Wireless communication method, network element, and device

Abstract

An embodiment of the present application provides a wireless communication method, a network element, and a device. The method is applicable to a session management network element, and the method includes: determining QoS parameters of a QoS flow of a first node in a first node group, where the QoS parameters of the QoS flow of the first node are determined according to the QoS parameters of the first node group. Based on the above technical solution, by introducing the first node group and the QoS parameters of the first node group, the session management network element can determine the QoS parameters of the QoS flow of the first node in the first node group. Furthermore, on the basis of enabling flexible cross-node resource scheduling within the first node group, the overall transmission quality of the first node group can be ensured.

Description

Technical Field

[0001] Embodiments of the present application relate to the field of communications, and more particularly, to wireless communication methods, network elements, and devices. Background Art

[0002] Up to now, a Quality of Service (QoS) flow is for a single User Equipment (UE), that is, a network device can allocate resources for each UE to ensure its transmission quality. However, for a communication scenario of a group of nodes, the network device needs to ensure the transmission quality of the entire group of multiple nodes simultaneously, rather than just the transmission quality of a single node.

[0003] Therefore, how to ensure the transmission quality of the entire group of multiple nodes simultaneously is a technical problem urgently to be solved in this field. Summary of the Invention

[0004] Embodiments of the present application provide a wireless communication method, a network element, and a device, which can achieve flexible cross-node resource scheduling, and thus can ensure the transmission quality of the entire group of multiple nodes simultaneously.

[0005] In a first aspect, a wireless communication method is provided. The method is applicable to a session management network element, and the method includes:

[0006] Determine QoS parameters of a QoS flow of a first node in a first node group, where the QoS parameters of the QoS flow of the first node are determined according to the QoS parameters of the first node group.

[0007] In a second aspect, a wireless communication method is provided. The method is applicable to a policy control network element, and the method includes:

[0008] Determine QoS parameters of a service flow of a first node in the first node group according to the QoS parameters of the first node group;

[0009] Send the QoS parameters of the service flow of the first node to the session management network element.

[0010] In a third aspect, a wireless communication method is provided. The method is applicable to an access and mobility management network element, and the method includes:

[0011] Receive second indication information; the second indication information is used to instruct the access and mobility management network element to select the same session management network element for the first node as that for other nodes; or the second indication information is used to instruct the mobility management network element to select a session management network element for the first node, where the session management network element of the first node is the same as or different from that of the other nodes; the other nodes include nodes other than the first node in the first node group.

[0012] In a fourth aspect, a wireless communication method is provided. The method is applicable to an access network device, and the method includes:

[0013] Obtain the capability information of each node in the first node group, where the capability information is used to indicate the data processing capability of the node, and the first node group includes nodes for the same task;

[0014] When the QoS parameters of the first node group are fixed, determine the QoS parameters of the QoS flow of each node in the first node group based on the capability information; and / or trigger a session modification process based on the capability information to modify the QoS parameters of the QoS flow of each node in the first node group.

[0015] In a fifth aspect, a session management network element is provided for performing the method in the first aspect or its various implementation manners. Specifically, the session management network element includes a functional module for performing the method in the first aspect or its various implementation manners.

[0016] In a sixth aspect, a policy control network element is provided for performing the method in the second aspect or its various implementation manners. Specifically, the policy control network element includes a functional module for performing the method in the second aspect or its various implementation manners.

[0017] In a seventh aspect, an access and mobility management network element is provided for performing the method in the third aspect or its various implementation manners. Specifically, the access and mobility management network element includes a functional module for performing the method in the third aspect or its various implementation manners.

[0018] In an eighth aspect, an access network device is provided for performing the method in the fourth aspect or its various implementation manners. Specifically, the access network device includes a functional module for performing the method in the fourth aspect or its various implementation manners.

[0019] In a ninth aspect, a communication device is provided, including a processor and a memory. The memory is used to store a computer program, and the processor is used to call and run the computer program stored in the memory to perform the method in any one of the first aspect to the fourth aspect or its various implementation manners.

[0020] In a tenth aspect, a chip is provided for implementing the method in any one of the first to fourth aspects or their respective implementation manners. Specifically, the chip includes: a processor configured to call and run a computer program from a memory, so that a device installed with the chip executes the method in any one of the first to fourth aspects or their respective implementation manners.

[0021] In an eleventh aspect, a computer-readable storage medium is provided for storing a computer program, where the computer program causes a computer to execute the method in any one of the first to fourth aspects or their respective implementation manners.

[0022] In a twelfth aspect, a computer program product is provided, including computer program instructions, where the computer program instructions cause a computer to execute the method in any one of the first to fourth aspects or their respective implementation manners.

[0023] In a thirteenth aspect, a computer program is provided, which when running on a computer, causes the computer to execute the method in any one of the first to fourth aspects or their respective implementation manners.

[0024] Based on the above technical solutions, by introducing the first node group and the QoS parameters of the first node group, the session management network element can determine the QoS parameters of the QoS flow of the first node in the first node group. Furthermore, on the basis of enabling flexible cross-node resource scheduling within the first node group, the overall transmission quality of the first node group can be guaranteed. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] Figure 1 and Figure 2 are examples of a communication system provided by an embodiment of the present application.

[0026] Figure 3 is a schematic diagram of the end-to-end QoS control and mapping relationship of the QoS flow in the user plane provided by an embodiment of the present application.

[0027] Figure 4 is a schematic flowchart of a session establishment process provided by an embodiment of the present application.

[0028] Figures 5 to 8 is an example of an application scenario corresponding to the group-GBR / MBR provided by an embodiment of the present application.

[0029] Figures 9 to 16 is a schematic flowchart of a wireless communication method provided by an embodiment of the present application.

[0030] Figure 17It is a schematic block diagram of a session management network element provided by an embodiment of the present application.

[0031] Figure 18 It is a schematic block diagram of a policy control network element provided by an embodiment of the present application.

[0032] Figure 19 It is a schematic block diagram of an access and mobility management network element provided by an embodiment of the present application.

[0033] Figure 20 It is a schematic block diagram of an access network device provided by an embodiment of the present application.

[0034] Figure 21 It is a schematic block diagram of a communication device provided by an embodiment of the present application.

[0035] Figure 22 It is a schematic block diagram of a chip provided by an embodiment of the present application. Detailed implementation manners

[0036] Next, the technical solutions in the embodiments of the present application will be described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are some, but not all, of the embodiments of the present application. For the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.

[0037] Embodiments of the present application can be applied to various communication systems, such as: Global System of Mobile communication (GSM) system, Code Division Multiple Access (CDMA) system, Wideband Code Division Multiple Access (WCDMA) system, General Packet Radio Service (GPRS), Long Term Evolution (LTE) system, Advanced long term evolution (LTE-A) system, New Radio (NR) system, an evolved system of the NR system, LTE-based access to unlicensed spectrum (LTE-U) system, NR-based access to unlicensed spectrum (NR-U) system, Universal Mobile Telecommunication System (UMTS), Wireless Local Area Networks (WLAN), Wireless Fidelity (WiFi), next-generation communication system or other communication systems, etc.

[0038] Generally speaking, traditional communication systems support a limited number of connections and are easy to implement. However, with the development of communication technologies, mobile communication systems will not only support traditional communications, but also support, for example, Device to Device (D2D) communication, Machine to Machine (M2M) communication, Machine Type Communication (MTC), and Vehicle to Vehicle (V2V) communication, etc. Embodiments of the present application can also be applied to these communication systems.

[0039] Embodiments of the present application do not limit the spectrum to be applied. For example, embodiments of the present application can be applied to licensed spectrum or unlicensed spectrum.

[0040] Figure 1 Exemplarily, a schematic diagram of a communication system 100 to which the present application is applied is shown. As Figure 1As shown, the communication system 100 mainly includes a User Equipment (UE) 101, an Access Network (AN) device 102, an Access and Mobility Management Function (AMF) entity 103, a Session Management Function (SMF) entity 104, a User Plane Function (UPF) entity 105, a Policy Control function (PCF) entity 106, a Unified Data Management (UDM) entity 107, a Data Network (DN) 108, an Application Function (AF) entity 109, an Authentication Server Function (AUSF) entity 110, and a Network Slice Selection Function (NSSF) entity 111.

[0041] Specifically, in communication system 100, UE 101 establishes an access stratum connection with AN device 102 through the Uu interface to exchange access stratum messages and perform wireless data transmission. UE 101 establishes a non-access stratum (NAS) connection with AMF entity 103 through the N1 interface to exchange NAS messages. AN device 102 is connected to AMF entity 103 through the N2 interface, and AN device 102 is connected to UPF entity 105 through the N3 interface. Multiple UPF entities 105 are connected through the N9 interface. UPF entity 105 is connected to DN 108 through the N6 interface. At the same time, UPF entity 105 is connected to SMF entity 104 through the N4 interface. SMF entity 104 is connected to PCF entity 106 through the N7 interface, SMF entity 104 is connected to UDM entity 107 through the N10 interface, and SMF entity 104 controls UPF entity 105 through the N4 interface. At the same time, SMF entity 104 is connected to AMF entity 103 through the N11 interface. Multiple AMF entities 103 are connected through the N14 interface. AMF entity 103 is connected to UDM entity 107 through the N8 interface, AMF entity 103 is connected to AUSF entity 110 through the N12 interface, AMF entity 103 is connected to NSSF entity 111 through the N22 interface. At the same time, AMF entity 103 is connected to PCF entity 106 through the N15 interface. PCF entity 106 is connected to AF entity 109 through the N5 interface. AUSF entity 110 is connected to UDM entity 107 through the N13 interface.

[0042] In communication system 100, UDM entity 107 is the subscription database in the core network, storing the subscription data of users in the 5G network. AMF entity 103 is the mobility management function in the core network. SMF entity 104 is the session management function in the core network. In addition to performing mobility management on UE 101, AMF entity 103 is also responsible for forwarding session management-related messages between UE 101 and SMF entity 104. PCF entity 106 is the policy management function in the core network, responsible for formulating policies related to the mobility management, session management, charging, etc. of UE 101. UPF entity 105 is the user plane function in the core network, performing data transmission with the external data network through the N6 interface and data transmission with AN device 102 through the N3 interface. After UE 101 accesses the 5G network through the Uu interface, under the control of SMF entity 104, a protocol data unit (PDU) session data connection between UE 101 and UPF entity 105 is established for data transmission. AMF entity 103 and SMF entity 104 respectively obtain user subscription data from UDM entity 107 through the N8 and N10 interfaces, and obtain policy data from PCF entity 106 through the N15 and N7 interfaces.

[0043] In addition, there is also a Network Exposure Function (NEF) entity in the communication system 100, which is used to interface with a third-party application server and transfer information between the core network node and the third-party application.

[0044] The UE 101 can also be referred to as a user equipment, access terminal, user unit, user station, mobile station, mobile device, remote station, remote terminal, mobile device, user terminal, terminal, wireless communication device, user agent, or user device, etc. The terminal device can be a station (STAION, ST) in a WLAN, a cellular phone, a cordless phone, a Session Initiation Protocol (SIP) phone, a Wireless Local Loop (WLL) station, a Personal Digital Assistant (PDA) device, a handheld device with wireless communication capabilities, a computing device, or other processing devices connected to a wireless modem, a vehicle-mounted device, a wearable device, and a next-generation communication system, such as a terminal device in an NR network or a terminal device in a future evolved Public Land Mobile Network (PLMN) network. By way of example and not limitation, in the embodiments of the present application, the terminal device may also be a wearable device. A wearable device can also be referred to as a wearable intelligent device, which is a general term for devices developed by applying wearable technologies to intelligentize daily wear, such as glasses, gloves, watches, clothing, and shoes. A wearable device is a portable device that is either directly worn on the body or integrated into the user's clothes or accessories. A wearable device is not just a hardware device, but also realizes powerful functions through software support, data interaction, and cloud interaction. Broadly speaking, wearable intelligent devices include those with complete functions and large sizes that can achieve complete or partial functions without relying on a smartphone, such as smart watches or smart glasses, etc., and those that only focus on a certain type of application function and need to cooperate with other devices such as smartphones, such as various smart bracelets and smart jewelry for physical sign monitoring.

[0045] The AN device 102 can be a device for communicating with a mobile device. The AN device 102 can be an access point (AP) in a WLAN, a base transceiver station (BTS) in GSM or CDMA, a Node B (NB) in WCDMA, an evolved Node B (eNB or eNodeB) in LTE, or a relay station or access point, or a vehicle-mounted device, a wearable device, and a base station (gNB) in an NR network, or a network device in a future evolved PLMN network, etc.

[0046] In the embodiments of this application, the AN device 102 provides services for a cell. The UE 101 communicates with the AN device 102 through the transmission resources (e.g., frequency domain resources, or in other words, spectrum resources) used by this cell. This cell can be the cell corresponding to the AN device 102 (such as a base station). This cell can belong to a macro base station or a base station corresponding to a small cell. Here, small cells can include: metro cells, micro cells, picocells, femtocells, etc. These small cells have the characteristics of small coverage range and low transmission power, and are suitable for providing high-rate data transmission services.

[0047] It should be noted that the above communication system 100 is described by taking a 5G communication system as an example. Of course, this application can also be applied to other 3GPP communication systems, such as a 4G communication system, or a future 3GPP communication system. This application is not limited thereto.

[0048] It should be understood that in the embodiments of this application, a device with communication functions in a network / system can be referred to as a communication device.

[0049] It should be understood that the terms "system" and "network" are often used interchangeably in this article. The term "and / or" in this article is merely a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. In addition, the character " / " in this article generally represents an "or" relationship between the front and rear associated objects.

[0050] With the continuous improvement of the performance of cameras and sensors on mobile terminals, more and more terminals can collect valuable training data that is essential for the training of AI / ML models. For many AI / ML tasks, the small sample data collected by mobile terminals is of great significance for training a global model.

[0051] Figure 2 This is an example of the communication system 200 provided by an embodiment of the present application. The communication system 200 may also be referred to as a federated learning architecture.

[0052] As Figure 2 shown, the federated learning server 201 completes the training of the global model by aggregating the local training results reported by each terminal 202. In each training iteration, the terminal 202 can use local training data to perform training on the global model downloaded from the federated learning server 201, and then report the intermediate training results (such as the gradients of the DNN) to the federated learning server 201 through the 5G uplink channel. Then, the federated learning server 201 aggregates the collected gradients and updates the global model. The federated learning server 201 distributes the updated global model to the terminal 202 through the 5G downlink channel, and the terminal 2020 performs the next iteration of training on this updated model.

[0053] The parameters used by the federated learning server 201 or the terminal 200 in the iterative training include, but are not limited to, the batch size, which is used to define the number of samples selected for one training, or the batch size is used to define the number of samples selected for each iteration of training. The value of the batch size affects the optimization degree and speed of the model, and also directly affects the use of the processor memory. Optionally, the smaller the processor memory, the smaller the value of the batch size. Different batch sizes require different transmission delays and transmission rates, which will be described below in conjunction with Table 1.

[0054] Table 1

[0055]

[0056] As shown in Table 1, the larger the batch size, the longer the processor processing time and the necessary delay, and the smaller the required data rate. Specifically, in one iteration process, the transmission rate of the model data sent by the federated learning server 201 is 6.5 - 20.3 Gbps. Similarly, the transmission rate of the training results uploaded by a group of terminals 202 to the federated learning server 201 is 6.5 - 20.3 Gbps. High-quality communication is required between a group of terminals 202 and the network to ensure data exchange, so as to ensure the diversity of the data set and the generalization of the model, rather than only ensuring the transmission quality of one or several terminals 202.

[0057] Data exchange between a group of terminals 202 and the network can be ensured through network slicing. That is, data is transmitted while being bound to the corresponding QoS flow. A network slice can be identified using a Single-Network Slice Selection Assistance Information (S-NSSAI). The set of S-NSSAIs forms the NSSAI. In combination Figure 1 For example, when the UE 101 needs to use a network slice, it first needs to request slice usage from the AMF entity 103. After the AMF entity 103 agrees, the UE 101 then requests to establish a PDU session in the slice to transmit data. The UE 101 places the S-NSSAI to be requested in the Requested NSSAI according to the service. The Requested NSSAI is included in the Registration request and sent to the AMF entity 103. The AMF entity 103 determines the Allowed NSSAI based on the subscription of the UE 101 and the scope of network slice deployment. The Allowed NSSAI is sent to the UE 101 in the Registration accept message and also sent to the AN device 102 in the N2 message. After receiving the Allowed NSSAI, the UE 101 needs to select the slice corresponding to the service in the slices in the Allowed NSSAI to establish a Protocol Data Unit (PDU) session. Data can be sent and received only after the PDU session is established.

[0058] It should be understood that Figure 2 The scenarios shown are only examples of the scenarios applicable to the solution of this application and should not be construed as a limitation to this application. In other words, the solution provided by this application is applicable to any application scenario that requires ensuring the communication quality of a group of nodes simultaneously.

[0059] Figure 3 It is a schematic diagram of the end-to-end QoS control and mapping relationship of the QoS flow provided by the embodiment of this application in the user plane.

[0060] As Figure 3As shown in the figure, the PCF formulates Policy Charging Control (PCC) rules based on the information collected from each network element and its own configuration, and sends the PCC rules to the SMF. Based on this, the SMF provides the following three types of information to the UPF, AN, and UE respectively to achieve end-to-end Quality of Service (QoS) control: The QoS profile provided by the SMF to the AN. Among them, the QoS profile may include the following QoS parameters of this QoS flow: 5G QoS Identifier (5QI), Allocation and Retention Priority (ARP), and bit rate requirements and other information. One or more QoS rules provided by the SMF to the UE, which are mainly used for the detection of uplink data. One or more Packet Detection Rules (PDRs) for uplink and downlink packets and corresponding QoS enforcement rules provided by the SMF to the UPF.

[0061] In the downlink direction, the UPF matches the received data packets according to the priority of the downlink packet filter set in the PDR sent by the SMF from high to low. If a downlink-matching PDR is found, the corresponding QFI is encapsulated into the header according to the matching result. The RAN maps the data packets to the corresponding DRB according to the QFI. If no downlink PDR is matched, the UPF discards the data packet. In the uplink direction, the UE matches the data packets to be sent according to the priority of the uplink packet filter set in the QoS rule from high to low. If a match is found, the UE binds the uplink packet to the QoS flow using the QFI in the corresponding QoS rule, and further binds the QoS flow to the corresponding Data Radio Bearer (DRB). If no match is found, the UE discards the data packet. However, there is a default QoS rule in the UE, and the packet filter set in it can allow all data packets, aiming to match all data packets and prevent the loss of uplink data packets.

[0062] As an important measure of communication quality, QoS parameters are usually used to represent the characteristics of QoS flows. QoS flows are mainly divided into Guaranteed Bit Rate (GBR) QoS flows and non-GBR QoS flows. For GBR QoS flows, the network needs to reserve resources to ensure bandwidth.

[0063] The QoS parameters mainly include 5QI, ARP, RQA, Guaranteed Flow Bit Rate (GFBR), Maximum Flow Bit Rate (MFBR), Notification Control, Aggregate Maximum Bit Rate (AMBR), etc. The following explains each parameter.

[0064] 5QI can be understood as a scalar pointing to multiple QoS characteristic values, which are divided into three types: standardized 5QI, pre-configured 5QI, and dynamically allocated 5QI. For the dynamically allocated 5QI, when the core network provides the QoS flow configuration of the QoS flow to the base station, it not only includes 5QI in the QoS flow configuration, but also includes the set of complete QoS characteristic values corresponding to this 5QI. For the standardized and pre-configured 5QI, the core network only needs to provide 5QI, and the base station can resolve the set of multiple QoS characteristic values corresponding to this 5QI. In addition, for a standardized or pre-configured 5QI, it is also allowed for the core network to provide one or more QoS characteristic values different from the standardization or pre-configuration to modify the corresponding standardized or pre-configured QoS characteristic values. Standardized 5QI is mainly used for relatively general and frequently used services. Dynamically allocated 5QI is mainly used for less general services that cannot be satisfied by standardized 5QI.

[0065] ARP allocates and maintains priorities, specifically including three types of information: priority level, resource preemption ability, and whether resource preemption is allowed, which is used to determine whether to allow the establishment, modification, and handover of QoS flows when resources are limited, and is generally used for the admission control of GBR type QoS flows. ARP is also used to preempt the resources of existing QoS flows when resources are limited. For example, a high-priority QoS flow can preempt the resources of a low-priority QoS flow.

[0066] RQA indicates that the QoS flow carried by some SDFs applies reverse mapping QoS.

[0067] GFBR indicates that the base station guarantees to reserve sufficient resources for the code rate transmitted by a QoS flow within an average time window. MFBR limits the maximum code rate transmitted for a QoS flow.

[0068] QoS Notification Control indicates that when the base station cannot guarantee the GFBR of the QoS flow, it continues to strive to maintain the QoS flow and notify the core network that the QoS requirements cannot be guaranteed. The NG-RAN attempts to re-guarantee and notify the SMF that the QoS requirements are re-guaranteed.

[0069] The Session-AMBR controls the total bitrate of all non-GBR type QoS flows of a PDU session. The UE-AMBR controls the total bitrate of all non-GBR type QoS flows of a UE.

[0070] Figure 4 It is a schematic flowchart of the session establishment process 300 provided by the embodiments of the present application.

[0071] As Figure 4 shown, the session establishment process 300 may include:

[0072] S301, the UE sends a session establishment request message to the AMF, including session identification, session type (initial establishment session, EPS to 5GS handover, Non-3GPP to 3GPP handover, request for emergency service), SCC mode, DNN, S-NSSAI and other parameters.

[0073] S302, the AMF selects a suitable SMF according to the DNN, S-NSSAI and subscription data.

[0074] S303, the AMF triggers session establishment by invoking the session service of the selected SMF.

[0075] S304, the SMF obtains session subscription data from the UDM, such as the SCC mode (mode) allowed by the user, session type, and Session-AMBR of the session.

[0076] S305, the SMF selects a PCF for this session.

[0077] S306, the SMF establishes a policy connection with the PCF and obtains PCC rules.

[0078] S307, the SMF establishes a user plane connection between the UE, AN, and UPF. mainly CN tunnel info allocation and AN tunnel info acquisition. The SMF sends a session establishment acceptance message to the UE through the AMF and AN.

[0079] S308, the SMF registers with the UDM, and the UDM records the SMF ID corresponding to this session.

[0080] S309, the SMF allocates an IPv6 prefix for the UE and sends it to the UE through the user plane.

[0081] It can be found that in Figure 4In the session establishment process 300 shown, the QoS flow is for a single UE, that is, the network can allocate resources for each UE to ensure its transmission quality. However, when encountering the above-mentioned scenario of federated learning, the network needs to ensure the transmission quality of a group of nodes as a whole, rather than just the quality of a single node. The parameters involved in the session establishment process 300 cannot indicate that the network can ensure the service quality of a group of nodes, nor can it achieve flexible cross-UE resource scheduling according to the communication quality and computing power differences among different nodes within the group, so as to ensure that a group of nodes can efficiently complete an iteration of training.

[0082] When the UE transmits AI model parameters, it requires an extremely high transmission rate. Therefore, in order to enable the network to ensure the service quality of a group of nodes, and at the same time, according to the communication quality and computing power differences among different nodes within the group, achieve flexible cross-UE resource scheduling, and ensure that a group of nodes can efficiently complete an iteration of training, this application introduces a new parameter, namely group-GBR / MBR

[0083] (Group-GBR / MBR). Group-GBR represents the transmission rate guaranteed by the network for a group of nodes performing the same task, that is, the sum of the GBRs of all QoS flows for the same task of all nodes within the group. Group-MBR represents the maximum transmission rate restricted by the network for a group of nodes performing the same task, that is, the sum of the GBRs of all QoS flows for the same task of all nodes within the group and / or the sum of the non-GBRs of all QoS flows for the same task of all nodes within the group.

[0084] Figures 5 to 8 is an example of the application scenario corresponding to the group-GBR / MBR provided in the embodiments of this application.

[0085] The following combines Figures 5 to 8 to describe the application scenario of the group-GBR / MBR provided in the embodiments of this application.

[0086] As Figure 5 shown, the PDU sessions of different nodes in the node group correspond to the same access network device and the same user plane function UPF; or as Figure 6 shown, the PDU sessions of different nodes in the node group correspond to the same access network device and different UPFs; or as Figure 7 shown, the PDU sessions of different nodes in the node group correspond to different access network devices and the same UPF; or as Figure 8 shown, the PDU sessions of different nodes in the node group correspond to different access network devices and different UPFs.

[0087] The embodiments of the present application provide a wireless communication method, a network element, and a device, which can achieve flexible cross-node resource scheduling, and thus can ensure the overall transmission quality of multiple nodes simultaneously.

[0088] Figure 9 It is a schematic block diagram of the wireless communication method 410 provided by the embodiments of the present application. The method 410 can be executed by a session management network element. For example, Figure 1 the SMF entity 104 shown. It should be noted that the session management network element in the embodiments of the present application can be, for example, an SMF entity in a 5G communication system. Of course, it can also be an entity with session management functions in other 3GPP communication systems. The present application is not limited thereto.

[0089] As Figure 9 shown, the method 410 may include:

[0090] S411, determining the QoS parameters of the QoS flow of the first node in the first node group, where the QoS parameters of the QoS flow of the first node are determined according to the QoS parameters of the first node group.

[0091] Based on the above technical solutions, by introducing the first node group and the QoS parameters of the first node group, the session management network element can determine the QoS parameters of the QoS flow of the first node in the first node group. Furthermore, on the basis of realizing flexible cross-node resource scheduling within the first node group, the overall transmission quality of the first node group can be ensured.

[0092] It should be noted that the solution provided by the embodiments of the present application aims to adjust the QoS parameters of the nodes in the first node group based on the QoS parameters of the first node group. Or rather, when the QoS parameters of the first node group are fixed or unchanged, adjust the QoS parameters of the nodes in the first node group. The embodiments of the present application do not make specific limitations on the specific QoS parameters of the nodes in the first node group. For example, it only needs to ensure that the QoS parameters of the first node group are greater than or equal to the sum of the QoS parameters of all nodes in the first node group.

[0093] In some embodiments of the present application, the first node group includes nodes for the same task.

[0094] In some embodiments of the present application, the same task includes a transmission task of model training parameters and / or a download task of a global model using the same network slice; and / or, the same task includes a transmission task of model training parameters and / or a download task of a global model for the same model.

[0095] In some embodiments of the present application, one node in the first node group corresponds to one protocol data unit (PDU) session, and the one PDU session is used to carry at least one quality of service (QoS) flow. The QoS parameters of the first node group include the sum of the QoS parameters of the QoS flows corresponding to the same task among the QoS flows carried by the PDU sessions of the first node group.

[0096] In some embodiments of the present application, the QoS parameters of the first node group may include group-GBR and / or group-MBR. The Group-GBR is the sum of the GBRs of the QoS flows corresponding to the same task of the first node group, and the group-MBR is the sum of the maximum bit rates (MBRs) of the QoS flows corresponding to the same task of the first node group.

[0097] In some embodiments of the present application, the PDU sessions of different nodes in the first node group correspond to the same access network device and the same user plane function (UPF); or the PDU sessions of different nodes in the first node group correspond to the same access network device and different UPFs; or the PDU sessions of different nodes in the first node group correspond to different access network devices and the same UPF; or the PDU sessions of different nodes in the first node group correspond to different access network devices and different UPFs.

[0098] In some embodiments of the present application, the method 410 may further include:

[0099] Determine the policy control network element of the first node. The policy control network element of the first node may be the same as or different from the policy control network elements of other nodes, and the other nodes include the nodes in the first node group except the first node.

[0100] Optionally, the session management network element of the first node is the same as the session management network elements of other nodes, and the policy control network element of the first node may be the same as or different from the policy control network elements of other nodes.

[0101] Optionally, the session management network element of the first node is different from the session management network elements of other nodes, and the policy control network element of the first node is the same as the policy control network elements of other nodes.

[0102] It should be understood that in the embodiments of the present application, it is only necessary to ensure that the QoS parameters of the QoS flow of the first node can be determined based on the QoS parameters of the first node group. Based on this, it is only necessary to ensure that the session management network element of the first node is the same as that of the other nodes, or to ensure that the policy control network element of the first node is the same as that of the other nodes. The embodiments of the present application do not limit the specific implementation manners.

[0103] In some embodiments of the present application, S411 may include:

[0104] When the QoS parameters of the first node group are fixed, determine the QoS parameters of the QoS flow of the first node according to the number of nodes in the first node group and the QoS parameters of the first node group.

[0105] For example, when the QoS parameters of the first node group are fixed, the SMF may directly convert the QoS parameters of the first node group into the QoS parameters of the QoS flow of the first node based on the local configuration information of the SMF and the number of nodes in the first node group. In other words, in the embodiments of the present application, the SMF can directly determine the QoS parameters of the QoS flow of the first node without the participation of the PCF.

[0106] In some embodiments of the present application, S411 may include:

[0107] Receive the QoS parameters of the service flow of the first node sent by the policy control network element; determine the QoS parameters of the QoS flow of the first node based on the QoS parameters of the service flow of the first node.

[0108] For example, the SMF first receives the QoS parameters of the service flow of the first node sent by the policy control network element, and then converts or maps the QoS parameters of the service flow of the first node into the QoS parameters of the QoS flow of the first node. In other words, in the embodiments of the present application, the SMF can convert the QoS parameters of the service flow of the first node determined by the PCF into the QoS parameters of the QoS flow of the first node with the participation of the PCF.

[0109] In some embodiments of the present application, the method 410 may further include:

[0110] Receive the QoS parameters of the first node group sent by the unified data management UDM.

[0111] Optionally, when the session to be established by the first node is a session for performing federated learning, receive the QoS parameters of the first node group sent by the UDM.

[0112] In some embodiments of the present application, the method 410 may further include:

[0113] Sending a session establishment or update request to a policy control network element, where the establishment or update request includes the QoS parameters of the first node group.

[0114] In some embodiments of the present application, the QoS parameters of the service flow of the first node include a Guaranteed Bit Rate (GBR) and / or a Maximum Bit Rate (MBR), and the QoS parameters of the QoS flow of the first node include a Guaranteed Flow Bit Rate (GFBR) and / or a Maximum Flow Bit Rate (MFBR).

[0115] In some embodiments of the present application, S411 may include:

[0116] Determining the QoS parameters of the QoS flow of the first node for a session establishment process and / or a session modification process.

[0117] In other words, the QoS parameters of the QoS flow of the first node determined by the SMF can be used for a session establishment process and / or a session modification process.

[0118] In some embodiments of the present application, the method 410 may further include:

[0119] Sending the QoS parameters of the first node group.

[0120] For example, sending the QoS parameters of the first node group to an access network device through an Access and Mobility Management Function (AMF).

[0121] Figure 10 FIG. is a schematic block diagram of a wireless communication method 420 provided by an embodiment of the present application. The method 420 may be executed by a policy control network element. For example, Figure 1 the PCF entity 106 shown. It should be noted that the policy control network element in the embodiments of the present application may be, for example, a PCF entity in a 5G communication system. Of course, it may also be an entity with policy control functions in other 3GPP communication systems. The present application is not limited thereto.

[0122] As Figure 10 shown, the method 420 may include:

[0123] S421, determining the QoS parameters of the service flow of the first node in the first node group according to the QoS parameters of the first node group;

[0124] S422, sending the QoS parameters of the service flow of the first node to a session management network element.

[0125] In some embodiments of the present application, the first node group includes nodes for the same task.

[0126] In some embodiments of the present application, the same task includes a task of transmitting model training parameters and / or a task of downloading a global model using the same network slice; and / or, the same task includes a task of transmitting model training parameters and / or a task of downloading a global model for the same model.

[0127] In some embodiments of the present application, one node in the first node group corresponds to one protocol data unit (PDU) session, the one PDU session is used to carry at least one quality of service (QoS) flow, and the QoS parameters of the first node group include the sum of the QoS parameters of the QoS flows corresponding to the same task in the QoS flows carried by the PDU sessions of the first node group.

[0128] In some embodiments of the present application, the QoS parameters of the first node group include a group guaranteed bit rate (Group-GBR) and / or a group maximum bit rate (Group-MBR); the Group-GBR is the sum of the GBRs of the QoS flows corresponding to the same task in the first node group, and the Group-MBR is the sum of the MBRs of the QoS flows corresponding to the same task in the first node group; or, the Group-GBR is the maximum value that can be reached by the sum of the GBRs of the QoS flows corresponding to the same task in the first node group, and the Group-MBR is the maximum value that can be reached by the sum of the MBRs of the QoS flows corresponding to the same task in the first node group.

[0129] In some embodiments of the present application, the PDU sessions of different nodes in the first node group correspond to the same access network device and the same user plane function (UPF); or the PDU sessions of different nodes in the first node group correspond to the same access network device and different UPFs; or the PDU sessions of different nodes in the first node group correspond to different access network devices and the same UPF; or the PDU sessions of different nodes in the first node group correspond to different access network devices and different UPFs.

[0130] In some embodiments of the present application, the policy control network element of the first node is the same as or different from the policy control network elements of other nodes, and the other nodes include the nodes in the first node group except the first node.

[0131] In some embodiments of the present application, the session management network element of the first node is the same as the session management network elements of other nodes, and the policy control network element of the first node is the same as or different from the policy control network elements of other nodes.

[0132] In some embodiments of the present application, the session management network element of the first node is different from the session management network elements of other nodes, and the policy control network element of the first node is the same as the policy control network elements of other nodes.

[0133] In some embodiments of the present application, S421 may include:

[0134] When the QoS parameters of the first node group are fixed, determine the QoS parameters of the traffic flow of the first node for the session establishment process according to the number of nodes in the first node group and the QoS parameters of the first node group.

[0135] In some embodiments of the present application, S421 may include:

[0136] Obtain first indication information for indicating the data processing capabilities of the nodes in the first node group; when the QoS parameters of the first node group are fixed, determine the QoS parameters of the traffic flow of the first node for the session modification process according to the number of nodes in the first node group, the QoS parameters of the first node group, and the first indication information.

[0137] In some embodiments of the present application, the first indication information includes the time for the nodes in the first node group to upload data.

[0138] In some embodiments of the present application, receive the first indication information sent by the server.

[0139] In some embodiments of the present application, method 420 may further include:

[0140] Trigger a session modification process based on the first indication information.

[0141] In some embodiments of the present application, method 420 may further include:

[0142] Receive a session establishment or update request sent by the session management network element, where the establishment or update request includes the QoS parameters of the first node group.

[0143] In some embodiments of the present application, the QoS parameters of the traffic flow of the first node include a guaranteed bit rate (GBR) and / or a maximum bit rate (MBR), and the QoS parameters of the QoS flow of the first node include a guaranteed flow bit rate (GFBR) and / or a maximum flow bit rate (MFBR).

[0144] Figure 11 It is a schematic block diagram of a wireless communication method 430 provided by an embodiment of the present application. Method 430 may be executed by a mobility management network element. For example, Figure 1The AMF entity 103 shown. It should be noted that the mobility management network element in the embodiments of this application may be, for example, the AMF entity in a 5G communication system. Of course, it may also be an entity with mobility management functions in other 3GPP communication systems. This application does not limit this.

[0145] As Figure 11 shown, the method 430 may include:

[0146] S431, receiving second indication information; the second indication information is used to indicate that the access and mobility management network element selects the same session management network element for the first node as for other nodes; or the second indication information is used to indicate that the mobility management network element selects a session management network element for the first node, and the session management network element of the first node is the same as or different from the session management network element of the other nodes; the other nodes include nodes other than the first node in the first node group.

[0147] In some embodiments of this application, the first node group includes nodes for the same task.

[0148] In some embodiments of this application, the same task includes a transmission task of model training parameters and / or a download task of a global model using the same network slice; and / or, the same task includes a transmission task of model training parameters and / or a download task of a global model for the same model.

[0149] In some embodiments of this application, one node in the first node group corresponds to one protocol data unit (PDU) session, and the one PDU session is used to carry at least one quality of service (QoS) flow. The QoS parameters of the first node group include the sum of the QoS parameters of the QoS flows corresponding to the same task in the QoS flows carried by the PDU sessions of the first node group.

[0150] In some embodiments of this application, the QoS parameters of the first node group include group guaranteed bit rate (Group-GBR) and / or group maximum bit rate (Group-MBR); the Group-GBR is the sum of the GBRs of the QoS flows corresponding to the same task in the first node group, and the Group-MBR is the sum of the MBRs of the QoS flows corresponding to the same task in the first node group; or, the Group-GBR is the maximum value that can be reached by the sum of the GBRs of the QoS flows corresponding to the same task in the first node group, and the Group-MBR is the maximum value that can be reached by the sum of the MBRs of the QoS flows corresponding to the same task in the first node group.

[0151] In some embodiments of the present application, the PDU sessions of different nodes in the first node group correspond to the same access network device and the same user plane function UPF; or the PDU sessions of different nodes in the first node group correspond to the same access network device and different UPFs; or the PDU sessions of different nodes in the first node group correspond to different access network devices and the same UPF; or the PDU sessions of different nodes in the first node group correspond to different access network devices and different UPFs.

[0152] In some embodiments of the present application, the method 430 may further include:

[0153] Determine the session management network element of the first node based on the second indication information.

[0154] In some embodiments of the present application, the method 430 may further include:

[0155] Receive a first message sent by the first node, where the first message includes a first single network slice selection assistance information S-NSSAI and / or a first identifier, the first identifier is used to indicate the identifier of the first model, the S-NSSAI adopted by the first node group is the first S-NSSAI, and the model adopted by the first node group is the first model.

[0156] In some embodiments of the present application, the QoS parameters of the traffic flow of the first node include a guaranteed bit rate GBR and / or a maximum bit rate MBR, and the QoS parameters of the QoS flow of the first node include a guaranteed flow bit rate GFBR and / or a maximum flow bit rate MFBR.

[0157] Figure 12 It is a schematic block diagram of a wireless communication method 440 provided by an embodiment of the present application. The method 230 may be executed by an access network device. For example, Figure 1 the AN device 102 shown.

[0158] As Figure 12 shown, the method 440 may include:

[0159] S441, obtain the capability information of each node in the first group of nodes, where the capability information is used to indicate the data processing capability of the node, and the first node group includes nodes for the same task;

[0160] S442, when the QoS parameters of the first node group are fixed, determine the QoS parameters of the QoS flow of each node in the first node group based on the capability information; and / or, trigger a session modification process based on the capability information to modify the QoS parameters of the QoS flow of each node in the first node group.

[0161] In some embodiments of the present application, the method 440 may further include:

[0162] Receiving the QoS parameters of the first node group.

[0163] In some embodiments of the present application, the capability information includes the time when the nodes in the first node group upload data.

[0164] In some embodiments of the present application, the first node group includes nodes for the same task.

[0165] In some embodiments of the present application, the same task includes a transmission task of model training parameters and / or a download task of a global model using the same network slice; and / or, the same task includes a transmission task of model training parameters and / or a download task of a global model for the same model.

[0166] In some embodiments of the present application, one node in the first node group corresponds to one protocol data unit (PDU) session, and the one PDU session is used to carry at least one quality of service (QoS) flow. The QoS parameters of the first node group include the sum of the QoS parameters of the QoS flows corresponding to the same task in the QoS flows carried by the PDU sessions of the first node group.

[0167] In some embodiments of the present application, the QoS parameters of the first node group include a group guaranteed bit rate (Group-GBR) and / or a group maximum bit rate (Group-MBR); the Group-GBR is the sum of the GBRs of the QoS flows corresponding to the same task in the first node group, and the Group-MBR is the sum of the MBRs of the QoS flows corresponding to the same task in the first node group; or, the Group-GBR is the maximum value that can be reached by the sum of the GBRs of the QoS flows corresponding to the same task in the first node group, and the Group-MBR is the maximum value that can be reached by the sum of the MBRs of the QoS flows corresponding to the same task in the first node group.

[0168] In some embodiments of the present application, the PDU sessions of different nodes in the first node group correspond to the same access network device and the same user plane function (UPF); or the PDU sessions of different nodes in the first node group correspond to the same access network device and different UPFs; or the PDU sessions of different nodes in the first node group correspond to different access network devices and the same UPF; or the PDU sessions of different nodes in the first node group correspond to different access network devices and different UPFs.

[0169] In some embodiments of the present application, the QoS parameters of the service flow of the first node include the Guaranteed Bit Rate (GBR) and / or the Maximum Bit Rate (MBR), and the QoS parameters of the QoS flow of the first node include the Guaranteed Flow Bit Rate (GFBR) and / or the Maximum Flow Bit Rate (MFBR).

[0170] It should be noted that the methods related to the above session management network element, policy control network element, access and mobility management network element, and access network device can be referred to each other. In other words, the corresponding steps in the above method 410, method 420, method 430, and method 440 can be referred to each other.

[0171] The solution of the present application will be described below with specific embodiments.

[0172] Embodiment 1:

[0173] In this embodiment, in the case of using the same SMF in the same network slice and / or the same AI model, the session establishment process based on group-GBR / MBR is described. Assume a group of nodes, that is, a group of UEs, use the same network slice or the same AI model to transmit model training parameters and download the global model. The network differentiates the policies related to federated learning from the communication policies of other services that the UEs are performing. Therefore, the network can adjust the QoS policy of each UE without affecting the data transmission of other non-federated learning.

[0174] Figure 13 It is a schematic block diagram of the session establishment process 500 provided by the embodiments of the present application. The method 500 can be interactively executed by the UE, AN, AMF, UPF, SMF, PCF, and UDM. For example Figure 1 the corresponding entities or network elements shown.

[0175] As Figure 13 shown, the session establishment process 500 may include some or all of the following:

[0176] S501, the UE sends a session establishment request message to the AMF, including the S-NSSAI, Deep Neural Networks (DNN), or an artificial intelligence (AI) model identifier.

[0177] S502, the SMF obtains the subscription data from the UDM, indicating that the same SMF as other federated nodes needs to be selected for the UE with this S-NSSAI and DNN or for executing the AI model training.

[0178] S503, the AMF triggers the session establishment by invoking the session service of the selected SMF.

[0179] S504. The SMF obtains session subscription data from the UDM. If the session is for a federated learning session of a federated node, the SMF obtains the subscribed group-GBR / MBR from the UDM.

[0180] S505. The SMF selects a PCF for this session.

[0181] S506. The SMF sends a session establishment / update request to the PCF, including the subscribed group-GBR / MBR.

[0182] S507a. Based on the number of federated nodes provided by the FL server and the group-GBR / MBR provided by the SMF, the PCF determines the GBR and MBR at the service flow level for the UE acting as a federated node to establish this session. The SCF formulates the GFBR and MFBR for the corresponding QoS flow of the UE based on the GBR and MBR.

[0183] S507b. Since all UEs are managed by the same SMF, the SMF itself can formulate the GFBR and MFBR for the corresponding QoS flow of the UE based on the group-GBR / MBR.

[0184] It should be noted that S507a and S507b are two implementation methods for formulating the GFBR and MFBR for the corresponding QoS flow of the UE. In practice, one of these methods can be selected to implement the solution of this embodiment.

[0185] S508. The SMF sends an N4 session establishment modification request to the UPF and allocates core network tunnel information (CN tunnelinfo).

[0186] S509. The SMF provides the GFBR and MFBR formulated based on the group-GBR / MBR to the AMF, and the AMF sends the GFBR and MFBR to the RAN.

[0187] S510. The GFBR and MFBR are included in the N2 message and sent to the base station.

[0188] S511. The RAN performs the corresponding radio interface resource establishment according to the received QoS parameters.

[0189] In this embodiment, by obtaining the subscribed group-GBR / MBR, the SMF and / or the PCF formulate the QoS parameters for a corresponding group of UEs, thereby realizing the network's guarantee of the service quality for a group of nodes.

[0190] Embodiment 2:

[0191] In this embodiment, in the case where the same network slice and / or the same AI model adopt the same PCF, the session establishment process based on group-GBR / MBR. That is, when nodes within a node group perform federated learning, different SMFs can be selected for different UEs to establish a session based on the same network slice or the same AI model, but these SMFs need to select the same PCF to formulate a unified session policy for a group of nodes.

[0192] Figure 14 It is a schematic block diagram of the session establishment process 600 provided by an embodiment of the present application. The method 600 can be interactively executed by a UE, an AN, an AMF, a UPF, an SMF, a PCF, and a UDM. For example Figure 1 The corresponding entities or network elements shown.

[0193] Such as Figure 14 As shown, the session establishment process 600 may include some or all of the following:

[0194] S601, The UE sends a session establishment request message to the AMF, including S-NSSAI, DNN, or an identifier of a certain AI model.

[0195] S602, The SMF obtains subscription data from the UDM, indicating that an SMF needs to be selected for this S-NSSAI and DNN or the UE performing the AI model training, but a group of nodes do not have to select the same SMF.

[0196] S603, The AMF triggers session establishment by invoking the session service of the selected SMF.

[0197] S604. The SMF obtains session subscription data from the UDM. If this session is a session for federated nodes to perform federated learning, the SMF obtains the subscribed group-GBR / MBR from the UDM.

[0198] S605, The SMF selects a PCF for this session. A group of federated nodes need to select the same PCF for federated learning.

[0199] S606, The SMF sends a session establishment / update request to the PCF, including the subscribed group-GBR / MBR.

[0200] S607, The PCF determines the GBR and MBR at the service flow level for the UEs that are federated nodes to establish this session according to the number of federated nodes provided by the FL server and the group-GBR / MBR provided by the SMF. The SMF formulates the GFBR and MFBR for the corresponding QoS flows of the UEs based on the GBR and MBR.

[0201] S608, The SMF sends an N4 session establishment modification request to the UPF and allocates core network tunnel information (CN tunnelinfo).

[0202] S609. The SMF provides the GFBR and MFBR formulated based on the group-GBR / MBR to the AMF, and the AMF sends the GFBR and MFBR to the RAN.

[0203] S610. The GFBR and MFBR are included in the N2 message and sent to the base station.

[0204] S611. The RAN performs the corresponding radio interface resource establishment according to the received QoS parameters.

[0205] In this embodiment, by obtaining the subscribed group-GBR / MBR, the SMF and / or the PCF formulate the QoS parameters of a corresponding group of UEs, so as to ensure the service quality of a group of nodes by the network.

[0206] Embodiment 3:

[0207] In this embodiment, resource sharing among federated nodes based on the group-GBR / MBR is realized on the core network side. Among different federated nodes, due to the difference in computing power, the time for each node to complete training and transmit the results is different. Therefore, only according to the GFBR and MFBR formulated in the session establishment process, the efficient information transmission of a group of nodes cannot be guaranteed. Therefore, in order to maximize the application of the group-GBR / MBR and ensure the overall performance of a group of nodes rather than the performance of a single node, the radio interface resources among various nodes need to be flexibly shared to achieve efficient iterative training.

[0208] Figure 15 It is a schematic block diagram of a wireless communication method 700 provided by an embodiment of the present application. The method 700 can be interactively executed by a UE, a base station, a core network control plane network element, a core network user plane network element, and an AI server. For example, the core network control plane network element can also be a policy control network element, the core network user plane network element can be a user plane function network element, and the AI server can be a server with learning ability or data processing ability.

[0209] As Figure 15 shown, the method 700 may include some or all of the following:

[0210] S701. Introduce first indication information, and the AI server indicates the time when a group of federated nodes upload training result data to the control plane network element of the core network.

[0211] S702. The network element of the core network triggers a session modification process according to the first indication information.

[0212] S703. When the group - GBR / MBR is fixed, modify the QoS parameters of the corresponding session of the corresponding UE according to the first indication information. For example, for the UE that transmits data earlier, decrease the values of GFBR and MFBR, and for the UE that transmits data slower, increase the values of GFBR and MFBR.

[0213] S704. The core network control plane sends the new QoS parameter values to the core network user plane network element.

[0214] S705. The core network control plane sends the new QoS parameter values to the base station, instructing the base station to schedule the radio interface resources of the nodes within the group.

[0215] S706. The core network control plane sends the new QoS parameter values to the UE for the transmission of the UE's uplink data.

[0216] In this embodiment, by introducing the first indication information, the core network side can flexibly allocate the radio interface resources of different UEs without changing the group - GBR / MBR, eliminate the difference in the data transmission completion time of a group of nodes caused by the difference in computing power between UEs, and achieve an efficient iteration of a group of nodes to complete a training.

[0217] Embodiment 4:

[0218] In this embodiment, the base station side realizes resource sharing between federated nodes based on group - GBR / MBR. When a group of federated nodes are all connected through the same base station for the transmission of federated learning data, the base station side can, according to the time when different nodes upload data, flexibly adjust the radio interface resources between the nodes without changing the overall group - GBR / MBR, improve the data transmission rate corresponding to the UE with low computing power, and reduce the data transmission rate corresponding to the UE with high computing power.

[0219] Figure 15 It is a schematic block diagram of the wireless communication method 800 provided by the embodiments of the present application. The method 800 can be interactively executed by the UE, the base station, the core network control plane network element, the core network user plane network element, and the AI server. For example, the core network control plane network element can also be a policy control network element, the core network user plane network element can be a user plane function network element, and the AI server can be a server with learning ability or data processing ability.

[0220] As Figure 15 shown, the method 800 may include some or all of the following:

[0221] S801. The base station obtains the group - GBR / MBR parameters of a group of nodes from the core network element.

[0222] S802. The base station can adjust the QoS parameters of each node based on the time when it receives data transmitted from different nodes, while ensuring a certain group-GBR / MBR. For example, for UEs that transmit data earlier, the values of GFBR and MFBR are decreased, and for UEs that transmit data slower, the values of GFBR and MFBR are increased.

[0223] S803. The base station triggers a session modification process.

[0224] For S804 - S806, reference can be made to S704 - S706 in Embodiment 3. To avoid repetition, it will not be elaborated here.

[0225] In this embodiment, the base station obtains the group-GBR / MBR and, while keeping the group-GBR / MBR unchanged, flexibly modifies the QoS parameters of a group of UEs, eliminates the difference in the data transmission completion time of a group of nodes caused by the difference in computing capabilities between UEs, and enables a group of nodes to efficiently complete one iteration of training.

[0226] In summary, the solution provided in the embodiments of the present application can ensure the service quality of a group of nodes by the network, and at the same time, according to the difference in communication quality between different nodes within the group, achieve flexible cross-UE resource scheduling to ensure that a group of nodes efficiently complete one iteration of federated learning training.

[0227] The preferred embodiments of the present application have been described in detail above with reference to the accompanying drawings. However, the present application is not limited to the specific details in the above embodiments. Within the scope of the technical concept of the present application, various simple modifications can be made to the technical solutions of the present application, and these simple modifications all fall within the protection scope of the present application. For example, the various specific technical features described in the above specific embodiments can be combined in any appropriate manner without contradiction. To avoid unnecessary repetition, the present application will not separately describe various possible combination methods. Again, any combination can be made between various different embodiments of the present application as long as it does not violate the idea of the present application, and it should also be regarded as the content disclosed by the present application.

[0228] Figure 17 It is a schematic block diagram of the session management network element 810 provided by the embodiments of the present application.

[0229] As Figure 17 shown, the session management network element 810 may include:

[0230] A determination unit 811, configured to determine the QoS parameters of the QoS flow of the first node in the first node group, where the QoS parameters of the QoS flow of the first node are determined according to the QoS parameters of the first node group.

[0231] In some embodiments of the present application, the first node group includes nodes for the same task.

[0232] In some embodiments of the present application, the same task includes a transmission task of model training parameters and / or a download task of a global model using the same network slice; and / or, the same task includes a transmission task of model training parameters and / or a download task of a global model for the same model.

[0233] In some embodiments of the present application, one node in the first node group corresponds to a protocol data unit (PDU) session, and the one PDU session is used to carry at least one quality of service (QoS) flow. The QoS parameters of the first node group include the sum of the QoS parameters of the QoS flows corresponding to the same task in the QoS flows carried by the PDU sessions of the first node group.

[0234] In some embodiments of the present application, the QoS parameters of the first node group include a group guaranteed bit rate (Group-GBR) and / or a group maximum bit rate (Group-MBR); the Group-GBR is the sum of the GBRs of the QoS flows corresponding to the same task in the first node group, and the Group-MBR is the sum of the MBRs of the QoS flows corresponding to the same task in the first node group; or, the Group-GBR is the maximum value that can be reached by the sum of the GBRs of the QoS flows corresponding to the same task in the first node group, and the Group-MBR is the maximum value that can be reached by the sum of the MBRs of the QoS flows corresponding to the same task in the first node group.

[0235] In some embodiments of the present application, the PDU sessions of different nodes in the first node group correspond to the same access network device and the same user plane function (UPF); or the PDU sessions of different nodes in the first node group correspond to the same access network device and different UPFs; or the PDU sessions of different nodes in the first node group correspond to different access network devices and the same UPF; or the PDU sessions of different nodes in the first node group correspond to different access network devices and different UPFs.

[0236] In some embodiments of the present application, the determining unit 811 is further configured to:

[0237] Determine the policy control network element of the first node, where the policy control network element of the first node is the same as or different from the policy control network elements of other nodes, and the other nodes include the nodes other than the first node in the first node group.

[0238] In some embodiments of the present application, the session management network element of the first node is the same as the session management network element of the other nodes, and the policy control network element of the first node is the same as or different from the policy control network elements of the other nodes.

[0239] In some embodiments of the present application, the session management network element of the first node is different from the session management network element of the other nodes, and the policy control network element of the first node is the same as the policy control network elements of the other nodes.

[0240] In some embodiments of the present application, the determining unit 811 is specifically configured to:

[0241] When the QoS parameters of the first node group are fixed, determine the QoS parameters of the QoS flows of the first node according to the number of nodes in the first node group and the QoS parameters of the first node group.

[0242] In some embodiments of the present application, the determining unit 811 is specifically configured to:

[0243] Receive the QoS parameters of the service flows of the first node sent by the policy control network element; based on the QoS parameters of the service flows of the first node, determine the QoS parameters of the QoS flows of the first node.

[0244] In some embodiments of the present application, the determining unit 811 is further configured to:

[0245] Receive the QoS parameters of the first node group sent by the Unified Data Management UDM.

[0246] In some embodiments of the present application, the determining unit 811 is specifically configured to:

[0247] When the session to be established by the first node is a session for performing federated learning, receive the QoS parameters of the first node group sent by the UDM.

[0248] In some embodiments of the present application, the determining unit 811 is further configured to:

[0249] Send a session establishment or update request to the policy control network element, where the establishment or update request includes the QoS parameters of the first node group.

[0250] In some embodiments of the present application, the QoS parameters of the service flows of the first node include the Guaranteed Bit Rate GBR and / or the Maximum Bit Rate MBR, and the QoS parameters of the QoS flows of the first node include the Guaranteed Flow Bit Rate GFBR and / or the Maximum Flow Bit Rate MFBR.

[0251] In some embodiments of the present application, the determining unit 811 is further configured to:

[0252] Determine the QoS parameters of the QoS flow of the first node for the session establishment process and / or the session modification process.

[0253] In some embodiments of the present application, the determining unit 811 is further configured to:

[0254] Send the QoS parameters of the first node group.

[0255] Figure 18 It is a schematic block diagram of the policy control network element 820 provided by the embodiments of the present application.

[0256] As Figure 18 shown, the policy control network element 820 may include:

[0257] A determining unit 821, configured to determine the QoS parameters of the service flow of the first node in the first node group according to the QoS parameters of the first node group;

[0258] A sending unit 822, configured to send the QoS parameters of the service flow of the first node to the session management network element.

[0259] In some embodiments of the present application, the first node group includes nodes for the same task.

[0260] In some embodiments of the present application, the same task includes a transmission task of model training parameters and / or a download task of a global model using the same network slice; and / or, the same task includes a transmission task of model training parameters and / or a download task of a global model for the same model.

[0261] In some embodiments of the present application, one node in the first node group corresponds to a protocol data unit PDU session, the one PDU session is used to carry at least one quality of service QoS flow, and the QoS parameters of the first node group include the sum of the QoS parameters of the QoS flows corresponding to the same task in the QoS flows carried by the PDU sessions of the first node group.

[0262] In some embodiments of the present application, the QoS parameters of the first node group include a group minimum guaranteed rate (Group-GBR) and / or a group maximum rate (Group-MBR); the Group-GBR is the sum of the GBRs of the QoS flows corresponding to the same task of the first node group, and the Group-MBR is the sum of the MBRs of the QoS flows corresponding to the same task of the first node group; alternatively, the Group-GBR is the maximum value that can be reached by the sum of the GBRs of the QoS flows corresponding to the same task of the first node group, and the Group-MBR is the maximum value that can be reached by the sum of the MBRs of the QoS flows corresponding to the same task of the first node group.

[0263] In some embodiments of the present application, the PDU sessions of different nodes in the first node group correspond to the same access network device and the same user plane function (UPF); or the PDU sessions of different nodes in the first node group correspond to the same access network device and different UPFs; or the PDU sessions of different nodes in the first node group correspond to different access network devices and the same UPF; or the PDU sessions of different nodes in the first node group correspond to different access network devices and different UPFs.

[0264] In some embodiments of the present application, the policy control network element of the first node is the same as or different from the policy control network elements of other nodes, and the other nodes include the nodes in the first node group except the first node.

[0265] In some embodiments of the present application, the session management network element of the first node is the same as that of other nodes, and the policy control network element of the first node is the same as or different from the policy control network elements of other nodes.

[0266] In some embodiments of the present application, the session management network element of the first node is different from that of other nodes, and the policy control network element of the first node is the same as the policy control network elements of other nodes.

[0267] In some embodiments of the present application, the determining unit 821 is specifically configured to:

[0268] When the QoS parameters of the first node group are fixed, determine the QoS parameters of the service flow of the first node for the session establishment process according to the number of nodes in the first node group and the QoS parameters of the first node group.

[0269] In some embodiments of the present application, the determining unit 821 is specifically configured to:

[0270] Obtain first indication information, where the first indication information is used to indicate the data processing capabilities of the nodes in the first node group; when the QoS parameters of the first node group are fixed, determine the QoS parameters of the service flow of the first node for the session modification process according to the number of nodes in the first node group, the QoS parameters of the first node group, and the first indication information.

[0271] In some embodiments of this application, the first indication information includes the time for the nodes in the first node group to upload data.

[0272] In some embodiments of this application, receive the first indication information sent by the server.

[0273] In some embodiments of this application, the determining unit 821 is further configured to:

[0274] Trigger a session modification process based on the first indication information.

[0275] In some embodiments of this application, the sending unit 822 is further configured to:

[0276] Receive a session establishment or update request sent by a session management network element, where the establishment or update request includes the QoS parameters of the first node group.

[0277] In some embodiments of this application, the QoS parameters of the service flow of the first node include a guaranteed bit rate (GBR) and / or a maximum bit rate (MBR), and the QoS parameters of the QoS flow of the first node include a guaranteed flow bit rate (GFBR) and / or a maximum flow bit rate (MFBR).

[0278] Figure 19 It is a schematic block diagram of an access and mobility management network element 830 provided by an embodiment of this application.

[0279] As Figure 19 shown, the access and mobility management network element 830 may include:

[0280] A receiving unit 831, configured to receive second indication information; the second indication information is used to indicate that the access and mobility management network element selects the same session management network element for the first node as for other nodes; or the second indication information is used to indicate that the mobility management network element selects a session management network element for the first node, and the session management network element of the first node is the same as or different from the session management network elements of the other nodes; the other nodes include the nodes in the first node group except the first node.

[0281] In some embodiments of this application, the first node group includes nodes for the same task.

[0282] In some embodiments of the present application, the same task includes a transmission task of model training parameters and / or a download task of a global model using the same network slice; and / or, the same task includes a transmission task of model training parameters and / or a download task of a global model for the same model.

[0283] In some embodiments of the present application, one node in the first node group corresponds to one protocol data unit (PDU) session, the one PDU session is used to carry at least one quality of service (QoS) flow, and the QoS parameters of the first node group include the sum of the QoS parameters of the QoS flows corresponding to the same task in the QoS flows carried by the PDU sessions of the first node group.

[0284] In some embodiments of the present application, the QoS parameters of the first node group include a group guaranteed bit rate (Group-GBR) and / or a group maximum bit rate (Group-MBR); the Group-GBR is the sum of the GBRs of the QoS flows corresponding to the same task in the first node group, and the Group-MBR is the sum of the MBRs of the QoS flows corresponding to the same task in the first node group; or, the Group-GBR is the maximum value that can be reached by the sum of the GBRs of the QoS flows corresponding to the same task in the first node group, and the Group-MBR is the maximum value that can be reached by the sum of the MBRs of the QoS flows corresponding to the same task in the first node group.

[0285] In some embodiments of the present application, the PDU sessions of different nodes in the first node group correspond to the same access network device and the same user plane function (UPF); or the PDU sessions of different nodes in the first node group correspond to the same access network device and different UPFs; or the PDU sessions of different nodes in the first node group correspond to different access network devices and the same UPF; or the PDU sessions of different nodes in the first node group correspond to different access network devices and different UPFs.

[0286] In some embodiments of the present application, the receiving unit 831 is further configured to:

[0287] Determine the session management network element of the first node based on the second indication information.

[0288] In some embodiments of the present application, the receiving unit 831 is further configured to:

[0289] Receive a first message sent by the first node, where the first message includes first single network slice selection assistance information (S-NSSAI) and / or a first identifier, the first identifier is used to indicate the identifier of a first model, the S-NSSAI adopted by the first node group is the first S-NSSAI, and the model adopted by the first node group is the first model.

[0290] In some embodiments of the present application, the QoS parameters of the traffic flow of the first node include a guaranteed bit rate (GBR) and / or a maximum bit rate (MBR), and the QoS parameters of the QoS flow of the first node include a guaranteed flow bit rate (GFBR) and / or a maximum flow bit rate (MFBR).

[0291] Figure 20 It is a schematic block diagram of an access network device 840 provided by an embodiment of the present application.

[0292] As Figure 20 shown, the access network device 840 may include:

[0293] An obtaining unit 841, configured to obtain the capability information of each node in a first node group, where the capability information is used to indicate the data processing capability of the node, and the first node group includes nodes for the same task;

[0294] A processing unit 842, configured to determine the QoS parameters of the QoS flow of each node in the first node group based on the capability information when the QoS parameters of the first node group are determined; and / or trigger a session modification process based on the capability information to modify the QoS parameters of the QoS flow of each node in the first node group.

[0295] In some embodiments of the present application, the processing unit 842 is further configured to:

[0296] Receive the QoS parameters of the first node group.

[0297] In some embodiments of the present application, the capability information includes the time for the nodes in the first node group to upload data.

[0298] In some embodiments of the present application, the first node group includes nodes for the same task.

[0299] In some embodiments of the present application, the same task includes a task of transmitting model training parameters and / or a task of downloading a global model using the same network slice; and / or the same task includes a task of transmitting model training parameters and / or a task of downloading a global model for the same model.

[0300] In some embodiments of the present application, one node in the first node group corresponds to one protocol data unit (PDU) session, and the one PDU session is used to carry at least one quality of service (QoS) flow. The QoS parameters of the first node group include the sum of the QoS parameters of the QoS flows corresponding to the same task among the QoS flows carried by the PDU sessions of the first node group.

[0301] In some embodiments of the present application, the QoS parameters of the first node group include group guaranteed bit rate (Group-GBR) and / or group maximum bit rate (Group-MBR); the Group-GBR is the sum of the GBRs of the QoS flows corresponding to the same task in the first node group, and the Group-MBR is the sum of the MBRs of the QoS flows corresponding to the same task in the first node group; or, the Group-GBR is the maximum value that can be reached by the sum of the GBRs of the QoS flows corresponding to the same task in the first node group, and the Group-MBR is the maximum value that can be reached by the sum of the MBRs of the QoS flows corresponding to the same task in the first node group.

[0302] In some embodiments of the present application, the PDU sessions of different nodes in the first node group correspond to the same access network device and the same user plane function (UPF); or the PDU sessions of different nodes in the first node group correspond to the same access network device and different UPFs; or the PDU sessions of different nodes in the first node group correspond to different access network devices and the same UPF; or the PDU sessions of different nodes in the first node group correspond to different access network devices and different UPFs.

[0303] In some embodiments of the present application, the QoS parameters of the service flow of the first node include guaranteed bit rate (GBR) and / or maximum bit rate (MBR), and the QoS parameters of the QoS flow of the first node include guaranteed flow bit rate (GFBR) and / or maximum flow bit rate (MFBR).

[0304] It should be understood that the apparatus embodiments and the method embodiments can correspond to each other, and similar descriptions can refer to the method embodiments. Specifically, the session management network element 810, the policy control network element 820, the access and mobility management network element 830, and the access network device 840 involved above can correspond to the corresponding entities in the method for implementing the embodiments of the present application, and the foregoing and other operations and / or functions of each unit in the session management network element 810, the policy control network element 820, the access and mobility management network element 830, and the access network device 840 involved above are respectively for implementing the corresponding processes in each method. For the sake of brevity, they will not be described in detail here.

[0305] In the above, the communication device according to the embodiments of the present application has been described from the perspective of functional modules. It should be understood that the functional modules can be implemented in the form of hardware, or in the form of instructions in software, or in a combination of hardware and software modules.

[0306] Specifically, each step of the method embodiments in the embodiments of the present application can be completed by the integrated logic circuit in the hardware in the processor and / or instructions in the form of software. The steps of the method disclosed in combination with the embodiments of the present application can be directly embodied as being executed and completed by the hardware decoding processor, or executed and completed by a combination of the hardware and software modules in the decoding processor.

[0307] Optionally, the software module can be located in a mature storage medium in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, an electrically erasable programmable memory, a register, etc. This storage medium is located in the memory, and the processor reads the information in the memory and combines its hardware to complete the steps in the above method embodiments.

[0308] For example, the processing unit and the communication unit involved above can be implemented by a processor and a transceiver respectively.

[0309] Figure 22 FIG. is a schematic structural diagram of a communication device 900 according to an embodiment of the present application.

[0310] As Figure 22 shown, the communication device 900 may include a processor 910.

[0311] Among them, the processor 910 can call and run a computer program from the memory to implement the method in the embodiments of the present application.

[0312] Please continue to refer to Figure 22 , the communication device 900 may further include a memory 920.

[0313] Among them, the memory 920 can be used to store indication information, and can also be used to store codes, instructions, etc. executed by the processor 910. Among them, the processor 910 can call and run a computer program from the memory 920 to implement the method in the embodiments of the present application. The memory 920 can be a separate device independent of the processor 910, or can be integrated in the processor 910.

[0314] Please continue to refer to Figure 22 , the communication device 900 may further include a transceiver 930.

[0315] Among them, the processor 910 can control the transceiver 930 to communicate with other devices. Specifically, it can send information or data to other devices, or receive information or data sent by other devices. The transceiver 930 can include a transmitter and a receiver. The transceiver 930 can further include an antenna, and the number of antennas can be one or more.

[0316] It should be understood that the components in the communication device 900 are connected through a bus system. Among them, the bus system includes not only a data bus, but also a power bus, a control bus, and a status signal bus.

[0317] It should also be understood that the communication device 900 can be the terminal device of the embodiment of the present application, and the communication device 900 can implement the corresponding processes implemented by the session management network element, the policy control network element, the access and mobility management network element, or the access network device in the various methods of the embodiment of the present application. That is to say, the communication device 900 of the embodiment of the present application can correspond to the session management network element 810, the policy control network element 820, the access and mobility management network element 830, and the access network device 840 mentioned above, and can correspond to the corresponding entities executing the methods according to the embodiments of the present application. Among them, the transceiver 930 can correspond to implement the operations and / or functions implemented by the sending unit 822 in the policy control network element 820, the receiving unit 831 in the access and mobility management network element 830, or the obtaining unit 841 in the access network device 840 at this time. The processor 910 can correspond to implement the operations and / or functions implemented by the determining unit 811 in the session management network element 810, the determining unit 821 in the policy control network element 820, or the processing unit 842 in the access network device 840 at this time. For the sake of brevity, it will not be elaborated here.

[0318] In addition, an integrated circuit chip is provided in the embodiment of the present application.

[0319] For example, the chip may be an integrated circuit chip with signal processing capabilities, and can implement or execute the various methods, steps, and logic block diagrams disclosed in the embodiments of the present application. The chip can also be called a system-on-chip, a system chip, a chip system, or a system-on-chip. Optionally, the chip can be applied to various communication devices, so that the communication device installed with the chip can execute the various methods, steps, and logic block diagrams disclosed in the embodiments of the present application.

[0320] Figure 22 It is a schematic structural diagram of the chip 1000 according to the embodiment of the present application.

[0321] As Figure 22 shown, the chip 1000 includes a processor 1010.

[0322] Among them, the processor 1010 can call and run a computer program from the memory to implement the method in the embodiments of the present application.

[0323] Please continue to refer to Figure 22 , and the chip 1000 may further include a memory 1020.

[0324] Among them, the processor 1010 can call and run a computer program from the memory 1020 to implement the method in the embodiments of the present application. The memory 1020 can be used to store indication information, and can also be used to store code, instructions, etc. executed by the processor 1010. The memory 1020 can be a separate device independent of the processor 1010, or can be integrated in the processor 1010.

[0325] Please continue to refer to Figure 22 , and the chip 1000 may further include an input interface 1030.

[0326] Among them, the processor 1010 can control the input interface 1030 to communicate with other devices or chips. Specifically, it can obtain information or data sent by other devices or chips.

[0327] Please continue to refer to Figure 22 , and the chip 1000 may further include an output interface 1040.

[0328] Among them, the processor 1010 can control the output interface 1040 to communicate with other devices or chips. Specifically, it can output information or data to other devices or chips.

[0329] It should be understood that the chip 1000 can be applied to the session management network element, policy control network element, access and mobility management network element or access network device in the embodiments of the present application, and the chip can implement the corresponding processes implemented by the session management network element, policy control network element, access and mobility management network element or access network device in the various methods of the embodiments of the present application. For the sake of brevity, it will not be elaborated here.

[0330] It should also be understood that the various components in the chip 1000 are connected through a bus system. Among them, the bus system includes, in addition to the data bus, a power bus, a control bus, and a status signal bus.

[0331] The processors mentioned above may include, but are not limited to:

[0332] General-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field programmable gate arrays (FPGAs) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc.

[0333] The processor can be used to implement or execute the various methods, steps and logic block diagrams disclosed in the embodiments of the present application. The steps of the method disclosed in combination with the embodiments of the present application can be directly embodied as being executed and completed by a hardware decoding processor, or executed and completed by a combination of hardware and software modules in the decoding processor. The software module can be located in a mature storage medium in the art such as random access memory, flash memory, read-only memory, programmable read-only memory or erasable programmable memory, register, etc. This storage medium is located in the memory, and the processor reads the information in the memory and combines its hardware to complete the steps of the above method.

[0334] The memory mentioned above includes but is not limited to:

[0335] Volatile memory and / or non-volatile memory. Among them, the non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM) or flash memory. The volatile memory can be random access memory (RAM), which is used as an external cache. By way of example but not limitation, many forms of RAM are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM) and direct rambus random access memory (DR RAM).

[0336] It should be noted that the memories described herein are intended to include these and any other suitable types of memories.

[0337] An embodiment of the present application also provides a computer-readable storage medium for storing a computer program. The computer-readable storage medium stores one or more programs, and the one or more programs include instructions that, when executed by a portable electronic device including a plurality of application programs, enable the portable electronic device to execute the methods of the method embodiments.

[0338] Optionally, the computer-readable storage medium can be applied to the session management network element, policy control network element, access and mobility management network element, or access network device in the embodiments of the present application, and the computer program enables the computer to execute the corresponding processes implemented by the corresponding execution entities in the various methods of the embodiments of the present application. For the sake of brevity, details are not described herein again.

[0339] An embodiment of the present application also provides a computer program product including a computer program.

[0340] Optionally, the computer program product can be applied to the session management network element, policy control network element, access and mobility management network element, or access network device in the embodiments of the present application, and the computer program enables the computer to execute the corresponding processes implemented by the corresponding execution entities in the various methods of the embodiments of the present application. For the sake of brevity, details are not described herein again.

[0341] An embodiment of the present application also provides a computer program. When the computer program is executed by a computer, it enables the computer to execute the methods of the method embodiments.

[0342] Optionally, the computer program can be applied to the session management network element, policy control network element, access and mobility management network element, or access network device in the embodiments of the present application. When the computer program runs on a computer, it enables the computer to execute the corresponding processes implemented by the corresponding execution entities in the various methods of the embodiments of the present application. For the sake of brevity, details are not described herein again.

[0343] In addition, an embodiment of the present application further provides a communication system, which may include the terminal device and network device involved above to form a communication system as shown in Figure 1 For the sake of brevity, details are not described herein again. It should be noted that terms such as "system" in this article may also be referred to as "network management architecture" or "network system", etc.

[0344] It should also be understood that the terms used in the embodiments of the present application and the appended claims are only for the purpose of describing specific embodiments and are not intended to limit the embodiments of the present application. For example, the singular forms "a", "the", "above-mentioned" and "this" used in the embodiments of the present application and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise.

[0345] Those skilled in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods for each specific application to implement the described functions, but such implementation should not be considered to exceed the scope of the embodiments of the present application.

[0346] If it is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiments of the present application, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in the embodiments of the present application. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories, random access memories, magnetic disks, or optical discs that can store program codes.

[0347] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the systems, devices, and units described above can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein.

[0348] In several embodiments provided by the present application, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. For example, the division of units, modules, or components in the device embodiments described above is only a logical functional division, and there can be other division methods in actual implementation. For example, multiple units, modules, or components can be combined or integrated into another system, or some units, modules, or components can be omitted or not executed. Again, for example, the units / modules / components described as separate / display components may or may not be physically separated, that is, they can be located in one place or distributed to multiple network units. Part or all of the units / modules / components can be selected according to actual needs to achieve the purpose of the embodiments of the present application.

[0349] The above content is only the specific implementation manner of the embodiments of the present application. However, the protection scope of the embodiments of the present application is not limited thereto. Any person skilled in the art within the technical scope disclosed by the embodiments of the present application can easily think of changes or substitutions, which should all be covered within the protection scope of the embodiments of the present application. Therefore, the protection scope of the embodiments of the present application shall be subject to the protection scope of the claims.

Claims

1. A wireless communication method, characterized in that, the method is applicable to a session management network element, and the method includes: determining QoS parameters of a QoS flow of a first node in a first node group, where the QoS parameters of the QoS flow of the first node are determined according to the QoS parameters of the first node group, and the QoS parameters of the first node group include a group maximum rate (Group-MBR), and the Group-MBR is the maximum value that can be reached by the sum of the MBRs of the QoS flows corresponding to the same task of the first node group.

2. The method according to claim 1, characterized in that, the first node group includes nodes for the same task.

3. The method according to claim 2, characterized in that, the same task includes a transmission task of model training parameters and / or a download task of a global model using the same network slice; and / or, the same task includes a transmission task of model training parameters and / or a download task of a global model for the same model.

4. The method according to claim 2 or 3, characterized in that, one node in the first node group corresponds to one protocol data unit (PDU) session, and the one PDU session is used to carry at least one QoS flow, and the QoS parameters of the first node group include the sum of the QoS parameters of the QoS flows corresponding to the same task in the QoS flows carried by the PDU sessions of the first node group.

5. The method according to any one of claims 1 to 3, characterized in that, the QoS parameters of the first node group further include a group minimum guaranteed rate (Group-GBR); the Group-GBR is the sum of the GBRs of the QoS flows corresponding to the same task of the first node group; or, the Group-GBR is the maximum value that can be reached by the sum of the GBRs of the QoS flows corresponding to the same task of the first node group.

6. The method according to any one of claims 1 to 3, characterized in that, the PDU sessions of different nodes in the first node group correspond to the same access network device and correspond to the same user plane function (UPF); or the PDU sessions of different nodes in the first node group correspond to the same access network device and correspond to different UPFs; or the PDU sessions of different nodes in the first node group correspond to different access network devices and correspond to the same UPF; or the PDU sessions of different nodes in the first node group correspond to different access network devices and correspond to different UPFs.

7. The method according to any one of claims 1 to 3, characterized in that, the method further includes: determining the policy control network element of the first node, where the policy control network element of the first node is the same as or different from the policy control network elements of other nodes, and the other nodes include the nodes in the first node group except the first node.

8. The method according to claim 7, characterized in that, the session management network element of the first node is the same as the session management network elements of other nodes, and the policy control network element of the first node is the same as or different from the policy control network elements of other nodes.

9. The method according to claim 7, wherein, the session management network element of the first node is different from that of the other nodes, and the policy control network element of the first node is the same as that of the other nodes.

10. The method according to any one of claims 1 to 3, wherein, determining the QoS parameters of the QoS flow of the first node in the first node group includes: when the QoS parameters of the first node group are fixed, determining the QoS parameters of the QoS flow of the first node according to the number of nodes in the first node group and the QoS parameters of the first node group.

11. The method according to any one of claims 1 to 3, wherein, determining the QoS parameters of the QoS flow of the first node in the first node group includes: receiving the QoS parameters of the traffic flow of the first node sent by the policy control network element; determining the QoS parameters of the QoS flow of the first node based on the QoS parameters of the traffic flow of the first node.

12. The method according to any one of claims 1 to 3, wherein, the method further includes: receiving the QoS parameters of the first node group sent by the Unified Data Management (UDM).

13. The method according to claim 12, wherein, receiving the QoS parameters of the first node group sent by the UDM includes: when the session to be established by the first node is a session for performing federated learning, receiving the QoS parameters of the first node group sent by the UDM.

14. The method according to any one of claims 1 to 3, wherein, the method further includes: sending a session establishment or update request to the policy control network element, where the establishment or update request includes the QoS parameters of the first node group.

15. The method according to claim 11, wherein, the QoS parameters of the traffic flow of the first node include the Guaranteed Bit Rate (GBR) and / or the Maximum Bit Rate (MBR), and the QoS parameters of the QoS flow of the first node include the Guaranteed Flow Bit Rate (GFBR) and / or the Maximum Flow Bit Rate (MFBR).

16. The method according to any one of claims 1 to 3, wherein, determining the QoS parameters of the QoS flow of the first node in the first node group includes: determining the QoS parameters of the QoS flow of the first node for the session establishment process and / or the session modification process.

17. The method according to any one of claims 1 to 3, wherein, the method further includes: sending the QoS parameters of the first node group.

18. A wireless communication method, wherein, the method is applicable to a policy control network element, and the method includes: Determine the QoS parameters of the traffic flow of the first node in the first node group according to the QoS parameters of the first node group. The QoS parameters of the first node group include the group maximum rate Group-MBR, and the Group-MBR is the maximum value that can be reached by the sum of the MBRs of the QoS flows corresponding to the same task in the first node group. Send the QoS parameters of the traffic flow of the first node to the session management network element.

19. The method according to claim 18, wherein, the first node group includes nodes for the same task.

20. The method according to claim 19, wherein, the same task includes a transmission task of model training parameters and / or a download task of a global model using the same network slice; and / or, the same task includes a transmission task of model training parameters and / or a download task of a global model for the same model.

21. The method according to claim 19 or 20, wherein, one node in the first node group corresponds to one protocol data unit PDU session, and the one PDU session is used to carry at least one quality of service QoS flow. The QoS parameters of the first node group include the sum of the QoS parameters of the QoS flows corresponding to the same task in the QoS flows carried by the PDU sessions of the first node group.

22. The method according to any one of claims 18 to 20, wherein, the QoS parameters of the first node group include the group minimum guaranteed rate Group-GBR; the Group-GBR is the sum of the GBRs of the QoS flows corresponding to the same task in the first node group; or, the Group-GBR is the maximum value that can be reached by the sum of the GBRs of the QoS flows corresponding to the same task in the first node group.

23. The method according to any one of claims 18 to 20, wherein, the PDU sessions of different nodes in the first node group correspond to the same access network device and correspond to the same user plane function UPF; or the PDU sessions of different nodes in the first node group correspond to the same access network device and correspond to different UPFs; or the PDU sessions of different nodes in the first node group correspond to different access network devices and correspond to the same UPF; or the PDU sessions of different nodes in the first node group correspond to different access network devices and correspond to different UPFs.

24. The method according to any one of claims 18 to 20, wherein, the policy control network element of the first node is the same as or different from the policy control network elements of other nodes, and the other nodes include the nodes in the first node group except the first node.

25. The method according to claim 24, wherein, the session management network element of the first node is the same as the session management network elements of other nodes, and the policy control network element of the first node is the same as or different from the policy control network elements of other nodes.

26. The method according to claim 24, wherein, The session management network element of the first node is different from that of the other nodes, and the policy control network element of the first node is the same as that of the other nodes.

27. The method according to any one of claims 18 to 20, wherein, determining the QoS parameter of the traffic flow of the first node in the first node group according to the QoS parameter of the first node group includes: When the QoS parameter of the first node group is fixed, determining the QoS parameter of the traffic flow of the first node for the session establishment process according to the number of nodes in the first node group and the QoS parameter of the first node group.

28. The method according to any one of claims 18 to 20, wherein, determining the QoS parameter of the traffic flow of the first node in the first node group according to the QoS parameter of the first node group includes: Obtaining first indication information for indicating the data processing capabilities of the nodes in the first node group; When the QoS parameter of the first node group is fixed, determining the QoS parameter of the traffic flow of the first node for the session modification process according to the number of nodes in the first node group, the QoS parameter of the first node group, and the first indication information.

29. The method according to claim 28, wherein, the first indication information includes the time for the nodes in the first node group to upload data.

30. The method according to claim 28, wherein, obtaining the first indication information includes: Receiving the first indication information sent by the server.

31. The method according to claim 28, wherein, the method further includes: Triggering a session modification process based on the first indication information.

32. The method according to any one of claims 18 to 20, wherein, the method further includes: Receiving a session establishment or update request sent by a session management network element, where the establishment or update request includes the QoS parameter of the first node group.

33. The method according to any one of claims 18 to 20, wherein, the QoS parameter of the traffic flow of the first node includes a guaranteed bit rate GBR and / or a maximum bit rate MBR, and the QoS parameter of the QoS flow of the first node includes a guaranteed flow bit rate GFBR and / or a maximum flow bit rate MFBR.

34. A session management network element, wherein, comprising: a determination unit configured to determine the QoS parameter of a QoS flow of a first node in a first node group, where the QoS parameter of the QoS flow of the first node is determined according to the QoS parameter of the first node group, and the QoS parameter of the first node group includes a group maximum bit rate Group-MBR, and the Group-MBR is the maximum value that can be reached by the sum of the MBRs of the QoS flows corresponding to the same task in the first node group.

35. A policy control network element, wherein, comprising: A determination unit, configured to determine the QoS parameter of the service flow of the first node in the first node group according to the QoS parameter of the first node group, where the QoS parameter of the first node group includes a group maximum rate Group-MBR, and the Group-MBR is the maximum value that can be reached by the sum of the MBRs of the QoS flows corresponding to the same task in the first node group; A sending unit, configured to send the QoS parameter of the service flow of the first node to a session management network element.

36. A session management network element, characterized in that, it includes: A processor and a memory, where the memory is used to store a computer program, and the processor is used to call and run the computer program stored in the memory to execute the method according to any one of claims 1 to 17.

37. A policy control network element, characterized in that, it includes: A processor and a memory, where the memory is used to store a computer program, and the processor is used to call and run the computer program stored in the memory to execute the method according to any one of claims 18 to 33.

38. A chip, characterized in that, it includes: A processor, configured to call and run a computer program from a memory, so that a device installed with the chip executes the method according to any one of claims 1 to 17 or the method according to any one of claims 18 to 33.

39. A computer-readable storage medium, characterized in that, it is used to store a computer program, and the computer program enables a computer to execute the method according to any one of claims 1 to 17 or the method according to any one of claims 18 to 33.

40. A computer program product, characterized in that, it includes computer program instructions, and the computer program instructions enable a computer to execute the method according to any one of claims 1 to 17 or the method according to any one of claims 18 to 33.

Images