Method, model training function, and model inference function

Abstract

A method performed by a user equipment (UE), the method comprising: receiving, from an access network node, a measurement configuration for requesting information regarding expected data communication with the access network node; and transmitting, to the access network node, a measurement report including the information, the information being used to output at least one parameter using a model for energy saving.

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 but not exclusively, to so-called "5G" or "New Radio" systems (also referred to as "next-generation" systems) and techniques for network energy saving (NES) in 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 a mobile communication device such as, for example, 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 typically operated by a user (thus, they 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 is the so-called "5G" or "New Radio" (NR) specifications, which refer to evolving communication technologies expected to support various applications and services such as MTC, IoT / communications, vehicle communications and autonomous vehicles, high-resolution video streaming, smart city services, etc. 3GPP intends to support 5G with the so-called 3GPP Next Generation (NextGen) radio access network (RAN) and 3GPP NextGen core (NGC) networks. 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 can be operated by humans or 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] The energy consumption of base stations and other similar access network nodes presents a concern regarding the impact on the environment of an operating telecommunication network, in addition to representing a significant operating expense for network operators. There are various tools for saving energy on the network side. For example, capacity cells (i.e., cells deployed to support a specific area during peak hours) can be turned off, and neighboring cells are aware of whether the capacity cell is available. This feature enables the optimization of energy consumption in a deployment that can distinguish, for example, between a capacity booster and a cell providing basic coverage, and allows an E-UTRA cell or an E-UTRA-New Radio Dual Connectivity (EN-DC) cell that provides additional capacity via single or dual connectivity to be turned off when its capacity is no longer needed and reactivated as necessary. The determination is typically based on cell load information. The determination to turn off may also be made by an Operations and Maintenance (O&M) node, or another suitable core network node.

[0007] The base station can start a handover operation to offload an off cell, and when performing subsequent operations, for example, when selecting a target cell for a subsequent handover, it can indicate the reason for the handover with an appropriate cause value to support the target node.

Prior Art Documents

Non-Patent Documents

[0008]

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

[0009] Generally, when the load is not sufficient and the UE can be offloaded to a neighboring cell, the network can decide to turn off the entire cell. However, this is not always achievable in a coverage cell, for example, when other cells are not available (because the network still has to guarantee services to the UE). Furthermore, in some cases, turning off the entire cell will cause neighboring cells to use more power (to enhance their coverage) than is saved for the off cell. This also causes some overhead signaling related to the handover of the UE to an appropriate neighboring cell.

[0010] Efficient implementation of network energy saving (NES) by a base station may include: 1) evaluating the current total load on a cell (optionally taking into account the load in neighboring cells and the core network); 2) determining an appropriate NES configuration from available configurations (e.g., turning off cells of the base station); and 3) implementing the determined NES configuration. Regarding the implementation of NES, 3GPP has proposed the use of artificial intelligence (AI) and machine learning (ML), often abbreviated as AI / ML, to assist in the implementation of NES to meet various stringent requirements of 5G networks. However, specific implementation forms of NES using AI / ML have not been proposed so far, and thus it is desirable to provide such implementation forms to meet these stringent requirements.

[0011] Therefore, the present disclosure aims to provide a method and related apparatus for addressing (at least in part) or at least alleviating the above-described 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 Problems

[0012] According to one aspect, a method performed by a user equipment (UE) is provided. The method includes receiving, from an access network node, a measurement configuration for requesting information regarding expected data communication with the access network node, and transmitting a measurement report including the information to the access network node. The information can be used to output at least one parameter using a model for energy saving.

[0013] The information may include the expected next uplink or downlink data arrival time and / or the next expected data packet size.

[0014] According to another aspect, a method performed by an access network node is provided. The method includes receiving, by the access network node, a measurement report from one or more user equipments (UEs) served by the access network node, and transmitting, to a model training function, input data including information used to output at least one parameter using a model for energy saving, wherein each of the measurement reports includes information regarding expected data communication with the access network node.

[0015] The information may include an expected next uplink or downlink data arrival time and / or a next expected data packet size. In some embodiments, the input data includes at least one data item from the group consisting of: i) a UE bearer context for each of one or more UEs to which each UE measurement report relates, ii) the location of each of one or more UEs to which each UE measurement report relates, iii) load information about the access network node, iv) the power consumption of the serving cell of the access network node, v) an indication of a coverage cell or a capacity cell, vi) the traffic volume of each of one or more UEs during a specific period, and vii) an indication of a model objective. The load information may alternatively or additionally include a physical random access channel (PRACH) load. The indication of the model objective may be one of load distribution, mobility robustness, and energy saving.

[0016] According to a further aspect, a method performed by a model training function of a communication network is provided. The method includes receiving, from at least one access network node, input data including information regarding expected data communication between a user equipment (UE) and the at least one access network node for energy saving; training a model using the input data; and outputting the trained model to a model inference function of the communication network to take measures for energy saving.

[0017] The information may include an expected next uplink or downlink data arrival time and / or a next expected data packet size. The input data may include at least one data item from the group consisting of: i) a UE bearer context for the UE to which the UE measurement report relates; ii) the location of the UE to which the UE measurement report relates; iii) load information for each of the at least one access network node; iv) the power consumption of the serving cell of each of the at least one access network node; v) an indication of a coverage cell or a capacity cell; vi) the traffic volume of each UE served by each of the at least one access network node during a specific period; vii) an indication of a model objective. The load information may include a Physical Random Access Channel (PRACH) load. The indication of the model objective may be one of load distribution, mobility robustness, and energy saving.

[0018] According to another aspect, there is provided a method performed by a model inference function of a communication network, the method comprising: receiving a model for outputting at least one parameter for energy saving; receiving input data including information regarding expected data communication between a user equipment (UE) and at least one of a plurality of access network nodes from at least one of the plurality of access network nodes; and determining an energy saving prediction or determination for at least one of the plurality of access network nodes using the input data and the model.

[0019] The input data may include the expected next uplink or downlink data arrival time between at least one access network node and the UE and / or the next expected data packet size. The input data may include at least one data item from the group consisting of: i) a UE bearer context for the UE to which the UE measurement report relates; ii) the location of the UE to which the UE measurement report relates; iii) load information for each of the at least one access network nodes; iv) the power consumption of the serving cell of each of the at least one access network nodes; v) an indication of a coverage cell or a capacity cell; vi) the traffic volume of each UE served by each of the at least one access network nodes during a specific period; and vii) an indication of the model objective. The load information may include Physical Random Access Channel (PRACH) load.

[0020] The model inference function may be part of an access network node, and the method may include receiving the input data from at least one access network node adjacent to the access network node.

[0021] The method may further include transmitting an energy prediction or determination notification to at least one access network node, the notification including at least one data item from the group consisting of: i) an activation or deactivation pattern; ii) a cell or BWP or beam or antenna port power pattern; iii) an energy saving level indication; iv) a power state indication; v) a relative power indication; vi) a transition time indication indicating when power should be adjusted; vii) a transition energy representing an energy value by which the serving cell can be reduced accordingly; viii) a handover determination parameter.

[0022] The activation or deactivation pattern may define the period and / or slot during which at least one cell or bandwidth part (BWP) or synchronization signal block (SSB) or channel state information reference signal (CSI-RS) or beam or antenna port of at least one access network node is activated or deactivated. The power state indication may indicate the sleep or non-sleep state of the serving cell of at least one access network node. The handover determination parameter includes a measurement event configuration for at least one UE of at least one access network node and / or a handover trigger time at the reception of the measurement event.

[0023] In some embodiments, the power pattern defines, for a period and a slot, how the power of each cell or BWP or beam or antenna port of at least one access network node is configured.

[0024] According to another aspect, there is provided a user equipment (UE) comprising means for receiving, from an access network node, a measurement configuration for requesting information regarding expected data communication with the access network node; and means for transmitting, to the access network node, a measurement report including the information. The information can be used to output at least one parameter using a model for energy saving.

[0025] According to another aspect, there is provided an access network node comprising means for receiving a measurement report from one or more user equipments (UEs) served by the access network node; and means for transmitting, to a model training function, input data including information used to output at least one parameter using a model for energy saving, each of the measurement reports including information regarding expected data communication with the access network node.

[0026] According to a further aspect, there is provided a model training function of a communication network, the model training function comprising means for receiving, from at least one access network node, input data including information regarding expected data communication between a user equipment (UE) and the at least one access network node for energy saving; means for training a model using the input data; and means for outputting, to a model inference function of the communication network, the trained model for taking measures for energy saving.

[0027] According to a further aspect, there is provided a model inference function for a communication network, the model inference function comprising means for receiving a model for outputting at least one parameter for energy saving; means for receiving input data including information regarding predicted data communication between a user equipment (UE) and at least one of a plurality of access network nodes from at least one of the plurality of access network nodes; and means for determining an energy saving prediction or determination for at least one of the plurality of access network nodes using the input data and the model.

[0028] Each feature disclosed in this specification (which term includes the claims) and / or each feature shown in the drawings may be incorporated into the present disclosure independently of (or in combination with) any other disclosed and / or illustrated features. Without limitation, in particular, any feature of any claim dependent on a particular independent claim may be introduced into that independent claim in any combination or individually.

Brief Description of the Drawings

[0029] Here, 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

[0030] Overview FIG. 1 schematically illustrates a mobile (cellular or wireless) telecommunication system 1 to which embodiments of the present disclosure may be applied.

[0031] 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 a core network 7 using an appropriate 3GPP radio access technology (RAT), e.g., Evolved Universal Terrestrial Radio Access (E-UTRA) and / or 5G RAT. It will be appreciated that several base stations 5 form a (wireless) access network, or (R)AN. As will be understood by those skilled in the art, FIG. 1 shows, for illustrative purposes, four mobile devices 3A, 3B, 3C, 3D and two base stations 5A, 5B, but the system will typically include other base stations / (R)AN nodes, and mobile devices (UEs) when implemented.

[0032] 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 a next-generation / 5G protocol may be referred to as a "gNB". It will be appreciated that some base stations 5 may be configured to support both 4G and 5G, and / or any other 3GPP or non-3GPP communication protocol.

[0033] The mobile device 3 and its service-providing base station 5 are connected via an appropriate air interface (such as, for example, the so-called "NR" air interface, "Uu" interface, etc.). The neighboring base stations 5 can be connected to each other via an appropriate inter-base station interface (such as, for example, the so-called "Xn" interface, "X2" interface, etc.). The base station 5 is also connected to the core network node via an appropriate interface (such as, for example, the so-called "NG-U" interface (in the case of the user plane), the so-called "NG-C" interface (in the case of the control plane), etc.).

[0034] The core network 7 (e.g., EPC in the case of LTE and NGC in the case of NR / 5G) typically includes logical nodes (or "functions") for supporting communications in the telecommunications system 1 and, in particular, for subscriber management, mobility management, billing, 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, which is responsible for handling connection and mobility management tasks of the mobile device 3, or the Mobility Management Entity in 4G. 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 can 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, via the UPF 11.

[0035] User Equipment (UE) Figure 2 is a block diagram illustrating 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 at least one connected node 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 or any combination of hardware, software, and firmware as needed. The controller 37 controls the operation of UE 3 according to software stored in the memory 39. The software may be pre-installed in the memory 39 and / or may be downloaded, for example, via the telecommunication 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.

[0036] The 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 the (R)AN node 5 and core network nodes. The signaling may include control signaling related to energy saving operations (e.g., system information and RRC). It will be understood that the communication control module 43 may include several sub-modules ("layers" or "entities") to support specific functions. For example, the 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.

[0037] 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 typically achieved by turning off specific components (e.g., transceiver circuit 31) for a specific period. In the following embodiments, as will be described in more detail below, the UE3 can assist the network in performing energy saving by taking various measures to help the network grasp a more accurate situation of the actual load currently borne by the network.

[0038] Access network node (base station) Figure 3 is a block diagram illustrating the main components of the base station 5 (or a similar access network node) shown in Figure 1. As shown, the base station 5 includes a transceiver circuit 51 operable to transmit signals to at least one connected UE3 via one or more antennas 53, receive signals from at least one UE3, transmit signals to other network nodes (either directly or indirectly) via a network interface 55, and receive signals from other network nodes. The network interface 55 typically includes appropriate inter-base station interfaces (such as the X2 / Xn interface) and appropriate inter-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.

[0039] 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.

[0040] 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.

[0041] Core network functions Figure 4 is a block diagram illustrating 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, OAM 8-5 shown in Figure 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. The controller 77 controls the operation of the core network function according to software stored in the memory 79. The software may be pre-installed in the memory 79 and / or may be downloaded, for example, via the telecommunication 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 (optionally) an energy saving module 85.

[0042] 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.

[0043] 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).

[0044] Artificial Intelligence(AI) / Machine Learning(ML) 3GPP has proposed a functional framework for AI / ML and how various entities in a telecommunications system interact in the context of this framework. In this regard, refer to FIG. 5 which illustrates these entities here.

[0045] 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 an AI / ML model inference output (e.g., a prediction or a decision), and the actor 97 is a function or node that receives the output from the model inference function 95 and triggers or performs corresponding actions (e.g., a (radio) access network node that increases or decreases its transmission power to achieve network energy saving).

[0046] The terms referred to by 3GPP in the context of this framework include the following. AI / ML Model: A data-driven algorithm that applies machine learning techniques to generate a set of outputs, including predicted 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 a trained AI / ML model for inference. AI / ML Inference: A process of making predictions or deriving decisions using a trained AI / ML model based on the collected data and the AI / ML model. Training Data: Data required as input for the AI / ML model training function. Inference Data: 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.

[0047] Detailed Description The following is an explanation of how network load can be determined using AI / ML, thereby enabling the network within system 1 shown in FIG. 1 to make better network energy saving decisions.

[0048] A first embodiment for determining a network energy saving configuration and taking appropriate further measures is to place the model inference function 95 within a base station 5, for example, within a (R)AN node such as a gNB or within the control unit of a gNB (gNB-CU). Advantageously, placing the model inference function 95 in the base station 5 enables rapid energy saving decisions to be made across cells as needed.

[0049] Here, a more detailed description of the first embodiment will be given with reference to the signaling diagram shown in FIG. 6.

[0050] As a summary, FIG. 6 illustrates the communication that occurs between UE3, a base station (RAN node 5A) that provides services to UE3, another neighboring base station (RAN node 5B), and a core network node 7 (such as the OAM8-5 function of core network 7) in the context of network energy savings 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 its predicted resource status to RAN node 5A as needed during the network energy savings procedure (details will be described later).

[0051] In step 1, RAN node 5A signals to UE3 a measurement configuration request that asks UE3 to 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) between the serving cell and neighboring cells of the UE, minimisation of drive tests (MDT) measurement data, UE speed information, UE positioning information (e.g., GPS data), etc.). Although only one UE3 is mentioned in FIG. 6 and the following related description, it should be understood that in fact, in step 1, multiple UEs are signaled by RAN node 5A 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 requests across the cells it operates.

[0052] Next, in step 2, UE3 collects the required measurements and / or location information, and in step 3, reports the collected information to RAN node 5A via a UE measurement report message. In addition to the above parameters, UE may also report information related to the expected data communication. For example, its expected next uplink / downlink (UL / DL) data arrival time, and / or its next expected data packet size (e.g., UE may model through data modeling which data it expects to receive / when it expects to receive the data).

[0053] Then, in step 4, RAN node 5A signals one or more received UE measurement reports together with its own data as input data for training the AI / ML model. This training is performed in the core network 7 (e.g., by the OAM function 8-5 of the core network). The information transmitted from RAN node 5A to core network node 7 may include: - Of UE3: · Bearer context (and its 5G quality of service identifier (5GQI)), · Measurement report including data modeling information determined by UE3 (e.g., UE's next expected UL / DL data arrival time, and / or its next expected data packet size), - Of RAN node 5A: · Load information including the physical random access channel (PRACH) load of the RAN node, · Power consumption in the serving cell operated by RAN node 5A, · Whether the cell operated by RAN node 5A is a coverage cell or a capacity cell, · Amount of traffic in the serving cell of the RAN node during a given period, and · Instructions for AI / ML purposes (e.g., for (network) energy savings, load distribution, mobility robustness, etc.).

[0054] Furthermore, RAN node 5B may also send, in step 4a, its own input data corresponding broadly to the above input data for model training to core network node 7. As those skilled in the art will understand, such data collection and reporting to core network node 7 is not a "one-time-only" activity. The UEs 3 served by base station 5 change over time as do their data requirements. Thus, either or both of RAN nodes 5A and 5B continue to send their respective input data to core network 7 at regular (or irregular) intervals. In this way, core network node 7 can retrain the model to reflect the changing traffic conditions within the network. Over time, as the network provides feedback on the predictions made using the model, the model is better calibrated to match network behavior, beneficially resulting in a model that provides predictions / judgments with higher accuracy.

[0055] As illustrated in step 5, the AI / ML model training function 93 located in core network 7 processes the input data received in steps 4 and 4a to train the AI / ML model. The AI / ML model is trained using conventional machine learning training techniques not described herein.

[0056] Upon training the AI / ML model, core network 7, in step 6, updates the AI / ML model stored locally in RAN node 5A (or, if the model is not stored locally by RAN node 5A, deploys the AI / ML model to RAN node 5A). The AI / ML model may also be deployed or updated in RAN node 5B.

[0057] Then, in step 7, the RAN node 5B sends its latest input data to the RAN node 5A for model inference of AI / ML-based network energy saving. The RAN node 5B sends this information to the RAN node 5A at regular intervals or whenever the RAN node 5B detects that its load has changed enough so that different NES decisions can be generated as a result of model inference.

[0058] In step 8, the UE 3 sends one or more updated UE measurement reports to the RAN node 5A. Then, in step 9, based on the input received from the RAN node 5B in step 7 and the one or more UE measurement reports received in step 8, the model inference function 95 of the RAN node 5A generates one or more model inference outputs (e.g., prediction and / or determination of network energy saving strategies, prediction and / or determination of handover strategies, etc.).

[0059] Optionally, in step 10, the RAN node 5A may send model performance feedback to the core network 7 as needed.

[0060] In step 11, the RAN node 5A executes network energy saving operations (or handover strategy prediction) according to the output generated by the model inference function 95 in step 9. If the output is a handover strategy, the RAN node 5A may select the most appropriate target cell for each UE before performing the handover.

[0061] Then, in steps 12 and 13, each RAN node 5B, 5A sends feedback information regarding the changes implemented by the RAN node 5A to the core network 7 according to the (updated) model received from the core network 7.

[0062] In the embodiment described above with reference to FIG. 6, the model inference function 95 was arranged in the RAN node 5, and the trained model was arranged in the core network. In the following second embodiment described with reference to FIG. 7, the model inference function is arranged in a separate node (instead of the RAN node 5A and / or the RAN node 5B). In this embodiment, similar to the previous embodiment, the model training function 93 is arranged in the core network 7.

[0063] Referring now to FIG. 7, steps 0 to 5 of this embodiment are substantially the same as steps 0 to 5 of the first embodiment illustrated in FIG. 6, and thus will not be described again.

[0064] Following step 6, the core network 7 deploys the trained model to the model inference node 6 (or updates the model if the model has already been deployed).

[0065] Once deployed / updated, the RAN node 5B transmits its latest input data to the model inference node 6 in step 7 for model inference of AI / ML-based network energy saving.

[0066] Then, in step 8, the model inference node 6 generates one or more model inference outputs (e.g., prediction and / or determination of network energy saving strategy, prediction and / or determination of handover strategy, etc.) based on the input received from the RAN node 5B in step 7, and provides the prediction / determination output in step 9 to the RAN node 5A. Such an output may include one or more of the following parameters for local implementation by the RAN node 5A. - Activation / deactivation pattern of cell / bandwidth part (BWP) / beam / antenna port that can indicate the specific time in day / week / month when the cell / BWP / beam / antenna port is activated or deactivated, - Cell / BWP / beam antenna port power pattern, - Low / medium / high energy saving levels, - Power state (including sleep / non-sleep modes for the serving cell operated by RAN node 5A, where the sleep mode refers to the dormant state of the serving cell), - Relative power indication (indicating a value to which the cell power is adjusted accordingly (this may take a specific value or may be represented by a power level set to, for example, "high", "low", or "intermediate")), - Transition time (indicating when the power should be adjusted over time), - Transition energy (representing an energy value by which the serving cell can be reduced accordingly), - Handover decision parameters (measurement event configuration, handover trigger times to each neighboring cell upon reception of each measurement event)

[0067] For example, the cell / BWP / SSB / CSI-RS / beam activation / deactivation pattern may define the periods and slots when the cell / BWP / beam is activated or deactivated, for example, as shown in the following table.

Table 1

[0068] As a further example, a cell in a commercial area of a city may be activated at 7 am and deactivated at 7 pm from Monday to Friday, and may remain deactivated on Saturday and Sunday. Similarly, the cell / BWP / SSB / CSI-RS / beam power pattern may define the periods and slots of how the power of each cell / BWP / beam is configured, for example, as shown in the following table.

Table 2

[0069] As shown in step 10, UE3 continues to send one or more updated UE measurement reports to RAN node 5A. Optionally, in step 11, RAN node 5A may send model performance feedback to core network 7 as needed.

[0070] In step 12, RAN node 5A executes network energy saving operations according to the output of model inference node 6 generated in step 8. If the output is a handover strategy, RAN node 5A may select the most appropriate target cell (e.g., the cell operated by RAN node 5B) for each UE3 before performing the handover.

[0071] Then, in steps 13 and 14, each of RAN nodes 5B and 5A sends feedback information regarding the changes implemented by RAN node 5A to core network 7 according to the output received from model inference node 6.

[0072] Modifications and alternatives The detailed embodiments have been described above. As those skilled in the art will understand, some modifications and alternatives can be made to the above embodiments while still benefiting from the disclosure embodied in the above embodiments. Some of these alternatives and modifications are described here by way of example only.

[0073] It will be understood that the above embodiments can be applied to both 5G New Radio (5G NR) and LTE systems (E-UTRAN). The above embodiments can also be applied to future systems (Beyond 5G, 6G, etc.).

[0074] Next-generation mobile networks support diverse service requirements, which are 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 conventional 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, which require guaranteed access within a very 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. Among these applications, some have relatively loose Quality of Service / Quality of Experience (QoS / QoE) requirements, but it should be understood that some applications may have relatively strict QoS / QoE requirements (e.g., high bandwidth and / or low latency).

[0075] 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, but in other applications, such as a system designed from the start 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 as software, hardware, firmware, or a mixture thereof.

[0076] Each controller may comprise a processing circuit in any suitable form including, by way of non-limiting 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 buses, data buses, and / or address buses), direct memory access (DMA) functionality, hardware or software-implemented counters, pointers, and / or timers, etc.

[0077] 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 performed by some or all of this software may be performed 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.

[0078] The functions of a 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 hosts higher-level functions and communicates 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, Service Data Adaptation Protocol (SDAP) layer, and Packet Data Convergence Protocol (PDCP) layer (or the RRC layer and PDCP layer of an 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 whose 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, as well as the user plane parts of the PDCP protocol and the 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.

[0079] When a distributed base station or a similar control plane - user plane (CP - UP) split is used, the base station may be split into a separate control plane entity and a user plane entity, each of which may include an associated transceiver circuit, antenna, network interface, controller, memory, operating system, and communication control module. It will be understood that when the base station comprises a distributed base station, the network interface (reference number 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) to communicate signals between the respective functions of the distributed base station. In this case, the communication control module also takes care of the communication (generation, transmission, and reception of signaling messages) between the control plane part and the user plane part of the base station. It will be understood that when a distributed base station is used, it is not necessary to involve both the control plane part and the user plane part for the preemption of communication resources as described in the above embodiments. Preemption can be handled by the user plane part of the base station without involving the control plane part (or vice versa).

[0080] 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.

[0081] The user equipment (or "UE", "mobile station", "mobile device", or "wireless device") in the present disclosure is an entity connected to the network via a wireless interface.

[0082] 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.

[0083] The terms "user equipment" or "UE" (as used by 3GPP), "mobile station", "mobile device", and "wireless device" are generally intended to be synonymous with each other and include stand-alone mobile stations such as terminals, cell phones, smartphones, tablets, cellular IoT devices, IoT devices, and machines. The terms "mobile station" and "mobile device" are also understood to include devices that remain stationary for long periods of time.

[0084] The UE may be, for example, an equipment item for production or manufacturing and / or an energy-related machinery item (e.g., a boiler; an engine; a turbine; a solar panel; a wind turbine; a hydroelectric generator; a thermal power generator; a nuclear power generator; a battery; a nuclear system and / or related equipment; heavy electrical equipment; a pump including a vacuum pump; a compressor; a fan; a blower; hydraulic equipment; pneumatic equipment; metalworking machinery; a manipulator; a robot and / or its application system; a tool; a mold or die; a roll; conveying equipment; lifting equipment; material handling equipment; textile machinery; a sewing machine; printing and / or related machinery; paper industry machinery; chemical machinery; mining and / or construction machinery and / or related facilities; machinery and / or appliances for agriculture, forestry and / or fisheries; safety and / or environmental protection equipment; a tractor; precision bearings; a chain; a gear; power transmission equipment; lubrication equipment; a valve; a pipe fitting; and / or an application system for any of the foregoing equipment or machinery, etc.).

[0085] The UE may be, for example, a transportation equipment item (e.g., a railway vehicle; a (powered) vehicle; a motorcycle; a bicycle; a train; a bus; a cart; a rickshaw; a ship or other vessel; an aircraft; a rocket; a satellite; a drone; a balloon, etc.).

[0086] The UE may be, for example, an information and communication equipment item (e.g., an electronic computer and related equipment; communication and related equipment; electronic components, etc.).

[0087] The UE may be, for example, a refrigerator, a refrigeration appliance product, a commercial and / or service industry equipment item, a vending machine, an automatic service machine, an office machine or equipment, a consumer electronics device and an electric appliance (for example, consumer electric appliances such as audio devices; video devices; speakers; radios; televisions; microwave ovens; rice cookers; coffee machines; dishwashers; washing machines; dryers; electric fans or related appliances; vacuum cleaners, etc.).

[0088] The UE may be, for example, an electrical application system or equipment (for example, electrical application systems or equipment such as X-ray systems; particle accelerators; radioisotope equipment; sonic equipment; electromagnetic application equipment; electric power application equipment, etc.).

[0089] 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 (for example, surveying or sensing devices such as smoke detectors; human sensors; motion sensors; wireless tags, etc.), a wristwatch or a clock, an inspection device, an optical device, a medical device and / or system, a weapon, a cutlery product, a hand tool, etc.

[0090] The UE may be, for example, a personal digital assistant or related equipment of wireless equipment (such as a wireless card or module designed to be attached to or inserted into another electronic device (for example, a personal computer, an electrical measuring instrument)).

[0091] The UE may be part of a device or system that uses various wired and / or wireless communication technologies to provide the applications, services, and solutions described later regarding the "internet of things (IoT)".

[0092] Internet of Things devices (or "things") can be equipped with appropriate electronic devices, software, sensors, network connections, etc. that enable these devices to collect data and exchange data with each other and other communication devices. IoT devices may include automated devices that follow software instructions stored in internal memory. IoT devices may operate without the need for human supervision or interaction. IoT devices may also remain stationary and / or inactive for long periods of time. IoT devices may be implemented as part of (generally) fixed installations. IoT devices may also be incorporated into non-fixed devices (e.g., vehicles) or attached to animals or people to be monitored / tracked.

[0093] It will be understood that IoT technology can be implemented on any communication device capable of connecting to a communication network to send / receive data, whether or not such communication device is controlled by human input or software instructions stored in memory.

[0094] It will be understood that IoT devices are sometimes also referred to as Machine-Type Communication (MTC) devices or Machine-to-Machine (M2M) communication devices. It will be understood that a UE may support one or more IoT applications 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.

[0095] [Table 3]

[0096] Applications, 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.

[0097] Furthermore, the UE categories described above are merely examples of the application of the technical ideas and embodiments described in this specification. Needless to say, these technical ideas and embodiments are not limited to the UEs described above, and various modifications can be made to them.

[0098] Various other modification examples will be apparent to those skilled in the art and will not be described in further detail here.

[0099] Although the present disclosure has been illustrated and described in detail with reference to the embodiments of the present disclosure, the present disclosure is not limited to these embodiments. It will be understood by those skilled in the art 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.

[0100] Each of the drawings or figures is merely an example for illustrating one or more embodiments. Each figure may not be associated with only one specific 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 the features or steps illustrated in one or more other figures to create, for example, embodiments that are not explicitly illustrated or described. Not all of the features or steps illustrated 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 any of the figures may be changed as needed.

[0101] All or part of the embodiments disclosed above can be described as follows, without limitation, in the following appendices. (Appendix A1) A method performed by a User Equipment (UE), receiving a measurement configuration from an access network node, transmitting a measurement report to the access network node, comprising wherein the measurement report includes information regarding expected data communication with the access network node, method. (Appendix A2) A method performed by an access network node, receiving one or more UE measurement reports from one or more user equipments (UE) served by the access network node, transmitting input data to a model training function, comprising wherein the UE measurement report includes information regarding expected data communication with the access network node, wherein the input data includes the information, method. (Appendix A3) A method performed by a model training function of a communication network, comprising: Receiving input data from at least one of a plurality of access network nodes; Training a model using the input data and outputting the trained model to a model inference function of the communication network; Including: The input data includes information regarding expected data communication between a user equipment and the access network node. Method. (Appendix A4) A method performed by a model inference function of a communication network, comprising: Receiving a model trained using the method described in Appendix A3; Receiving updated input data from at least one of a plurality of access network nodes; Using the received updated input data and the model to determine an energy saving prediction or determination for at least one access network node; Including: The updated input data includes information regarding expected data communication between a user equipment and the at least one access network node. Method. (Appendix A5) A user equipment (UE), comprising: Means for receiving a measurement configuration from an access network node; Means for transmitting a measurement report to the access network node; Comprising: The measurement report includes information regarding expected data communication with the access network node. UE. (Appendix A6) An access network node, Means for receiving one or more UE measurement reports from one or more user equipment (UE) provided with services by the access network node; Means for transmitting input data to the model training function; Comprising; The UE measurement report includes information regarding expected data communication with the access network node; The input data includes the information; Access network node. (Appendix A7) A model training function of a communication network, Means for receiving input data from at least one of a plurality of access network nodes; Means for training a model using the input data and outputting the trained model to the model inference function of the communication network; Comprising; The input data includes information regarding expected data communication between a user equipment and at least one access network node; Model training function. (Appendix A8) A model inference function of a communication network, Means for receiving a model trained using the method described in Appendix A3; Means for receiving updated input data from at least one of a plurality of access network nodes; Means for determining an energy saving prediction or judgment for at least one access network node using the received updated input data and the model; Comprising; The updated input data includes information regarding expected data communication between a user equipment and the at least one access network node; Model inference function.

[0102] (Appendix B1) A method performed by a user equipment (UE), comprising: receiving, from an access network node, a measurement configuration for requesting information regarding expected data communication with the access network node; transmitting, to the access network node, a measurement report including the information; wherein the information is used to output at least one parameter using a model for energy saving; Method. (Appendix B2) The method according to Appendix B1, wherein the information includes an expected next uplink or downlink data arrival time and / or a next expected data packet size. (Appendix B3) A method performed by an access network node, comprising: receiving a measurement report from one or more user equipments (UEs) served by the access network node; transmitting, to a model training function, input data including the information used to output at least one parameter using a model for energy saving; wherein each of the measurement reports includes information regarding expected data communication with the access network node; Method. (Appendix B4) The method according to Appendix B3, wherein the information includes an expected next uplink or downlink data arrival time and / or a next expected data packet size. (Appendix B5) The input data includes i) a UE bearer context for each of one or more UEs to which each UE measurement report relates; ii) the location of each of the one or more UEs to which each UE measurement report relates; iii) Load information about the access network node, iv) Power consumption of the serving cell of the access network node, v) Indication of a coverage cell or a capacity cell, vi) Traffic volume of each of the one or more UEs during a specific period, and vii) Indication of the model objective The method according to Appendix B3 or B4, comprising at least one data item from the group consisting of: (Appendix B6) The load information includes the Physical Random Access Channel (PRACH) load, and the method according to Appendix B5. (Appendix B7) The indication of the model objective is one of load balancing, mobility robustness, and energy saving, and the method according to Appendix B5 or B6. (Appendix B8) A method performed by a model training function of a communication network, Receiving, from at least one access network node, input data including information regarding expected data communication between a user equipment (UE) and the at least one access network node for energy saving; Training a model using the input data; Outputting the trained model to a model inference function of the communication network to take actions for energy saving; The method comprising: (Appendix B9) The information includes the expected next uplink or downlink data arrival time and / or the next expected data packet size, and the method according to Appendix B8. (Appendix B10) The input data i) UE bearer context for the UE to which the UE measurement report relates, ii) the location of the UE to which the UE measurement report relates, iii) load information for each of the at least one access network node, iv) the power consumption of the serving cell of each of the at least one access network node, v) an indication of a coverage cell or a capacity cell, vi) the traffic volume of each UE served by each of the at least one access network node during a specific period, vii) an indication of a model objective A method according to appendix B8 or B9, comprising at least one data item from the group consisting of: (Appendix B11) The method according to appendix B10, wherein the load information includes a Physical Random Access Channel (PRACH) load. (Appendix B12) The method according to appendix B10 or B11, wherein the indication of the model objective is one of load distribution, mobility robustness, and energy saving. (Appendix B13) A method performed by a model inference function of a communication network, comprising: receiving a model for outputting at least one parameter for energy saving; receiving, from at least one of a plurality of access network nodes, input data including information regarding expected data communication between a user equipment (UE) and at least one of the plurality of access network nodes; using the input data and the model to determine an energy saving prediction or determination for at least one of the plurality of access network nodes; A method comprising: (Appendix B14) The input data includes the predicted next uplink or downlink data arrival time and / or the next predicted data packet size between the at least one access network node and the UE, and is the method described in Appendix B13. (Appendix B15) The input data includes i) the UE bearer context for the UE to which the UE measurement report relates, ii) the location of the UE to which the UE measurement report relates, iii) load information for each of the at least one access network node, iv) the power consumption of the serving cell of each of the at least one access network node, v) an indication of a coverage cell or a capacity cell, vi) the traffic volume of each UE served by each of the at least one access network node during a specific period, and vii) an indication of the model purpose and includes at least one data item from the group consisting of the method described in Appendix B13 or B14. (Appendix B16) The load information includes the Physical Random Access Channel (PRACH) load, and is the method described in Appendix B15. (Appendix B17) The model inference function is part of an access network node, The method includes receiving the input data from at least one access network node adjacent to the access network node and is the method described in any one of Appendices B13 to B16. (Appendix B18) The method further includes transmitting an energy prediction or a judgment notification to the at least one access network node, The notification includes i) an activation or deactivation pattern, ii) Cell, BWP, beam, or antenna port power pattern, iii) Energy saving level indication, iv) Power state indication, v) Relative power indication, vi) Transition time indication indicating when the power should be adjusted, vii) Transition energy representing an energy value that can reduce the serving cell accordingly, viii) Handover decision parameter A method according to any one of Appendices B13 to B16, comprising at least one data item from the group consisting of: (Appendix B19) (Appendix B20) (Appendix B20) The activation or deactivation pattern defines the period and / or slot during which the cell, bandwidth part (BWP), synchronization signal block (SSB), channel state information reference signal (CSI-RS), beam, or antenna port of the at least one access network node is activated or deactivated, according to the method described in Appendix B18. (Appendix B21) The power pattern defines, for the period and slot, how the power of each cell, BWP, beam, or antenna port of the at least one access network node is configured, according to the method described in Appendix B18 or B19. (Appendix B22) The handover decision parameter includes a measurement event configuration for at least one UE of the at least one access network node and / or a handover trigger time at the reception of a measurement event, and is the method according to any one of Appendices B18 to B21. (Appendix B23) A user equipment (UE) comprising: means for receiving, from an access network node, a measurement configuration for requesting information regarding expected data communication with the access network node; means for transmitting, to the access network node, a measurement report including the information; and wherein the information is used to output at least one parameter using a model for energy saving. UE. (Appendix B24) An access network node comprising: means for receiving a measurement report from one or more user equipments (UEs) served by the access network node; means for transmitting, to a model training function, input data including information used to output at least one parameter using a model for energy saving; and wherein each of the measurement reports includes information regarding expected data communication with the access network node. Access network node. (Appendix B25) A model training function of a communication network, comprising: means for receiving, from at least one access network node, input data including information regarding expected data communication between a user equipment (UE) and the at least one access network node for energy saving; means for training a model using the input data; Means for outputting a model trained in the model inference function of the communication network to take actions for energy conservation, A model training function comprising (Appendix B26) A model inference function of a communication network, Means for receiving a model for outputting at least one parameter for energy conservation, Means for receiving input data including information on expected data communication between a user equipment (UE) and at least one of the plurality of access network nodes from at least one of the plurality of access network nodes, Means for determining an energy conservation prediction or determination for at least one of the plurality of access network nodes using the input data and the model, A model inference function comprising

[0103] This application claims the benefit of priority based on UK Patent Application No. 2211641.2 filed on August 9, 2022, the disclosure of which is incorporated herein by reference in its entirety.

Explanation of Signs

[0104] 1 Mobile (cellular or wireless) telecommunications system 3 Mobile device 5 Base station 6 (One or more) Cells 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) 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 a user equipment (UE), comprising: receiving, from an access network node, a measurement configuration for requesting information regarding expected data communication with the access network node; transmitting, to the access network node, a measurement report including the information; wherein the information is used to output at least one parameter using a model for energy saving. The method.

2. The method according to claim 1, wherein the information includes an expected next uplink or downlink data arrival time and / or a next expected data packet size. The method according to claim 1.

3. A method performed by an access network node, comprising: receiving, from one or more user equipments (UEs) served by the access network node, a measurement report; transmitting, to a model training function, input data including information used to output at least one parameter using a model for energy saving; wherein each of the measurement reports includes the information regarding expected data communication with the access network node. The method.

4. The method according to claim 3, wherein the information includes an expected next uplink or downlink data arrival time and / or a next expected data packet size. The method according to claim 3.

5. The input data includes i) a UE bearer context for each of the one or more UEs to which each UE measurement report relates; ii) the location of each of the one or more UEs to which each UE measurement report relates; iii) load information about the access network node; iv) the power consumption of the serving cell of the access network node; v) an indication of a coverage cell or a capacity cell; vi) the traffic volume of each of the one or more UEs during a specific period; and vii) an indication of a model purpose and includes at least one data item from the group consisting of. The method according to claim 3 or 4.

6. The method according to claim 5, wherein the load information includes a Physical Random Access Channel (PRACH) load. The method according to claim 5.

7. The instruction of the model objective is one of load distribution, mobility robustness, and energy saving. The method according to claim 5 or 6.

8. A method performed by a model training function of a communication network, the method comprising: Receiving, from at least one access network node, input data including information regarding predicted data communication between a user equipment (UE) and the at least one access network node for energy saving; Training a model using the input data; Outputting a model trained by the model inference function of the communication network to take measures for energy saving; A method comprising.

9. The information includes predicted next uplink or downlink data arrival times and / or next predicted data packet sizes. The method according to claim 8.

10. The input data includes: i) UE bearer context for the UE related to the UE measurement report; ii) The location of the UE related to the UE measurement report; iii) Load information for each of the at least one access network node; iv) Power consumption of the serving cell of each of the at least one access network node; v) Indication of a coverage cell or a capacity cell; vi) Traffic volume of each UE served by each of the at least one access network node during a specific period; vii) Instruction of the model objective including at least one data item from the group consisting of: The method according to claim 8 or 9.

11. The method according to claim 10, wherein the load information includes a Physical Random Access Channel (PRACH) load.

12. The instruction of the model objective is one of load distribution, mobility robustness, and energy saving. The method according to claim 10 or 11.

13. A method performed by a model inference function of a communication network, the method comprising: Receiving a model for outputting at least one parameter for energy saving; Receiving input data including information regarding predicted data communication between a user equipment (UE) and at least one of the plurality of access network nodes from at least one of the plurality of access network nodes; Determining an energy saving prediction or determination for at least one of the plurality of access network nodes using the input data and the model; A method comprising:

14. The method according to claim 13, wherein the input data includes a predicted next uplink or downlink data arrival time and / or a next predicted data packet size of a transmission between the at least one access network node and the UE.

15. The input data is i) a UE bearer context for the UE to which the UE measurement report relates, ii) the location of the UE to which the UE measurement report relates, iii) load information for each of the at least one access network node, iv) power consumption of a serving cell of each of the at least one access network node, v) an indication of a coverage cell or a capacity cell, vi) the traffic volume of each UE served by each of the at least one access network node during a specific period, and vii) an indication of the model purpose including at least one data item from the group consisting of: The method according to claim 13 or 14.

16. The method according to claim 15, wherein the load information includes a Physical Random Access Channel (PRACH) load.

17. The model inference function is part of an access network node, The method is Receiving the input data from at least one access network node adjacent to the access network node including: The method according to any one of claims 13 to 16.

18. Further comprising transmitting an energy prediction or determination notification to at least one access network node, The notification is i) an activation or deactivation pattern, ii) a cell or BWP or beam or antenna port power pattern, iii) an energy saving level indication, iv) a power state indication, v) a relative power indication, vi) A transition time indication indicating when the power should be adjusted; vii) A transition energy representing an energy value that can reduce the serving cell accordingly; viii) A handover determination parameter comprising at least one data item from the group consisting of: The method according to any one of claims 13 to 16.

19. The activation or deactivation pattern defines a period and / or slot during which at least one cell or bandwidth part (BWP) of the at least one access network node, or a synchronization signal block (SSB), or a channel state information reference signal (CSI-RS), or a beam or antenna port is activated or deactivated; The method according to claim 18.

20. The power pattern defines, for a period and a slot, how the power of each cell or BWP or beam or antenna port of the at least one access network node is configured, according to the method of claim 18 or 19.

21. The power state indication indicates a sleep or non-sleep state of the serving cell of the at least one access network node, according to the method of any one of claims 18 to 20.

22. The handover decision parameter includes a measurement event configuration for at least one UE of the at least one access network node and / or a handover trigger time when the measurement event is received; The method according to any one of claims 18 to 21.

23. A user equipment (UE), means for receiving from an access network node a measurement configuration for requesting information regarding expected data communication with the access network node; means for transmitting to the access network node a measurement report including the information; comprising wherein the information is used to output at least one parameter using a model for energy saving; UE.

24. An access network node, means for receiving a measurement report from one or more user equipment (UE) served by the access network node; means for transmitting input data including information used by a model training function to output at least one parameter using a model for energy saving; comprising; each of the measurement reports includes information regarding expected data communication with the access network node; Access network node.

25. A model training function of a communication network, means for receiving, from at least one access network node, input data including information regarding expected data communication between a user equipment (UE) and the at least one access network node for energy saving; means for training a model using the input data; means for outputting a model trained in a model inference function of the communication network to take an action for the energy saving; A model training function comprising.

26. A model inference function of a communication network, means for receiving a model for outputting at least one parameter for energy saving; means for receiving, from at least one of a plurality of access network nodes, input data including information regarding expected data communication between a user equipment (UE) and the at least one of the plurality of access network nodes; means for determining an energy saving prediction or determination for the at least one of the plurality of access network nodes using the input data and the model A model inference function comprising.

Images