Method for supporting ai / ML functions for wireless communication, apparatus, and computer-readable medium
The framework supports AI/ML functions in wireless communication by optimizing network slicing through data collection and reporting, addressing the challenge of resource allocation and enhancing performance and utilization.
Patent Information
- Application Number
- PCT/CN2024/075468
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2024-02-02
- Publication Date
- 2025-08-07
AI Technical Summary
Current wireless communication technologies lack effective methods for optimizing the allocation of time and frequency resources, particularly in network slicing, to support artificial intelligence and machine learning (AI/ML) functions across different communication nodes.
A framework for wireless communication that includes data collection and reporting mechanisms between communication nodes to support AI/ML functions, utilizing AI/ML model training and inference for intelligent resource allocation, specifically through data requests and reports that include predicted resource usage, UE registration, and capacity information.
Enhances network slicing optimization by enabling dynamic and optimal resource allocation, improving performance and resource utilization through AI/ML-based decision-making.
Smart Images

Figure CN2024075468_07082025_PF_FP_ABST
Abstract
Description
METHOD FOR SUPPORTING AI / ML FUNCTIONS FOR WIRELESS COMMUNICATION, APPARATUS, AND COMPUTER-READABLE MEDIUMTECHNICAL FIELD
[0001] This disclosure is generally related to wireless communication, and more particularly to data collection to support an artificial intelligence / machine learning logic for wireless communication.BACKGROUND
[0002] Wireless communication technologies are pivotal components of the increasingly interconnecting global communication networks. Wireless communications rely on accurately allocated time and frequency resources for transmitting and receiving wireless signals. Therefore, how to optimize the allocation of time or frequency resources, such as network slices, has been a topic for the technicians in this field.SUMMARY
[0003] This summary is a brief description of certain aspects of this disclosure. It is not intended to limit the scope of this disclosure.
[0004] According to some embodiments of this disclosure, a wireless communication method is disclosed. The method includes sending, from a first communication node to a second communication node, a data request for supporting an artificial intelligence or machine learning (AI / ML) function of the first communication node; and receiving, by the first communication node from the second communication node, a data report in response to the data request. The data request indicates at least one of: a requested assistance information indication, indicating requested information; a type indication of requested assistance information, indicating the type of requested assistance information; a cell ID (identification) of a cellular network corresponding to the AI / ML function; a PLMN (Public Land Mobile Network) ID corresponding to the AI / ML function; S-NSSAI (Network Slice Selection Assistance Information) ; an SST (Slice / Service Type) field; an NSI (Network Slice Instance) ID; or a reporting periodicity.
[0005] According to some embodiments of this disclosure, another wireless communication method is disclosed. The method includes sending, from a first communication node to a second communication node, a data request for supporting an artificial intelligence or machine learning (AI / ML) function of the first communication node; and receiving, by the first communication node from the second communication node, a data report in response to the data request. The data request includes a requested assistance information indication, wherein the requested assistance information indication indicates requested information, including one or more of: a per-node or per-cell predicted resource usage status of a network slice; a per-node or per-cell predicted number of UE registration of a network slice; a per-node or per-cell predicted number of session establishment of a network slice; a predicted average ratio of successful PDU session setup of a network slice; a predicted relative AMF capacity; a prediction confidence; a per-node or per-cell resource usage status of a network slice; a per-node or per-cell number of UE registration of a network slice; a per-node or per-cell number of session establishment of a network slice; an average ratio of successful PDU session setup of a network slice; or a relative AMF capacity.
[0006] According to some embodiments of this disclosure, another wireless communication method is disclosed. The method includes sending, from a first communication node to a second communication node, a data request for supporting an artificial intelligence or machine learning (AI / ML) function of the first communication node; and receiving, by the first communication node from the second communication node, a data report in response to the data request. The data report includes one or more pieces of the following information, including: a per-node or per-cell predicted resource usage status of a network slice; a per-node or per-cell predicted number of UE registration of a network slice; a per-node or per-cell predicted number of session establishment of a network slice; a predicted average ratio of successful PDU session setup of a network slice; a predicted relative AMF capacity; a prediction confidence; a per-node or per-cell resource usage status of a network slice; a per-node or per-cell number of UE registration of a network slice; a per-node or per-cell number of session establishment of a network slice; an average ratio of successful PDU session setup of a network slice; or a relative AMF capacity.
[0007] Still another embodiment of this disclosure provides a wireless communication apparatus, including one or more memory units storing one or more programs and one or more processors electrically coupled to the one or more memory units and configured to execute the one or more programs to perform any method or step or their combinations or sub-combinations in this disclosure.
[0008] Still another embodiment of this disclosure provides non-transitory computer-readable storage medium, storing one or more programs, the one or more programs being configured to, when performed by at least one processor, cause to perform any method or step or their combinations or sub-combinations in this disclosure.
[0009] According to some embodiments of this disclosure, one or more wireless communication methods are further disclosed, the methods include combinations of certain methods, aspects, elements, and steps (either in a generic view or specific view) disclosed in the various embodiments of this disclosure.
[0010] The above and other aspects and their implementations are described in greater detail in the drawings, the descriptions, and the claims.BRIEF DESCRIPTION OF THE DRAWINGS
[0011] Various exemplary embodiments of the present disclosure are described in detail below with reference to the following drawings. The drawings are provided for purposes of illustration only and merely depict exemplary embodiments of the present disclosure to facilitate the understanding of the present disclosure. Therefore, the drawings should not be considered as limiting of the breadth, scope, or applicability of the present disclosure. It should be noted that for clarity and ease of illustration these drawings are not necessarily drawn to scale.
[0012] FIG. 1 shows a framework of an intelligent slice resource management system;
[0013] FIGS. 2A to 2D show exemplary arrangements of AI / ML functions for wireless communication applications;
[0014] FIG. 3 shows an exemplary communication operation between a RAN node and a CN;
[0015] FIG. 4 shows another exemplary communication operation between a RAN node and a CN;
[0016] FIG. 5 shows another exemplary communication operation between a RAN node and a CN with PDU containers;
[0017] FIG. 6 shows another exemplary communication operation between a RAN node and a CN with PDU containers;
[0018] FIG. 7 shows an exemplary communication operation between a gNB-CU node and a gNB-DU;
[0019] FIG. 8 shows an exemplary communication operation between a RAN node and another RAN node; and
[0020] FIG. 9 shows a wireless communication system structure.DETAILED DESCRIPTION
[0021] A RAN (Random Access Network) with AI / ML (Artificial Intelligence and Machine Learning) functions and logic is under development. For example, there can be, for example, three AI / ML-based use cases, such as AI / ML-based Load Balancing, AI / ML-based Mobility Optimization, and AI / ML-based Network Energy Saving. Additionally, network slicing can be improved with AI / ML logics in order to help a network optimizes the resource allocation for network slicing. For example, AI / ML models can make intelligent decisions on how to allocate resources to certain UEs among different slices dynamically, including the scenarios of non-mobility and mobility applications, which ensures optimal performance and resource utilization to fulfill the requirement of an SLA (Service Level Agreement) .
[0022] In addition to the support for AI / ML functions on a RAN (Radio Access Network) side (such as a base station implemented with the RAN) , a CN (Core Network) can also possess AI / ML capabilities, such as a Network Data Analytics Function (NWDAF) . However, the details to implement such application are currently in a vacuum.
[0023] This disclosure provides solutions regarding coordination among different communication nodes, such as NG-RAN nodes and a CN, including split architectures or non-split architectures, to support AI / ML-based network applications, such as network slicing. This disclosure improves the network slicing optimization, so as to improve the determining of the optimal placement of network slices and allocate resources.
[0024] FIG. 1 shows a framework of intelligent slice resource management system. The intelligent slice resource management system includes a data collector, a model trainer (or training circuitry) , an inference unit (inference logic or circuitry) , and a function actor. The data collector is configured to receive feedback information from the actor and provide input data to the model trainer and model inference unit. On the other hand, the model trainer performs model training, such as training of artificial intelligent (AI) or machine learning (ML) models, validation, and testing. The action can generate model performance metrics as a part of the model testing procedure. As example, the training can include reinforcement learning, unsupervised learning, supervised learning, transfer learning, semi-supervised learning, or self-supervised learning. AI / ML inference may generally include a model or algorithm that represents the knowledge or patterns learned from data. The training done by the trainer can be used to prepare the model. The inference data can be fed into the model from the data collector to produce an output or prediction. The AI / ML model here may include at least one of decision trees, support vector machines, artificial neural networks, ensemble models, generative models, reinforcement leaning models, and / or probabilistic models, to name a few.
[0025] The inference unit (or inference logic or circuitry) is configured to provide an AI / ML model inference output based on the inference data provided by the data collector. The output can be predictive. The inference may include online / real-time inference, batch inference, and edge inference, for example. The output of the model inference unit may include one or more policies, rules, or guidance for an actor, such as a core network or a base station. The actor uses such one or more policies, rules, or guidance to allocate the slice resources of the communication system. In addition, the actor is configured to monitor the performance of enforcing the output of the model inference unit and feedback related information to the data collector for the future training.
[0026] According to some examples as shown in FIG. 2A, the AI / ML model trainer can be located in an OAM (operations, administration, and management function) of a core network (CN) . The AI / ML modal inference can be done at the gNB, like a base station (BS) .
[0027] Alternatively or additionally, as shown in FIG. 2B, the AI / ML model training and AI / ML model inference can be both located in the gNB. Additionally, the gNB can be also allowed to continue the model training based on AI / ML model trained in the OAM. Alternatively or additionally, as shown in FIG. 2C, in which the RAN node is split to have a CU-DU split architecture, there can be different arrangements. For example, the AI / ML model training is located in the OAM, and the AI / ML model inference is located in the gNB-CU. Alternatively or additionally as shown FIG. 2D, the AI / ML model training and model inference are both located in the gNB-CU. The above disclosure regarding AI or ML functions can be implemented or used by the following examples in this disclosure for any application of AI / ML functions.
[0028] To support AI / ML-based resource allocation, such as Load Balancing, Mobility Optimization, and Network Energy Saving, at least one of the following information can be configured to be reported by an NG-RAN node, including predicted resource status information, UE performance feedback, a measured UE trajectory, or an energy cost (EC) . For example, the collection and reporting can be configured through a data collection reporting initiation procedure, while the actual reporting can be performed through a data collection reporting procedure.
[0029] According to some examples, a wireless communication method is disclosed. The method includes sending, from a first communication node to a second communication node, a data request for an artificial intelligence or machine learning (AI / ML) function of the first communication node; and receiving, by the first communication node from the second communication node, a data report in response to the data request. For example, the first communication node is a RAN (random access network) node and the second communication node is a core network. Alternatively, the first communication node is a core network and the second communication node is a RAN node. Alternatively, the first communication node is a central unit of a base station and the second communication node is a distributed unit of a base station. Alternatively, the first communication node is a RAN node and the second communication node is another RAN node.
[0030] According to some examples, the data request indicates at least one of the following information, including a requested assistance information indication, which indicates requested information; a type indication of requested assistance information, which indicates the type of requested information; a cell ID (identification) of a cellular network corresponding to the AI / ML function; a PLMN (Public Land Mobile Network) ID corresponding to the AI / ML function; S-NSSAI (Network Slice Selection Assistance Information) ; an SST (Slice / Service Type) field; an NSI ID (Network Slice Instance) ; or a reporting periodicity.
[0031] According to some examples, the requested information includes at least one of a per-node or per-cell predicted resource usage status of a network slice; a per-node or per-cell predicted number of UE registration of a network slice; a per-node or per-cell predicted number of session establishment of a network slice; a predicted average ratio of successful PDU session setup of a network slice; a predicted relative AMF capacity; a prediction confidence; a per-node or per-cell resource usage status of a network slice; a per-node or per-cell number of UE registration of a network slice; a per-node or per-cell number of session establishment of a network slice; an average ratio of successful PDU session setup of a network slice; or a relative AMF capacity.
[0032] FIG. 3 shows an exemplary communication operation between a RAN node and a CN. In this example, the CN (core network) provides the assistance information to NG-RAN node 1 upon a request to support an AI / ML function via the data collection request and the data collection report. For example, at S11, the NG-RAN node 1 triggers or sends the data collection request to the CN to request the assistance information to support an AI / ML function. The data collection request may indicate at least one of the following information, including a requested assistance information indication; a type of requested assistance information; a cell ID (identification) of a cellular network corresponding to the AI / ML function; a PLMN (Public Land Mobile Network) ID corresponding to an AI / ML function; S-NSSAI (Network Slice Selection Assistance Information) ; an SST (Slice / Service Type) field; an NSI ID (Network Slice Instance) ; or a reporting periodicity.
[0033] For example, the requested assistance information indication may indicate the requested information. The kinds of assistance information requested by the node to support an AI / ML function may include predicted information, measured information, evaluated information, statistical information, and / or collected information. The requested information may be associated with a particular network, a particular node, a particular cell, and / or a particular network slice of a particular node. In some cases, the CN (or the data provider) may also have some inference functions that can make a prediction of certain information. Therefore, the NG-RAN node 1 can request some predicted information from the CN. The predicted information can be used by the NG-RAN node 1 to support some AI / ML functions. For example, the function can be used by the receiver of the data to make inference. The data can also be used by the data receiver to guide their action.
[0034] For example, the requested information by the NG-RAN node 1, as indicated in the request, may include at least one of a per-node or per-cell predicted resource usage status of a network slice; a per-node or per-cell predicted number of UE registration of a network slice; a per-node or per-cell predicted number of session establishment of a network slice; a predicted average ratio of successful PDU session setup of a network slice; a predicted relative AMF capacity; a prediction confidence; a per-node or per-cell resource usage status of a network slice; a per-node or per-cell number of UE registration of a network slice; a per-node or per-cell number of session establishment of a network slice; an average ratio of successful PDU session setup of a network slice; or a relative AMF capacity.
[0035] Exemplarily, the resource usage status of a network slice indicates usage of PRBs (Physical Resource Block) of a network slice. The number of UE registration may, for example, indicate a total number of user equipment registered at a certain device, network, cell, or a certain network slice. The number of session establishment may, for example, indicate the number of sessions established at a certain network slice. The average ratio of successful PDU session setup may, for example, indicate an average ratio of successful setup PDU sessions over PDU sessions that can be set up to a certain network slice. The relative AMF capacity may represent an available capacity of an AMF (Access and Mobility Management Function) . The prediction confidence may be associated with one or more reported predicted values. The prediction confidence may, for example, represent the confidence of the predicted values. As explained above, the reported information may be an actual measured and / or collected information, and alternative, the reported information can be a predicted value.
[0036] On the other hand, the type of requested assistance information can, for example be used to indicate the type or categories of the requested information. The cell ID (identification) of a cellular network may be used to represent the cell corresponding to the AI / ML function to be supported or to indicate the requested information corresponds to which cell. The PLMN (Public Land Mobile Network) ID corresponding to the AI / ML function may represent an ID of the PLMN corresponding to a certain AI / ML function. The S-NSSAI (Network Slice Selection Assistance Information) can be used to uniquely identify a Network Slice. The S-NSSAI may contain two components, including the SST (Slice / Service Type) and an optional SD (Slice Differentiator) . The SST (Slice / Service Type) field may be used to represent a type of a certain slice and service type. The NSI (Network Slice Instance) ID can be used to identify a certain NSI for which the requested information is requested. The reporting periodicity may be used to indicate how often (such as the frequency or the period) the data providers should report the requested data.
[0037] At S12, according to the data collection request, the CN sends the NG-RAN Node 1 a data collection report. The data collection report may include data or information collected according to the data collection request. For example, the data or information provided by the CN in the data collection report may include at least some assistance information for supporting AI / ML function. For example, the data or information provided by the CN in the data collection report may include at least one of: a per-node or per-cell predicted resource usage status of a network slice; a per-node or per-cell predicted number of UE registration of a network slice; a per-node or per-cell predicted number of session establishment of a network slice; a predicted average ratio of successful PDU session setup of a network slice; a predicted relative AMF capacity; a prediction confidence; a per-node or per-cell resource usage status of a network slice; a per-node or per-cell number of UE registration of a network slice; a per-node or per-cell number of session establishment of a network slice; an average ratio of successful PDU session setup of a network slice; or a relative AMF capacity. The collected data or information in the data collection report may include predicted information, measured information, evaluated information, statistical information, and / or collected information.
[0038] At S13, the data requester, the NG-RAN Node 1, receives the data or information in the data collection report. Then, at S14, the data receiver, the NG-RAN Node 1, may use the received data or information from the data collection report to support an AI / ML function. For example, the AI / ML function may include training for one or more AI / ML models located at NG-RAN Node 1, performing AI / ML inference according to one or more AI / ML models located at NG-RAN Node 1, performing AI / ML model evaluation according to one or more AI / ML models located at NG-RAN Node 1, or conducting wireless communication according to the AI / ML function’s output data included in the data collection report.
[0039] FIG. 4 shows another exemplary communication operation between a RAN node and a CN. The key difference here is that the CN becomes the data requester for assistance information for an AI / ML function and that the NG-RAN Node 1 becomes the data providers for the AI / ML function. The data collection request and the data collection report may include the same or the similar data or information as explained in the example associated with FIG. 3.
[0040] For example, at S21, the CN triggers the data collection request to the NG-RAN Node 1 to request the assistance information to support an AI / ML function. The data collection request may indicate at least one of the following information, including a requested assistance information indication; a type of requested assistance information; a cell ID (identification) of a cellular network corresponding to the AI / ML function; a PLMN (Public Land Mobile Network) ID corresponding to an AI / ML function; S-NSSAI (Network Slice Selection Assistance Information) ; an SST (Slice / Service Type) field; an NSI ID (Network Slice Instance) ; or a reporting periodicity.
[0041] For example, the requested assistance information indication may indicate the requested information. The kinds of assistance information requested by the node to support an AI / ML function may include predicted information, measured information, evaluated information, statistical information, and / or collected information. The requested information may be associated with a particular network, a particular node, a particular cell, and / or a particular network slice of a particular node. In some cases, the NG-RAN Node 1 (or the data provider) may also have some inference function that can make a prediction of certain information. Therefore, the CN can request some predicted information from the NG-RAN Node 1. The predicted information can be used by the CN to support some AI / ML functions. For example, the function can be used by the receiver of the data to make inference. The data can also be used by the data receiver to guide their action.
[0042] For example, the requested information by the CN, as indicated in the request, may include at least one of a per-node or per-cell predicted resource usage status of a network slice; a per-node or per-cell predicted number of UE registration of a network slice; a per-node or per-cell predicted number of session establishment of a network slice; a predicted average ratio of successful PDU session setup of a network slice; a predicted relative AMF capacity; a prediction confidence; a per-node or per-cell resource usage status of a network slice; a per-node or per-cell number of UE registration of a network slice; a per-node or per-cell number of session establishment of a network slice; an average ratio of successful PDU session setup of a network slice; or a relative AMF capacity.
[0043] Exemplarily, resource usage status of a network slice indicates usage of PRBs of a network slice. The number of UE registration may, for example, indicate a total number of user equipment registered at a certain device, network, cell, or a certain network slice. The number of session establishment may, for example, indicate the number of sessions established at a certain network slice. The average ratio of successful PDU session setup may, for example, indicate an average ratio of successfully setup PDU sessions over PDU sessions that can be set up to a certain network slice. The relative AMF capacity may represent an available capacity of an AMF (Access and Mobility Management Function) . The prediction confidence may be associated with one or more reported predicted values. The prediction confidence may, for example, represent the confidence of the predicted values. As explained above, the reported information may be an actual measured or collected information, and alternative, the reported information can be a predicted value.
[0044] On the other hand, the type of requested assistance information can, for example be used to indicate the type or categories of the requested information. The cell ID (identification) of a cellular network may be used to represent the cell corresponding to the AI / ML function to be supported or to indicate the requested information corresponds to which cell. The PLMN (Public Land Mobile Network) ID corresponding to the AI / ML function may represent an ID of the PLMN corresponding to a certain AI / ML function. The S-NSSAI (Network Slice Selection Assistance Information) can be used to uniquely identify a Network Slice. The S-NSSAI may contain two components, including the SST (Slice / Service Type) and an optional SD (Slice Differentiator) . The SST (Slice / Service Type) field may be used to represent a type of a certain slice and service type. The NSI (Network Slice Instance) ID can be used to identify a certain NSI for which the requested information is requested. The reporting periodicity may be used to indicate how often (such as the frequency or the period) the data providers should report the requested data.
[0045] At S22, according to the data collection request, the NG-RAN Node 1 sends the CN a data collection report. The data collection report may include data or information collected according to the data collection request. For example, the data or information provided by the NG-RAN Node 1 in the data collection report may include at least some assistance information for supporting AI / ML function. For example, the data or information provided by the NG-RAN Node 1 in the data collection report may include at least one of: a per-node or per-cell predicted resource usage status of a network slice; a per-node or per-cell predicted number of UE registration of a network slice; a per-node or per-cell predicted number of session establishment of a network slice; a predicted average ratio of successful PDU session setup of a network slice; a predicted relative AMF capacity; a prediction confidence; a per-node or per-cell resource usage status of a network slice; a per-node or per-cell number of UE registration of a network slice; a per-node or per-cell number of session establishment of a network slice; an average ratio of successful PDU session setup of a network slice; or a relative AMF capacity. The collected data or information in the data collection report may include predicted information, measured information, evaluated information, statistical information, and / or collected information.
[0046] At S23, the data requester, the CN, receives the data or information in the data collection report. Then, at S24, the data receiver, the CN, may use the received data or information from the data collection report to support an AI / ML function. For example, the AI / ML function may include training for one or more AI / ML models located at the CN, performing AI / ML inference according to one or more AI / ML models located at the CN, performing AI / ML model evaluation according to one or more AI / ML models located at the CN, or conducting wireless communication according to the AI / ML function’s output data included in the data collection report.
[0047] FIG. 5 shows another exemplary communication operation between a RAN node and a CN. As compared to the examples in FIG. 3, the communication, including the data request and data collection report can be transmitted in one or more PDU containers. Unless states otherwise, all the disclosure related to FIG. 3 can be applicable to the example in FIG. 5, such as the information or data included in the data request (here in FIG. 5 denoted as data collection request message) and the data collection report (here in FIG. 5 denoted as data collection report message) . The explanation would not be repeated.
[0048] For example at S31, the NG-RAN node 1 invokes a N2 transport message towards the CN to request the transfer of a data collection report message for support of an AI / ML function. The message may include at least one of a PDU container and / or a NWDAF Correlation ID. Exemplarily, the PDU container may include an NG-RAN node –NWDAF (network data analytics function) message, for example, the data collection request message. The NWDAF Correlation ID can used to identify an NWDAF within the core network (CN) .
[0049] For example at S32, after the CN receives the data request message, the CN generates the requested information or data, such as predicted information or statistical information. The CN returns the N2 Transport message (data collection report message) to the NG-RAN node. The message may include at least one of a PDU container and / or a NWDAF Correlation ID. Exemplarily, the PDU container may include an NG-RAN node –NWDAF (network data analytics function) message, for example, the data collection response message. The NWDAF Correlation ID can used to identify an NWDAF within the core network (CN) .
[0050] The data collection request message may indicate at least one of the following information, including a requested assistance information indication; a type of requested assistance information; a cell ID (identification) of a cellular network corresponding to the AI / ML function; a PLMN (Public Land Mobile Network) ID corresponding to an AI / ML function; S-NSSAI (Network Slice Selection Assistance Information) ; an SST (Slice / Service Type) field; an NSI ID (Network Slice Instance) ; or a reporting periodicity.
[0051] For example, the requested assistance information indication may indicate the requested information. The kinds of assistance information requested by the node to support an AI / ML function may include predicted information, measured information, evaluated information, statistical information, and / or collected information. The requested information may be associated with a particular network, a particular node, a particular cell, and / or a particular network slice of a particular node. In some case, the CN (or the data provider) may also have some inference function that can make a prediction of certain information. Therefore, the NG-RAN node 1 can request some predicted information from the CN. The predicted information can be used by the NG-RAN node 1 to support some AI / ML functions. For example, the function can be used by the receiver of the data to make inference. The data can also be used by the data receiver to guide their action.
[0052] For example, the requested information by the NG-RAN node 1, as indicated in the request message, may include at least one of a per-node or per-cell predicted resource usage status of a network slice; a per-node or per-cell predicted number of UE registration of a network slice; a per-node or per-cell predicted number of session establishment of a network slice; a predicted average ratio of successful PDU session setup of a network slice; a predicted relative AMF capacity; a prediction confidence; a per-node or per-cell resource usage status of a network slice; a per-node or per-cell number of UE registration of a network slice; a per-node or per-cell number of session establishment of a network slice; an average ratio of successful PDU session setup of a network slice; or a relative AMF capacity.
[0053] On the other hand, the type of requested assistance information can, for example be used to indicate the type or categories of the requested information. The cell ID (identification) of a cellular network may be used to represent the cell corresponding to the AI / ML function to be supported or to indicate the requested information corresponds to which cell. The PLMN (Public Land Mobile Network) ID corresponding to the AI / ML function may represent an ID of the PLMN corresponding to a certain AI / ML function. The S-NSSAI (Network Slice Selection Assistance Information) can be used to uniquely identify a Network Slice. The S-NSSAI may contain two components, including the SST (Slice / Service Type) and an optional SD (Slice Differentiator) . The SST (Slice / Service Type) field may be used to represent a type of a certain slice and service type. The NSI (Network Slice Instance) ID can be used to identify a certain NSI for which the requested information is requested. The reporting periodicity may be used to indicate how often (such as the frequency or the period) the data providers should report the requested data.
[0054] The data collection report message may include data or information collected according to the data collection request. For example, the data or information provided by the CN in the data collection report message may include at least some assistance information for supporting AI / ML function. For example, the data or information provided by the CN in the data collection report message may include at least one of: a per-node or per-cell predicted resource usage status of a network slice; a per-node or per-cell predicted number of UE registration of a network slice; a per-node or per-cell predicted number of session establishment of a network slice; a predicted average ratio of successful PDU session setup of a network slice; a predicted relative AMF capacity; a prediction confidence; a per-node or per-cell resource usage status of a network slice; a per-node or per-cell number of UE registration of a network slice; a per-node or per-cell number of session establishment of a network slice; an average ratio of successful PDU session setup of a network slice; or a relative AMF capacity. The collected data or information in the data collection report message may include predicted information, measured information, evaluated information, statistical information, and / or collected information.
[0055] At S33, the data requester, the NG-RAN Node 1, receives the data or information in the data collection report message in one or more PDU containers. Then, at S34, the data receiver, the NG-RAN Node 1, may use the received data or information from the data collection report message to support an AI / ML function. For example, the AI / ML function may include training for one or more AI / ML models located at NG-RAN Node 1, performing AI / ML inference according to one or more AI / ML models located at NG-RAN Node 1, performing AI / ML model evaluation according to one or more AI / ML models located at NG-RAN Node 1, or conducting wireless communication according to the AI / ML function’s output data included in the data collection report.
[0056] FIG. 6 shows another exemplary communication operation between a RAN node and a CN. As compared to the examples in FIG. 4, the communication, including the data request and data collection report can be transmitted in one or more PDU containers here. Unless states otherwise, all the disclosure related to FIG. 4 can be applicable to the example in FIG. 6, such as the information or data included in the data request (here in FIG. 6 denoted as data collection request message) and the data collection report (here in FIG. 6 denoted as data collection report message) . The explanation would not be repeated.
[0057] For example at S41, the CN invokes a N2 transport message towards the NG-RAN Node 1to request the transfer of a data collection report message for support of an AI / ML function. The message may include at least one of a PDU container and / or a NWDAF Correlation ID. Exemplarily, the PDU container may include an NG-RAN node –NWDAF (network data analytics function) message, for example, the data collection request message. The NWDAF Correlation ID can used to identify an NWDAF within the core network (CN) .
[0058] For example at S42, after the NG-RAN Node 1receives the data request message, the NG-RAN Node 1generates the requested information or data, such as predicted information or statistical information. The NG-RAN Node 1returns the N2 Transport message (data collection report message) to the CN. The message may include at least one of a PDU container and / or a NWDAF Correlation ID. Exemplarily, the PDU container may include an NG-RAN node –NWDAF (network data analytics function) message, for example, the data collection response message. The NWDAF Correlation ID can used to identify an NWDAF within the core network (CN) .
[0059] The data collection request message may indicate at least one of the following information, including a requested assistance information indication; a type of requested assistance information; a cell ID (identification) of a cellular network corresponding to the AI / ML function; a PLMN (Public Land Mobile Network) ID corresponding to an AI / ML function; S-NSSAI (Network Slice Selection Assistance Information) ; an SST (Slice / Service Type) field; an NSI ID (Network Slice Instance) ; or a reporting periodicity.
[0060] For example, the requested assistance information indication may indicate the requested information. The kinds of assistance information requested by the node to support an AI / ML function may include predicted information, measured information, evaluated information, statistical information, and / or collected information. The requested information may be associated with a particular network, a particular node, a particular cell, and / or a particular network slice of a particular node. In some case, the NG-RAN Node 1 (or the data provider) may also have some inference function that can make a prediction of certain information. Therefore, the CN can request some predicted information from the NG-RAN Node 1. The predicted information can be used by the CN to support some AI / ML functions. For example, the function can be used by the receiver of the data to make inference. The data can also be used by the data receiver to guide their action.
[0061] For example, the requested information by the CN, as indicated in the request message, may include at least one of a per-node or per-cell predicted resource usage status of a network slice; a per-node or per-cell predicted number of UE registration of a network slice; a per-node or per-cell predicted number of session establishment of a network slice; a predicted average ratio of successful PDU session setup of a network slice; a predicted relative AMF capacity; a prediction confidence; a per-node or per-cell resource usage status of a network slice; a per-node or per-cell number of UE registration of a network slice; a per-node or per-cell number of session establishment of a network slice; an average ratio of successful PDU session setup of a network slice; or a relative AMF capacity.
[0062] On the other hand, the type of requested assistance information can, for example be used to indicate the type or categories of the requested information. The cell ID (identification) of a cellular network may be used to represent the cell corresponding to the AI / ML function to be supported or to indicate the requested information corresponds to which cell. The PLMN (Public Land Mobile Network) ID corresponding to the AI / ML function may represent an ID of the PLMN corresponding to a certain AI / ML function. The S-NSSAI (Network Slice Selection Assistance Information) can be used to uniquely identify a Network Slice. The S-NSSAI may contain two components, including the SST (Slice / Service Type) and an optional SD (Slice Differentiator) . The SST (Slice / Service Type) field may be used to represent a type of a certain slice and service type. The NSI (Network Slice Instance) ID can be used to identify a certain NSI for which the requested information is requested. The reporting periodicity may be used to indicate how often (such as the frequency or the period) the data providers should report the requested data.
[0063] The data collection report message may include data or information collected according to the data collection request. For example, the data or information provided by the NG-RAN Node 1 in the data collection report message may include at least some assistance information for supporting AI / ML function. For example, the data or information provided by the CN in the data collection report message may include at least one of: a per-node or per-cell predicted resource usage status of a network slice; a per-node or per-cell predicted number of UE registration of a network slice; a per-node or per-cell predicted number of session establishment of a network slice; a predicted average ratio of successful PDU session setup of a network slice; a predicted relative AMF capacity; a prediction confidence; a per-node or per-cell resource usage status of a network slice ; a per-node or per-cell number of UE registration of a network slice; a per-node or per-cell number of session establishment of a network slice; an average ratio of successful PDU session setup of a network slice; or a relative AMF capacity. The collected data or information in the data collection report message may include predicted information, measured information, evaluated information, statistical information, and / or collected information.
[0064] At S43, the data requester, the CN, receives the data or information in the data collection report message in one or more PDU containers. Then, at S44, the data receiver, the CN, may use the received data or information from the data collection report message to support an AI / ML function. For example, the AI / ML function may include training for one or more AI / ML models located at the CN, performing AI / ML inference according to one or more AI / ML models located at the CN, performing AI / ML model evaluation according to one or more AI / ML models located at the CN, or conducting wireless communication according to the AI / ML function’s output data included in the data collection report.
[0065] FIG. 7 shows an exemplary communication operation between a gNB-CU node and a gNB-DU. The above examples about data request and data response between two communication nodes can be implemented between a gNB-CU (central unit) node and a gNB-DU (distributed united) node. For example, an AI / ML function can be implemented at the gNB-CU node, which usually handled more complicated computation. The gNB-CU node can request the data for supporting AI / ML function from gNB-DU.
[0066] For example, at S51, the gNB-CU triggers the data collection request to the gNB-DU to request the assistance information to support an AI / ML function. The data collection request may indicate at least one of the following information, including a requested assistance information indication; a type of requested assistance information; a cell ID (identification) of a cellular network corresponding to the AI / ML function; a PLMN (Public Land Mobile Network) ID corresponding to an AI / ML function; S-NSSAI (Network Slice Selection Assistance Information) ; an SST (Slice / Service Type) field; an NSI ID (Network Slice Instance) ; or a reporting periodicity.
[0067] For example, the requested assistance information indication may indicate the requested information. The kinds of assistance information requested by the node to support an AI / ML function may include predicted information, measured information, evaluated information, statistical information, and / or collected information. The requested information may be associated with a particular network, a particular node, a particular cell, and / or a particular network slice of a particular node. In some cases, the gNB-DU (or the data provider) may also have some inference function that can make a prediction of certain information. Therefore, the gNB-CU can request some predicted information from the gNB-DU. The predicted information can be used by the gNB-CU to support some AI / ML functions. For example, the function can be used by the receiver of the data to make inference. The data can also be used by the data receiver to guide their action.
[0068] For example, the requested information by the gNB-CU, as indicated in the request, may include at least one of a per-node or per-cell predicted resource usage status of a network slice; a per-node or per-cell predicted number of UE registration of a network slice; a per-node or per-cell predicted number of session establishment of a network slice; a predicted average ratio of successful PDU session setup of a network slice; a predicted relative AMF capacity; a prediction confidence; a per-node or per-cell resource usage status of a network slice; a per-node or per-cell number of UE registration of a network slice; a per-node or per-cell number of session establishment of a network slice; an average ratio of successful PDU session setup of a network slice; or a relative AMF capacity.
[0069] Exemplarily, the resource usage status of a network slice indicates usage of PRBs (Physical Resource Block) of a network slice. The number of UE registration may, for example, indicate a total number of user equipment registered at a certain device, network, cell, or a certain network slice. The number of session establishment may, for example, indicate the number of sessions established at a certain network slice. The average ratio of successful PDU session setup may, for example, indicate an average ratio of successfully setup PDU sessions over PDU sessions that can be set up to a certain network slice. The relative AMF capacity may represent an available capacity of an AMF (Access and Mobility Management Function) . The prediction confidence may be associated with one or more reported predicted values. The prediction confidence may, for example, represent the confidence of the predicted values. As explained above, the reported information may be an actual measured or collected information, and alternative, the reported information can be a predicted value.
[0070] On the other hand, the type of requested assistance information can, for example be used to indicate the type or categories of the requested information. The cell ID (identification) of a cellular network may be used to represent the cell corresponding to the AI / ML function to be supported or to indicate the requested information corresponds to which cell. The PLMN (Public Land Mobile Network) ID corresponding to the AI / ML function may represent an ID of the PLMN corresponding to a certain AI / ML function. The S-NSSAI (Network Slice Selection Assistance Information) can be used to uniquely identify a Network Slice. The S-NSSAI may contain two components, including the SST (Slice / Service Type) and an optional SD (Slice Differentiator) . The SST (Slice / Service Type) field may be used to represent a type of a certain slice and service type. The NSI (Network Slice Instance) ID can be used to identify a certain NSI for which the requested information is requested. The reporting periodicity may be used to indicate how often (such as the frequency or the period) the data providers should report the requested data.
[0071] At S52, according to the data collection request, the gNB-DU sends the gNB-CU a data collection response. The data collection response may include data or information collected according to the data collection request. For example, the data or information provided by the gNB-DU in the data collection response may include at least some assistance information for supporting AI / ML function. For example, the data or information provided by the gNB-DU in the data collection response may include at least one of: a per-node or per-cell predicted resource usage status of a network slice; a per-node or per-cell predicted number of UE registration of a network slice; a per-node or per-cell predicted number of session establishment of a network slice; a predicted average ratio of successful PDU session setup of a network slice; a predicted relative AMF capacity; a prediction confidence; a per-node or per-cell resource usage status of a network slice; a per-node or per-cell number of UE registration of a network slice; a per-node or per-cell number of session establishment of a network slice; an average ratio of successful PDU session setup of a network slice; or a relative AMF capacity. The collected data or information in the data collection response may include predicted information, measured information, evaluated information, statistical information, and / or collected information. Additionally, the gNB-DU may send a data collection update, regularly or upon a detection of an update by the gNB-DU, to the gNB-CU at S52-1, if there is any update of the data to be collected as indicated in the data collection request.
[0072] At S53, the data requester, the gNB-CU, receives the data or information in the data collection report message in one or more PDU containers. Then, at S54, the data receiver, gNB-CU, may use the received data or information from the data collection report message to support an AI / ML function. For example, the AI / ML function may include training for one or more AI / ML models located at the gNB-CU, performing AI / ML inference according to one or more AI / ML models located at the gNB-CU, performing AI / ML model evaluation according to one or more AI / ML models located at the gNB-CU, or conducting wireless communication according to the AI / ML function’s output data included in the data collection report.
[0073] FIG. 8 shows an exemplary communication operation between a NG-RAN node 1 and a NG-RAN node 2. The above examples about data request and data response between two communication nodes can be implemented between a NG-RAN node 1 and a NG-RAN node 2. For example, an AI / ML function can be implemented at the NG-RAN node 1, which usually handled more complicated computation. The NG-RAN node 1 can request the data for supporting AI / ML function from the NG-RAN node 2.
[0074] For example, at S61, the NG-RAN node 1 triggers the data collection request to the NG-RAN node 2 to request the assistance information to support an AI / ML function. The data collection request may indicate at least one of the following information, including a requested assistance information indication; a type of requested assistance information; a cell ID (identification) of a cellular network corresponding to the AI / ML function; a PLMN (Public Land Mobile Network) ID corresponding to an AI / ML function; S-NSSAI (Network Slice Selection Assistance Information) ; an SST (Slice / Service Type) field; an NSI ID (Network Slice Instance) ; or a reporting periodicity.
[0075] For example, the requested assistance information indication may indicate the requested information. The kinds of assistance information requested by the node to support an AI / ML function may include predicted information, measured information, evaluated information, statistical information, or collected information. The requested information may be associated with a particular network, a particular node, a particular cell, and / or a particular network slice of a particular node. In some cases, the NG-RAN node 2 (or the data provider) may also have some inference function that can make a prediction of certain information. Therefore, the NG-RAN node 1 can request some predicted information from the NG-RAN node 2. The predicted information can be used by the NG-RAN node 1 to support some AI / ML functions. For example, the function can be used by the receiver of the data to make inference. The data can also be used by the data receiver to guide their action.
[0076] For example, the requested information by the NG-RAN node 1, as indicated in the request, may include at least one of a per-node or per-cell predicted resource usage status of a network slice; a per-node or per-cell predicted number of UE registration of a network slice; a per-node or per-cell predicted number of session establishment of a network slice; a predicted average ratio of successful PDU session setup of a network slice; a predicted relative AMF capacity; a prediction confidence; a per-node or per-cell resource usage status of a network slice; a per-node or per-cell number of UE registration of a network slice; a per-node or per-cell number of session establishment of a network slice; an average ratio of successful PDU session setup of a network slice; or a relative AMF capacity.
[0077] Exemplarily, the resource usage status of a network slice indicates usage of PRBs (Physical Resource Block) of a network slice. The number of UE registration may, for example, indicate a total number of user equipment registered at a certain device, network, cell, or a certain network slice. The number of session establishment may, for example, indicate the number of sessions established at a certain network slice. The average ratio of successful PDU session setup may, for example, indicate an average ratio of successful setup PDU sessions over PDU sessions that can be set up to a certain network slice. The relative AMF capacity may represent an available capacity of an AMF (Access and Mobility Management Function) . The prediction confidence may be associated with one or more reported predicted values. The prediction confidence may, for example, represent the confidence of the predicted values. As explained above, the reported information may be an actual measured or collected information, and alternative, the reported information can be a predicted value.
[0078] On the other hand, the type of requested assistance information can, for example be used to indicate the type or categories of the requested information. The cell ID (identification) of a cellular network may be used to represent the cell corresponding to the AI / ML function to be supported or to indicate the requested information corresponds to which cell. The PLMN (Public Land Mobile Network) ID corresponding to the AI / ML function may represent an ID of the PLMN corresponding to a certain AI / ML function. The S-NSSAI (Network Slice Selection Assistance Information) can be used to uniquely a Network Slice. The S-NSSAI may contain two components, including the SST (Slice / Service Type) and an optional SD (Slice Differentiator) . The SST (Slice / Service Type) field may be used to represent a type of a certain slice and service type. The NSI (Network Slice Instance) ID can be used to identify a certain NSI for which the requested information is requested. The reporting periodicity may be used to indicate how often (such as the frequency or the period) the data providers should report the requested data.
[0079] At S62, according to the data collection response, the NG-RAN node 2 sends the NG-RAN node1 a data collection report. The data collection response may include data or information collected according to the data collection request. For example, the data or information provided by the NG-RAN node 2 in the data collection response may include at least some assistance information for supporting AI / ML function. For example, the data or information provided by the NG-RAN node 2 in the data collection response may include at least one of: a per-node or per-cell predicted resource usage status of a network slice; a per-node or per-cell predicted number of UE registration of a network slice; a per-node or per-cell predicted number of session establishment of a network slice; a predicted average ratio of successful PDU session setup of a network slice; a predicted relative AMF capacity; a prediction confidence; a per-node or per-cell resource usage status of a network slice; a per-node or per-cell number of UE registration of a network slice; a per-node or per-cell number of session establishment of a network slice; an average ratio of successful PDU session setup of a network slice; or a relative AMF capacity. The collected data or information in the data collection report may include predicted information, measured information, evaluated information, statistical information, or collected information. Additionally, the NG-RAN node 2 may send a data collection update, regularly or upon a detection of an update by the NG-RAN node 2, to the NG-RAN node 1 at S62-1, if there is any update of the data to be collected as indicated in the data collection request.
[0080] At S63, the data requester, the NG-RAN node 1, receives the data or information in the data collection report message in one or more PDU containers. Then, at S64, the data receiver, NG-RAN node 1, may use the received data or information from the data collection report message to support an AI / ML function. For example, the AI / ML function may include training for one or more AI / ML models located at the NG-RAN node 1, performing AI / ML inference according to one or more AI / ML models located at the NG-RAN node 1, performing AI / ML model evaluation according to one or more AI / ML models located at the NG-RAN node 1, or conducting wireless communication according to the AI / ML function’s output data included in the data collection report.
[0081] FIG. 9 illustrates a block diagram of an exemplary wireless communication system 20, in accordance with some embodiments of this disclosure. The system 20 may perform the methods / steps and their combination disclosed in this disclosure. The system 20 may include components and elements configured to support operating features that need not be described in detail herein.
[0082] The system 20 may include at least one base station (BS) 110 (or a RAN node, a gNB-CU, or gNB-DU) , at least one user equipment (UE) 120, and at least one core network (CN) 130. The BS 110 includes a BS transceiver or transceiver module 112, a BS antenna system 116, a BS memory or memory module / circuitry 114, a BS processor or processor module 113, and a network interface 111. The components of BS 110 may be electrically coupled and in communication with one another as necessary via a data communication bus 180. Likewise, the UE 120 includes a UE transceiver or transceiver module 122, a UE antenna system 126, a UE memory or memory module / circuitry 124, a UE processor or processor module 123, and an I / O interface 121. The components of the UE 120 may be electrically coupled and in communication with one another as necessary via a data communication bus 190. The BS 110 communicates with the UE 120 via communication channels therebetween, which can be any wireless channel or other medium known in the art suitable for transmission of data as described herein. The channels may include carriers of PCells and SCells. The CN 130 includes at least one CN transceiver or transceiver module 132, at least one CN antenna system 136, at least one CN memory or memory module / circuitry 134, at least one CN processor or processor module 133, and at least one network interface 131. The CN can be form by a distributed system, including multiple devices 136.
[0083] The processor modules 113, 123, 133 may be implemented, or realized, with a general-purpose processor, a content addressable memory, a digital signal processor, an application specific integrated circuit, a field programmable gate array, any suitable programmable logic device, discrete gate or transistor logic, discrete hardware components, or any combination thereof, designed to perform the functions described herein. In this manner, a processor module may be realized as a microprocessor, a controller, a microcontroller, a state machine, or the like. A processor module may also be implemented as a combination of computing devices, e.g., a combination of a digital signal processor and a microprocessor, a plurality of microprocessors, one or more microprocessors in conjunction with a digital signal processor core, or any other such configuration. A processor module may also be implemented as a combination of multiple computing devices, such as multiple servers.
[0084] Furthermore, the steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied directly in hardware, in firmware, in a software module performed by processor modules 113, 123, 133, respectively, or in any practical combination thereof. The memory module / circuitry 113, 123, 133 may be realized as RAM memory, flash memory, EEPROM memory, registers, ROM memory, EPROM memory, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art. In this regard, the memory module / circuitry 114, 124, 134 may be coupled to the processor modules 113, 123, 133 respectively, such that the processors modules 113, 123, 133 can read information from, and write information to, memory module / circuitry 114, 124, 134 respectively. The memory module / circuitry 114, 124, 134 may also be integrated into their respective processor modules 113, 123, 133. In some embodiments, the memory module / circuitry 114, 124, 134 may each include a cache memory for storing temporary variables or other intermediate information during execution of instructions to be performed by processor modules 113, 123, 133, respectively. The memory module / circuitry 114, 124, 134 may also each include non-volatile memory for storing instructions to be performed by the processor modules 113, 123, 133, respectively.
[0085] Various exemplary embodiments of the present disclosure are described herein with reference to the accompanying figures to enable a person of ordinary skill in the art to make and use the present disclosure. The present disclosure is not limited to the exemplary embodiments and applications described and illustrated herein. Additionally, the specific order and / or hierarchy of steps in the methods disclosed herein are merely exemplary approaches. Based upon design preferences, the specific order or hierarchy of steps of the disclosed methods or processes can be re-arranged while remaining within the scope of the present disclosure. Thus, those of ordinary skill in the art would understand that the methods and techniques disclosed herein present various steps or acts in exemplary order (s) , and the present disclosure is not limited to the specific order or hierarchy presented unless expressly stated otherwise.
[0086] This disclosure is intended to cover any conceivable variations, uses, combination, or adaptive changes of this disclosure following the general principles of this disclosure, and includes well-known knowledge and conventional technical means in the art and undisclosed in this application.
[0087] It is to be understood that this disclosure is not limited to the precise structures or operation described above and shown in the accompanying drawings, and various modifications and changes may be made without departing from the scope of this application. The scope of this application is subject only to the appended claims.
[0088] The methods, devices, processing, circuitry, and logic described above may be implemented in many different ways and in many different combinations of hardware and software. For example, all or parts of the implementations may be circuitry that includes an instruction processor or controller, such as a Central Processing Unit (CPU) , microcontroller, or a microprocessor; or as an Application Specific Integrated Circuit (ASIC) , Programmable Logic Device (PLD) , or Field Programmable Gate Array (FPGA) ; or as circuitry that includes discrete logic or other circuit components, including analog circuit components, digital circuit components or both; or any combination thereof. The circuitry may include discrete interconnected hardware components or may be combined on a single integrated circuit die, distributed among multiple integrated circuit dies, or implemented in a Multiple Chip Module (MCM) of multiple integrated circuit dies in a common package, as examples.
[0089] Accordingly, the circuitry may store or access instructions for execution, or may implement its functionality in hardware alone. The instructions may be stored in a tangible storage medium that is other than a transitory signal, such as a flash memory, a Random Access Memory (RAM) , a Read Only Memory (ROM) , an Erasable Programmable Read Only Memory (EPROM) ; or on a magnetic or optical disc, such as a Compact Disc Read Only Memory (CDROM) , Hard Disk Drive (HDD) , or other magnetic or optical disk; or in or on another machine-readable medium. A product, such as a computer program product, may include a storage medium and instructions stored in or on the medium, and the instructions when performed by the circuitry in a device may cause the device to implement any of the processing described above or illustrated in the drawings.
[0090] The implementations may be distributed. For instance, the circuitry may include multiple distinct system components, such as multiple processors and memories, and may span multiple distributed processing systems. Parameters, databases, and other data structures may be separately stored and managed, may be incorporated into a single memory or database, may be logically and physically organized in many different ways, and may be implemented in many different ways. Example implementations include linked lists, program variables, hash tables, arrays, records (e.g., database records) , objects, and implicit storage mechanisms. Instructions may form parts (e.g., subroutines or other code sections) of a single program, may form multiple separate programs, may be distributed across multiple memories and processors, and may be implemented in many different ways. Example implementations include stand-alone programs, and as part of a library, such as a shared library like a Dynamic Link Library (DLL) . The library, for example, may contain shared data and one or more shared programs that include instructions that perform any of the processing described above or illustrated in the drawings, when performed by the circuitry.
[0091] In some examples, each unit, subunit, and / or module of the system may include a logical component. Each logical component may be hardware or a combination of hardware and software. For example, each logical component may include an application specific integrated circuit (ASIC) , a Field Programmable Gate Array (FPGA) , a digital logic circuit, an analog circuit, a combination of discrete circuits, gates, or any other type of hardware or combination thereof. Alternatively or in addition, each logical component may include memory hardware, such as a portion of the memory, for example, that includes instructions executable with the processor or other processors to implement one or more of the features of the logical components. When any one of the logical components includes the portion of the memory that includes instructions executable with the processor, the logical component may or may not include the processor. In some examples, each logical component may just be the portion of the memory or other physical memory that includes instructions executable with the processor or other processor to implement the features of the corresponding logical component without the logical component including any other hardware. Because each logical component includes at least some hardware even when the included hardware includes software, each logical component may be interchangeably referred to as a hardware logical component.
[0092] A second action may be said to be “in response to” a first action independent of whether the second action results directly or indirectly from the first action. The second action may occur at a substantially later time than the first action and still be in response to the first action. Similarly, the second action may be said to be in response to the first action even if intervening actions take place between the first action and the second action, and even if one or more of the intervening actions directly cause the second action to be performed. For example, a second action may be in response to a first action if the first action sets a flag and a third action later initiates the second action whenever the flag is set.
[0093] To clarify the use of and to hereby provide notice to the public, the phrases “at least one of , , …and <N> ” or “at least one of , , …<N> , or combinations thereof” or “ , , …and / or <N> ” are defined by the Applicant in the broadest sense, superseding any other implied definitions hereinbefore or hereinafter unless expressly asserted by the Applicant to the contrary, to mean one or more elements selected from the group comprising A, B, …and N. In other words, the phrases mean any combination of one or more of the elements A, B, …or N including any one element alone or the one element in combination with one or more of the other elements which may also include, in combination, additional elements not listed.
Claims
1.A wireless communication method, comprising:sending, from a first communication node to a second communication node, a data request for supporting an artificial intelligence or machine learning (AI / ML) function of the first communication node, the data request indicating at least one of:a requested assistance information indication, indicating requested information;a type of requested assistance information;a cell ID (identification) of a cellular network corresponding to the AI / ML function;a PLMN (Public Land Mobile Network) ID corresponding to the AI / ML function;S-NSSAI (Network Slice Selection Assistance Information) ;an SST (Slice / Service Type) field;an NSI (Network Slice Instance) ID; ora reporting periodicity; andreceiving, by the first communication node from the second communication node, a data report in response to the data request.2.The method of claim 1, wherein the requested information includes one or more of:a per-node or per-cell predicted resource usage status of a network slice;a per-node or per-cell predicted number of UE registration of a network slice;a per-node or per-cell predicted number of session establishment of a network slice;a predicted average ratio of successful PDU session setup of a network slice;a predicted relative AMF capacity;a prediction confidence;a per-node or per-cell resource usage status of a network slice;a per-node or per-cell number of UE registration of a network slice;a per-node or per-cell number of session establishment of a network slice;an average ratio of successful PDU session setup of a network slice; ora relative AMF capacity.3.The method of claim 1, wherein the data report includes one or more pieces of the following information, including:a per-node or per-cell predicted resource usage status of a network slice;a per-node or per-cell predicted number of UE registration of a network slice;a per-node or per-cell predicted number of session establishment of a network slice;a predicted average ratio of successful PDU session setup of a network slice;a predicted relative AMF capacity;a prediction confidence;a per-node or per-cell resource usage status of a network slice;a per-node or per-cell number of UE registration of a network slice;a per-node or per-cell number of session establishment of a network slice;an average ratio of successful PDU session setup of a network slice; ora relative AMF capacity.4.The method of claim 1, wherein at least one of the data request or the data report is in a PDU container.5.The method of any one of claims 1 to 4, wherein:the first communication node is a RAN (random access network) node and the second communication node is a core network;the first communication node is a core network and the second communication node is a RAN node;the first communication node is a central unit of a base station and the second communication node is a distributed unit of a base station; orthe first communication node is a RAN node and the second communication node is another RAN node.6.The method of any one of claims 1 to 4, further comprising using the data report to support the AI / ML function.7.The method of claim 1, wherein a type of the requested assistance information includes at least one piece of predicted information type or statistical information type.8.A wireless communication method, comprising:sending, from a first communication node to a second communication node, a data request for an artificial intelligence or machine learning (AI / ML) function of the first communication node, the data request including a requested assistance information indication, wherein the requested assistance information indication indicates requested information, including one or more of:a per-node or per-cell predicted resource usage status of a network slice;a per-node or per-cell predicted number of UE registration of a network slice;a per-node or per-cell predicted number of session establishment of a network slice;a predicted average ratio of successful PDU session setup of a network slice;a predicted relative AMF capacity;a prediction confidence;a per-node or per-cell resource usage status of a network slice;a per-node or per-cell number of UE registration of a network slice;a per-node or per-cell number of session establishment of a network slice;an average ratio of successful PDU session setup of a network slice; ora relative AMF capacity; andreceiving, by the first communication node from the second communication node, a data report in response to the data request.9.The method of claim 8, wherein the data request further comprises at last one of:a type of the requested assistance information;a cell ID (identification) of a cellular network corresponding to the AI / ML function;a PLMN (Public Land Mobile Network) ID corresponding to the AI / ML function;S-NSSAI (Network Slice Selection Assistance Information) ;an SST (Slice / Service Type) field;an NSI (Network Slice Instance) ID; ora reporting periodicity.10.The method of claim 8, wherein at least one of the data request or the data report is in a PDU container.11.The method of any one of claims 8 to 10, wherein:the first communication node is a RAN (random access network) node and the second communication node is a core network;the first communication node is a core network and the second communication node is a RAN node;the first communication node is a central unit of a base station and the second communication node is a distributed unit of a base station; orthe first communication node is a RAN node and the second communication node is another RAN node.12.The method of any one of claims 8 to 10, further comprising using the data report to support the AI / ML function.13.A wireless communication method, comprising:sending, from a first communication node to a second communication node, a data request for supporting an artificial intelligence or machine learning (AI / ML) function of the first communication node; andreceiving, by the first communication node from the second communication node, a data report in response to the data request, wherein the data report includes one or more pieces of the following information, including:a per-node or per-cell predicted resource usage status of a network slice;a per-node or per-cell predicted number of UE registration of a network slice;a per-node or per-cell predicted number of session establishment of a network slice;a predicted average ratio of successful PDU session setup of a network slice;a predicted relative AMF capacity;a prediction confidence;a per-node or per-cell resource usage status of a network slice;a per-node or per-cell number of UE registration of a network slice;a per-node or per-cell number of session establishment of a network slice;an average ratio of successful PDU session setup of a network slice; ora relative AMF capacity.14.The method of claim 13, wherein the data request indicates at least one of:a requested assistance information indication, indicating requested information;a type of the requested assistance information;a cell ID (identification) of a cellular network corresponding to the AI / ML function;a PLMN (Public Land Mobile Network) ID corresponding to the AI / ML function;S-NSSAI (Network Slice Selection Assistance Information) ;an SST (Slice / Service Type) field;an NSI (Network Slice Instance) ID; ora reporting periodicity.15.The method of claim 14, wherein a type of the requested assistance information includes at least one piece of predicted information type or statistical information type.16.The method of claim 13, wherein at least one of the data request or the data report is in a PDU container.17.The method of any one of claims 13 to 15, wherein:the first communication node is a RAN (random access network) node and the second communication node is a core network;the first communication node is a core network and the second communication node is a RAN node;the first communication node is a central unit of a base station and the second communication node is a distributed unit of a base station; orthe first communication node is a RAN node and the second communication node is another RAN node.18.The method of any one of claims 13 to 15, further comprising using the data report to support the AI / ML function.19.A wireless communication apparatus, comprising memory circuitry storing one or more programs and one or more processors electrically coupled to the memory circuitry and configured to execute the one or more programs to perform any one of the methods or their combinations of claims 1 to 18.20.A non-transitory computer-readable storage medium, storing one or more programs, the one or more programs being configured to, when executed by at least one processor, cause to perform any one of the methods or their combinations or sub-combinations of claims 1 to 18.
Citation Information
Patent Citations
User access control method, information sending method and device
CN111225420A
Network slice analysis
CN116034602A
Network Slicing Scalability Attributes
US20220377655A1
Monitoring an attribute of a network slice
US20230036993A1
Method and apparatus for managing resource through service demand information analysis in wireless communication system
US20230077340A1