UE distribution information exchange for ai / ML-on NG-ran

Abstract

An apparatus, a method, a computer program, a computer program product, and a computer readable medium are provided for exchanging UE distribution information for an AI / ML-enabled NG-RAN. The method for use in a network node includes receiving measurement data from at least one user equipment located within a cell managed by the network node, and determining user equipment distribution information for the at least one user equipment based on the received measurement data.

Description

Technical Field

[0001] Various exemplary embodiments relate to apparatus, methods, systems, computer programs, computer program products, and computer-readable media for exchanging UE distribution information for an AI / ML-enabled NG-RAN.

[0002] Abbreviations

[0003] AI Artificial Intelligence

[0004] KPI Key Performance Indicator

[0005] MDT Minimized Drive Test

[0006] ML Machine Learning

[0007] NG-RAN Next Generation Radio Access Network

[0008] RLF Radio Link Failure

[0009] RRM Radio Resource Management

[0010] RSRP Reference Signal Received Power

[0011] RSRQ Reference Signal Received Quality

[0012] SINR Signal to Interference and Noise Ratio

[0013] UE User Equipment Background Art

[0014] Recently, a 3GPP study item (SI) led by RAN3 entitled "Study on Enhancements for Data Collection for NR and EN-DC" (RP-201620) was summarized in Release 17. The work item (WI) RP-213602 on AI / ML for NG-RAN will soon follow this study. The general purpose of the SI is to study the high-level principles for enabling AI / ML in RAN and the functional framework including the inputs and outputs required by AI / ML functionality and ML algorithms. Specifically, the SI aims to identify the data required by AI functions in input and the data generated in output, as well as the impact of standardization at nodes in existing architectures or in network interfaces for transmitting this input / output data through them. Three use cases are prioritized to evaluate the benefits of AI / ML in the network, namely energy saving, load balancing, and mobility enhancement. For network energy saving and load balancing, the following are given. italic The emphasis on intra-network information exchange has been proposed in Sections 5.1.2.4, 5.1.2.6, 5.2.2.4, and 5.2.2.6 of 3GPP 37.817 as follows:

[0015] 5.1.2.4 Input for AI / ML-based Network Energy Saving

[0016] To predict optimized network energy-saving decisions, NG-RAN may require the following information as input data for AI / ML-based network energy saving:

[0017] Input information from the local node:

[0018] -UE mobility / trajectory prediction

[0019] - Current / forecast energy efficiency

[0020] -Current / forecasted resource status

[0021] Input information from UE:

[0022] - UE location information (e.g., coordinates, serving cell ID, moving speed) interpreted by the Gnb implementation when available

[0023] - UE measurement reports including cell-level and beam-level UE measurements (e.g., UE RSRP, RSRQ, SINR measurements, etc.)

[0024] Input from neighboring NG-RAN nodes:

[0025] - Current / forecast energy efficiency

[0026] -Current / forecasted resource status

[0027] - Current energy state (e.g., active, high, low, deactivated)

[0028] 5.1.2.6 Feedback on AI / ML-based Network Energy Saving

[0029] To optimize the performance of AI / ML-based network energy-saving models, the following feedback can be collected from NG-RAN nodes:

[0030] - Resource status of neighboring NG-RAN nodes

[0031] -Energy efficiency

[0032] - UE performance affected by the energy saving action (e.g., UE in handover), including bit rate, packet loss, latency, between.

[0033] - System KPIs (e.g. throughput, latency, RLF of current and neighboring NG-RAN nodes)

[0034] If Gnb requires existing UE measurements for AI / ML-based network energy savings, RAN3 will reuse the existing framework (including MDT and RRM measurements)."

[0035] 5.2.2.4 Inputs to AI / ML-based Load Balancing

[0036] To predict optimized load balancing decisions, NG-RAN may require the following information as input data for AI / ML-based load balancing:

[0037] From the local node:

[0038] - Current and projected state of own resources

[0039] -UE trajectory prediction

[0040] -Current and forecasted UE traffic

[0041] - Predicted resource status information of neighboring NG-RAN nodes

[0042] From UE:

[0043] - UE location information (e.g., coordinates, serving cell ID, moving speed) as interpreted by the gNB implementation, when available

[0044] -UE mobility history information

[0045] - UE measurement reports including cell-level and beam-level UE measurements (e.g., UE RSRP, RSRQ, SINR measurements, etc.)

[0046] From adjacent NG-RAN nodes:

[0047] -Current and projected resource status

[0048] -UE performance measurements at neighboring cells with traffic offload

[0049] 5.2.2.6 Feedback on AI / ML-based Load Balancing

[0050] To optimize the performance of AI / ML-based load balancing models, the following feedback can be collected from NG-RAN nodes:

[0051] -UE capability information from the target NG-RAN (for those UEs being handed over from the source NG-RAN node)

[0052] - Resource status information update from target NG-RAN

[0053] - System KPIs (e.g., current and neighbor throughput, latency, RLF)

[0054] For network energy saving and load balancing use cases, the source node switches a set of UEs to a target node. For example, when a capacity cell is shut down, the set of UEs is switched to another capacity cell or coverage cell. Similarly, when a load balancing action is taken at the source node, the set of UEs is switched from the source cell to a target cell in the same node or another node. However, in both cases, the UE distribution in the target cell plays a key role in evaluating the performance of the action and the impact of the action on the target node.

[0055] More specifically, when a capacity cell is switched off, the distribution of UEs in the target (coverage cell) will determine how much benefit (in terms of energy savings) the cell switching action will achieve. Naturally, if, after handover, a greater number of UEs will reside closer to the center of the target coverage cell compared to the cell edge, the energy savings will be higher. The higher the number of UEs residing at the cell edge, the lower the energy efficiency. Similarly, for the load balancing use case, the performance of offloading multiple users from one cell to another depends on the distribution of these users at the target node. According to current technology, there is no mechanism for the source NG-RAN node to determine the distribution of UEs in the target NG-RAN node after performing AI / ML-based actions (network energy savings or load balancing). At the same time, without information about the UE distribution after AI / ML network energy savings or load balancing actions, it can be difficult to evaluate the impact of AI / ML actions, for example, in terms of cost metrics such as energy consumption, energy efficiency, etc., in incurring a certain additional load at the target node, or in terms of the achieved load distribution.

[0056] Receiving only energy efficiency / consumption information in feedback is not sufficient, because at the source, the root cause for the measured energy efficiency / consumption or the load distribution, such as UE distribution, is still unknown. Therefore, the source node cannot retrain the model accordingly.

[0057] Figure 1 Shown is a solution where model training and model inference are located at the NG-RAN for AI / ML network energy saving and load balancing use cases. Figure 1 and its following description are disclosed in 3GPP TR 37.817.

[0058] Step 0: Assume that NG-RAN node 2 optionally has an AI / ML model, which can provide input information to NG-RAN node 1.

[0059] Step 1: NG-RAN node 1 configures measurement information on the UE side and sends a configuration message to the UE to perform measurement procedures and reporting.

[0060] Step 2: The UE collects the indicated measurements, e.g., UE measurements related to RSRP, RSRQ, SINR of the serving cell and neighboring cells.

[0061] Step 3: The UE sends a measurement report including the required measurement results to the NG-RAN node 1.

[0062] Step 4: NG-RAN node 2 sends the required input data to NG-RAN node 1 for AI / ML-based network energy saving model training.

[0063] Step 5: NG-RAN node 1 trains an AI / ML model for AI / ML-based energy saving based on the collected data. Optionally, NG-RAN node 2 is assumed to have an AI / ML model for AI / ML-based energy saving, which can also generate predicted results / actions.

[0064] Step 6: NG-RAN node 2 sends the required input data to NG-RAN node 1 for model inference based on AI / ML network energy saving.

[0065] Step 7: The UE sends (multiple) UE measurement reports to NG-RAN node 1.

[0066] Step 8: Based on the local input of NG-RAN node 1 and the input received from NG-RAN node 2, NG-RAN node 1 generates model inference output (e.g., energy saving strategy, handover strategy, etc.).

[0067] Step 9: NG-RAN node 1 performs network energy saving actions based on the model inference output. If the output is a handover strategy, NG-RAN node 1 can select the most suitable target cell for each UE before it performs the handover.

[0068] Step 10: NG-RAN node 2 provides feedback to NG-RAN node 1.

[0069] In view of the above, steps 3 and 7 indicate measurement reports from the UE, which may include, for example, RSRP, RSRQ, and SINR measurements, as indicated in TR 37.817. As previously mentioned, RSRP, RSRQ, and SINR measurements can provide an indication of how close the UE is to the cell center. Therefore, by using this information, the node can train (and execute) an ML model (e.g., based on unsupervised learning) to model the UE distribution at the cell. It should be noted that the UE measurement information is only received by the source NG-RAN node and used as input parameters for the ML modeling.

[0070] After the network energy saving action in step 9, feedback information is sent from the target node to the source node. The feedback may include UE performance feedback of the handover UE. For all use cases, it is agreed in RAN3#117-e that UE performance feedback may include the following information: "UE performance (e.g., UL / DL throughput, packet delay, packet loss)".

[0071] Currently, the allowed feedback information from the target to the source takes into account the impact on UE performance from the action. However, with respect to step 10, there is currently no mechanism for a node to calculate and provide the impact on UE distribution or other relevant metrics such as energy efficiency / energy consumption as feedback to another node. Summary of the Invention

[0072] Various exemplary embodiments are directed to addressing at least some of the above-mentioned issues and / or problems and disadvantages.

[0073] It is an object of various example embodiments to provide apparatus, methods, systems, computer programs, computer program products, and computer-readable media for exchanging UE distribution information for AI / ML-enabled NG-RAN.

[0074] According to aspects of various example embodiments, there is provided a method for use in a network node, comprising:

[0075] receiving measurement data from at least one user equipment located within a cell managed by the network node, and

[0076] User equipment distribution information of the at least one user equipment is determined based on the received measurement data.

[0077] According to another aspect of various example embodiments, there is provided a method for use in a first network node, comprising:

[0078] sending a request for user equipment distribution information to the second network node,

[0079] UE distribution information is received from the second network node according to the request.

[0080] According to another aspect of various example embodiments, there is provided a method for use in a second network node, comprising:

[0081] receiving a request for user equipment distribution information from a first network node,

[0082] UE distribution information is calculated by the second network node, and

[0083] The calculated UE distribution information is reported to the first network node.

[0084] According to another aspect of some example embodiments, there is provided an apparatus for use in a network node, comprising:

[0085] means for receiving measurement data from at least one user equipment located within a cell managed by said network node, and

[0086] According to another aspect of some example embodiments, there is provided an apparatus for use in a first network node, comprising:

[0087] means for sending a request for user equipment distribution information to the second network node,

[0088] means for receiving UE distribution information from the second network node according to the request.

[0089] According to another aspect of some example embodiments, there is provided an apparatus for use in a second network node, comprising:

[0090] means for receiving a request for user equipment distribution information from the first network node,

[0091] means for calculating, by the second network node, UE distribution information, and

[0092] means for reporting the calculated UE distribution information to the first network node.

[0093] According to another aspect of the present invention, there is provided a computer program product comprising code means adapted to, when loaded into the memory of a computer, produce the steps of any of the methods described above.

[0094] According to a further aspect of the present invention, there is provided a computer program product as defined above, wherein the computer program product comprises a computer readable medium having the software code portions stored thereon.

[0095] According to a further aspect of the present invention, there is provided a computer program product as defined above, wherein the program is directly loadable into an internal memory of a processing device.

[0096] According to an aspect of various exemplary embodiments, there is provided a computer-readable medium storing the computer program as described above.

[0097] According to an exemplary aspect, a computer program product is provided, comprising a computer-executable computer program code, which, when the program is run on a computer (e.g., a computer of an apparatus according to any one of the aforementioned exemplary aspects related to apparatuses of the present disclosure), is configured to cause the computer to perform a method according to any one of the aforementioned exemplary aspects related to methods of the present disclosure.

[0098] Such a computer program product may comprise (or be embodied as) a (tangible) computer-readable (storage) medium or the like having computer-executable computer program code stored thereon, and / or the program may be directly loadable into the internal memory of a computer or its processor.

[0099] Further aspects and features of the invention are set out in the dependent claims. BRIEF DESCRIPTION OF THE DRAWINGS

[0100] These and other objects, features, details and advantages will become more fully apparent from the following detailed description of various aspects / embodiments taken in conjunction with the accompanying drawings, in which:

[0101] Figure 1 is a diagram illustrating an example of model training and model inference for AI / ML energy saving use cases at NG-RAN;

[0102] Figure 2 is a diagram illustrating a relationship among UE measurement, UE distribution information, and UE efficiency distribution information according to some example embodiments of the present invention.

[0103] Figure 3 is a diagram illustrating examples of machine learning algorithms and their input and output parameters according to some example embodiments of the present invention;

[0104] Figure 4 is a diagram illustrating an example of outputting UE distribution information according to corresponding RSRP ranges and percentages of UEs in UE distribution categories according to some example embodiments of the present invention;

[0105] Figure 5 is a diagram illustrating an example of periodic UE distribution information feedback for a use case of network energy saving according to some exemplary embodiments of the present invention;

[0106] Figure 6 is a diagram illustrating an example of one-time UE distribution information feedback for a use case of network energy saving according to some example embodiments of the present invention;

[0107] Figure 7 is a diagram illustrating an example of one-time UE distribution information feedback for a use case of network energy saving for cell deactivation according to some example embodiments of the present invention;

[0108] Figure 8 is a diagram illustrating an example of periodic UE distribution information feedback for a use case of load balancing handover according to some example embodiments of the present invention;

[0109] Figure 9 is a diagram illustrating an example of a UE distribution information request according to some example embodiments of the present invention;

[0110] Figure 10 is a diagram illustrating another example of a UE distribution information request according to some example embodiments of the present invention;

[0111] Figure 11 is a flow chart illustrating an example of a method according to some example embodiments of the present invention;

[0112] Figure 12 is a flow chart illustrating another example of a method according to some example embodiments of the present invention;

[0113] Figure 13 is a flow chart illustrating another example of a method according to some example embodiments of the present invention;

[0114] Figure 14 is a block diagram illustrating an example of an apparatus according to some example embodiments of the present invention;

[0115] Figure 15 is a block diagram illustrating another example of an apparatus according to some example embodiments of the present invention;

[0116] Figure 16 is a block diagram illustrating another example of an apparatus according to some example embodiments of the present invention;

[0117] Figure 17 is a block diagram illustrating another example of an apparatus according to some example embodiments of the present invention;

[0118] Figure 18 is a block diagram illustrating another example of an apparatus according to some example embodiments of the present invention;

[0119] Figure 19 is a block diagram illustrating another example of an apparatus according to some example embodiments of the present invention. DETAILED DESCRIPTION

[0120] The present disclosure is described herein with reference to specific non-limiting examples and embodiments that are presently considered to be conceivable. It will be understood by those skilled in the art that the present disclosure is by no means limited to these examples and can be applied more broadly.

[0121] It should be noted that the following description of the present disclosure and its embodiments primarily refers to specifications used as non-limiting examples of certain exemplary network configurations and deployments. That is, the present disclosure and its embodiments are primarily described with respect to 3GPP specifications, which are used as non-limiting examples of certain exemplary network configurations and deployments. Therefore, the description of the exemplary embodiments presented herein particularly refers to terminology directly related thereto. Such terminology is used only in the context of the non-limiting examples presented and naturally does not limit the present disclosure in any way. Rather, any other communication or communication-related system deployment, etc., may also be utilized as long as it conforms to the features described herein.

[0122] Hereinafter, various embodiments and implementations of the present disclosure and aspects or embodiments thereof are described using several variations and / or alternatives. It is generally noted that, depending on certain needs and constraints, all described variations and / or alternatives may be provided individually or in any conceivable combination (also including combinations of individual features of the various variations and / or alternatives).

[0123] According to some example embodiments of the present invention, a method is introduced to enable exchange of UE distribution information between two NG-RAN nodes.

[0124] A gNB, as an example of an NG-RAN node, can "unambiguously" identify the UE distribution about the cell edge based on the configured range of values ​​for a given measurement quantity.

[0125] RSRP range 1

[0126] RSRP range 2

[0127] RSRP range 3

[0128] UEs with very high RSRP measurements (above a threshold) can be assumed to be closer to the cell center, while UEs with very low RSRP measurements (below a threshold) can be assumed to be closer to the cell edge. Thus, UEs with higher RSRP values ​​(exceeding a threshold or falling within a specific range of RSRP values) can be assumed to contribute less to network energy consumption than UEs with lower RSRP values ​​(or falling within such a range of very low RSRP values).

[0129] As another alternative, the gNB can implicitly determine the UE distribution and determine that a UE belongs to the cell edge based on the energy consumed by the UE. That is, all UEs with energy consumption above a threshold (which can be set based on the median energy consumption) are assumed to belong to the cell edge, while the remaining UEs are assumed to belong to the cell center. Note that other groupings of UE distribution can be considered, not just RSRP values ​​and / or consumed energy.

[0130] As another alternative, the node can compare the distribution of UEs being offloaded by the action with a UE distribution that indicates a "balanced" UE distribution. The difference between the two distributions can then be calculated, and the result can indicate how much the two distributions differ. Therefore, the difference between the distribution after the offload action and the balanced distribution can be an indicator of how the offload action affects the balance of the network load (whether it becomes more balanced or less balanced).

[0131] A node requests this information from neighbors as part of feedback after completing an action (eg handover due to energy saving or load balancing decision) to evaluate the achieved UE distribution after the action (or its impact on performance).

[0132] According to some example embodiments of the present invention, the UE distribution itself is considered as a direct measure of the UE distribution in the cell coverage. The UE distribution is also considered for deriving other metrics, such as the energy efficiency distribution and / or energy consumption distribution corresponding to the UE distribution, which can then be exchanged. This is in Figure 2 Shown in.

[0133] Figure 3 Input parameters, output parameters and ML algorithms are shown, which can be based on non-ML statistical methods or ML methods.

[0134] like Figure 3 As shown, the input parameters are UE measurements such as RSRP, RSRQ, SINR, etc., which are input to the non-ML statistical UE distribution algorithm or the ML unsupervised learning algorithm. As output parameters, the UE coverage distribution metric and UE coverage distribution category (cell center, cell edge) are output.

[0135] Figure 4 The output UE distribution information is depicted regarding the percentage of UEs in the corresponding RSRP range, or more abstractly mapped to cell coverage using an ML-based clustering algorithm. Figure 4 It is shown that in the statistical UE coverage distribution, 40% of the UEs are in range 1, 20% are in each of range 2 and range 3, and 10% are in range 4. In addition, Figure 4 ML-based UE distribution classes (unsupervised) about cell center, mid-range and cell edge are shown.

[0136] According to some example embodiments of the present invention, in brief, the following methods are proposed.

[0137] According to the first approach, the source NG-RAN node requests feedback from the target NG-RAN node on UE distribution or other derived metrics such as energy efficiency or energy consumption metrics. This can be triggered by sending a measurement and reporting configuration from the source NG-RAN node to the target NG-RAN node, which will be used by the target NG-RAN node to calculate implicit or explicit UE distribution information.

[0138] According to the second method, the source NG-RAN node triggers measurements, UE distribution calculation, and reporting at the target RAN node. The configuration may include the set of UEs over which the UE distribution is calculated. The UEs may be all UEs affected by the AI / ML action. Alternatively, the UEs may be all UEs that are part of the provided UE trace. The AI / ML actions include:

[0139] - Load Balancing: A load balancing action at the source node where some UEs are offloaded to neighboring nodes. The source node requests UE distribution information for all candidate cells to which the UE is handed over. The source node may alternatively request an indicator (e.g., difference) of the impact of the network action on a metric (e.g., a balanced load metric).

[0140] - Network Energy Saving: Energy saving actions at the source node that involve cell on / off. The source node requests UE distribution information for all cells of the target node after cell activation or cell deactivation. Alternatively, the source node can request an indicator of the impact of the energy saving action on the cell's energy consumption (e.g., how much it increased or whether the offloaded UEs contributed more than the median energy consumption).

[0141] According to a third approach, an explicit or implicit UE distribution triggers a feedback request for a set of UEs that have switched to a specific target.

[0142] - In case of UE distributed feedback based on UE trajectories, the target node collects measurements only from those UEs that follow a given UE trajectory, ie all UEs camping on the target cell from a given source cell.

[0143] - Feedback can be triggered by AI / ML actions (e.g., switching one or multiple UEs for AI / ML load balancing or energy saving), by cell activation or cell deactivation.

[0144] To request UE distribution information from neighboring nodes, some example embodiments of the present invention introduce a new XnAP procedure. For example, this procedure can be a subscription-based procedure, such as an AIML information request / response / update. In the AIML information request message, the gNB can indicate to the neighbor the configuration related to the requested UE distribution. This configuration may include the following information:

[0145] ● Implicit or explicit UE distribution determination information:

[0146] o Explicit: If the UE distribution is determined explicitly, the measurement range over which the UE distribution is determined needs to be included.

[0147] Specifically, the following information is required in this case:

[0148] ■Range measurement: Range measurement represents a specific measurement quantity and related configuration,

[0149] ●Measurement quantity is based on RSRP or RSRQ or SINR

[0150] ● Range boundaries and range numbers of measured quantities

[0151] ○ Range boundaries / number of ranges and range measurements can be configured by the source node

[0152] ○ Range boundaries, number of ranges, and range measurements can be configured by OAM

[0153] o For example, range boundaries can be explicit (e.g. RSRP from 60 to 80 dB) or implicit “cell edge”, “mid-range”, “cell center” to allow the target node to determine which UEs are offloaded in the areas consuming the most energy per transmitted bit.

[0154] ● Range interval: The range interval is determined depending on the range boundaries and the number of possible ranges. For example, in the above example, there are 4 ranges of range intervals, Range 1, Range 2, Range 3, Range 4, or 3 ranges representing cell edge, cell center, and middle ranges.

[0155] ■ UE distribution averaging window: The distribution averaging window indicates the duration during which the distribution needs to be calculated. This can be indicated by a period of time, such as 15 minutes, 10 minutes, 5 minutes, to give a few examples.

[0156] ■ Reporting Method: The reporting method indicates whether the report is event-based or periodic.

[0157] ● For example, periodic reporting can be considered until the cell is completely shut down

[0158] ● For example, when the UE distribution changes by a threshold, event-based reporting can be considered

[0159] ○ Implicit: The UE distribution is implicitly provided through the impact on the performance metrics. In this case, the configuration should include the metrics to be used to evaluate the UE distribution. The metrics provided can be about energy consumption / energy efficiency or about energy consumption exceeding a threshold, for example, a threshold on energy consumption can be provided based on the median value of the energy consumption consumed by a set of UEs. When a set of UEs are offloaded from one node to another due to an action triggered by an ML use case (e.g. network energy saving or load balancing), the resulting energy consumption in the target node may be different from the source node. One of the contributors to this difference is the UE distribution on the target node. Therefore, the difference in the metrics (e.g. energy consumption) as shown below can be used as an implicit measure of the change in the UE distribution between the two nodes.

[0160] ■ Case 1: UE(s) mainly distributed in the cell center of node 1 are handed over to node 1 in a distributed manner along the cell edge. This will lead to an increase in energy consumption in node 2 due to the fact that node 2 has to use more radio resources and power to serve the UE(s).

[0161] ■ Case 2: UE(s) that were primarily distributed at the cell edge of node 1 are handed over to node 1 in a manner that they are distributed closer to the cell center. This will result in a reduction in energy consumption in node 2. This is due to the fact that node 2 can now serve the UE(s) with less radio resources and power.

[0162] Additionally, the network may indicate rules for which UEs the metrics will be evaluated for. That is, the rules may identify multiple UEs for which UE distribution should be provided. Some examples include the following:

[0163] ■ Calculate the energy consumption metric (in joules) or energy efficiency (in bits / joule) for all UEs affected by the shutdown decision (all UEs in a cell) or all UEs in a trajectory. UEs are classified as being in the "cell center" or "cell edge" based on a defined range of different values ​​the metric can take (e.g., the UEs consuming the most energy are classified as being on the cell edge). These ranges can also be provided in the configuration.

[0164] ■ Determine whether the energy consumption of all UEs affected by the switch-off decision (all UEs in a specific cell) or all UEs in a specific trajectory exceeds a threshold. Those UEs are determined to be UEs belonging to the cell edge.

[0165] As another example, the metric may be a load balancing metric, such as a metric indicating how balanced the UE distribution in the network is. The metric may be evaluated for all UEs in the cell, or only for UEs that have been offloaded by a load balancing action. The source node may request an indicator, such as the difference between the distribution after the offloading action and the balanced distribution, to determine how well the offloading action has performed. A higher difference value indicates that the action was suboptimal because there was a higher difference from the balanced distribution.

[0166] Next, some specific examples according to some exemplary embodiments of the present invention are described.

[0167] Figure 5 An example of a network energy saving use case is shown. UE distribution information feedback is sent periodically after cell activation.

[0168] Once NG-RAN node 1 decides to activate a cell in NG-RAN node 2, it requests UE distribution information feedback to monitor the UE distribution for a specified duration after the cell activation is triggered. After the cell activation, UEs will start moving from NG-RAN node 1 to NG-RAN node 2. This will happen over a period of time, and therefore NG-RAN node 2 needs to monitor the UE distribution information and report it according to the requested periodicity.

[0169] That is, in step S51, NG-RAN node 1 sends an AI / ML Information Request message including the UE distribution information configuration to NG-RAN node 2. In step S52, NG-RAN node 2 checks the indicated UE distribution measurement configuration and sends an OK / NOK (Yes / No) depending on whether it accepts / rejects the request. In step S53, NG-RAN node 1 sends a Cell Activation Request message to NG-RAN node 2. Then, in steps S54, S55, etc., NG-RAN node 2 periodically sends AI / ML Information Update messages including the UE distribution information to NG-RAN node 1 at the requested period.

[0170] Figure 6 Another example of a network energy saving use case is shown. After cell activation, UE distribution information is sent as a one-time feedback.

[0171] According to option #1 (such as Figure 6 As shown in the figure, when a one-time report is requested, NG-RAN node 1 waits for a specific duration (to ensure that all UEs have completed moving to the newly activated cell), after which it requests UE distribution information. The "wait duration" at NG-RAN node 1 can be a configuration parameter, or node 1 can trigger it after the handover process for all UEs to be handed over is completed. Therefore, the AI ​​ML information request process is shown in the figure after the cell activation process.

[0172] Specifically, in step S61, NG-RAN node 1 sends a cell activation request to NG-RAN node 1. Then, after the specified duration, in step S62, NG-RAN node 1 sends an AI / ML Information Request message including UE profile information configuration to NG-RAN node 2. In step S63, NG-RAN node 2 responds with an AI / ML Information Response message indicating OK or Not OK. Then, in step S64, NG-RAN node 2 sends an AI / ML Information Update message including UE profile information to NG-RAN node 1.

[0173] According to option #2, when requesting a one-time report, the NG-RAN node 1 indicates a specific duration in the UE distribution information configuration, after which the NG-RAN node 2 will report the one-time UE distribution information.

[0174] Figure 7 The case of network energy saving using one-time reported cell deactivation is shown.

[0175] In this case, in step S71, NG-RAN node 2 decides to deactivate one or more cells for network energy conservation. After deactivating the cells, NG-RAN node 2 then sends a one-time report of UE distribution information to NG-RAN node 1 in step S72. This is to enable NG-RAN node 1 to evaluate UE distribution metrics in other cells after deactivation and analyze whether there is any degradation.

[0176] Figure 8 A case of load balancing handover with periodic reporting is shown.

[0177] When NG-RAN node 1 decides to trigger a load balancing handover, it triggers a periodic reporting request to NG-RAN node 2. The selected UE(s) are offloaded to NG-RAN node 2 using a conventional handover procedure that will occur over a period of time. Since NG-RAN node 1 intends to monitor the distribution over the period of time that the handover occurs, periodic reporting is requested.

[0178] That is, in step S81, NG-RAN node 1 sends an AI / ML Information Request message including UE distribution information configuration to NG-RAN node 2. In step S82, NG-RAN node 2 responds with an AI / ML Information Response message indicating OK or Not OK. In step S83, NG-RAN node 2 triggers load balancing handover, and in step S84, NG-RAN node 2 begins periodically sending AI / ML Information Update messages including UE distribution information to NG-RAN node 1.

[0179] Similar to the network power saving use case, one-time reporting can also be used after the load balancing action is completed.

[0180] Figure 9 An example is shown where UE distribution information for a set of cell(s) is requested from NG-RAN node 1 after a specific action (e.g. cell activation / deactivation or load balancing).

[0181] In this example, in step S91, NG-RAN node 1 triggers a UE distribution information reporting procedure for a set of cell(s) to NG-RAN node 2. The configuration provided in the request message specifies the measurement range, range interval, distribution window, and reporting type (periodic, one-time). NG-RAN node 2 will use the measurement range, range interval, distribution window, and reporting type to calculate the UE distribution and report it back to NG-RAN node 1. NG-RAN node 2 checks the indicated UE distribution measurement configuration and sends an OK / NOK response in step S92 depending on whether it accepts / rejects the request. After a specific action, such as cell activation / deactivation or load balancing, NG-RAN node 2 begins measurements in step S93, calculates the UE distribution, and reports it to NG-RAN node 1 in steps S94 and S95 based on the reporting characteristics.

[0182] In this option, UE distribution information is based on actual UE measurements and is sent from the target node to the source node. This is used as a feedback metric at the source node to evaluate the impact of the actions performed.

[0183] exist Figure 10 In

[15] , the source node requests the target node to predict the UE distribution for a given UE trajectory. The source node requests the target node to offload the predicted impact (UE distribution) of the group of UEs with the predicted UE trajectory, and the target node then responds with the prediction. For example, the source node can be configured such that it requires the UE distribution of all UEs following the trajectory (node ​​1 / cell X, node 2 / cell Y). In this case, node 2 will calculate the UE distribution of all UEs that switch from node 1 / cell X to node 2 / cell Y during the indicated time window and report it to node 1.

[0184] In step S101, NG-RAN node 1 triggers a UE distribution request procedure to NG-RAN node 2, configuring the measurement range, range interval, distribution window, and reporting type to be used. NG-RAN node 2 will calculate the UE distribution based on these and report it to the NG-RAN node. NG-RAN node 2 checks the indicated UE distribution measurement configuration and sends an OK / NOK response in step S102 depending on whether it accepts / rejects the request. NG-RAN node 2 starts measurements only for those UEs that follow the indicated trajectory, calculates the UE distribution, and reports it to NG-RAN node 1 in steps S103 and S104, based on the reporting characteristics.

[0185] Below, refer to Figures 11 to 19 An exemplary version of the invention is described more generally.

[0186] Figure 11 is a flow chart illustrating examples of methods according to some example versions of the invention.

[0187] According to an example version of the present invention, the method may be implemented in a network node or may be part of a network node, such as an NG-RAN node, a gNB, etc. The method comprises receiving measurement data from at least one user equipment located in a cell managed by the network node in step S111, and determining user equipment distribution information of the at least one user equipment based on the received measurement data in step S112.

[0188] According to some example versions of the invention, the measurement data indicates at least one of reference signal received power RSRP, reference signal received quality RSRQ, and signal to interference and noise ratio SINR, and the network node determines the distribution of at least one user equipment within a cell managed by the network node by comparing at least one of RSRP, RSRQ, and SINR with a predetermined threshold or a predetermined range of values.

[0189] According to some example versions of the present invention, the method further includes determining that at least one user equipment belongs to a cell center if at least one of RSRP, RSRQ, and SINR is above a predetermined threshold or within a first predetermined value range, and determining that at least one user equipment belongs to a cell edge if RSRQ and SINR, RSRP, RSRQ, and SINR are below a predetermined threshold or within a second predetermined value range.

[0190] According to some example versions of the invention, the measurement data indicates energy consumption of at least one user equipment, and the network node determines a distribution of the at least one user equipment within a cell managed by the network node by comparing the energy consumption with a predetermined threshold.

[0191] According to some example versions of the invention, the method further comprises determining that the at least one user equipment belongs to a cell center if the energy consumption is below a predetermined threshold, and determining that the at least one user equipment belongs to a cell edge if the energy consumption is above a predetermined threshold.

[0192] According to some example versions of the present invention, the method further comprises comparing the determined user equipment distribution with a predetermined user equipment distribution, and determining a difference between the determined user equipment distribution and the predetermined user equipment distribution.

[0193] Figure 12 is a flow chart illustrating another example of a method according to some example versions of the invention.

[0194] According to an example version of the present invention, the method may be implemented in a first network node or may be part of the first network node, such as a source NG-RAN node, such as a gNB, etc. The method comprises: sending a request for user equipment distribution information to a second network node in step S121, and receiving UE distribution information from the second network node according to the request in step S122.

[0195] According to some example versions of the invention, the method further comprises performing a predetermined action, and receiving UE distribution information from the second network node before and / or after the predetermined action has been performed.

[0196] According to some example versions of the invention, the predetermined action comprises requesting activation of a cell in the second network node, wherein the UE distribution information is received after the cell has been activated in the second network node and after at least one user equipment has moved from the first network node to the second network node.

[0197] According to some example versions of the invention, the predetermined action comprises triggering a handover procedure to hand over the UE from the first network node to the second network node, wherein the UE distribution information is received after at least one user equipment has moved from the first network node to the second network node.

[0198] According to some example versions of the invention, the request for the UE distribution information includes measurement and reporting configuration information to be used by the second network node to calculate the UE distribution information.

[0199] According to some example versions of the present invention, the reporting configuration indicates that the UE distribution information is reported periodically for a predetermined reporting period, or the reporting configuration indicates that the UE distribution information is reported only once.

[0200] According to some example versions of the invention, the request for UE distribution information comprises information about a set of UEs for which the UE distribution information is to be calculated by the second network node.

[0201] According to some example versions of the present invention, the set of UEs includes UEs affected by artificial intelligence / machine learning AI / ML actions, where the AI / ML actions include one of the following: load balancing, network energy saving, and mobility robustness optimization.

[0202] According to some example versions of the invention, the set of UEs comprises UEs following a predetermined trajectory defined by a sequence of cells.

[0203] Figure 13 is a flow chart illustrating another example of a method according to some example versions of the invention.

[0204] According to an example version of the present invention, the method may be implemented in a second network node or may be part of the second network node, such as a target NG-RAN node, such as a gNB. The method includes: receiving a request for user equipment distribution information from a first network node in step S131; calculating UE distribution information by the second network node in step S132; and reporting the calculated UE distribution information to the first network node in step S133.

[0205] According to an example version of the invention, the UE distribution information is calculated before and / or after the predetermined action is performed by the first network node.

[0206] According to an example version of the invention, the predetermined action comprises requesting activation of a cell in the second network node, wherein the second network node starts calculating the UE distribution information after the cell has been activated in the second network node and after at least one user equipment has moved from the first network node to the second network node.

[0207] According to an example version of the invention, the predetermined action comprises triggering a handover procedure to hand over the UE from the first network node to the second network node, wherein the second network node starts calculating the UE distribution information after at least one user equipment has moved from the first network node to the second network node.

[0208] According to an example version of the invention, the request for the UE distribution information comprises measurement and reporting configuration information to be used by the second network node to calculate the UE distribution information.

[0209] According to an example version of the present invention, depending on the reporting configuration information, the second network node periodically reports the UE distribution information for a predetermined reporting period, or the second network node reports the UE distribution information only once.

[0210] According to an example version of the invention, the second network node calculates UE distribution information for a set of UEs indicated in the request for UE distribution information from the first network node.

[0211] According to an example version of the present invention, the UE set includes UEs affected by artificial intelligence / machine learning AI / ML actions, wherein the AI / ML actions include one of the following: load balancing, network energy saving, and mobility robustness optimization.

[0212] According to an example version of the invention, the set of UEs comprises UEs following a predetermined trajectory defined by a sequence of cells.

[0213] Figure 14 is a block diagram illustrating examples of apparatus according to some example versions of the present invention.

[0214] exist Figure 14 , a block circuit diagram of the configuration of the diagram device 140 is shown, which is configured to implement the above-mentioned various aspects of the present invention. It should be noted that Figure 14 The device 140 shown in FIG may include several additional elements or functions in addition to those described herein below, which are omitted for simplicity as they are not necessary for understanding the present invention. In addition, the device may also be another device with similar functions, such as a chipset, a chip, a module, etc., which may also be part of the device or attached to the device as a separate element, etc.

[0215] Device 140 may include a processing function or processor 141, such as a CPU, which executes instructions given by a program, etc. Processor 141 may include one or more processing sections dedicated to a specific process, as described below, or the process may be performed within a single processor. The sections used to perform such specific processes may also be provided as discrete components, or provided within one or more processors or processing sections, such as within a physical processor (e.g., a CPU) or across several physical entities. Reference numeral 142 denotes a transceiver or input / output (I / O) unit (interface) connected to processor 141. I / O unit 142 may be used to communicate with one or more other network elements, entities, terminals, etc. I / O unit 142 may be a combined unit including communication equipment for several network elements, or may include a distributed structure with multiple different interfaces for different network elements. Device 140 also includes at least one memory 143, which may be used, for example, to store data and programs to be executed by processor 141 and / or serve as working memory for processor 141.

[0216] The processor 141 is configured to perform processing related to the above-mentioned aspects.

[0217] In particular, the apparatus 140 may be implemented in a first network entity or may be a part of the first network entity, such as an EASDF, and may be configured to perform the combined Figure 11 The processing described.

[0218] Therefore, according to some example versions of the present invention, there is provided an apparatus 140 for use in a network node, comprising at least one processor 141 and at least one memory 143 for storing instructions to be executed by the processor 141, wherein the at least one memory 143 and the instructions are configured to, together with the at least one processor 141, cause the apparatus 140 to at least perform the steps of receiving measurement data from at least one user equipment located in a cell managed by the network node, and determining user equipment distribution information of the at least one user equipment based on the received measurement data.

[0219] Figure 15is a block diagram illustrating another example of an apparatus according to some example versions of the present invention. Figure 15 The device shown in FIG has basically the same Figure 14 The structural components and arrangement of the device are the same, so their description will not be repeated.

[0220] The processor 151 is configured to perform processing related to the above-mentioned aspects.

[0221] In particular, the apparatus 150 may be implemented in a first network node or may be a part of a first network node and may be configured to perform the combined Figure 12 The processing described.

[0222] Therefore, according to some example versions of the present invention, there is provided an apparatus 150 for use in a first network node, comprising at least one processor 151 and at least one memory 153 for storing instructions to be executed by the processor 151, wherein the at least one memory 153 and the instructions are configured to, together with the at least one processor 151, cause the apparatus 150 to at least perform sending a request for user equipment distribution information to a second network node, and receiving UE distribution information from the second network node according to the request.

[0223] Figure 16 is a block diagram illustrating another example of an apparatus according to some example versions of the present invention. Figure 16 The device shown in FIG has basically the same Figure 14 The structural components and arrangement of the device are the same, so their description will not be repeated.

[0224] The processor 161 is configured to perform processing related to the above-mentioned aspects.

[0225] In particular, the apparatus 160 may be implemented in the second network node or may be a part of the second network node and may be configured to perform the combined Figure 13 The processing described.

[0226] Therefore, according to some example versions of the present invention, there is provided an apparatus 160 for use in a second network node, comprising at least one processor 161 and at least one memory 163 for storing instructions to be executed by the processor 161, wherein the at least one memory 163 and the instructions are configured to, together with the at least one processor 161, cause the apparatus 160 to at least perform receiving a request for user equipment distribution information from the first network node, calculating the UE distribution information by the second network node, and reporting the calculated UE distribution information to the first network node.

[0227] In addition, the present invention can be implemented by an apparatus for a network node, the apparatus comprising components for performing the above-mentioned processing, such as Figure 17 shown.

[0228] That is, according to some example versions of the present invention, such as Figure 17 As shown, the apparatus for use in a network node comprises a component 171 for receiving measurement data from at least one user equipment located in a cell managed by the network node, and a component 172 for determining user equipment distribution information of the at least one user equipment based on the received measurement data.

[0229] Furthermore, the present invention may be implemented by an apparatus for a first network node, the apparatus comprising means for performing the above-mentioned processing, such as Figure 18 shown.

[0230] That is, according to some example versions of the present invention, such as Figure 18 As shown, the apparatus for use in a first network node comprises a component 181 for sending a request for user equipment distribution information to a second network node, and a component 182 for receiving UE distribution information from the second network node according to the request.

[0231] Furthermore, the present invention may be implemented by an apparatus for a second network node, the apparatus comprising means for performing the above-mentioned processing, such as Figure 19 shown.

[0232] That is, according to some example versions of the present invention, such as Figure 19 As shown, the apparatus for use in the second network node comprises a component 191 for receiving a request for user equipment distribution information from the first network node, a component 192 for calculating the UE distribution information by the second network node, and a component 193 for reporting the calculated UE distribution information to the first network node.

[0233] In addition, according to some example versions of the present invention, there is provided a computer program comprising instructions, which, when executed by an apparatus for use in a network node, causes the apparatus to perform: receiving measurement data from at least one user equipment located in a cell managed by the network node, and determining user equipment distribution information of the at least one user equipment based on the received measurement data.

[0234] In addition, according to some example versions of the present invention, there is provided a computer program comprising instructions, which, when executed by an apparatus for use in a first network node, causes the apparatus to execute: sending a request for user equipment distribution information to a second network node, and receiving UE distribution information from the second network node according to the request.

[0235] In addition, according to some example versions of the present invention, there is provided a computer program comprising instructions, which, when executed by an apparatus for use in a second network node, causes the apparatus to perform: receiving a request for user equipment distribution information from a first network node, calculating the UE distribution information by the second network node, and reporting the calculated UE distribution information to the first network node.

[0236] The computer program product may comprise code means adapted to produce the steps of any of the methods described above when loaded into the memory of a computer.

[0237] According to some example versions of the invention, there is provided a computer program product as defined above, wherein the computer program product comprises a computer-readable medium on which the software code portions are stored.

[0238] According to some example versions of the invention, there is provided a computer program product as defined above, wherein the program is directly loadable into an internal memory of a processing device / apparatus.

[0239] According to some example versions of the present invention, there is provided a computer-readable medium storing a computer program as described above.

[0240] According to some example versions of the present invention, a computer program product is provided comprising a computer-executable computer program code, which, when the program is run on a computer (e.g., a computer of an apparatus according to any one of the aforementioned apparatus-related exemplary aspects of the present disclosure), is configured to cause the computer to perform a method according to any one of the aforementioned method-related exemplary aspects of the present disclosure.

[0241] Such a computer program product may comprise (or be embodied as) a (tangible) computer-readable (storage) medium or the like having computer-executable computer program code stored thereon, and / or the program may be directly loadable into the internal memory of a computer or its processor.

[0242] Furthermore, the present invention may be implemented by a device used in a network node, the device comprising corresponding circuits for performing the above-mentioned processing.

[0243] That is, according to some example versions of the present invention, there is provided an apparatus for use in a network node, comprising a receiving circuit for receiving measurement data from at least one user equipment located within a cell managed by the network node, and a determining circuit for determining user equipment distribution information of the at least one user equipment based on the received measurement data.

[0244] Furthermore, the present invention may be implemented by an apparatus for use in a first network node, the apparatus comprising corresponding circuits for performing the above-mentioned processing.

[0245] That is, according to some example versions of the present invention, there is provided an apparatus for use in a first network node, comprising a sending circuit for sending a request for user equipment distribution information to a second network node, and a receiving circuit for receiving the UE distribution information from the second network node according to the request.

[0246] Furthermore, the present invention may be implemented by an apparatus for use in a second network node, the apparatus comprising corresponding circuits for performing the above-mentioned processing.

[0247] That is, according to some example versions of the present invention, there is provided an apparatus for use in a second network node, comprising a receiving circuit for receiving a request for user equipment distribution information from a first network node, a calculating circuit for calculating the UE distribution information by the second network node, and a reporting circuit for reporting the calculated UE distribution information to the first network node.

[0248] For further details on the functionality of the apparatus and computer program, reference is made to the above description of the method according to some exemplary versions of the invention, as described in conjunction with Figures 11 to 13 described.

[0249] In the foregoing exemplary description of the device, only the units / components relevant to understanding the principles of the present invention have been described using functional blocks. The device may include additional units / components necessary for their respective operations. However, the description of these units / components is omitted in this specification. The arrangement of the functional blocks of the device should not be interpreted as limiting the present invention, and the functions may be performed by one block or further divided into sub-blocks.

[0250] When it is stated in the foregoing description that the apparatus (or some other component) is configured to perform some functions, this will be interpreted as equivalent to a description stating that (i.e., at least one) processor or corresponding circuitry, potentially in cooperation with computer program code stored in a memory of the corresponding apparatus, is configured to cause the apparatus to perform at least the functions mentioned thereby. Furthermore, such functions will be interpreted as being equivalently implementable by circuits or components specifically configured to perform the corresponding functions (i.e., the expression "a unit configured to..." will be interpreted as being equivalent to expressions such as "a component for...").

[0251] As used in this application, the term "circuitry" may refer to one or more or all of the following:

[0252] (a) hardware-only circuit implementation (e.g., implementation in analog and / or digital circuitry only), and

[0253] (b) a combination of hardware circuitry and software such as (as applicable):

[0254] (i) a combination of analog and / or digital hardware circuitry and software / firmware,

[0255] as well as

[0256] (ii) any portion of a hardware processor (including a digital signal processor) with software, software, and memory that work together to enable a device such as a mobile phone or server to perform various functions), and

[0257] (c) Hardware circuits and / or processors (e.g., a microprocessor or portion of a microprocessor) that require software (e.g., firmware) for operation, but where software is not required for operation, the software may not be present.

[0258] This definition of circuitry applies to all uses of this term in this application, including in any claims. As a further example, as used in this application, the term circuitry also covers an implementation of merely a hardware circuit or processor (or multiple processors) or a portion of a hardware circuit or processor and its (or their) accompanying software and / or firmware. The term circuitry also covers, for example and if applicable to the particular claim element, a baseband integrated circuit or processor integrated circuit for a mobile device, or a similar integrated circuit in a server, cellular network device, or other computing or networking device.

[0259] For the purpose of the present invention as described above, it should be noted that

[0260] - the method steps which may be implemented as software code portions and executed on an apparatus using a processor (as an example of a device, an apparatus and / or its modules, or as an example of an entity thus comprising an apparatus and / or a module) are independent of the software code and may be specified using any known or later developed programming language as long as the functionality defined by the method steps is preserved;

[0261] - generally, any method step is suitable for being implemented as software or by hardware without changing the idea of ​​the aspect / embodiment and its modification in terms of the functionality achieved;

[0262] - the method steps and / or devices, units or parts (e.g., devices that perform the functions of the apparatus according to the aspects / embodiments as described above) that may be implemented as hardware components at the apparatus defined above or any module thereof are hardware-independent and may be implemented using any known or future developed hardware technology or any mixture of these, such as MOS (metal oxide semiconductor), CMOS (complementary MOS), BiMOS (bipolar MOS), BiCMOS (bipolar CMOS), ECL (emitter coupled logic), TTL (transistor-transistor logic), etc., using, for example, ASIC (application specific IC) components, FPGA (field programmable gate array) components, CPLD (complex programmable logic device) components, APU (accelerated processor unit), GPU (graphics processor unit) or DSP (digital signal processor) components;

[0263] - devices, units or components (e.g. the apparatus defined above, or any of their respective units / components) may be implemented as separate devices, units or components, but this does not exclude that they are implemented in a distributed manner throughout the system, as long as the functionality of the devices, units or components is preserved;

[0264] - the apparatus may be embodied by a semiconductor chip, a chipset or a (hardware) module comprising such a chip or chipset; however, this does not exclude the possibility that the functionality of the apparatus or module is not implemented in hardware but as software in a (software) module, such as a computer program or computer program product comprising executable software code portions for execution / running on a processor;

[0265] - For example, a device may be considered to be a means or an assembly of more than one means, whether they functionally cooperate with each other or functionally independent of each other but in the same device housing.

[0266] In general, it should be noted that the various functional blocks or elements according to the above aspects can be implemented in the form of hardware and / or software by any known means, if only suitable for performing the described functions of the various parts. The mentioned method steps can be implemented in separate functional blocks or by separate devices, or one or more method steps can be implemented in a single functional block or by a single device.

[0267] In general, any method step is suitable for implementation as software or hardware without changing the concept of the present invention. Devices and means may be implemented as individual devices, but this does not preclude their implementation in a distributed manner throughout the system, as long as the functionality of the device is preserved. Such and similar principles are considered to be known to those skilled in the art.

[0268] Software in the sense of this specification comprises software code, which itself comprises code means or portions for performing the corresponding functions, or a computer program or a computer program product, as well as software (or a computer program or a computer program product) embodied on a tangible medium, such as a computer-readable (storage) medium on which the corresponding data structures or code means / portions are stored, or which may be embodied in a signal or a chip during processing thereof.

[0269] It should be noted that the foregoing aspects / embodiments and general and specific examples are provided for illustrative purposes only and are not intended to limit the invention thereto. On the contrary, the invention is to cover all changes and modifications falling within the scope of the appended claims.

Claims

1. A method for use in a network node, comprising: receiving measurement data from at least one user equipment located within a cell managed by the network node, and User equipment distribution information of the at least one user equipment is determined based on the received measurement data.

2. The method according to claim 1, wherein The measurement data indicates at least one of the following: reference signal received power RSRP, reference signal received quality RSRQ, and signal to interference plus noise ratio SINR, and The network node determines the distribution of the at least one user equipment within the cell managed by the network node by comparing at least one of the RSRP, RSRQ and SINR with a predetermined threshold or a predetermined value range.

3. The method according to claim 2, further comprising: If at least one of the RSRP, RSRQ and SINR is higher than the predetermined threshold or within a first predetermined value range, determining that the at least one user equipment belongs to the center of the cell, and If the RSRQ and SINR, the RSRP, RSRQ and SINR are lower than the predetermined threshold or within a second predetermined value range, it is determined that the at least one user equipment belongs to the edge of the cell.

4. The method according to claim 3, wherein: The measurement data indicates energy consumption of the at least one user equipment, and The network node determines the distribution of the at least one user equipment within the cell managed by the network node by comparing the energy consumption with a predetermined threshold.

5. The method according to claim 4, further comprising: If the energy consumption is lower than the predetermined threshold, determining that the at least one user equipment belongs to the center of the cell, and If the energy consumption is higher than the predetermined threshold, it is determined that the at least one user equipment belongs to the edge of the cell.

6. The method according to any one of claims 1 to 5, further comprising: comparing the determined user equipment distribution with a predetermined user equipment distribution, and A difference between the determined user equipment distribution and the predetermined user equipment distribution is determined.

7. A method for use in a first network node, comprising: sending a request for user equipment distribution information to the second network node, and UE distribution information is received from the second network node according to the request.

8. The method according to claim 7, further comprising: Perform the intended action, and Before and / or after the predetermined action has been performed, UE distribution information is received from the second network node.

9. The method according to claim 8, wherein The predetermined action comprises requesting activation of a cell in the second network node, wherein the UE distribution information is received after the cell has been activated in the second network node and after at least one user equipment has moved from the first network node to the second network node.

10. The method according to claim 8, wherein The predetermined action comprises triggering a handover procedure to hand over a UE from the first network node to the second network node, wherein the UE distribution information is received after at least one user equipment has moved from the first network node to the second network node.

11. The method according to any one of claims 7 to 10, wherein The request for UE distribution information includes measurement and reporting configuration information to be used by the second network node to calculate the UE distribution information.

12. The method according to claim 11, wherein The reporting configuration indicates that the UE distribution information is periodically reported for a predetermined reporting period, or The reporting configuration indicates that the UE distribution information is reported only once.

13. The method according to any one of claims 7 to 12, wherein: The request for UE distribution information comprises information about a set of UEs for which the UE distribution information is to be calculated by the second network node.

14. The method according to claim 13, wherein: The UE set includes UEs affected by artificial intelligence / machine learning AI / ML actions, wherein the AI / ML actions include one of the following: load balancing, network energy saving, and mobility robustness optimization.

15. The method according to claim 13, wherein The set of UEs includes UEs that follow a predetermined trajectory defined by a sequence of cells.

16. A method for use in a second network node, comprising: receiving a request for user equipment distribution information from a first network node, The second network node calculates UE distribution information, and The calculated UE distribution information is reported to the first network node.

17. The method according to claim 16, wherein The UE distribution information is calculated before and / or after the first network node performs a predetermined action.

18. The method according to claim 17, wherein The predetermined action comprises requesting activation of a cell in the second network node, wherein the second network node starts calculating the UE distribution information after the cell has been activated in the second network node and after at least one user equipment has moved from the first network node to the second network node.

19. The method according to claim 17, wherein The predetermined action comprises triggering a handover procedure to hand over the UE from the first network node to the second network node, wherein the second network node starts calculating the UE distribution information after at least one user equipment has moved from the first network node to the second network node.

20. The method according to any one of claims 16 to 19, wherein The request for UE distribution information includes measurement and reporting configuration information to be used by the second network node to calculate the UE distribution information.

21. The method according to claim 20, wherein Depending on the reporting configuration information, the second network node periodically reports the UE distribution information for a predetermined reporting period, or the second network node reports the UE distribution information only once.

22. The method according to any one of claims 16 to 21, wherein The second network node calculates the UE distribution information for a set of UEs indicated in the request for UE distribution information from the first network node.

23. The method according to claim 22, wherein The UE set includes UEs affected by artificial intelligence / machine learning AI / ML actions, wherein the AI / ML actions include one of the following: load balancing, network energy saving, and mobility robustness optimization.

24. The method according to claim 22, wherein The set of UEs includes UEs that follow a predetermined trajectory defined by a sequence of cells.

25. An apparatus for use in a network node, comprising: means for receiving measurement data from at least one user equipment located within a cell managed by said network node, and Means for determining user equipment distribution information of the at least one user equipment based on the received measurement data.

26. An apparatus for use in a first network node, comprising: means for sending a request for user equipment distribution information to the second network node, means for receiving UE distribution information from the second network node according to the request.

27. An apparatus for use in a second network node, comprising: means for receiving a request for user equipment distribution information from the first network node, means for calculating, by the second network node, UE distribution information, and means for reporting the calculated UE distribution information to the first network node.

28. A computer program comprising instructions which, when executed by an apparatus, cause the apparatus to perform the method according to any one of claims 1 to 6.

29. A computer program comprising instructions which, when executed by an apparatus, cause the apparatus to perform the method according to any one of claims 7 to 15.

30. A computer program comprising instructions which, when executed by an apparatus, cause the apparatus to perform the method according to any one of claims 16 to 24.

Images