Method and communication network device

Abstract

A method performed by an access network node of a communication network is disclosed. The method includes transmitting, to another node of the communication network, input data including at least one data item from a group of: i) at least one Synchronisation Signal Block (SSB) index that overlaps with a cell of the other node and the number of UEs for each SSB that overlaps with the cell of the other node, ii) hardware load data indicating the hardware load of the access network node, iii) radio resource load data indicating the radio resource load of the access network node, and iv) objective data indicating the objective of a model trained or updated by the other node. The input data is used to train a model for outputting at least one parameter for load distribution.

Description

Technical Field

[0001] The present disclosure relates to a wireless communication system operating according to 3rd Generation Partnership Project (3GPP) (registered trademark) standards or equivalent or derivative standards thereof, and devices thereof. The present disclosure relates, in particular although not exclusively, to load distribution techniques in so-called "5G" or "New Radio" systems (also referred to as "next-generation" systems) and similar systems.

Background Art

[0002] Under 3GPP standards, a NodeB (or "eNB" in LTE, "gNB" in 5G) is a base station for a communication device (user equipment, or "UE") to connect to a core network and communicate with other communication devices or remote servers. Communication between the UE and the base station is controlled using a so-called Radio Resource Control (RRC) protocol. The communication device may be, for example, a mobile communication device such as a mobile phone, smartphone, smartwatch, personal digital assistant, laptop / tablet computer, web browser, e-book reader, etc. Such mobile (or more generally fixed) devices are usually operated by a user (and thus are often collectively referred to as user equipment "UE"), but it is also possible to connect Internet of Things (IoT) devices and similar Machine Type Communication (MTC) devices to the network. For simplicity, in this application, the term base station is used to refer to any such base station, and the terms mobile device or UE are used to refer to any such communication device.

[0003] The latest development of the 3GPP specifications refers to the so-called "5G" or "New Radio" (NR) specifications, which are evolving communication technologies expected to support various applications and services such as MTC / IoT communication, vehicle communication and autonomous vehicles, high-resolution video streaming, and smart city services. 3GPP intends to support 5G with the so-called 3GPP Next Generation (NextGen) radio access network (RAN) and 3GPP NextGen core (NGC) network. Various details of the 5G network are described, for example, in Non-Patent Document 1.

[0004] End-user communication devices are generally called User Equipment (UE) and may be operated by humans or may be equipped with automated (MTC / IoT) devices. The base stations of the 5G / NR communication system are generally called New Radio Base Station ("NR-BS") or "gNB", but it will be understood that they may more typically be referred to using the term "eNB" (or 5G / NR eNB) associated with Long Term Evolution (LTE) base stations (also generally called "4G" base stations). Non-Patent Document 2 and Non-Patent Document 3 define, among other things, the following nodes. gNB: A node that provides protocol terminations for the NR user plane and control plane towards the UE and is connected to the 5G core network (5GC) via the NG interface. ng-eNB: A node that provides protocol terminations for the Evolved Universal Terrestrial Radio Access (E-UTRA) user plane and control plane towards the UE and is connected to the 5GC via the NG interface. En-gNB: A node that provides protocol termination for the NR user plane and control plane towards the UE and functions as a secondary node in E-UTRA-NR Dual Connectivity (EN-DC). NG-RAN node: Either a gNB or an ng-eNB.

[0005] The terms base station or access network node or RAN node are used in this specification to refer to any such node.

[0006] Some of the additional developments in 3GPP relate to the use of artificial intelligence (AI) and machine learning (ML), often abbreviated as AI / ML. Several use cases have been proposed for AI / ML, one in the context of load distribution. Generally, load distribution is the process by which traffic within a radio access network is distributed as evenly as possible between cells and between cell areas. Alternatively, load distribution may instead involve transferring some of the traffic from a congested cell or from a congested area of a cell, or offloading users from one cell, cell area, carrier, or radio access technology (RAT) to improve network performance as evenly as possible. Such distribution can be achieved by optimizing the handover parameters used in the radio access network and by handover actions made by the RAT.

Prior Art Documents

Non-Patent Documents

[0007]

Non-Patent Document 1

Non-Patent Document 2

Non-Patent Document 3

Non-Patent Document 4

Summary of the Invention

Problems to be Solved by the Invention

[0008] In this regard, in addition to multiple frequency bands used in commercial network deployments, it will be understood that due to a significant increase in network traffic, it has become particularly difficult for network operators to control traffic in a balanced manner when applying known load balancing techniques. Specifically, current load balancing decisions that depend on the cell load situation of the current / past state are insufficient for the rapid changes in network traffic load and resource situation, especially in the context of advanced 5G networks. For example, scenarios involving high mobility and a large number of connections can lead to ping-pong handovers between different cells, cell overload, and ultimately a degradation in user service quality.

[0009] Therefore, it is desired to make better load balancing decisions in a telecommunications network. A base station can do this if it has more accurate load information of at least one cell it controls and / or more accurate load information of adjacent cells.

[0010] Accordingly, the present disclosure seeks to provide a method and related apparatus for addressing or at least mitigating (at least some of) the above-mentioned problems. The present disclosure is set forth in the appended independent claims. Optional features are set forth in the appended dependent claims.

Means for Solving the Problem

[0011] According to one aspect, a method performed by an access network node of a communication network is provided. The method includes transmitting, to another node of the communication network, input data including at least one data item from a group of: i) at least one SSB index of a Synchronisation Signal Block (SSB) that overlaps with a cell of the other node, and the number of UEs for each SSB that overlaps with the cell of the other node; ii) hardware load data indicating the hardware load of the access network node; iii) radio resource load data indicating the radio resource load of the access network node; iv) objective data indicating the objective of a model trained or updated by the other node. The input data can be used to output at least one parameter for load distribution.

[0012] When the input data includes radio resource load data, the input data may indicate the usage amount of physical resource blocks (PRBs) by the access network node.

[0013] When the input data includes hardware load data or radio resource load data, the input data may represent a filtered average load of the access network load over a past period of time. The filtered average load may be represented by a general load state descriptor (such as "low", "medium", "high", etc.) or by a predetermined load ratio (such as 20% of the available capacity).

[0014] If the input data includes the target data, the target data may be one of load balancing, mobility robustness, and energy saving.

[0015] The method may further include receiving a measurement report from one or more user equipments (UEs) served by an access network node or another access network node, and transmitting may be performed by transmitting the input data together with the measurement report.

[0016] The method may further include receiving a model trained with the input data and using the model to output at least one parameter for load balancing. The model may include a mapping table that associates the power of at least one SSB of an access network node with the number of UEs that provide at least one measurement report to at least one access network node adjacent to the access network node.

[0017] According to another aspect, a method executed by an access network node is provided. This method may be executed by the same or different access network nodes that executed the first method. The method comprises receiving a model including a mapping table that associates the power of at least one Synchronisation Signal Block (SSB) of the access network node with the number of user equipment (UE) that provides at least one measurement report to at least one adjacent access network node adjacent to the access network node, receiving input information from at least one adjacent access network node, and using the input information and the model to determine at least one load balancing action to be executed by the access network node, wherein the input information includes at least one data item from a group of (i) at least one SSB index of at least one SSB that overlaps with each cell of at least one adjacent access network node, and the number of UEs for each SSB that overlaps with each cell of at least one adjacent access network node, (ii) hardware load data indicating the hardware load of the access network node, and (iii) radio resource load data indicating the radio resource load of the access network node.

[0018] The at least one load balancing action may include at least one of changing (increasing and / or decreasing) the transmission power of at least one SSB, changing at least one handover decision parameter used by the access network node to determine when to hand over a UE to an adjacent access network node, changing a measurement event that triggers a handover of a UE to an adjacent access network node, changing the elapsed time after a measurement event is reported to trigger a handover, and changing the measurement configuration of at least one UE and transmitting the measurement configuration to at least one UE.

[0019] When the load of the SSB is greater than the load of at least one adjacent access network node, and when the load of at least one adjacent access network node is greater than the load of at least one SSB, at least one load balancing action may occur in at least one of these cases. At least one load balancing action may include reducing the transmission power of at least one SSB when the load in the SSB is greater than the load in at least one adjacent access network node. At least one load balancing action may include increasing the transmission power of at least one SSB when the load in at least one adjacent access network node is greater than the load in at least one SSB.

[0020] At least one action may include changing the measurement configuration of at least one UE and transmitting the measurement configuration to at least one UE, and the measurement configuration may define a situation in which at least one UE is caused to transmit a measurement report to an access network node.

[0021] In some embodiments, the method may further comprise transmitting to an adjacent access network node other input information related to the load on the access network node for the purpose of load balancing, and the other input information may include at least one data item from the group of the SSB index of the SSB that overlaps with the cell of the adjacent access network node, the number of UEs for each SSB that overlaps with the cell of the adjacent access network node, the hardware load, and the radio resource load. The other input data may be updated input data.

[0022] The method may further comprise receiving a measurement report transmitted from one or more user equipment (UE) served by an access network node or another access network node, and the use is performed using the measurement report.

[0023] According to another aspect, a method executed in a communication network is provided. The method includes receiving input data from at least one of a plurality of access network nodes, and using the input data and a model from at least one of the plurality of access network nodes to determine at least one load prediction for at least one of the plurality of access network nodes. The at least one load prediction includes at least one data item from the group of: i) the total number of user equipment (UE) served by at least one access network node, ii) the number of UEs per Synchronisation Signal Block (SSB) of at least one access network node, iii) the number of UEs served by at least one access network node that transmits a measurement report identifying a given neighbouring cell, and iv) the predicted radio resource load of at least one access network node. The input data may include at least one of: i) at least one SSB index of SSBs overlapping with cells of neighbouring access network nodes adjacent to one of the at least one access network nodes, and the number of UEs per SSB overlapping with cells of neighbouring access network nodes, ii) hardware load data indicating the hardware load of the access network node, iii) radio resource load data indicating the radio resource load of the access network node, and iv) target data indicating the target of the model to be trained or updated. The method may be executed by a model inference node or an access network node of the communication network, and the model used may be obtained from a model training function.

[0024] At least one data item of the at least one load prediction may include a deviation from the predicted number indicated by the at least one data item.

[0025] If at least one of the data items of at least one load prediction includes the predicted radio resource load of at least one access network node, the predicted radio resource load may include the physical resource block usage per cell or per SSB.

[0026] The method may further comprise using at least one load prediction, model, and input data from neighboring access network nodes or UEs to determine a load balancing command for at least one access network node, the load balancing command including at least one data item from the group of: i) power parameters, ii) measurement configuration, iii) handover decision configuration, and iv) UE handover decision. The power parameters may be cell, SSB beam, or site power parameters. The measurement configuration may be for the UE and may define a situation in which the UE is caused to send a measurement report to the access network node. The handover configuration decision may define at least one condition necessary for at least one access network node to trigger a handover of the UE to a neighboring cell. For example, the at least one condition includes at least one of: i) a measurement event signaled by the UE before triggering a handover of the UE to a neighboring cell, and ii) the elapsed time from the measurement event before the UE handover is triggered.

[0027] In some embodiments, the UE handover decision identifies at least one UE served by at least one access network node and a target cell to which the at least one UE is to be handed over.

[0028] According to another aspect, an access network node of a communication network is provided, the access network node comprising means for transmitting to another node of the communication network input data comprising at least one data item from the group of: i) at least one SSB index of a Synchronisation Signal Block (SSB) overlapping with a cell of the other node, and the number of UEs per SSB overlapping with a cell of the other node, ii) hardware load data indicating the hardware load of the access network node, iii) radio resource load data indicating the radio resource load of the access network node, iv) objective data indicating the objective of a model trained or updated by the other node. The input data can be used to train a model for outputting at least one parameter for load distribution.

[0029] According to another aspect, means for receiving a model including a mapping table associating the power of at least one Synchronisation Signal Block (SSB) of an access network node with the number of user equipment (UE) that provides at least one measurement report to at least one adjacent access network node adjacent to the access network node, means for receiving input information from at least one adjacent access network node, and means for using the input information and the model to determine at least one load balancing action to be performed by the access network node, wherein the input information includes at least one data item from a group of: i) at least one Synchronisation Signal Block (SSB) index of the SSB overlapping with each cell of at least one adjacent access network node, and the number of UEs for each SSB overlapping with each cell of at least one adjacent access network node, ii) hardware load data indicating the hardware load of the access network node, and iii) radio resource load data indicating the radio resource load of the access network node, is provided to the access network node.

[0030] According to another aspect, means for receiving input data from at least one of a plurality of access network nodes, and means for using the input data and a model from at least one of the plurality of access network nodes to determine at least one load prediction for at least one of the plurality of access network nodes, wherein the at least one load prediction includes at least one data item from the group of: i) the total number of user equipment (UE) served by at least one access network node, ii) the number of UEs per Synchronisation Signal Block (SSB) of at least one access network node, iii) the number of UEs served by at least one access network node that transmits a measurement report identifying a given neighbouring cell, and iv) the predicted radio resource load of at least one access network node. The input data may include at least one of: i) at least one SSB index of SSBs overlapping with cells of neighbouring access network nodes adjacent to one of the at least one access network nodes, and the number of UEs per SSB overlapping with cells of neighbouring access network nodes, ii) hardware load data indicating the hardware load of the access network node, iii) radio resource load data indicating the radio resource load of the access network node, iv) objective data indicating the objective of the model to be trained or updated.

[0031] Each feature disclosed in this specification (including the terms in the claims) and / or shown in the drawings may be incorporated into the present disclosure independently of (or in combination with) other disclosed and / or shown features. In particular, without limitation, any feature of any claim dependent on a particular independent claim may be introduced into that independent claim either in any combination or individually.

Brief Description of the Drawings

[0032] Next, embodiments of the present disclosure will be described by way of example with reference to the accompanying drawings.

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

Figure 12

Figure 13

Mode for Carrying Out the Invention

[0033] Overview FIG. 1 schematically illustrates a mobile (cellular or wireless) telecommunications system 1 to which embodiments of the present disclosure may be applied.

[0034] In this system 1, users of mobile devices 3 (UEs) can communicate with each other and with other users via base stations 5 (and other access network nodes) and the core network 7 using an appropriate 3GPP radio access technology (RAT), such as Evolved Universal Terrestrial Radio Access (E-UTRA) and / or 5G RAT. It will be appreciated that several base stations 5 form a (radio) access network or (R) AN. As will be understood by those skilled in the art, for illustrative purposes, four mobile devices 3A, 3B, 3C, and 3D and two base stations 5A and 5B are shown in FIG. 1, but the system, when implemented, will typically include other base stations / (R) AN nodes and mobile devices (UEs).

[0035] Each base station 5 controls one or more associated cells 6 (either directly or via other nodes such as home base stations, relays, remote radio heads, distributed units, etc.). A base station 5 that supports next-generation / 5G protocols may be referred to as a "gNB". It will be appreciated that several base stations 5 may be configured to support both 4G and 5G protocols, and / or any other 3GPP or non-3GPP communication protocols.

[0036] The mobile device 3 and its serving base station 5 are connected via a suitable air interface (e.g., the so-called "NR" air interface, "Uu" interface, etc.). The neighboring base stations 5 may be connected to each other via a suitable inter-base station interface (e.g., the so-called "Xn" interface, "X2" interface, etc.). The base station 5 is also connected to the core network node via a suitable interface (e.g., the so-called "NG-U" interface (for the user plane), the so-called "NG-C" interface (for the control plane), etc.).

[0037] The core network 7 (e.g., EPC in the case of LTE or NGC in the case of NR / 5G) typically includes logical nodes (or "functions") for supporting communication in the telecommunications system 1 and, in particular, for subscriber management, mobility management, charging, security, and call / session management. For example, the core network 7 of a "next-generation" / 5G system includes user plane entities and control plane entities such as one or more control plane functions (CPF) 8-2 and one or more user plane functions (UPF) 8-3. The core network 7 also includes the so-called Access and Mobility Management Function (AMF) 8-1 in 5G or the Mobility Management Entity (MME) in 4G, which is responsible for handling the connection of the mobile device 3 and mobility management tasks. The Session Management Function (SMF) 8-4 is responsible for handling communication sessions for the mobile device 3, such as session establishment, modification, and release. The Operations, Administration and Maintenance (OAM) function 8-5 may be implemented in the software of one or more 5G CN nodes. The core network 7 is connected to a data network 20 such as the Internet or a similar Internet Protocol (IP)-based network.

[0038] User Equipment (UE) Figure 2 is a block diagram showing the main components of the mobile device (UE) 3 shown in Figure 1. As shown, UE 3 includes a transceiver circuit 31 operable to transmit signals to and receive signals from one or more connected nodes via one or more antennas 33. Although not necessarily shown in Figure 2, UE 3 of course has all the normal functions of a conventional mobile device (such as user interface 35), which may be provided by any one of hardware, software, and firmware, or any combination thereof, as required. Controller 37 controls the operation of UE 3 according to software stored in memory 39. The software may be pre-installed in memory 39 and / or downloaded, for example, via telecommunications network 1 or from a removable data storage device (RMD). The software includes, among other things, an operating system 41, a communication control module 43, and an energy saving module 45.

[0039] Communication control module 43 is responsible for processing (generating / transmitting / receiving) signaling messages and uplink / downlink data packets between UE 3 and other nodes including (R)AN node 5 and core network nodes. The signaling may include control signaling related to energy saving operations (such as system information or via RRC). It will be understood that communication control module 43 may include several sub-modules ("layers" or "entities") to support specific functions. For example, communication control module 43 may include a PHY sub-module, a MAC sub-module, an RLC sub-module, a PDCP sub-module, an SDAP sub-module, an IP sub-module, an RRC sub-module, etc.

[0040] The energy saving module 45 is responsible for operations related to energy saving (by the UE3 itself and / or by network nodes such as access network node / base station 5). Energy saving by the UE itself is usually achieved by turning off specific components (e.g., transceiver circuit 31) for a specific period. As will be described in more detail below, in the following embodiments, the UE3 can assist the network in performing energy saving by taking various actions that help the network obtain a more accurate picture of the actual load currently on the network.

[0041] Access network node (base station) FIG. 3 is a block diagram showing the main components of the base station 5 (or a similar access network node) shown in FIG. 1. As shown, the base station 5 includes a transceiver circuit 51 operable to transmit signals to and receive signals from at least one connected UE3 via one or more antennas 53 and to transmit signals to and receive signals from other network nodes (directly or indirectly) via a network interface 55. The network interface 55 typically includes appropriate base station-to-base station interfaces (such as the X2 / Xn interface) and appropriate base station-core network interfaces (such as the S1 / N1 / N2 / N3 interface). The controller 57 controls the operation of the base station 5 according to software stored in the memory 59. The software may be pre-installed in the memory 59 and / or may be downloaded, for example, via the telecommunications network 1 or from a removable data storage device (RMD). The software includes, among other things, an operating system 61, a communication control module 63, and an energy saving module 65.

[0042] The communication control module 63 is responsible for processing (generating / sending / receiving) signaling between the base station 5 and other nodes such as the UE 3 and core network nodes. The signaling may include control signaling related to energy saving operations (e.g., via system information or RRC). It will be understood that the communication control module 63 may include several sub-modules ("layers" or "entities") to support specific functions. For example, the communication control module 63 may include a PHY sub-module, a MAC sub-module, an RLC sub-module, a PDCP sub-module, an SDAP sub-module, an IP sub-module, an RRC sub-module, etc.

[0043] The energy saving module 65 is responsible for operations related to energy saving (by the UE 3 and / or by the access network node / base station 5 itself). Energy saving is typically achieved by turning off specific components (e.g., the transceiver circuit 51) for a specific period.

[0044] Core network function FIG. 4 is a block diagram showing the main components of a general core network node or function 8 such as the AMF 8-1, CPF 8-2, UPF 8-3, SMF 8-4, or OAM 8-5 shown in FIG. 1. As shown, the core network function includes a transceiver circuit 71 operable to transmit signals to and receive signals from other nodes (including the UE 3, the base station 5, and other core network nodes) via a network interface 75. A controller 77 controls the operation of the core network function according to software stored in a memory 79. The software may be pre-installed in the memory 79 and / or may be downloaded, for example, via the telecommunications network 1 or from a removable data storage device (RMD). The software includes, among other things, an operating system 81, a communication control module 83, and an (optional) energy saving module 85.

[0045] The communication control module 83 is responsible for processing (generating / sending / receiving) signaling between the core network function and other nodes such as the UE 3, the base station 5, and other core network nodes. The signaling may include, for example, UE context / UE capability indication of the UE 3 related to energy saving.

[0046] When present, the energy saving module 85 is responsible for operations related to energy saving (e.g., by the UE 3 and / or by the access network node / base station 5).

[0047] Artificial Intelligence(AI) / Machine Learning(ML) 3GPP has proposed a functional framework for AI / ML and how various entities in a telecommunication system interact in the context of this framework. Refer to Figure 5 showing these entities in this regard.

[0048] The entities involved are related to the data collection function 91, the model training function 93, the model inference function 95, and the actor 97. The data collection function 91 provides input data (training data) to the model training function 93 and the model inference function 95. The model training function 93 performs ML model training, verification, and testing that can generate model performance metrics as part of the model test procedure. The model inference function 95 provides AI / ML model inference output (e.g., prediction or decision), and the actor 97 is a function or node that receives the output from the model inference function 95 and triggers or executes corresponding actions (e.g., a (radio) access network node that increases or decreases its transmission power to perform load distribution).

[0049] The terms referred to by 3GPP in the context of this framework include the following. AI / ML Model: A data-driven algorithm by applying machine learning techniques that generate a set of outputs including prediction information and / or decision parameters based on a set of inputs. AI / ML Training: An online or offline process for training an AI / ML model by learning the features and patterns that best represent the data and obtaining an AI / ML model trained for inference. AI / ML Inference: A process of making predictions or deriving decisions based on the collected data and the AI / ML model using the trained AI / ML model. Training Data: The data required as input for the AI / ML model training function. Inference Data: The data required as input for the AI / ML model inference function. Model Deployment / Update: Used to initially deploy a trained, validated, and tested AI / ML model to the model inference function or to pass an updated model to the model inference function.

[0050] Detailed Description The following is an explanation of a method that can determine network load using AI / ML, thereby enabling the network to make better load distribution decisions within the system 1 shown in FIG. 1.

[0051] A first embodiment for determining network load information and taking appropriate further actions is that the model training function 93 is located within a core network node 7 such as within OAM 8-5, while the model inference function 95 is located within a (R)AN node, for example within a gNB or within the control unit of a gNB (gNB-CU), i.e., within a base station. Advantageously, by placing the model inference function 95 in the base station 5, it becomes possible to make quick decisions regarding appropriately adjusting the load of the network across multiple cells.

[0052] Next, a more detailed description of the first embodiment will be given with reference to the signaling diagram shown in FIG. 6.

[0053] As a summary, FIG. 6 shows the communication that takes place between UE3, the base station (RAN node 5A) that provides services to UE3, another neighboring base station (RAN node 5B), and a core network 7 node (such as the OAM8-5 function of the core network 7) in the context of load distribution using AI / ML. Before examining this signaling in more detail, step 0 indicates that RAN node 5B may optionally be equipped with its own AI / ML model, which can provide useful input information such as the predicted resource state (described in more detail below) to RAN node 5A as needed during the load distribution procedure.

[0054] In step 1, RAN node 5A signals to UE3 the requirement that UE3 should report measurement and / or location information (e.g., radio resource management (RRM) measurements, reference signal received power (RSRP), reference signal received quality (RSRQ), signal to interference plus noise ratio (SINR) of the serving cell and neighboring cells of the UE, minimization of drive test (MDT) measurement data, UE speed information, UE location information (e.g., GPS data), etc.). Although only one UE3 is referenced in FIG. 6 and the related description below, it should be understood that in practice, multiple UEs are signaled by RAN node 5A in step 1 and RAN node 5A receives corresponding measurement reports from each of these UEs. Further, RAN node 5A may be configured to operate two or more cells, and thus, RAN node 5A may make such a requirement across all or some of the cells it operates.

[0055] Next, in step 2, UE3 collects the required measurements and / or location information and reports the collected information to RAN node 5A. Then, in step 3, RAN node 5A signals the received UE measurement report, along with other input data such as the hardware load at RAN node 5A, the radio resource load at RAN node 5A, and instructions for AI / ML purposes (e.g., for load balancing, mobility robustness, (network) energy savings, etc.), as input data for AI / ML model training, to the model training function 93 located in core network 7 (e.g., the OAM function of the core network). The radio resource load may be represented by the usage of physical resource blocks (PRBs) in the serving cell of RAN node 5A, and the hardware load and radio resource load may be filtered average loads within a past period (e.g., within the last 30 seconds, 60 seconds, etc., or within an alternative period as required). Further, the hardware load and radio resource load signaled in step 3 may be represented by descriptors that can be mutually interpreted by the receiving entity, such as "high, medium, low", or as a given percentage of the available capacity, such as "10%, 20%, 30%".

[0056] Also, in step 3, RAN node 5B may send its own input data for model training to the core network. In this regard, it should be understood that either or both of RAN nodes 5A and 5B continue to send their respective input data to core network 7 at regular intervals, or when more measurement data is available, or when there are changes in their loads. In this way, the model can be better calibrated by the model training function 93 in each iteration of the process (as described in subsequent steps below), and advantageously, result in a model that provides predictions / decisions with higher accuracy.

[0057] As shown in step 4, the AI / ML model training function 93 located in the core network 7 processes the input data signaled in step 3 to train the AI / ML model. The AI / ML model is trained using conventional machine learning training techniques not described here.

[0058] The core network 7 that has trained the AI / ML model updates (or, if the model is not yet locally stored in the RAN node 5A, deploys the AI / ML model to the RAN node 5A) the AI / ML model locally stored in the RAN node 5A in step 5. This model includes a mapping table that associates the power of each synchronization signal block (SSB), sometimes called a Synchronisation Signal / Physical Broadcast Channel block (SS / PBCH block), with the number of user equipment reporting measurement reports for each adjacent cell / frequency (examples of two such mapping tables will be described later).

[0059] In step 6, the UEs within the cell continue to send their measurement reports to the RAN node 5A. In step 7, the RAN node 5A receives from an adjacent RAN node B the input information that the AI / ML model stored in the RAN node 5A can use to perform its load distribution inference. This input information may include the SSB index of the RAN node 5B, the number of UEs per SSB, the hardware load, and the radio resource load (such as the PRB utilization per SSB / cell). Using the latest information received from UE3 in step 6 and the current load information received from the adjacent RAN node 5B in step 7, an accurate mobility load distribution prediction may be made in step 8 using the model inference 95 of the RAN node 5A.

[0060] The first exemplary mapping table included in the model signaled in step 5 configures the synchronization signal block power of RAN node 5A for the cell in which it operates (i.e., the serving cell) so that RAN node 5A can calibrate the SSB power of its serving cell according to the load distribution to be achieved. A part of this mapping table is shown below and its use will be described in detail below.

Table 1

[0061] RAN node 5A knows which UE providing the service is on which SSB. UE3 reports that it has been received from the UE that RAN node 5A is serving in step 6, and thus can be divided into reports for each SSB. Base station 5 also knows which of its SSBs indicate which neighboring cells. Therefore, when RAN node 5A knows that 8 UEs are on its SSB1, it can view the measurement reports from these 8 UEs. In this example, these reports identify that these UEs can also view neighboring cell 1, which is operated by RAN node 5B in this example, and have reported on neighboring cell 1.

[0062] Therefore, based on the load information received from RAN node 5B, RAN node 5A can determine the load of this neighboring base station. Specifically, RAN node 5B knows that its SSB4 beam is directed towards the cell operated by RAN node 5A. Therefore, when RAN node 5B reports its load to RAN node 5A, it uses SSB4 to identify the number of UEs currently being served. This is because SSB4 is the beam to which UEs that may be handed over from RAN node 5A move to cell 1 of neighboring base station RAN node 5B. Similarly, if RAN node 5B also has a similar model inference, RAN node 5A knows that its SSB1 points to cell 1 of RAN node 5B. So, when reporting its load to RAN node 5B, it reports regarding SSB1. This is because SSB1 is the SSB to which UEs are handed over when they move from RAN node 5B to RAN node 5A. Depending on the difference between the load of the adjacent SSB4 and the load of the serving cell's SSB1, RAN node 5A can increase or decrease the transmission power of SSB1 using the above table. For example, if the adjacent RAN node 5B has 30 UEs being served by its SSB4, and it is reported that there are 8 UEs recognized as cell 1 of RAN node 5B on the serving cell's SSB1, and the PRB usage at RAN node 5A is 15% and the hardware load is reported to be 18%, since the adjacent SSB4 already has a higher load than SSB1, a high transmission power of SSB1 (e.g., -24 dBm as in row 1 of the above table) can be set or maintained. However, if the adjacent base station 5B has only 5 UEs on SSB4, and there are 25 UEs currently being served by SSB1 which reports recognizing cell 1 of RAN node 5B, and it is reported that both the PRB usage of SSB1 and the hardware load of RAN node 5A exceed 40%, then RAN node 5A reduces the transmission power on SSB1 (e.g., to -26 dBm) in order to move some of the UEs being served on SSB1 to SSB4 of the adjacent base station 5B.When the RAN node 5B provides information regarding its own hardware load and / or resource load, the RAN node 5A may also compare this load information with its own hardware and PRB load information to determine the transmission power of its SSB1.

[0063] Assuming that the neighboring base stations 5 also execute a similar AI / ML inference function 95, the RAN node 5A reports its load information to those neighboring base stations. For example, since the RAN node 5A knows that its SSB1 beam is directed towards the cell 1 of the RAN node 5B (due to the received measurement report), the RAN node 5A may report the load of its SSB1 to the RAN node 5B. In this way, the neighboring base stations can take corresponding actions. Thus, for example, when the RAN node 5A increases the transmission power of its SSB1, the RAN node 5B may decrease the transmission power of its SSB4. In this way, the load is distributed among the neighboring base stations. Additionally, a plurality of SSBs of the RAN node 5B may point to the serving cell of the RAN node 5A. In this case, the RAN node 5B reports the loads of all of those SSBs, and when determining the transmission power of the SSB1, the RAN node 5A considers the load of its SSB1 in comparison with the loads of those other SSBs of the RAN node 5B.

[0064] In the above description, the situation between two adjacent base stations was considered. Obviously, the same action can be performed for all adjacent cells. Instead of changing the transmission power of SSB1, the RAN node 5A changes the transmission power of the relevant SSB that indicates the corresponding adjacent cell. Thus, for example, from the above table, it can be seen that the SSB2 of the RAN node 5A indicates the adjacent cell 2 of the adjacent base station. Since the SSB3 of that base station indicates the RAN node 5A, the RAN node 5A reports how many UEs are on its SSB3 so that it can make a similar decision regarding the transmission power of its SSB2 as shown in the above table. If the adjacent base station operating cell 2 also has a similar AI / ML model, the RAN node 5A can report the number of UEs on its SSB2 to that adjacent base station so that it can make a corresponding load distribution decision. Although not shown, the table has similar entries for each SSB of the RAN node 5A.

[0065] Now, refer to FIGS. 7 and 8 showing the impact of such load distribution in a telecommunication system. FIG. 7 shows the cell operated by the RAN node 5A (this cell operates at the first frequency f1), the cell operated by the RAN node 5B (this cell operates at a different second frequency f2), and the cell operated by a further RAN node (this cell is operated by a third RAN node at another third frequency f3) before any load distribution operation is performed. Cell f1 provides service to 2 UEs, and cells f2 and f3 each provide service to 10 UEs. Also, as shown using dashed circles, there are three overlapping coverage areas between the following cells, namely, A) Cell f1 and f2 (2 UEs are in this overlapping coverage area, and the overlap can be formed by one or more SSBs of cells f1 and f2 that overlap each other), B) Cell f1 and f3 (2 UEs are also in this overlapping coverage area, and the overlap can be formed by one or more SSBs of cells f1 and f3 that overlap each other), and C) Cells f2 and f3 (six UEs are in this overlapping coverage area, and the overlap can be formed by one or more SSBs of overlapping cells f2 and f3 with each other), exist.

[0066] Therefore, it can be understood that cells f2 and f3 are overloaded with UEs for cell f1. As a result, based on the signaling sequence shown in FIG. 6, when the RAN node 5A operating cell f1 increases its coverage area so that UEs in the overlapping coverage area hand over to cell f1, as shown in FIG. 8, the RAN node 5A can perform a load distribution prediction predicting that it will receive some UEs via handover from cells f2 and f3. In response, it determines to increase its coverage area (by increasing the transmission power), thereby causing the UEs to hand over from the overloaded cells f2 and f3. At the same time, the RAN nodes operating cells f2 and f3 reduce their coverage areas (by reducing their transmission powers), thereby ensuring that the UEs they previously served hand over to cell f1 (cell f1 will have a much larger RSRP for those UEs at the cell edge than the RSRP of cells f2 and f3 as a result of the change in transmission power).

[0067] Returning to the timing diagram shown in FIG. 6, at step 8, for example, in the situation shown in FIG. 7, the RAN node 5A can perform an accurate load distribution prediction of its own cell (or its multiple cells according to the deployment of the RAN node 5A) based on the latest information processed by the model inference 95. Optionally, at step 9, the RAN node 5A may transmit model performance feedback to the core network 7 as needed.

[0068] When a prediction is made by model inference, the RAN node 5A executes a mobility load dispersion action according to the prediction made by model inference (e.g., the situation shown in FIG. 8) in step 10. As a result, some UEs may be moved (handed over) between the serving cell of the RAN node 5A and the cell of the adjacent RAN node 5B (or other adjacent cells as required), so as to disperse the load across the cells operated by these nodes.

[0069] When one or more handovers of at least one UE occur between the respective cells of the RAN nodes 5A and 5B (or one or more other cells), each of the RAN nodes 5A and 5B feeds back, in step 11, feedback information regarding the change, e.g., information regarding the load that each of the RAN nodes 5A and 5B is currently experiencing (which should be equal to that before the change is implemented) to the core network 7.

[0070] In the above embodiment, the model inference located at the RAN node 5A uses a mapping table to adapt the transmission power of the SSB broadcast by the RAN node 5A to achieve the desired load dispersion operation. Instead of changing the transmission power, the base station may change the handover decision parameters used to control the handover of the UEs served by the RAN node 5A to other adjacent RAN nodes (or, alternatively, the trained model may simultaneously indicate corrections to both the SSB power and the handover parameters of the RAN node 5A using both mapping tables). Examples of mapping tables that can be used in such embodiments are provided below.

Table 2

[0071] For example, referring to the first row of the table, the SSB power of the serving cell (i.e., RAN Node 5A) is configured to -24 dB, and 10 UEs being served by RAN Node 5A report that their neighboring cell is Cell 1 (e.g., the cell formed by RAN Node 5B), the hardware load of the neighboring cell is 10%, and its PRB usage is 10%. In this case, the serving cell reconfigures the measurement configuration of UE3, i.e., the measurement parameter configuration (MeasConfig1) of the situation in which UE3 should trigger its measurement report. (Sent to UE3 via signaling not explicitly shown in Step 10 of FIG. 6) Each MeasConfig IE defines a threshold value, and when the threshold value is met, the following configured events, i.e., - Event A1 (the serving cell becomes better than the threshold value), - Event A2 (the serving cell deteriorates compared to the threshold value), - Event A3 (the neighboring cell is offset better than the SpCell), - Event A4 (the neighboring cell becomes better than the threshold value), and - Event A5 (the SpCell (special cell) deteriorates compared to Threshold 1 and the neighboring cell becomes better than Threshold 2), as a result of which UE3 reports its RSRP / RSRP.

[0072] Furthermore, Model Inference 6 outputs updated handover decision parameters regarding the number of measurement event configurations required to trigger a handover (in this example, 3 events), and the elapsed time after the measurement event is signaled to trigger its handover (in this example, 100 milliseconds) to RAN Node 5A.

[0073] Figure 9 shows the scenario described above for the first row. In this example, the cell formed by base station A (with an SSB power of -24 dB) is currently serving 23 UEs, while cell 1 (formed by RAN node 5B) is serving only 3 UEs. When the hardware load of RAN node 5B is 10% and its PRB usage is 10%, RAN node 5A applies the parameters of MeasConfig1 so that the UEs that can be handed over to RAN node 5B (i.e., the 10 UEs that reported receiving signaling from cell 1 formed by RAN node 5B) are handed over to RAN node 5B 100 milliseconds after the third measurement event is signaled. As a result, the load between cells is dispersed, and when the handover from RAN node A to RAN node B is completed, both cells serve 13 UEs each.

[0074] In the embodiment described above with reference to FIGS. 6 to 9, the AI / ML model inference 95 disperses the load between cells by calculating the appropriate SSB power and adapting the handover decision parameters when the model inference 95 is located in the RAN node and the model training function 93 is located in the core network. In the following second embodiment described with reference to FIG. 10, the AI / ML model inference 95 is instead located in a separate node (not RAN nodes 5A / 5B, etc.). In this embodiment, as in the former, the model training function 93 is located in the core network 7.

[0075] Referring now to FIG. 10, steps 1 through 6 of this embodiment are substantially the same as steps 1 through 6 of the first embodiment shown in FIG. 6, and thus will not be repeated here. However, in step 5 of this embodiment, the AI / ML model is deployed / updated by the core network 7 at the model inference node 6 (instead of at the RAN node 5A as in the previous embodiment). Continuing with step 7, both the RAN node 5A and the RAN node 5B send their respective input data for load balancing to the model inference node 6. The input data is the same as that provided in the above-described embodiments. Next, in step 8, mobility and load balancing predictions are performed at the model inference node 6, and the model inference node 6 determines a prediction of the load of each base station over a certain period in the future.

[0076] In steps 9a and 9b, the model inference node 6 uses the predicted load to determine and send load balancing commands to the RAN node 5A and the RAN node 5B respectively, thereby causing the base stations to perform appropriate load balancing actions. The commands may have one or more of at least one power parameter, a measurement configuration, a handover decision configuration, and parameters for UE handover decisions. The at least one power parameter may define the cell transmit power, the SSB beam power of each SSB, and / or the power of the entire site of the base station. Similar to the previous embodiments, the measurement configuration may define for each UE, for each UE within a given SSB, or for all UEs served by the base station, which situations should trigger the UE to send a measurement report. Similar to the previous embodiments, the UE handover decision parameters define the situations in which the base station should trigger a handover of the UE. Thus, the handover decision parameters may define the measurement event that triggers the handover and the time elapsed after the measurement event reported to trigger the handover. The UE handover decision parameters may identify one or more UEs to be handed over to another base station. This parameter identifies which UEs should be handed over and the target cell for each of these UEs.

[0077] Finally, steps 10 to 13 of this embodiment are the same as steps 9 to 11 of the first embodiment shown in FIG. 6, respectively, and will not be repeated here.

[0078] Here, refer to FIG. 11 showing the influence of the above-described signaling of the second embodiment on the cell of the telecommunication system. As shown in FIG. 11, assuming that the RAN node 5A described in FIG. 10 is operating cell A, there are six cells operated by six RAN nodes. Only three UEs exist within the coverage of cell A, and there are an additional twelve UEs within the coverage of both cell A and another cell (two UEs are within the coverage of cells A and B, one UE is within the coverage of cells A and C, four UEs are within the coverage of cells A and D, three UEs are within the coverage of cells A and E, and two UEs are within the coverage of cells A and F).

[0079] Therefore, when the target cell is not overloaded, two UEs can hand over to cell B, one UE can hand over to cell C, four UEs can hand over to cell D, three UEs can hand over to cell E, and two UEs can hand over to cell F (on the other hand, three UEs do not have candidate cells to hand over to).

[0080] According to the procedure shown in FIG. 10 for the scenario shown in FIG. 11, the core network 7 deploys the AI / ML model to the model inference node 6 that predicts the load in different cells and determines which UEs can hand over to which adjacent cells. Then, the model inference node 6 transmits respective load distribution commands to each base station operating cells A to F. In this way, the RAN node 5A is instructed by the model inference node 6 to change its operating parameters, or change its handover parameters, or hand over a specific UE to another cell, and as a result, the load is more evenly distributed across cells A to F.

[0081] Modifications and Alternatives Detailed embodiments have been described above. As those skilled in the art will understand, while further benefiting from the disclosure embodied in the above embodiments, several modifications and alternatives can be made to those embodiments. By way of example, only some of these alternatives and modifications will be described here.

[0082] In the embodiment described with reference to FIG. 10, in step 8, the model inference node 6 predicted the load of each base station cell. However, the load may also or alternatively be predicted by the core network node 7 each time the model is updated (such as by the OAM function) using the input data supplied by the base station. The model inference node 6 may then determine and transmit a load distribution command to the base station 5 as before. A timing diagram of such an embodiment is shown in FIG. 12.

[0083] FIG. 12 generally corresponds to the procedure shown in FIG. 10, and corresponding steps will not be repeated here. In step 5, the core network node 7 predicts the load of the RAN nodes 5A and 5B based on the input data received from these nodes in step 3. The load prediction message is sent to the model inference 6 together with the trained (or updated) model. This load prediction message may include one or more of the following parameters: Next prediction period: 100 ms, 200 ms, 500 ms, 1 s, 5 s, 10 s, 30 s, 1 m, 5 m, etc.; Next predicted load: total number of UEs within a given deviation, e.g., 200 UEs ± 30, and / or number of UEs per SSB within a given deviation, e.g., 25 UEs ± 30; Next predicted load with adjacent cells: number of UEs reporting measurements of a given cell within a specific deviation, e.g., 50 UEs ± 10. This parameter helps the serving cell determine which UEs can hand over to which adjacent cells, and as a result, the serving cell can distribute the load by handing over at least one UE to one or more adjacent cells; Next predicted radio resource load: per-cell / per-SSB PRB usage, e.g., within a given deviation of 40% ± 5%.

[0084] As a result of the core network node 7 performing the load prediction, it is not necessary for the model inference node 6 to perform the same prediction (i.e., steps 6 to 8 as shown in FIG. 10 are effectively skipped). Instead, the model inference node 6 determines appropriate load distribution commands in steps 7a and 7b based on the predicted load received from the core network node 7 and transmits them to the RAN node 5A and the RAN node 5B.

[0085] Furthermore, instead of the model inference node 6 determining the load distribution commands, when the load of each base station is predicted (by either the core network node 7 or the model inference node 6), the predicted load information of the base station 5 may be transmitted to the base station 5, and then the base station 5 determines its own load distribution actions to be taken based on the predicted load distribution between the base station and its neighboring base stations. A timing diagram of such an embodiment is shown in FIG. 13, which roughly corresponds to the procedure shown in FIG. 10, and the corresponding steps are not repeated here.

[0086] In FIG. 13, instead of the core network 7 generating the load prediction and transmitting it to the model inference node 6, in this example, the model inference node 6 generates the load prediction in step 6 and directly transmits a load prediction message including one or more of the parameters described above in the description of FIG. 12 to the RAN nodes 5A and 5B in step 7, whereby these RAN nodes 5 can perform their own load distribution actions to distribute the load between them.

[0087] According to another alternative form, each base station (RAN node 5) may transmit input data identifying each SSB index, the number of UEs on that SSB, and at least one cell identifier of an adjacent base station overlapping with that SSB to the model training function and the model inference function. The model training function is used to train the model, and the model inference function is used to make a prediction regarding the load in the network or to make a decision on load distribution.

[0088] It will be understood that the above embodiments may be applicable to both 5G New Radio (5G NR) and LTE systems (E-UTRAN). The above embodiments may also be applicable to future systems (such as 5G, 6G and later).

[0089] Next-generation mobile networks support diverse service requirements classified by the International Telecommunication Union (ITU) into three categories: Enhanced Mobile Broadband (eMBB), Ultra-Reliable and Low-Latency Communications (URLLC), and Massive Machine Type Communications (mMTC). eMBB aims to provide enhanced support for traditional mobile broadband, focusing on services that require large amounts of guaranteed bandwidth, such as High Definition (HD) video, Virtual Reality (VR), and Augmented Reality (AR). URLLC is a requirement for critical applications such as autonomous driving and factory automation that require guaranteed access within an extremely short time. mMTC needs to support a huge number of connected devices, such as smart meters and environmental monitoring, but can usually tolerate a certain access delay. It is understood that some of these applications may have relatively relaxed Quality of Service / Quality of Experience (QoS / QoE) requirements, while some may have relatively strict QoS / QoE requirements (e.g., high bandwidth and / or low latency).

[0090] In the above description, the UE, access network node (base station), and core network node have been described as having several individual modules (such as a communication control module) for ease of understanding. These modules may be provided in this way in certain applications where, for example, an existing system has been modified to implement the present disclosure. However, in other applications, such as a system designed from the outset with the features of the present invention in mind, these modules may be incorporated into the overall operating system or code, and thus these modules may not be distinguishable as individual entities. These modules may also be implemented in software, hardware, firmware, or a combination thereof.

[0091] Each controller may comprise a processing circuit in any suitable form, including, but not limited to, for example, one or more hardware-implemented computer processors, microprocessors, central processing units (CPUs), arithmetic logic units (ALUs), input / output (I / O) circuits, internal memory / cache (program and / or data), processing registers, communication buses (such as control, data, and / or address buses), direct memory access (DMA) functionality, hardware or software-implemented counters, pointers, and / or timers.

[0092] In the above embodiments, several software modules have been described. As those skilled in the art will understand, the software modules may be provided in a compiled form or an uncompiled form, and may be supplied to the UE, the access network node (base station), and the core network node via a computer network or as a signal on a recording medium. Further, the functions executed by some or all of this software may be executed using one or more dedicated hardware circuits. However, the use of software modules is preferred because it facilitates the update of the UE, the access network node, and the core network node for updating their functions.

[0093] The functions of the base station (referred to as a "distributed" base station or gNB) may be split between one or more distributed units (DUs) and a central unit (CU), where the CU typically performs higher-level functions and communication with the next-generation core, and the DU performs lower-level functions and communication via an air interface with nearby UEs (i.e., within the cell operated by the gNB). It will be understood that the distributed gNB includes the following functional units: gNB Central Unit (gNB-CU): A logical node that controls the operation of one or more gNB-DUs and hosts the Radio Resource Control (RRC) layer, the Service Data Adaptation Protocol (SDAP) layer, and the Packet Data Convergence Protocol (PDCP) layer (or the RRC layer and PDCP layer of the en-gNB) of the gNB. The gNB-CU terminates the so-called F1 interface connected to the gNB-DU. gNB Distributed Unit (gNB-DU): A logical node that hosts the Radio Link Control (RLC) layer, Medium Access Control (MAC) layer, and Physical (PHY) layer of a gNB or en-gNB, and its operation is partially controlled by the gNB-CU. One gNB-DU supports one or more cells. One cell is supported by only one gNB-DU. The gNB-DU terminates the F1 interface connected to the gNB-CU. gNB-CU-Control Plane (gNB-CU-CP): A logical node that hosts the control plane part of the RRC and PDCP protocols of the gNB-CU for an en-gNB or gNB. The gNB-CU-CP terminates the so-called E1 interface connected to the gNB-CU-UP and the F1-C (F1 control plane) interface connected to the gNB-DU. gNB-CU-User Plane (gNB-CU-UP): A logical node that hosts the user plane part of the PDCP protocol of the gNB-CU for an en-gNB, and the user plane parts of the PDCP protocol and SDAP protocol of the gNB-CU for a gNB. The gNB-CU-UP terminates the E1 interface connected to the gNB-CU-CP and the F1-U (F1 user plane) interface connected to the gNB-DU.

[0094] When a distributed base station or a similar control plane - user plane (CP - UP) split is adopted, the base station may be split into separate control plane and user plane entities, each of which may include associated transceiver circuitry, antennas, network interfaces, controllers, memory, operating systems, and communication control modules. It will be appreciated that when the base station comprises a distributed base station, the network interface (reference numeral 55 in FIG. 3) also includes an E1 interface and an F1 interface (F1 - C for the control plane and F1 - U for the user plane) for communicating signals between the respective functions of the distributed base station. In this case, the communication control module is also responsible for communication (generation, transmission, and reception of signaling messages) between the control plane part and the user plane part of the base station. When a distributed base station is used, it will be appreciated that, as described in the above embodiments, for pre - emption of communication resources, it is not necessary to be involved in both the control plane part and the user plane part. It will be understood that pre - emption can be handled by the user plane part of the base station without involvement in the control plane part (or vice versa).

[0095] The above embodiments are also applicable to "non - mobile" or generally fixed user equipment. The mobile devices described above may include MTC / IoT devices and the like.

[0096] A user equipment (or "UE", "mobile station", "mobile device", or "wireless device") in the present disclosure is an entity connected to a network via a wireless interface.

[0097] It should be noted that the present disclosure is not limited to dedicated communication devices and can be applied to any device having a communication function as described in the following paragraphs.

[0098] The terms "user equipment" or "UE" (as used by 3GPP), "mobile station", "mobile device", and "wireless device" are generally considered synonymous with each other and include stand-alone mobile stations such as terminals, cell phones, smartphones, tablets, cellular IoT devices, IoT devices, and machines. It should be understood that the terms "mobile station" and "mobile device" also include devices that remain stationary for long periods of time.

[0099] A UE may be, for example, an item of equipment for production or manufacturing and / or an item of energy-related machinery (e.g., boilers, engines, turbines, solar panels, wind turbines, hydroelectric generators, thermal generators, nuclear power generators, batteries, nuclear systems and / or related equipment, heavy electrical machinery, pumps including vacuum pumps, compressors, fans, blowers, hydraulic equipment, pneumatic equipment, metalworking machinery, manipulators, robots and / or their application systems, tools, molds or dies, rolls, conveying equipment, elevators, material handling equipment, textile machinery, sewing machinery, printing and / or related machinery, paper converting machinery, chemical machinery, mining machinery and / or construction machinery and / or related equipment, machinery and / or appliances for agriculture, forestry and / or fisheries, safety and / or environmental protection equipment, tractors, precision bearings, chains, gears, power transmission equipment, lubrication equipment, valves, pipe fittings, and / or application systems for any of the aforementioned equipment or machinery, etc.).

[0100] A UE may be, for example, an item of transportation equipment (e.g., transportation equipment such as rolled materials, automobiles, motorcycles, bicycles, trains, buses, carts, human-powered vehicles, ships and other watercraft, aircraft, rockets, satellites, drones, balloons, etc.).

[0101] A UE may be, for example, an item of information and communication equipment (e.g., electronic computers and related equipment, communication and related equipment, information and communication equipment such as electronic components).

[0102] The UE may be, for example, a refrigerator, a refrigeration appliance product, an item of trading and / or service industry equipment, a vending machine, an automatic service machine, an office machine or equipment, a household appliance and an electronic device (such as a household appliance device like an audio device, a video device, a loudspeaker, a radio, a television, a microwave oven, a rice cooker, a coffee machine, a dishwasher, a washing machine, a dryer, an electric fan or related equipment, a vacuum cleaner, etc.).

[0103] The UE may be, for example, an electrical application system or equipment (such as an electrical application system or equipment like an X-ray system, a particle accelerator, a radioisotope device, a sonic device, an electromagnetic application device, a power application device, etc.).

[0104] The UE may be, for example, an electronic lamp, a lighting fixture, a measuring instrument, an analyzer, a tester, or a surveying or sensing device (such as a surveying or sensing device like a smoke detector, a human sensor, a motion sensor, a wireless tag, etc.), a wristwatch or clock, an inspection device, an optical device, a medical device and / or system, a weapon, a cutlery product, a hand tool, etc.

[0105] The UE may be, for example, a mobile information terminal of wireless equipment or related equipment (such as a wireless card or module designed for attachment or insertion to another electronic device (such as a personal computer, an electrical measuring instrument)).

[0106] The UE may be a part of a device or system that uses various wired and / or wireless communication technologies to provide applications, services, and solutions related to the "internet of things (IoT)" described later.

[0107] An Internet of Things device (or "Thing") may comprise suitable electronic devices, software, sensors, network connectivity, etc. that enable these devices to collect and exchange data with each other and with other communication devices. An IoT device may comprise automated devices that follow software instructions stored in internal memory. An IoT device may operate without the need for human supervision or interaction. An IoT device may also remain stationary and / or inactive for long periods of time. An IoT device may be implemented as part of a (generally) stationary device. An IoT device may also be embedded in a non-stationary device (e.g., a vehicle), or worn by an animal or person being monitored / tracked.

[0108] It will be appreciated that IoT technology may be implemented on any communication device capable of connecting to a communication network to send / receive data, regardless of whether such communication device is controlled by human input or software instructions stored in memory.

[0109] It will be appreciated that IoT devices may also be referred to as Machine-Type Communication (MTC) devices or Machine-to-Machine (M2M) communication devices. It will be appreciated that a UE may support one or more IoT or MTC applications. Some examples of MTC applications are listed in the following table (Source: Non-Patent Document 4, Annex B, the content of which is incorporated herein by reference). This list is not exhaustive and is intended to show some examples of machine type communication applications.

[0110] [Table 3]

[0111] The uses, services, and solutions may include Mobile Virtual Network Operator (MVNO) services, emergency wireless communication systems, Private Branch eXchange (PBX) systems, PHS / digital cordless telecommunications systems, Point of sale (POS) systems, advertising call systems, Multimedia Broadcast and Multicast Service (MBMS), Vehicle to Everything (V2X) systems, train wireless systems, location-related services, disaster / emergency wireless communication services, community services, video streaming services, femtocell application services, Voice over LTE (VoLTE) services, charging services, wireless on-demand services, roaming services, activity monitoring services, telecommunications carrier / communication NW selection services, function-limited services, Proof of Concept (PoC) services, personal information management services, ad hoc network / Delay Tolerant Networking (DTN) services, etc.

[0112] Furthermore, the UE categories described above are merely application examples of the technical ideas and embodiments described in this document. Needless to say, these technical ideas and embodiments are not limited to the UEs described above and can be variously modified.

[0113] Various other modifications will be apparent to those skilled in the art and will not be further described here in detail.

[0114] Although the present disclosure has been particularly shown and described with reference to its embodiments, the present disclosure is not limited to these embodiments. Those skilled in the art will understand that various changes in form and detail can be made without departing from the spirit and scope of the present disclosure defined by the claims. Also, each embodiment can be appropriately combined with at least one of the embodiments.

[0115] Each of the drawings or figures is merely an example for explaining one or more embodiments. Each figure need not be associated with only one particular embodiment and may be associated with one or more other embodiments. As will be understood by those skilled in the art, various features or steps described with reference to any one of the figures can be combined with features or steps shown in one or more other figures, for example, to generate embodiments not explicitly illustrated or described. Not all of the features or steps shown in any one of the figures for explaining an embodiment are necessarily essential, and some features or steps may be omitted. The order of the steps described in each figure may be changed as appropriate.

[0116] All or part of the above embodiments may be described, without limitation, as follows in the following appendices. (Appendix A1) A method performed by an access network node of a communication network, comprising: receiving a measurement report from one or more user equipment (UE) provided with services by the access network node; transmitting input data to a second node of the communication network; wherein the input data comprises at least one data item selected from the group consisting of: i) at least one SSB index of a Synchronisation Signal Block (SSB) overlapping with a cell of at least one adjacent access network node, and the number of UEs in the SSB; ii) hardware load data indicating the hardware load of the access network node; iii) radio resource load data indicating the radio resource load of the access network node, and iv) objective data indicating the objective of a model trained or updated by the second node. Method. (Appendix A2) The input data transmitted by the access network node includes the wireless resource load data, and is the method described in Appendix A1, which indicates the usage amount of physical resource blocks (PRBs) by the access network node. (Appendix A3) The input data transmitted by the access network node includes the hardware load data, and the hardware load data represents the filtered average load of the access network load over a certain past period, and is the method described in Appendix A1 or A2. (Appendix A4) The filtered average load is represented by a general load state descriptor or a percentage of a predetermined load, and is the method described in Appendix A3. (Appendix A5) The input data transmitted by the access network node includes the wireless resource load data, and the wireless resource load data represents the filtered average load of the access network load over a certain past period, and is the method described in any one of Appendices A1 to A4. (Appendix A6) The filtered average load is represented by a general load state descriptor or a percentage of a predetermined load, and is the method described in Appendix A5. (Appendix A7) The input data transmitted by the access network node includes target data that is one of load distribution, mobility robustness, and energy saving, and is the method described in any one of Appendices A1 to A6. (Appendix A8) The transmitting is to transmit the input data to a model training function or a model inference function, and is the method described in any one of Appendices A1 to A7. (Appendix A9) Sending as described in appended appendix A8, which includes sending input data including at least one UE measurement report received from one or more UEs for which the access network node provides services. (Appended appendix A10) Sending as described in any one of appendices A1 to A9, which includes sending the input data to an adjacent access network node. (Appended appendix A11) A method executed by an access network node, including receiving a model from a model training function, wherein the model includes a mapping table that associates the power of at least one Synchronisation Signal Block (SSB) of the access network node with the number of User Equipments (UEs) that provide measurement reports to at least one adjacent access network node, the method includes receiving input information from the at least one adjacent access network node, receiving measurement reports from one or more User Equipments (UEs) for which the access network node provides services, using the input information from the at least one adjacent access network node, at least one of the UE measurement reports, and the model to determine at least one load balancing action to be executed by the access network node, and including. (Appended appendix A12) The at least one action includes changing the transmission power of the at least one SSB, as described in appended appendix A11. (Appended appendix A13) The method according to appendix A12, wherein when the load in the SSB is greater than the load in the at least one adjacent access network node, the at least one action includes reducing the transmission power of the at least one SSB. (Appendix A14) The method according to appendix A12 or A13, wherein when the load in the at least one adjacent access network node is greater than the load in the at least one SSB, the at least one action includes increasing the transmission power of the at least one SSB. (Appendix A15) The method according to any one of appendices A11 to A14, wherein the at least one action includes changing at least one handover decision parameter used by the access network node to determine when to hand over the UE to an adjacent access network node. (Appendix A16) The method according to appendix A15, wherein the at least one action includes changing a measurement event that triggers a handover of the UE to an adjacent access network node. (Appendix A17) The method according to appendix A15 or A16, wherein the at least one action includes changing the elapsed time after a measurement event is reported to trigger a handover. (Appendix A18) The method according to any one of appendices A11 to A17, wherein the at least one action includes changing the measurement parameter configuration of at least one UE and transmitting the changed measurement parameter configuration to the at least one UE. (Appendix A19) The method according to any one of appendices A11 to A18, wherein the input information received from the at least one adjacent access network node includes at least one item selected from the group consisting of the SSB index of the SSB overlapping with the cell of the access network node, the number of UEs in the SSB, the hardware load, and the radio resource load. (Appendix A20) For the purpose of load distribution, it further includes transmitting input information related to the load in the access network node to an adjacent access network node, and the input information includes at least one item selected from the group consisting of the SSB index of the SSB overlapping with the cell of the adjacent cell, the number of UEs in the SSB, the hardware load, and the radio resource load. The method according to any one of Appendices A11 to A19. (Appendix A21) A method executed in a communication network, Receiving input data from at least one of a plurality of access network nodes, Using the input data from at least one of the plurality of access network nodes and a model obtained from a model training function to determine at least one load prediction for at least one of the plurality of access network nodes, Comprising, The load prediction is, i) The total number of user equipment (UEs) served by the at least one access network node, ii) The number of UEs per SSB of the at least one access network node, iii) The number of UEs served by the at least one access network node that transmits a measurement report identifying a given adjacent cell, and iv) The predicted radio resource load of the at least one access network node, Including at least one data item selected from the group of, Including, a method. (Appendix A22) At least one of the data items of the load prediction includes a deviation from the predicted number. The method according to Appendix A21. (Appendix A23) The method according to appendix A21 or A22, wherein the at least one load prediction includes a predicted radio resource load of the at least one access network node including the physical resource block usage per cell or per Synchronisation Signal Block (SSB). (Appendix A24) The method according to any one of appendices A21 to A23, wherein the method is executed by a model inference node, and the method further includes receiving the model from the model training function. (Appendix A25) Further including using the at least one load prediction to determine a load distribution command for at least one access network node, wherein the load distribution command i) power parameters, ii) measurement configuration, iii) handover decision configuration, iv) UE handover decision, includes at least one data item selected from the group of The method according to any one of appendices A21 to A24. (Appendix A26) The method according to appendix A25, wherein using the at least one load prediction to determine a load distribution command is executed by a model inference node or an access network node of the communication network. (Appendix A27) The method according to appendix A25 or A26, wherein the power parameter is a power parameter of a cell, an SSB beam, or a site. (Appendix A28) The method according to any one of appendices A25 to A27, wherein the measurement configuration is for a UE and defines a situation in which the UE is caused to transmit a measurement report to the access network node. (Appendix A29) The handover configuration determination is a method according to any one of Appendices A25 to A28, which defines at least one condition necessary for triggering the handover of the UE to an adjacent cell by the at least one access network node. (Appendix A30) The at least one condition includes at least one of: i) a measurement event signaled by the UE before triggering the handover of the UE to an adjacent cell, and ii) the elapsed time from the measurement event before the handover of the UE is triggered, according to the method described in Appendix A29. (Appendix A31) The UE handover determination is a method according to any one of Appendices A25 to A30, which identifies at least one UE served by the at least one access network node and a target cell to which the at least one UE is to be handed over. (Appendix A32) A method executed by a model training function of a communication network, comprising receiving input data from at least one of a plurality of access network nodes, The input data includes i) at least one SSB index of a Synchronisation Signal Block (SSB) overlapping with a cell of at least one adjacent access network node, and the number of UEs in the SSB, ii) hardware load data indicating the hardware load of the access network node, iii) radio resource load data indicating the radio resource load of the access network node, and iv) objective data indicating the objective of the model trained or updated by the second node, including at least one data item selected from the group of The method includes using the input data to train a model and outputting the trained model to a model inference function of the communication network. A method comprising (Appendix A33) An access network node of a communication network, means for receiving a measurement report from one or more user equipments (UEs) to which a service is provided by the access network node, means for transmitting input data to a second node of the communication network, comprising wherein the input data i) at least one SSB index of a Synchronisation Signal Block (SSB) overlapping with a cell of at least one adjacent access network node, and the number of UEs in the SSB, ii) hardware load data indicating the hardware load of the access network node, iii) radio resource load data indicating the radio resource load of the access network node, and iv) objective data indicating the objective of a model trained or updated by the other node, comprises at least one data item selected from the group of an access network node. (Appendix A34) An access network node, comprising means for receiving a model from a model training function, wherein the model comprises a mapping table associating the power of at least one Synchronisation Signal Block (SSB) of the access network node with the number of user equipments (UEs) providing measurement reports to at least one adjacent access network node, wherein the access network node comprises means for receiving input information from the at least one adjacent access network node, Means for receiving a measurement report from one or more user equipments (UEs) to which a service is provided by the access network node; Means for using at least one of the input information from the at least one adjacent access network node, the UE measurement report, and the model to determine at least one load balancing action to be performed by the access network node; An access network node comprising: (Appendix A35) A communication network, Means for receiving input data from at least one of a plurality of access network nodes; Means for using the input data from at least one of the plurality of access network nodes and a model obtained from a model training function to determine at least one load prediction for at least one of the plurality of access network nodes; Comprising: The load prediction is i) The total number of user equipments (UEs) to which a service is provided by the at least one access network node, ii) The number of UEs per SSB of the at least one access network node, iii) The number of UEs to which a service is provided by the at least one access network node that transmits a measurement report for identifying a given adjacent cell, and iv) The predicted radio resource load of the at least one access network node, Including at least one data item selected from the group of: A communication network. (Appendix A36) A model training function of a communication network, Comprising means for receiving input data from at least one of a plurality of access network nodes, The input data is i) At least one SSB index of a Synchronisation Signal Block (SSB) that overlaps with the cell of at least one adjacent access network node, and the number of UEs for each SSB that overlaps with the cell of the said SSB, ii) Hardware load data indicating the hardware load of the said access network node, iii) Radio resource load data indicating the radio resource load of the said access network node, and iv) Objective data indicating the objective of the model trained or updated by the said second node, including at least one data item selected from the group of The said model training function means for using the said input data to train a model and output the trained model to the model inference function of the said communication network A model training function comprising. (Appendix A37) A computer-executable instruction product comprising computer-executable instructions for providing a programmable computer device for executing the method according to any one of Appendices A1 to A32.

[0117] (Appendix B1) A method executed by an access network node of a communication network, to another node of the said communication network, i) At least one SSB index of a Synchronisation Signal Block (SSB) that overlaps with the cell of the said another node, and the number of UEs for each SSB that overlaps with the cell of the said another node, ii) Hardware load data indicating the hardware load of the said access network node, iii) Radio resource load data indicating the radio resource load of the said access network node, and iv) Objective data indicating the objective of the model trained or updated by the said another node, Transmitting input data including at least one data item from the group including the input data is used to train a model for outputting at least one parameter for load balancing Method (Appendix B2) When the input data includes the radio resource load data, the input data indicates the usage amount of physical resource blocks (PRBs) by the access network node The method according to Appendix B1 (Appendix B3) When the input data includes the hardware load data or the radio resource load data, the input data represents the filtered average load of the access network load over a certain period in the past The method according to Appendix B1 or B2 (Appendix B4) The method according to Appendix B3, wherein the filtered average load is represented by a general load state descriptor or a percentage of a predetermined load (Appendix B5) When the input data includes the target data, the target data includes one of load balancing, mobility robustness, and energy saving The method according to any one of Appendices B1 to B4 (Appendix B6) Receiving a measurement report from one or more user equipments (UEs) served by the access network node or another access network node further including the transmitting is performed by transmitting the input data together with the measurement report The method according to any one of Appendices B1 to B5 (Appendix B7) Receiving the model trained by the input data Outputting, using the model, the at least one parameter for load distribution The method according to any one of Appendices B1 to B6, further comprising (Appendix B8) The model includes a mapping table that associates the power of at least one SSB of the access network node with the number of UEs that provide at least one measurement report to at least one access network node adjacent to the access network node The method according to any one of Appendices B1 to B7 (Appendix B9) A method performed by an access network node, comprising Receiving a model including a mapping table that associates the power of at least one Synchronisation Signal Block (SSB) of the access network node with the number of user equipment (UEs) that provide at least one measurement report to at least one adjacent access network node adjacent to the access network node Receiving input information from the at least one adjacent access network node Using the input information and the model to determine at least one load distribution action to be performed by the access network node Comprising The input information includes i) at least one SSB index of at least one Synchronisation Signal Block (SSB) that overlaps each cell of the at least one adjacent access network node, and the number of UEs for each SSB that overlaps each cell of the at least one adjacent access network node ii) hardware load data indicating the hardware load of the access network node, and iii) radio resource load data indicating the radio resource load of the access network node A method comprising at least one data item from a group of methods. (Appendix B10) The method according to Appendix B9, wherein the at least one load balancing action comprises changing the transmission power of the at least one SSB. (Appendix B11) The at least one load balancing action comprises reducing the transmission power of the at least one SSB, increasing the transmission power of the at least one SSB, changing at least one handover decision parameter used by the access network node to determine when to hand over the UE to an adjacent access network node, changing a measurement event that triggers a handover of the UE to an adjacent access network node, changing the elapsed time after a measurement event has been reported to trigger a handover, and changing the measurement configuration of the at least one UE and transmitting the measurement configuration to the at least one UE The method according to Appendix B9 or B10, comprising at least one of (Appendix B12) when the load of the SSB is greater than the load of the at least one adjacent access network node, and when the load of the at least one adjacent access network node is greater than the load of the at least one SSB, The method according to Appendix B11, wherein the at least one load balancing action occurs in at least one of the above cases. (Appendix B13) When the load in the SSB is greater than the load in the at least one adjacent access network node, the at least one load balancing action comprises reducing the transmission power of the at least one SSB. The method according to Appendix B12. (Appendix B14) The method according to appendix B12, wherein when the load of the at least one adjacent access network node is greater than the load of the at least one SSB, the at least one load balancing action includes increasing the transmission power of the at least one SSB. (Appendix B15) The at least one action includes changing the measurement configuration of at least one UE and transmitting the measurement configuration to the at least one UE. The measurement configuration defines a situation in which the at least one UE is caused to transmit a measurement report to the access network node. The method according to any one of appendices B12 to B14. (Appendix B16) For the purpose of load balancing, transmitting other input information related to the load in the access network node to an adjacent access network node. Further comprising The other input information includes the SSB index of the SSB overlapping with the cell of the adjacent access network node and the number of UEs for each SSB overlapping with the cell of the adjacent access network node, hardware load, and radio resource load including at least one data item from the group of The method according to any one of appendices B9 to B15. (Appendix B17) Further comprising receiving a measurement report transmitted from one or more user equipment (UE) served by the access network node or another access network node. Further comprising The using is performed using the measurement report. The method according to any one of appendices B9 to B16. (Appendix B18) A method executed in a communication network, Receiving input data from at least one of a plurality of access network nodes; Using the input data and a model from at least one of the plurality of access network nodes to determine at least one load prediction for at least one of the plurality of access network nodes; comprising wherein the at least one load prediction i) the total number of user equipment (UE) served by the at least one access network node; ii) the number of UEs per Synchronisation Signal Block (SSB) of the at least one access network node; iii) the number of UEs served by the at least one access network node that transmits a measurement report identifying a given neighbouring cell, and iv) the predicted radio resource load of the at least one access network node; includes at least one data item from the group of wherein the input data i) at least one SSB index of the SSBs that overlap with the cells of neighbouring access network nodes adjacent to one of the at least one access network node, and the number of UEs per SSB that overlaps with the cells of the neighbouring access network nodes; ii) hardware load data indicating the hardware load of the access network node; iii) radio resource load data indicating the radio resource load of the access network node, and iv) objective data indicating the objective of the model to be trained or updated; includes at least one of a method. (Appendix B19) The method according to appended note B18, wherein at least one of the at least one data item of the load prediction includes a deviation from the predicted number indicated by at least one of the data items. (Appended note B20) When at least one of the at least one data item of the load prediction includes the predicted radio resource load of the at least one access network node, the predicted radio resource load includes the physical resource block usage per cell or per SSB. The method according to appended note B18 or B19. (Appended note B21) The method according to any one of appended notes B18 to B20, further comprising receiving the model from the model training function. (Appended note B22) Further comprising using the at least one load prediction, the model, and input data from adjacent access network nodes or UEs to determine a load distribution command for at least one access network node. The load distribution command i) power parameter, ii) measurement configuration, iii) handover decision configuration, and iv) UE handover decision, including at least one data item from the group of The method according to any one of appended notes B18 to B21. (Appended note B23) The method according to appended note B22, which is executed by a model inference node or an access network node of the communication network. (Appended note B24) The method according to appended note B22 or B23, wherein the power parameter is a power parameter of a cell, an SSB beam, or a site. (Appended note B25) The method according to any one of appended notes B22 to B24, wherein the measurement configuration is for a UE and defines a situation in which the UE is caused to transmit a measurement report to the access network node. (Appendix B26) The handover configuration determination is the method according to any one of Appendices B22 to B25, which defines at least one condition necessary for triggering the handover of the UE to an adjacent cell in the at least one access network node. (Appendix B27) The at least one condition is i) a measurement event signaled by the UE before triggering the handover of the UE to an adjacent cell, and ii) the elapsed time from the measurement event before the handover of the UE is triggered, The method according to Appendix B26, including at least one of the above. (Appendix B28) The UE handover determination is the method according to any one of Appendices B22 to B27, which identifies at least one UE served by the at least one access network node and a target cell to which the at least one UE is to be handed over. (Appendix B29) An access network node of a communication network, to another node of the communication network, i) at least one SSB index of a Synchronisation Signal Block (SSB) overlapping with the cell of the other node and the number of UEs for each SSB overlapping with the cell of the other node, ii) hardware load data indicating the hardware load of the access network node, iii) radio resource load data indicating the radio resource load of the access network node, and iv) target data indicating the purpose of a model trained or updated by the other node, Means for transmitting input data including at least one data item from the group above Comprising The input data is used to train a model for outputting at least one parameter for load balancing. Access network node. (Appendix B30) An access network node, means for receiving a model including a mapping table that associates the power of at least one Synchronisation Signal Block (SSB) of the access network node with the number of user equipment (UE) that provides at least one measurement report to at least one adjacent access network node adjacent to the access network node; means for receiving input information from the at least one adjacent access network node; means for using the input information and the model to determine at least one load balancing action to be performed by the access network node; comprising wherein the input information is i) at least one SSB index of a Synchronisation Signal Block (SSB) that overlaps with each cell of the at least one adjacent access network node, and the number of UEs for each SSB that overlaps with each cell of the at least one adjacent access network node, ii) hardware load data indicating the hardware load of the access network node, and iii) radio resource load data indicating the radio resource load of the access network node, including at least one data item from the group of Access network node. (Appendix B31) A communication network, means for receiving input data from at least one of a plurality of access network nodes; Means for using the input data and the model from at least one of the plurality of access network nodes to determine at least one load prediction for at least one of the plurality of access network nodes, comprising wherein the at least one load prediction comprises i) the total number of user equipment (UE) served by the at least one access network node, ii) the number of UEs per Synchronisation Signal Block (SSB) of the at least one access network node, iii) the number of UEs served by the at least one access network node that transmits a measurement report identifying a given neighbouring cell, and iv) the predicted radio resource load of the at least one access network node, comprising at least one data item from the group of wherein the input data comprises i) at least one SSB index of SSBs overlapping with cells of neighbouring access network nodes adjacent to one of the at least one access network node, and the number of UEs per SSB overlapping with cells of the neighbouring access network nodes, ii) hardware load data indicating the hardware load of the access network node, iii) radio resource load data indicating the radio resource load of the access network node, and iv) objective data indicating the objective of the model to be trained or updated, comprising at least one of a communication network.

[0118] This application claims the benefit of priority based on UK Patent Application No. 2211627.1, filed on Aug. 9, 2022, the disclosure of which is hereby incorporated by reference in its entirety.

Description of the Reference Numerals

[0119] 1 Mobile (cellular or wireless) telecommunications system 3 Mobile device 5 Base station 6 Cell 7 Core network 8-1 Access and Mobility Management Function (AMF) 8-2 control plane function (CPF) 8-3 user plane function (UPF) 8-4 Session Management Function (SMF) 8-5 Operations, Administration and Maintenance (OAM) function 20 Data network 31 Transceiver circuit 33 Antenna 35 User interface 37 Controller 39 Memory 41 Operating system 43 Communication control module 45 Energy saving module 51 Transceiver circuit 53 Antenna 55 Network interface 57 Controller 59 Memory 61 Operating system 63 Communication control module 65 Energy saving module 71 Transceiver circuit 75 Network interface 77 Controller 79 Memory 81 Operating system 83 Communication control module 85 Energy Saving Module 91 Data Collection Function 93 Model Training Function 95 Model Inference Function 97 Actuator

Claims

1. A method performed by an access network node of a communication network, comprising: transmitting to another node of the communication network: i) at least one Synchronisation Signal Block (SSB) / Physical Broadcast Channel (PBCH) block index of an SSB that overlaps with a cell of the other node, and the number of user equipment (UE) for each SSB that overlaps with the cell of the other node; ii) hardware load data indicating the hardware load of the access network node; iii) radio resource load data indicating the radio resource load of the access network node; and iv) objective data indicating the objective of a model trained or updated by the other node, wherein the input data includes at least one data item from the group; receiving information for deriving output data including at least one parameter for load distribution; wherein the output data is generated by a model trained by the input data, the method.

2. The method according to claim 1, wherein when the input data includes the radio resource load data, the input data indicates the usage amount of physical resource blocks (PRBs) by the access network node.

3. The method according to claim 1 or 2, wherein when the input data includes the hardware load data or the radio resource load data, the input data represents a filtered average load of the access network over a certain past period.

4. The method according to claim 3, wherein the filtered average load is represented by a general load state descriptor or a percentage of a predetermined load.

5. The method according to any one of claims 1 to 4, wherein when the input data includes the objective data, the objective data includes one of load distribution, mobility robustness, and energy saving.

6. Receiving measurement reports from one or more user equipment (UE) served by the access network node or another access network node ​ ​ ​ ​ further comprising wherein said transmitting is performed by transmitting said input data together with said measurement report The method according to any one of claims 1 to 5. **Claim 7** wherein said information includes said model trained by said input data wherein said deriving of said output data is performed by using said model to output said output data including said at least one parameter for load balancing The method according to any one of claims 1 to 6. **Claim 8** wherein said information includes said output data itself The method according to any one of claims 1 to 6. **Claim 9** said model includes a mapping table associating the power of at least one SSB of said access network node with the number of UEs providing at least one measurement report to at least one access network node adjacent to said access network node The method according to any one of claims 1 to 8. **Claim 10** A method performed by an access network node, comprising: receiving a model including a mapping table associating the power of at least one Synchronisation Signal Block (SSB) / Physical Broadcast Channel (PBCH) block of said access network node with the number of user equipment (UEs) providing at least one measurement report to at least one adjacent access network node adjacent to said access network node; receiving input information from said at least one adjacent access network node; using said input information and said model to determine at least one load balancing action to be performed by said access network node; comprising wherein said input information i) at least one SSB index of SSBs overlapping with each cell of said at least one adjacent access network node, and the number of UEs for each of said SSBs overlapping with each of said cells of said at least one adjacent access network node; ii) hardware load data indicating the hardware load of said access network node, and iii) Radio resource load data indicating the radio resource load of the access network node, including at least one data item from the group of methods. **Claim 11** The method according to claim 10, wherein the at least one load balancing action includes changing the transmission power of the at least one SSB. **Claim 12** The at least one load balancing action includes decreasing the transmission power of the at least one SSB, increasing the transmission power of the at least one SSB, changing at least one handover decision parameter used by the access network node to determine when to hand over a UE to an adjacent access network node, changing a measurement event that triggers a handover of the UE to an adjacent access network node, changing the elapsed time after a measurement event has been reported to trigger a handover, and changing the measurement configuration of at least one UE and transmitting the measurement configuration to the at least one UE The method according to claim 10 or 11, including at least one of. **Claim 13** When the load of the SSB is greater than the load of the at least one adjacent access network node, and When the load of the at least one adjacent access network node is greater than the load of the at least one SSB, The at least one load balancing action occurs in at least one of the cases of The method according to claim 12. **Claim 14** When the load in the SSB is greater than the load in the at least one adjacent access network node, the at least one load balancing action includes decreasing the transmission power of the at least one SSB. The method according to claim 13. **Claim 15** When the load of the at least one adjacent access network node is greater than the load of the at least one SSB, the at least one load balancing action includes increasing the transmission power of the at least one SSB. The method according to claim 13. **Claim 16** The at least one action includes changing the measurement configuration of at least one UE and transmitting the measurement configuration to the at least one UE, The measurement configuration causes the at least one UE to transmit a measurement report to the access network node, and defines a situation The method according to any one of claims 13 to 15.

17. For the purpose of load distribution, transmitting other input information related to the load in the access network node to an adjacent access network node further comprising The other input information is the SSB index of the SSB overlapping with the cell of the adjacent access network node, and the number of UEs for each SSB overlapping with the cell of the adjacent access network node hardware load, and radio resource load including at least one data item from the group of The method according to any one of claims 10 to 16.

18. receiving a measurement report transmitted from one or more user equipment (UE) served by the access network node or another access network node further comprising The using is performed using the measurement report The method according to any one of claims 10 to 17.

19. A method performed in a communication network, comprising: receiving input data from at least one of a plurality of access network nodes; and using the input data and a model from at least one of the plurality of access network nodes to determine at least one load prediction for the at least one of the plurality of access network nodes comprising The at least one load prediction is i) the total number of user equipment (UE) served by the at least one access network node; ii) the number of UEs for each Synchronisation Signal Block (SSB) / Physical Broadcast Channel (PBCH) block of the at least one access network node; iii) the number of UEs served by the at least one access network node that transmits a measurement report identifying a given adjacent cell; and iv) the predicted radio resource load of the at least one access network node including at least one data item from a group of wherein the input data i) at least one SSB index of SSBs overlapping with a cell of an adjacent access network node adjacent to one of the at least one access network nodes, and the number of UEs for each SSB overlapping with the cell of the adjacent access network node, ii) hardware load data indicating the hardware load of the access network node, iii) radio resource load data indicating the radio resource load of the access network node, and iv) objective data indicating the objective of the model to be trained or updated, including at least one of a method. **Claim 20** The method according to claim 19, wherein at least one of the data items of the at least one load prediction includes a deviation from a predicted number indicated by at least one of the data items. **Claim 21** The method according to claim 19 or 20, wherein when at least one of the data items of the at least one load prediction includes a predicted radio resource load of the at least one access network node, the predicted radio resource load includes a physical resource block usage per cell or per SSB. The method according to claim 19 or 20. **Claim 22** The method according to any one of claims 19 to 21, further comprising receiving the model from a model training function. **Claim 23** using the at least one load prediction, the model, and input data from an adjacent access network node or a UE to determine a load distribution command for at least one access network node, further comprising wherein the load distribution command i) power parameters, ii) measurement configurations, iii) handover decision configurations, and iv) UE handover decisions, including at least one data item from a group of The method according to any one of claims 19 to 22. **Claim 24** The method according to claim 23, wherein the method is executed by a model inference node or an access network node of the communication network. **Claim 25** The method according to claim 23 or 24, wherein the power parameter is a cell, SSB beam, or site power parameter. **Claim 26** The measurement configuration is for a UE, and the method according to any one of claims 23 to 25, which defines a situation for causing the UE to transmit a measurement report to the access network node.

27. The handover decision configuration defines at least one condition necessary for causing at least one access network node to trigger a handover of a UE to an adjacent cell, the method according to any one of claims 23 to 26.

28. The at least one condition is i) a measurement event signaled by the UE before triggering a handover of the UE to an adjacent cell, and ii) the elapsed time from the measurement event before the handover of the UE is triggered, The method according to claim 27, including at least one of them.

29. The UE handover decision identifies at least one UE served by the at least one access network node and a target cell to which the at least one UE is to be handed over, the method according to any one of claims 23 to 28.

30. An access network node of a communication network, to another node of the communication network, i) at least one SSB / Physical Broadcast Channel (PBCH) block index of a Synchronisation Signal Block (SSB) overlapping with the cell of the other node, and the number of user equipment (UE) for each SSB overlapping with the cell of the other node, ii) hardware load data indicating the hardware load of the access network node, iii) radio resource load data indicating the radio resource load of the access network node, and iv) objective data indicating the objective of a model trained or updated by the other node, means for transmitting input data including at least one data item from the group; means for receiving information for deriving output data including at least one parameter for load distribution; comprising The output data is generated by a model trained by the input data, Access network node.

31. An access network node, Means for receiving a model comprising a mapping table that associates the power of at least one Synchronisation Signal Block (SSB) / Physical Broadcast Channel (PBCH) block of the access network node with the number of user equipments (UEs) that provide at least one measurement report to at least one adjacent access network node adjacent to the access network node, Means for receiving input information from the at least one adjacent access network node, Means for using the input information and the model to determine at least one load balancing action to be performed by the access network node, Comprising, The input information is, i) at least one SSB index of at least one SSB that overlaps with each cell of the at least one adjacent access network node, and the number of UEs for each of the at least one SSB that overlaps with each cell of the at least one adjacent access network node, ii) hardware load data indicating the hardware load of the access network node, and iii) radio resource load data indicating the radio resource load of the access network node, including at least one data item from the group of, Access network node.

32. A communication network, Means for receiving input data from at least one of a plurality of access network nodes, Means for using the input data and a model from at least one of the plurality of access network nodes to determine at least one load prediction for the at least one of the plurality of access network nodes, Comprising, The at least one load prediction is, i) the total number of user equipments (UEs) served by the at least one access network node, ii) The number of UEs per Synchronisation Signal Block (SSB) / Physical Broadcast Channel (PBCH) block of the at least one access network node, iii) The number of UEs served by the at least one access network node that transmits a measurement report identifying a given neighbouring cell, and iv) The predicted radio resource load of the at least one access network node, including at least one data item from the group of The input data is i) At least one SSB index of an SSB that overlaps with a cell of an adjacent access network node adjacent to one of the at least one access network nodes, and the number of UEs per said SSB that overlaps with said cell of the adjacent access network node, ii) Hardware load data indicating the hardware load of the access network node, iii) Radio resource load data indicating the radio resource load of the access network node, and iv) Objective data indicating the objective of the model to be trained or updated, including at least one of A communication network.

Images