[0162] In one possible design, one or more modules shown in FIG9 may be implemented by one or more processors, or by one or more processors and memories, or by one or more processors and transceivers, or by one or more processors, memories, and transceivers, although this is not limited in the present embodiment. The processors, memories, and transceivers may be provided separately or integrated.
[0163] The device has the function of implementing the terminal described in the embodiment of the present application. For example, the device includes a module or unit or means corresponding to the steps involved in the terminal described in the embodiment of the present application. The function or unit or means can be implemented by software, or by hardware, or by hardware executing the corresponding software implementation, or by a combination of software and hardware. For details, please refer to the corresponding description in the aforementioned corresponding method embodiment. Alternatively, the device has the function of implementing the wireless access network device described in the embodiment of the present application. For example, the device includes a module or unit or means corresponding to the steps involved in the wireless access network device described in the embodiment of the present application. The function or unit or means can be implemented by software, or by hardware, or by hardware executing the corresponding software implementation, or by a combination of software and hardware. For details, please refer to the corresponding description in the aforementioned corresponding method embodiment.
[0164] In one possible design, apparatus 900 includes an interface module 901 and a processing module 902. Apparatus 900 may be, for example, a radio access network device, or a component of the radio access network device (e.g., a processor, chip, or chip system), or a logical node, logic module, or software capable of implementing all or part of the functions of the radio access network device. Interface module 901 is configured to obtain a precoding matrix for first data to be transmitted of at least one terminal, wherein the precoding matrix corresponds to a priority weight of the at least one terminal, the priority weight corresponds to a first factor, the first factor corresponds to first status information, and the first status information corresponds to the first data to be transmitted of the at least one terminal. Processing module 902 is configured to complete precoding of the first data to be transmitted of the at least one terminal based on the precoding matrix. Interface module 901 is further configured to output first data, wherein the first data is the data obtained by performing the precoding on the first data to be transmitted of the at least one terminal.
[0165] In a possible implementation manner of the device 900 , the first data to be transmitted is single-mode data to be transmitted.
[0166] In a possible implementation of the device 900, the first data to be transmitted is multimodal data to be transmitted.
[0167] In a possible implementation manner of the apparatus 900, the first status information includes an activation status and an expected average transmission rate of the at least one terminal.
[0168] In a possible implementation of the device 900, the first status information corresponds to the first data to be transmitted of the at least one terminal, including: determining the activation status of the at least one terminal according to an arrival time of the first data to be transmitted.
[0169] In a possible implementation of the device 900, the above-mentioned first status information corresponds to the above-mentioned first data to be transmitted of the above-mentioned at least one terminal, including: determining the above-mentioned expected average transmission rate of the above-mentioned first terminal based on the data volume of the above-mentioned data to be transmitted of the first terminal and the remaining transmission time for the above-mentioned first terminal to transmit the above-mentioned data to be transmitted, the above-mentioned first terminal is one of the above-mentioned at least one terminal, and the above-mentioned first data to be transmitted includes the above-mentioned data to be transmitted.
[0170] In a possible implementation of the apparatus 900, the expected average transmission rate satisfies:
[0171] Among them, R k is the expected average transmission rate of one terminal k in the at least one terminal, q k is the total amount of data to be transmitted from the terminal k in the first data to be transmitted, τ k is the remaining transmission time for the terminal k to transmit the data to be transmitted of the terminal k.
[0172] In a possible implementation of the apparatus 900, the expected average transmission rate satisfies:
[0173] Among them, R k is the expected average transmission rate of one terminal k in the at least one terminal, q k,n is the total amount of data to be transmitted in the nth mode in the data to be transmitted of the terminal k in the first data to be transmitted, τ k,n The remaining transmission time for the terminal k to transmit the data to be transmitted in the nth mode, where n is a positive integer less than or equal to N.
[0174] In a possible implementation of the device 900, there is a corresponding relationship between the first factor and the first state information, including: a deep reinforcement learning (DRL) network determines the first factor according to the first state information.
[0175] In a possible implementation manner of the apparatus 900 , the priority weight corresponds to the first factor, including: determining the priority weight according to the first factor and the expected average transmission rate.
[0176] In a possible implementation of the apparatus 900, the priority weights satisfy:
[0177] Among them, α k is the priority weight of one terminal k in the at least one terminal, C is the first factor of the terminal k, R k is the expected average transmission rate of the terminal k, R max is the maximum value of the above-mentioned expected average transmission rates of the above-mentioned at least one terminal.
[0178] In a possible implementation of the device 900, the interface module 901 is further used to obtain a first ratio, which corresponds to the first data, and the first ratio is the ratio of the amount of correctly received data in the first data to the amount of data in the first data.
[0179] In a possible implementation of the device 900, the first ratio and the second status information are used to update the DRL network, the second status information corresponds to the second data to be transmitted of the at least one terminal, and the second data to be transmitted is the next data to be transmitted after the first data to be transmitted is transmitted.
[0180] In a possible implementation of the device 900, the first data to be transmitted is data to be transmitted in the first time slot, the second data to be transmitted is data to be transmitted in the second time slot, the first time slot and the second time slot are continuous in the time domain, and the second time slot is located after the first time slot.
[0181] In one possible design, apparatus 900 includes an interface module 901 and a processing module 902. Apparatus 900 may be, for example, a terminal, or a component of a terminal (e.g., a processor, chip, or chip system), or a logical node, logic module, or software capable of implementing all or part of the terminal's functions. Interface module 901 is configured to receive second data, wherein first data includes the second data, the first data being precoded for first data to be transmitted of at least one terminal, the precoding corresponding to a precoding matrix, the precoding matrix corresponding to a priority weight of the at least one terminal, the priority weight corresponding to a first factor, the first factor corresponding to first status information, and the first status information corresponding to the first data to be transmitted of the at least one terminal. Processing module 902 is configured to determine a second ratio based on the second data, the second ratio corresponding to the second data, the second ratio being the ratio of the amount of correctly received data in the second data to the amount of the second data. Interface module 901 is further configured to send the second ratio.
[0182] In a possible implementation manner of the device 900 , the first data to be transmitted is single-mode data to be transmitted.
[0183] In a possible implementation of the device 900, the first data to be transmitted is multimodal data to be transmitted.
[0184] In a possible implementation manner of the apparatus 900, the first status information includes an activation status and an expected average transmission rate of the at least one terminal.
[0185] In a possible implementation of the device 900, the first status information corresponds to the first data to be transmitted of the at least one terminal, including: determining the activation status of the at least one terminal according to an arrival time of the first data to be transmitted.
[0186] In a possible implementation of the device 900, the above-mentioned first status information corresponds to the above-mentioned first data to be transmitted of the above-mentioned at least one terminal, including: determining the above-mentioned expected average transmission rate of the above-mentioned first terminal based on the data volume of the above-mentioned data to be transmitted of the first terminal and the remaining transmission time for the above-mentioned first terminal to transmit the above-mentioned data to be transmitted, the above-mentioned first terminal is one of the above-mentioned at least one terminal, and the above-mentioned first data to be transmitted includes the above-mentioned data to be transmitted.
[0187] In a possible implementation of the apparatus 900, the expected average transmission rate satisfies:
[0188] Among them, R k is the expected average transmission rate of one terminal k in the at least one terminal, q k is the total amount of data to be transmitted from the terminal k in the first data to be transmitted, τ k is the remaining transmission time for the terminal k to transmit the data to be transmitted of the terminal k.
[0189] In a possible implementation of the apparatus 900, the expected average transmission rate satisfies:
[0190] Among them, R k is the expected average transmission rate of one terminal k in the at least one terminal, q k,n is the total amount of data to be transmitted in the nth mode in the data to be transmitted of the terminal k in the first data to be transmitted, τ k,n The remaining transmission time for the terminal k to transmit the data to be transmitted in the nth mode, where n is a positive integer less than or equal to N.
[0191] In a possible implementation of the device 900, there is a corresponding relationship between the first factor and the first state information, including: a deep reinforcement learning (DRL) network determines the first factor according to the first state information.
[0192] In a possible implementation of the device 900, the second ratio and the second status information are used to update the DRL network, the second status information corresponds to the second data to be transmitted of the at least one terminal, and the second data to be transmitted is the next data to be transmitted after the first data to be transmitted is transmitted.
[0193] In a possible implementation of the device 900, the first data to be transmitted is data to be transmitted in the first time slot, the second data to be transmitted is data to be transmitted in the second time slot, the first time slot and the second time slot are continuous in the time domain, and the second time slot is located after the first time slot.
[0194] It is understandable that the beneficial effects corresponding to the above-mentioned device 900 and various possible implementations can be referred to the description in the aforementioned method embodiment or invention content, and will not be repeated here.
[0195] Optionally, the apparatus 900 may further include a storage module 903 for storing data or instructions (also referred to as code or program). The other modules may interact or couple with the storage module to implement the corresponding methods or functions. For example, the processing module 902 may read the data or instructions in the storage module 903 so that the apparatus 900 implements the method in the above embodiment.
[0196] In one example, the module in the above-mentioned device can be one or more integrated circuits configured to implement the above method, such as: one or more application specific integrated circuits (ASICs), or one or more digital singnal processors (DSPs), or one or more field programmable gate arrays (FPGAs), or a combination of at least two of these integrated circuit forms. For another example, when the module in the device can be implemented in the form of a processing element scheduler, the processing element can be a general-purpose processor, such as a central processing unit (CPU) or other processor that can call a program. For another example, these units can be integrated together and implemented in the form of a system-on-a-chip (SOC).
[0197] Referring to Figure 10, a schematic diagram of a device provided in an embodiment of the present application can be used to implement the above-mentioned method 700 and various possible implementation methods. As shown in Figure 10, the device includes: a processor 1010 and an interface 1030, and the processor 1010 is coupled to the interface 1030. The interface 1030 is used to communicate with other modules or devices. The interface 1030 can be a transceiver or an input / output interface. The interface 1030 can be, for example, an interface circuit. Optionally, the device also includes a memory 1020 for storing instructions executed by the processor 1010 or storing input data required by the processor 1010 to execute instructions or storing data generated after the processor 1010 executes instructions.
[0198] The above method 700 and various possible implementations can be implemented by the processor 1010 calling a program or instruction stored in the memory 1020. The memory 1020 can be inside the device or outside the device, which is not limited in this application.
[0199] Optionally, the functions / implementation processes of the interface module 901 and the processing module 902 in FIG9 can be implemented by the processor 1010 in the apparatus shown in FIG10. Alternatively, the functions / implementation processes of the processing module 902 in FIG9 can be implemented by the processor 1010 in the apparatus shown in FIG10, and the functions / implementation processes of the interface module 901 in FIG9 can be implemented by the interface 1030 in the apparatus shown in FIG10. Exemplarily, the functions / implementation processes of the interface module 901 can be implemented by the processor calling program instructions in the memory to drive the interface 1030.
[0200] When the above-mentioned device is a chip applied to a terminal, the chip of the terminal implements the functions of the terminal in the above-mentioned method embodiment. The chip receives information from other modules in the terminal (such as a radio frequency module or antenna), and the information is from other terminals or wireless access network devices; or the chip sends information to other modules in the terminal (such as a radio frequency module or antenna), and the information is sent by the terminal to other terminals or wireless access network devices.
[0201] When the above-mentioned device is a chip applied to a wireless access network device, the chip implements the functions of the wireless access network device in the above-mentioned method embodiments. The chip receives information from other modules (such as a radio frequency module or antenna) in the wireless access network device, where the information comes from other wireless access network devices or terminals; or the chip sends information to other modules (such as a radio frequency module or antenna) in the wireless access network device, where the information comes from the wireless access network device to other wireless access network devices or terminals.
[0202] Those skilled in the art will understand that the various numerical numbers such as the first and second involved in this application are only for the convenience of description and are not used to limit the scope of the embodiments of the present application, and also indicate the order of precedence. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the objects associated before and after are in an "or" relationship. "At least one" refers to one or more. At least two refers to two or more. "At least one", "any one" or similar expressions refer to any combination of these items, including any combination of single items (individuals) or plural items (individuals). For example, at least one item (individual, kind) of a, b, or c can represent: a, b, c, ab, ac, bc or abc, where a, b, c can be single or multiple. "Multiple" refers to two or more, and other quantifiers are similar.
[0203] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.
[0204] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When software is used for implementation, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from a website, computer, server or data center to another website, computer, server or data center via a wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) method. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integrations. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state drive (SSD)).
[0205] The steps of the method described in the embodiments of the present application can be directly embedded in hardware, a software unit executed by a processor, or a combination of the two. The software unit can be stored in a random access memory (RAM), a flash memory, a read-only memory (ROM), a register, a hard disk, a removable disk, or other storage media in any form in the art. Exemplarily, the storage medium can be connected to the processor so that the processor can read information from the storage medium and can write information to the storage medium. Alternatively, the storage medium can also be integrated into the processor. The processor and the storage medium can be arranged in an ASIC.
[0206] The present application also provides a computer-readable medium having a computer program stored thereon, which implements the functions of any of the above method embodiments when executed by a computer.
[0207] The present application also provides a computer program product that implements the functions of any of the above-mentioned method embodiments when executed by a computer. The same or similar parts between the various embodiments in this application can refer to each other. In the various embodiments in this application, and the various implementation methods / implementation methods / implementation methods in each embodiment, if there is no special explanation and logical conflict, the terms and / or descriptions between different embodiments and the various implementation methods / implementation methods / implementation methods in each embodiment are consistent and can be referenced to each other. The technical features in different embodiments and the various implementation methods / implementation methods / implementation methods in each embodiment can be combined to form new embodiments, implementation methods, implementation methods, or implementation methods according to their inherent logical relationships. The above-described implementation methods of the present application do not constitute a limitation on the scope of protection of this application.
[0208] The above is only a specific implementation method of the present application, but the scope of protection of the present application is not limited thereto. Any technician familiar with this technical field can easily think of changes or replacements within the technical scope disclosed in this application, which should be covered by the scope of protection of the present application.
Claims
1. A communication method, characterized in that: include: Obtain a precoding matrix of first data to be transmitted of at least one terminal, where the precoding matrix corresponds to a priority weight of the at least one terminal, the priority weight corresponds to a first factor, the first factor corresponds to first state information, and the first state information corresponds to the first data to be transmitted of the at least one terminal; Complete precoding of the first to-be-transmitted data of the at least one terminal according to the precoding matrix; Output first data, where the first data is data obtained by performing the precoding on the first data to be transmitted of the at least one terminal.
2. The method according to claim 1, characterized in that The first data to be transmitted is single-mode data to be transmitted.
3. The method according to claim 1, characterized in that The first data to be transmitted is multimodal data to be transmitted.
4. The method according to any one of claims 1 to 3, characterized in that The first state information includes an activation state and an expected average transmission rate of the at least one terminal.
5. The method according to any one of claims 1 to 4, characterized in that The first state information corresponds to the first data to be transmitted of the at least one terminal, including: The activation state of the at least one terminal is determined according to the arrival time of the first data to be transmitted.
6. The method according to claim 1, 2, 4 or 5, characterized in that: The first state information corresponds to the first data to be transmitted of the at least one terminal, including: The expected average transmission rate of the first terminal is determined according to the amount of data to be transmitted of the first terminal and the remaining transmission time for the first terminal to transmit the data to be transmitted, the first terminal is one of the at least one terminals, and the first data to be transmitted includes the data to be transmitted.
7. The method according to claim 2 or 4-6, characterized in that: The expected average transmission rate satisfies: Among them, R k is the expected average transmission rate of a terminal k in the at least one terminal, q k is the total amount of data to be transmitted of the terminal k in the first data to be transmitted, τ k The remaining transmission time for the terminal k to transmit the data to be transmitted by the terminal k.
8. The method according to claim 3 or 4-6, characterized in that: The expected average transmission rate satisfies: Among them, R k is the expected average transmission rate of a terminal k in the at least one terminal, q k,n is the total amount of data to be transmitted in the nth mode in the data to be transmitted of the terminal k in the first data to be transmitted, τ k,n The remaining transmission time for the terminal k to transmit the data to be transmitted in the nth mode, where n is a positive integer less than or equal to N.
9. The method according to any one of claims 1 to 8, characterized in that The first factor and the first state information have a corresponding relationship, including: The deep reinforcement learning (DRL) network determines the first factor according to the first state information.
10. The method according to any one of claims 2 to 9, characterized in that: The priority weight corresponds to the first factor and includes: The priority weight is determined according to the first factor and the expected average transmission rate.
11. The method according to any one of claims 2 to 10, characterized in that: The priority weights satisfy: Among them, α k is the priority weight of a terminal k among the at least one terminal, C is the first factor of the terminal k, R k is the expected average transmission rate of the terminal k, R max is the maximum value of the expected average transmission rates of the at least one terminal.
12. The method according to claim 1, characterized in that The method further comprises: A first ratio is obtained, where the first ratio corresponds to the first data, and the first ratio is a ratio of the amount of correctly received data in the first data to the amount of the first data.
13. The method according to claim 9 or 12, characterized in that: The first ratio and the second state information are used to update the DRL network, the second state information corresponds to second data to be transmitted of the at least one terminal, and the second data to be transmitted is the next data to be transmitted after the first data to be transmitted is transmitted.
14. The method according to claim 13, characterized in that The first data to be transmitted is data to be transmitted in a first time slot, the second data to be transmitted is data to be transmitted in a second time slot, the first time slot and the second time slot are continuous in the time domain, and the second time slot is located after the first time slot.
15. A communication method, characterized in that: include: receiving second data, where the first data includes the second data, the first data is data after first data to be transmitted of at least one terminal is precoded, the precoding corresponds to a precoding matrix, the precoding matrix and a priority weight of the at least one terminal are in a corresponding relationship, the priority weight corresponds to a first factor, the first factor and first state information are in a corresponding relationship, and the first state information corresponds to the first data to be transmitted of the at least one terminal; Determine a second ratio according to the second data, where the second ratio corresponds to the second data, and the second ratio is a ratio of the amount of correctly received data in the second data to the amount of the second data; The second ratio is transmitted.
16. The method according to claim 15, characterized in that The first data to be transmitted is single-mode data to be transmitted.
17. The method according to claim 15, characterized in that The first data to be transmitted is multimodal data to be transmitted.
18. The method according to any one of claims 15 to 17, characterized in that: The first state information includes an activation state and an expected average transmission rate of the at least one terminal.
19. The method according to any one of claims 15 to 18, characterized in that The first state information corresponds to the first data to be transmitted of the at least one terminal, including: The activation state of the at least one terminal is determined according to the arrival time of the first data to be transmitted.
20. The method according to claim 15, 16, 18 or 19, characterized in that The first state information corresponds to the first data to be transmitted of the at least one terminal, including: The expected average transmission rate of the first terminal is determined according to the amount of data to be transmitted of the first terminal and the remaining transmission time for the first terminal to transmit the data to be transmitted, the first terminal is one of the at least one terminals, and the first data to be transmitted includes the data to be transmitted.
21. The method according to claim 16 or 18-20, characterized in that The expected average transmission rate satisfies: Among them, R k is the expected average transmission rate of a terminal k in the at least one terminal, q k is the total amount of data to be transmitted of the terminal k in the first data to be transmitted, τ k The remaining transmission time for the terminal k to transmit the data to be transmitted by the terminal k.
22. The method according to any one of claims 17 or 18 to 20, characterized in that: The expected average transmission rate satisfies: Among them, R k is the expected average transmission rate of a terminal k in the at least one terminal, q k,n is the total amount of data to be transmitted in the nth mode in the data to be transmitted of the terminal k in the first data to be transmitted, τ k,n The remaining transmission time for the terminal k to transmit the data to be transmitted in the nth mode, where n is a positive integer less than or equal to N.
23. The method according to any one of claims 15 to 22, characterized in that The first factor and the first state information have a corresponding relationship, including: The deep reinforcement learning (DRL) network determines the first factor according to the first state information.
24. The method according to claim 15 or 23, characterized in that The second ratio and the second state information are used to update the DRL network, the second state information corresponds to the second data to be transmitted of the at least one terminal, and the second data to be transmitted is the next data to be transmitted after the first data to be transmitted is transmitted.
25. The method according to claim 24, characterized in that The first data to be transmitted is data to be transmitted in a first time slot, the second data to be transmitted is data to be transmitted in a second time slot, the first time slot and the second time slot are continuous in the time domain, and the second time slot is located after the first time slot.
26. A communication device, characterized in that: include: A processor, wherein the processor is coupled to a memory, wherein the memory is used to store programs or instructions, and when the programs or instructions are executed by the processor, the device executes the method according to any one of claims 1 to 14.
27. A communication device, characterized in that: include: A processor, wherein the processor is coupled to a memory, wherein the memory is used to store programs or instructions, and when the programs or instructions are executed by the processor, the device executes the method according to any one of claims 15 to 25.
28. A computer-readable storage medium having instructions stored thereon, characterized in that: When the instructions are executed, the computer executes the method according to any one of claims 1 to 14, or the method according to any one of claims 15 to 25.
29. A computer program product, characterized in that The method comprises a computer program code, and when the computer program code is executed, the method according to any one of claims 1 to 14 is implemented, or the method according to any one of claims 15 to 25 is implemented.
Citation Information
Patent Citations
Method, device and system for determining precoding matrix
CN112803975A
Transmitting and receiving method and device based on orbital angular momentum
CN114205005A
Multi-mode precoding matrix information report for orbital angular momentum based communication system
WO2022184161A1
Data-driven WTRU-specific MIMO pre-coder codebook design
WO2023059881A1
