Message passing machine learning (ML) prediction between network nodes

Abstract

Message passing machine learning (ML) prediction between network nodes is disclosed. A method performed by a network node is provided. The method includes performing a machine learning (ML) operation to generate a prediction of at least one of: (i) a number of user equipment (UEs) expected at a radio cell during a time window, or (ii) a UE resource for the number of UEs expected at the radio cell during the time window. The method further includes sending, based on the prediction, a message to another network node indicating the prediction of a UE related procedure for the radio cell.

Description

Technical Field

[0001] This disclosure generally relates to telecommunications, and more specifically to artificial intelligence (AI) / machine learning (ML) in telecommunications systems. Background Technology

[0002] A telecommunications system can be viewed as a facility that enables a communication session between two or more entities (such as user terminals, base stations, and / or other nodes) by providing carriers between various entities involved in the communication path. For example, a telecommunications system can be provided via a communication network and one or more compatible communication devices. The communication session may include, for example, communication of data carrying communications such as voice, video, email, text messages, multimedia, and / or content data. Non-limiting examples of the services provided include two-way or multiplexing, data communication or multimedia services, and access to data network systems such as the Internet.

[0003] In a wireless telecommunications system, at least a portion of a communication session between at least two stations occurs via a wireless link. Examples of wireless telecommunications systems include Public Land Mobile Networks (PLMNs), satellite-based communication systems, and various wireless local area networks (WLANs). Some wireless systems can be divided into cells and are therefore often referred to as cellular systems.

[0004] Users can access telecommunications systems using appropriate communication equipment or terminals. A user's communication equipment may be referred to as user equipment (UE) or user gear. The communication equipment is equipped with appropriate signal receiving and transmitting means for enabling communication, such as access to a communication network or direct communication with other users. The communication equipment can access a carrier provided by a station (e.g., a base station in a cell) and transmit and / or receive communication on that carrier.

[0005] Telecommunication systems and associated equipment typically operate according to given standards or specifications that define what the various entities associated with the communication system are permitted to do and how they should operate. Communication protocols and / or parameters used to connect the various entities are also usually defined. An example of a telecommunications system is the Universal Mobile Telecommunications System (UMTS). Other examples of telecommunications systems are Long Term Evolution (LTE), LTE-Advanced, and so-called 5G or New Radio (NR) networks. NR is being standardized by the 3rd Generation Partnership Project (3GPP). Summary of the Invention

[0006] The exemplary implementations disclosed herein relate to telecommunications, and more specifically, to artificial intelligence (AI) / machine learning (ML) in telecommunications systems. This disclosure includes, but is not limited to, the following exemplary implementations.

[0007] Some example implementations provide an apparatus for implementing a network node, the apparatus comprising: at least one memory configured to store instructions; and at least one processing circuitry configured to access the at least one memory and execute the instructions to cause the apparatus to at least: perform machine learning (ML) operations to generate a prediction of at least one of: (i) the number of user equipments (UEs) expected at the radio cell during a time window, or (ii) UE resources for the number of UEs expected at the radio cell during a time window; and based on the prediction, send a message to another network node instructing the prediction of UE-related processes for the radio cell.

[0008] Some example implementations provide a method performed by a network node, comprising: performing a machine learning (ML) operation to generate a prediction of at least one of: (i) the number of user equipments (UEs) expected at the radio cell during a time window, or (ii) UE resources for the number of UEs expected at the radio cell during a time window; and, based on the prediction, sending a message to another network node instructing the prediction of UE-related processes for the radio cell.

[0009] Some example implementations provide an apparatus for implementing a network node, the apparatus comprising: at least one memory configured to store instructions; and at least one processing circuitry configured to access the at least one memory and execute the instructions such that the apparatus at least: receives from another node a message indicating a prediction of at least one of: (i) the number of user equipments (UEs) expected at the radio cell during a time window; or (ii) UE resources for the number of UEs expected at the radio cell during a time window; and performs UE-related procedures for the radio cell based on the prediction.

[0010] Some example implementations provide a method performed by a network node, comprising: receiving from another node a message indicating a prediction of at least one of: (i) the number of user equipments (UEs) expected at the radio cell during a time window; or (ii) UE resources for the number of UEs expected at the radio cell during a time window; and, based on the prediction, performing UE-related procedures for the radio cell.

[0011] These and other features, aspects, and advantages of this disclosure will become apparent from the following detailed description and the accompanying drawings, which are briefly described below. This disclosure includes any combination of two, three, four, or more features or elements set forth herein, whether or not such features or elements are explicitly combined or otherwise described in the particular example implementation described herein. This disclosure is intended to be read holistically, and therefore any separable feature or element of this disclosure should be considered composable in any aspect and example implementation unless the context of this disclosure expressly provides otherwise.

[0012] Therefore, it should be understood that the content of this invention is provided merely to summarize some exemplary implementations in order to provide a basic understanding of some aspects of this disclosure. Consequently, it should be understood that the above-described exemplary implementations are merely examples and should not be construed as limiting the scope or spirit of this disclosure in any way. Other exemplary implementations, aspects, and advantages will become apparent from the following detailed description taken in conjunction with the accompanying drawings, which illustrate the principles of some of the described exemplary implementations by way of example. Attached Figure Description

[0013] The exemplary implementation of this disclosure has been described in general terms. Reference will now be made to the accompanying drawings, which are not necessarily drawn to scale, and in which: Figure 1 The present disclosure illustrates a telecommunications system comprising one or more Public Land Mobile Networks (PLMNs) coupled to one or more external data networks, according to some example implementations of this disclosure; Figure 2 The deployment of a PLMN is shown based on some example implementations; Figure 3 and Figure 4 Signaling diagrams illustrating the process according to various example implementations are shown; Figure 5A and Figure 5B It is a graph showing the number of user equipment (UE) at a cell in a radio access network (RAN) node at a corresponding time step, based on some example implementations; Figure 6 The signaling diagram shows the process according to some example implementations; Figure 7 and Figure 8 This is a flowchart illustrating the various steps in a method executed by the corresponding network node according to various example implementations; and Figure 9 The apparatus is shown according to some example implementations. Detailed Implementation

[0014] Some implementations of this disclosure will now be described more fully below with reference to the accompanying drawings, which illustrate some, but not all, implementations of this disclosure. In fact, various implementations of this disclosure may be embodied in many different forms and should not be construed as limited to the implementations set forth herein; rather, these exemplary implementations are provided so that this disclosure will be thorough and complete, and will fully convey the scope of this disclosure to those skilled in the art. Throughout the text, the same reference numerals refer to the same elements.

[0015] Unless otherwise stated or clear from the context, references to “first,” “second,” etc., should not be construed as implying a particular order. A feature described as above another feature (unless otherwise stated or clear from the context) may alternatively be below, and vice versa; and similarly, a feature described as to the left of another feature may alternatively be to the right, and vice versa. Furthermore, while this document may refer to quantitative measurements, values, geometric relationships, etc., any one or more of these (if not all) may be absolute or approximate, unless otherwise stated, to account for acceptable variations that may occur, such as those due to engineering tolerances, etc.

[0016] As used herein, unless otherwise stated or clearly indicated from the context, "OR" in the operand set is "inclusive OR" and is therefore true if and only if one or more operands are true, not "XOR" which is false if all operands are true. Thus, for example, "[A] OR [B]" is true if [A] is true, or if [B] is true, or if both [A] and [B] are true. Furthermore, the articles "a" and "an" indicate "one or more" unless otherwise stated or clearly indicated from the context. Additionally, it should be understood that, unless otherwise stated, the terms "data," "content," "digital content," "information," and similar terms are sometimes used interchangeably. The term "network" can refer to a group of interconnected computers, including clients and servers; and within a network, these computers can be interconnected directly or indirectly by various means, including via one or more switches, routers, gateways, access points, etc.

[0017] This disclosure discusses systems and architectures that are broadly applicable to a wide range of technologies while using specific terminology. For example, while this disclosure may refer to technologies from 3GPP, such as Global System for Mobile Communications (GSM), UMTS, LTE, Advanced LTE, 5G NR, 5G Advanced, and 6G, it also relates to non-3GPP technologies such as IEEE 802, Bluetooth, and Bluetooth Low Energy. The exemplary implementations of this disclosure described herein also refer to Public Land Mobile Networks (PLMNs) and Mobile Network Operators (MNOs), but the exemplary implementations are similarly applicable to Standalone Non-Public Networks (SNPNs) and the private entities operating these networks. Furthermore, although some examples and figures focus on Radio Access Networks (RANs) and 3GPP access, the exemplary implementations are applicable to any type of network access. This includes not only 5G or 6G 3GPP access, but also non-3GPP access, such as wired access, untrusted non-3GPP access, and trusted non-3GPP network access, which use Radio Access Gateway Function (W-AGF), Non-3GPP Interoperability Function (N3IWF), or Trusted Non-3GPP Gateway Function (TNGF) to connect to the 5G or 6G core network.

[0018] Furthermore, as used in this application, the term "circuit" may refer to one or more or all of the following: (a) implemented solely by hardware circuitry (e.g., implemented with purely analog and / or digital circuitry); (b) a combination of hardware circuitry and software, such as (if applicable): (i) a combination of (multiple) analog and / or digital hardware circuitry and software / firmware, and (ii) any part of a hardware processor having software (including (multiple) digital signal processors, software, and (multiple) memories, which work together to enable a device (e.g., a mobile phone or a server) to perform various functions); and (c) (multiple) hardware circuitry and / or (multiple) processors that require software (e.g., firmware) for operation, such as (multiple) microprocessors or parts thereof, but where the software may be absent when operation does not require it.

[0019] The above definition of "circuit" applies to all uses of the term in this application, including in any claim. As a further example, as used in this application, the term "circuit" also covers only hardware circuitry or processors (or processors), or a portion of hardware circuitry or processors and their accompanying software and / or firmware implementations. For example, where applicable to a particular claim element, the term "circuit" also covers baseband integrated circuits or processor integrated circuits for mobile devices or similar integrated circuits in servers, cellular network devices, or other computing or network devices.

[0020] Figure 1A telecommunications system 100 according to various example implementations of this disclosure is illustrated. A telecommunications system typically includes one or more telecommunications networks. As shown, for example, the system includes one or more PLMNs 102 coupled to one or more other external data networks 104—particularly including wide area networks (WANs), such as the Internet. As will be understood, PLMNs can be deployed in a variety of different ways. In particular, some deployments of 4G LTE and 5G NR are considered standalone (SA) deployments. Other deployments combine 4G LTE and 5G technologies and are referred to as non-standalone (NSA) deployments.

[0021] Each PLMN 102 includes a core network (CN) 106 backbone, such as the Evolved Packet Core (EPC) for 4G LTE, the 5G Core Network (5GC) (sometimes referred to as NGC) for 5G NR, and the 6G Core Network (6GC) for 6G; and each core network and the Internet are coupled to one or more RANs 108, air interfaces, etc., implementing one or more Radio Access Technologies (RATs). Examples of these RANs include the Evolved UMTS Terrestrial Radio Access Network (E-UTRAN) for 4G LTE, the Next Generation Radio Access Network (NG-RAN) for 5G NR, and the 6G RAN. As used herein, “network equipment” refers to any suitable equipment on the network side of a telecommunications network. Examples of suitable network equipment are described in more detail below.

[0022] Examples of RATs include 3GPP radio access technologies such as GSM, CDMA2000 1xEV-DO (HRPD), CDMA2000 1x (1xRTT), UTRA, E-UTRA, 5G NR, 5G Advanced, and 6G. Other examples of RATs include IEEE 802 technologies such as IEEE 802.11 (Wi-Fi), IEEE 802.15 (including 802.15.1 (WPAN / Bluetooth), 802.15.4 (Zigbee), and 802.15.6 (WBAN)), Bluetooth, Bluetooth Low Energy (BLE), Ultra Wideband (UWB), etc. Generally, RAT can refer to any 2G, 3G, 4G, 5G, 6G, or higher generation RAT and its different versions, as well as any other RAT that can be configured to operate in conjunction with such mobile communication technologies to provide access to CN 106 of the MNO.

[0023] Telecommunication system 100 also includes one or more radio units, which may be referred to as user equipment (UE) 110, terminal equipment, terminal gear, mobile station, etc. A UE is typically a device configured to communicate with network equipment in the telecommunications network or another UE. A UE may be a portable computer (e.g., laptop computer, notebook computer, tablet computer), a mobile phone (e.g., cellular phone, smartphone), a wearable computer (e.g., smartwatch), etc. In other examples, a UE may be an Internet of Things (IoT) device, an Industrial IoT (IIoT) device, a vehicle equipped with vehicle-to-everything (V2X) communication technology, etc. In some examples, as referenced by 3GPP, a UE may be a narrowband IoT (NB-IoT) device, an enhanced machine-type communication (eMTC) device, a redcap device, an environmental IoT device, etc.

[0024] In operation, these UEs 110 can connect to one or more RANs in RAN 108 based on their specific RAT, thereby accessing a specific CN 106 of PLMN 102, or accessing one or more external data networks 104 (e.g., the Internet). External data networks can provide Internet access, operator services, third-party services, etc. For example, the International Telecommunication Union (ITU) has classified 5G mobile network services into three categories: enhanced mobile broadband (eMBB), ultra-reliable and low-latency communications (URLLC), and massive machine-type communications (mMTC) or massive Internet of Things (MIoT).

[0025] In various examples, RAN 108 can be configured as one or more macro cells, micro cells, pico cells, femto cells, etc. RAN typically includes one or more RAN nodes that interact with UE 110. In various examples, RAN nodes can be referred to as base stations (BS), access points (AP), base transceivers (BTS), node B (NB), evolved NB (eNB), macro BS, NB (MNB) or eNB (MeNB), home BS, NB (HNB) or eNB (HeNB), next-generation NB (gNB), enhanced gNB (en-gNB), next-generation eNB (ng-eNB), 6G NB (6gNB), etc. The term 'gNB' in 5G NR can correspond to eNB in ​​4G LTE. In addition, NG-RAN nodes can refer to gNB or ng-eNB. Unless otherwise stated, gNB in ​​5G NR or 6gNB in ​​6G can sometimes be more generally referred to as (6)gNB or more simply as gNB.

[0026] RAN 108 may include some type of network control / management entity responsible for controlling the RAN nodes. The network control / management entity and the RAN nodes may be separate or integrated into a single device. The network control / management entity may include processing circuitry configured to perform various management functions, etc. The processing circuitry may be associated with memory, computer-readable storage media, or a database for maintaining information required for the management functions.

[0027] Figure 2 The deployment of PLMN 102 is illustrated, such as a 5G NR or 6G deployment. As shown, RAN 108 (e.g., NG-RAN, 6G RAN) includes one or more RAN nodes 202 (e.g., (6)gNB) configured to connect one or more UEs 110 to the RAN for access to CN 106 (e.g., EPC, 5GC, 6GC). In some deployments, the operation of gNB or other RAN nodes may be distributed or functionally split into components including one or more Remote Radio Heads (RRHs) or Radio Units (RUs) and Baseband Units (BBUs); and in some architectures, the BBU may be split into a Central / Centralized Unit (CU) 204 (Central Node) and a Distributed Unit (DU) 206 (Distributed Node). CUs may be, for example, servers, hosts, or nodes. In some architectures, RRHs / RUs and DUs may be co-located. Node operations may also be distributed among multiple servers, hosts, or nodes.

[0028] although Figure 2 Only one DU 206 is shown, but RAN node 202 may include CU 204 that controls multiple DUs. CUs and DUs can be connected via network interfaces, such as F1 interfaces that support the exchange of signaling messages between CUs and DUs. Signaling messages can be formatted according to application layer protocols, such as the F1 Application Protocol (F1AP).

[0029] It should also be understood that the distribution of work between core network operations and RAN node operations can vary depending on the implementation. 5G network architecture can be based on so-called CU-DU splitting. In the case of gNB, one gNB-CU (CU 204) can control one or more gNB-DUs (DU 206). A gNB-CU can control multiple spatially separated gNB-DUs, at least acting as transmit / receive (Tx / Rx) nodes. However, in some example implementations, a gNB-DU may include, for example, the Radio Link Control (RLC), Media Access Control (MAC) layer, and Physical (PHY) layer, while the gNB-CU may include layers above the RLC layer, such as the Packet Data Convergence Protocol (PDCP) layer, Radio Resource Control (RRC), and Internet Protocol (IP) layer. Other functional splitting is also possible. It is assumed that those skilled in the art are familiar with the OSI model and the functions within each layer.

[0030] In some example implementations, the server or CU 204 can generate a virtual network through which the server communicates with the radio nodes. Typically, virtual networking can involve the process of combining hardware and software network resources and functions into a single software-based management entity (virtual network). Such a virtual network can provide flexible operational distribution between the server and the radio heads / nodes. In practice, any digital signal processing task can be performed in the CU or DU 206, and the boundaries of responsibility transferred between the CU and DU can be selected depending on the implementation.

[0031] RAN node 202 requires proper coordination between CU 204 and DU 206. Currently, the DU is unaware of the number of UEs 110 expected in the near future at the DU (and thus the RAN node)'s cells (radio cells) and the UE resources available for that number of UEs. Depending on the rate at which high-priority UEs arrive at the cell, the situation at the DU could escalate into congestion within the DU. This lack of information regarding the expected UEs and / or UE resources that may be needed in the near future could lead to suboptimal UE-related processes, such as admission control. For example, the lack of information about the expected UEs and / or UE resources could result in situations where resources are pre-allocated for different services. Such pre-allocation of resources can sometimes lead to congestion for lower-priority services, which may sometimes be insufficient for higher-priority services.

[0032] In Release 17, 3GPP introduced artificial intelligence (AI) / machine learning (ML) functionality in RAN108 by allowing RAN node 202 to exchange AI / ML-related measurements or predictions. This can include the number of UEs 110 that may be anticipated at the cell or UE resources for said number of UEs. A framework for training and performing inference from ML models at the RAN node is proposed. In the case of a CU-DU split architecture, predictions can be performed at CU 204 due to the availability of information for training the ML model and its greater computational resources. Multiple use cases for predictions from ML models can include processes initiated by DU 206, but placing the ML model at the DU is not appropriate due to its lack of computational resources. F1AP currently does not support CU sending predictions to DU.

[0033] In light of the foregoing, the example implementations of this disclosure provide a solution that introduces an interface between network nodes (such as CU 204 and DU 206) that can be used by one of the network nodes (e.g., CU) to send predictions (results of ML inference) to (multiple) other network nodes (e.g., DU). This interface may include the exchange of information (such as information elements (IEs)) indicating a prediction of the number of UEs 110 and / or UE resources expected at the cell during a time window. In some examples, this information may also include one or more of the following: the UE type of the number of UEs (e.g., urgent, high priority, normal, slice ID), cell identifier (ID), the validity period of the prediction, etc. The solutions of some example implementations can improve at least one UE-related process for a cell, such as admission control.

[0034] According to some example implementations, a network node (e.g., CU 204) can perform ML operations, such as inference from an ML model, to generate predictions for: (i) the number of UEs 110 expected at the cell (radio cell) during a time window, and / or (ii) UE resources for said number of UEs expected at the cell during the time window. The network node can then send a message to another network node (e.g., DU 206) based on these predictions, indicating predictions for UE-related processes at the cell.

[0035] In some examples, CU 204 or other network nodes can perform ML operations to continuously generate predictions, such as once per time window of the corresponding prediction. In some of these examples, the time window can be configured by the operator as a timer, and the duration of the time window / timer can indicate the valid period of the corresponding prediction. When the timer expires and the corresponding prediction is available, the CU can construct a message indicating the corresponding prediction and send that message to DU 206 or other network nodes. The DU can use this message to trigger, initiate, or execute at least one UE-related procedure (e.g., admission control). The CU can then restart the timer for the next prediction.

[0036] In some examples, the message indicating the prediction may include prediction-related information, which may be formatted in one or more IEs in some examples. The message may include, for example, the UE type for the number of UEs 110, the cell ID of the cell where the expected UE is located, and / or the time window used for the prediction. For a given UE, the UE type may indicate the type of UE (e.g., emergency, high priority, normal, slice), and the cell ID may indicate the cell where the expected UE is located. In some examples, the message may include at least one data field corresponding to the given UE, and the data field may include the UE type and / or the cell ID. Therefore, in some examples, the message may include a list, where each item in the list corresponds to a given UE and includes data fields for that given UE.

[0037] Upon receiving a message, DU 206 or other network nodes can obtain the length of a list corresponding to the number of UEs 110 expected at the cell during the time window. The DU can also obtain the UE type of that number of UEs and / or the cell ID of the expected number of UEs at that location. Similarly, the time window can be included in the message, such that the prediction can be considered valid only for the duration of the time window following the receipt of the message. When the DU receives a new prediction for the next time window, the DU can discard earlier predictions that can be replaced by the new prediction.

[0038] Figure 3Signaling diagram 300 illustrates the procedures involving CU 204 and DU 206 of RAN node 202 according to some example implementations. As shown in steps 301 and 302, a timer for the corresponding prediction expires, and ML inference (ML operation) is performed or implemented to generate a prediction of the expected number of UEs 110 and / or UE resources at the cell of the DU. Then, at step 303, the CU may send a message indicative of the prediction (predicted number of UEs result) to the DU. In some examples, the message may include the UE type, cell ID, and / or time window for the number of UEs / UE resources. The DU may receive the message, and at step 304, the DU may trigger at least one UE-related procedure based on the prediction.

[0039] According to some example implementations, DU 206 or other network nodes can request a prediction. In some of these examples, CU 204 or another network node can receive the prediction request and perform an ML operation to generate a prediction based on the request. The CU can then respond to the request by sending a message indicating the prediction to the DU. Similar to the above, this message may include, for example, the UE type for the number of UEs 110, the cell ID of the cell where the expected UE is located, and / or the time window for the prediction.

[0040] In some of these examples, DU 206 can request predictions based on the service patterns within the DU's cell. In this regard, the DU can be configured with or otherwise defined with a threshold number of UEs 110 at the cell (sometimes referred to as a "maximum number of UEs" threshold), which can conceptually be expressed as... N UEs_THR Similarly, a DU can be configured with or defined to set a threshold for the number of UEs exceeding a certain threshold (sometimes referred to as the "maximum change of UEs above the threshold" threshold), which can be conceptually represented as... N UEs_THR_delta In these examples, when the number of UEs at the cell exceeds... N UEs_THR And higher than N UEs_THR The number of UEs changed more than N UEs_THR_delta At that time, DU can request a prediction.

[0041] And in some other examples, such as based on the cell location exceeding N UEs_THR The number of UE 110, and more than N UEs_THR_delta higher than N UEs_THRAs the number of UEs changes, DU 206 or other network nodes can determine the time window for the requested prediction. The DU's request for prediction can then include the time window for the prediction. Similar to the above, the time window can indicate the valid period for the corresponding prediction, indicating how long the prediction should be given (sometimes called the prediction window).

[0042] Figure 4 Signaling diagram 400 illustrates the process involving CU 204 and DU 206 of RAN node 202 according to some example implementations. As shown in step 401, the DU can determine that the number of UEs at the cell exceeds... N UEs_THR And higher than N UEs_THR The number of UEs changed more than N UEs_THR_delta In response, the DU can determine a time window for predicting the expected number of UEs and / or UE resources at the cell. At step 402, the DU can send a request for the prediction (Predicted Number of UEs Request) to the CU, and this request may include the time window determined at the DU. At step 403, the CU can perform or implement ML inference (ML operation) to generate a prediction of the expected number of UEs and / or UE resources. Then, at step 404, the CU can send a message indicative of the prediction to the DU (Predicted Number of UEs Result).

[0043] In some of these examples, the time window for prediction, determined by DU 206, can have a value inversely proportional to the value exceeded. In other words, the more the threshold is exceeded, the shorter the time window becomes. The value for the time window will correspond to the inverse of the slope, i.e.:

[0044] In front t THR This indicates that the threshold has been reached ( N UEs_THR (time) and t THR_delta Indicates in t THR Then equals the threshold ( N UEs_THR_delta The number of UEs has reached the time. Furthermore, Δ N UE Indicates the number of UEs (N) UEs ) and threshold ( N UEs_THR The difference between the number of UEs in (). Figure 5A and Figure 5B It is based on some examples at the corresponding time step. t 0 andt The graphs 500A and 500B show the number of UEs located in the cell. As shown in the figure, the threshold... N UEs_THR =8, and threshold N UEs_THR_delta =1.

[0045] Depending on the implementation, DU 206 or other network nodes may request predictions based on UE type. In some of these examples, the prediction request from the DU to CU 204 (or other network nodes) may indicate the UE type (e.g., urgent, high priority, normal, slice ID). In other examples, the DU may request predictions based on both the UE type and the service mode for that UE type. In these other examples, the request may also include a time window for the prediction, which may be determined by the DU as described above.

[0046] CU 204 can receive a request, perform ML operations to generate a prediction based on the request, and in response to the request send a message indicative of the prediction to DU 206. Similar to the above, the message may include, for example, the UE type for the number of UEs 110, the cell ID of the cell where the expected UE is located, and / or the time window used for the prediction. Additionally or alternatively, in some examples, the message may include information indicating the threshold number of UEs for triggering one or more resource reservation actions (DU needs to consider the number of UEs triggering one or more resource reservation actions).

[0047] Figure 6 Signaling diagram 600 illustrates the processes involving CU 204 and DU 206 of RAN node 202 according to some example implementations. As shown in step 601, the DU may send a request (Predict Number of UEs Request) to the CU for predicting the expected number of UEs of a UE type and / or the UE resources of UEs of a UE type at the DU's cell, and the request may indicate the UE type. At step 602, the CU may perform or implement ML inference (ML operation) to generate a prediction of the expected number of UEs and / or UE resources for the UE type. The CU may also determine a threshold number of UEs for triggering a resource reservation action by the DU. Then, at step 603, the CU may send a message indicating the prediction (Predict Number of UEs Request) to the DU, and at step 604, the DU may perform an evaluation of the threshold to determine whether to perform a resource reservation action.

[0048] Figure 7This is a flowchart illustrating various steps in method 700 performed by a network node according to various example implementations. The method includes performing machine learning (ML) operations to generate predictions for at least one of: (i) the expected number of user equipments (UEs) at the radio cell during a time window, or (ii) UE resources for said number of UEs expected at the radio cell during the time window, as shown in box 702. The method includes sending a message of the predicted UE-related processes for the radio cell to another network node based on the predictions, as shown in box 704.

[0049] In some examples, a network node is a centralized unit (CU) of a radio access network (RAN) node, and another network node is a distributed unit (DU) of a RAN node.

[0050] In some examples, the message includes or indicates a time window, and at least one data field corresponding to a corresponding UE among the UEs expected at the radio cell during the time window, and in some of these examples, at least one data field includes the UE type for the corresponding UE among the UEs expected at the radio cell during the time window.

[0051] In some examples, at least one data field also includes a cell identifier for the corresponding UE in the UE expected at the radio cell.

[0052] In some examples, performing the ML operation at block 706 includes repeatedly performing the ML operation to generate a continuous prediction for at least one of: (i) the number of UEs expected at the radio cell during a continuous time window, or (ii) UE resources for the number of UEs expected at the radio cell during a continuous time window. In some of these examples, method 700 further includes starting a timer for the corresponding prediction in the continuous prediction, the timer having a duration corresponding to the corresponding time window in the continuous time window and indicating the validity period of the corresponding prediction. Furthermore, in some of these examples, sending a message at block 704 includes sending a continuous message for the corresponding prediction in the continuous prediction, and the continuous message includes a corresponding message for the corresponding prediction sent when the timer expires.

[0053] In some examples, method 700 also includes receiving a request for a prediction. In some of these examples, in response to the request, an ML operation is performed at box 702 to generate a prediction, and a message indicative of the prediction is sent at box 704.

[0054] In some examples, the request specifies a time window for the prediction, and the time window is based on the change in the number of UEs exceeding a threshold number at the radio cell, and the change in the number of UEs exceeding the threshold number. In some of these examples, at box 702, an ML operation is performed to generate a prediction based on the time window indicated in the request.

[0055] In some examples, the request for prediction includes a UE type indicating the UE service type. In some of these examples, at box 702, an ML operation is performed to generate a prediction for at least one of the following: (i) the number of UEs of the expected UE type at the radio cell during the time window, or (ii) UE resources for the number of UEs of the expected UE type at the radio cell during the time window.

[0056] In some examples, the message includes or indicates at least one of the following: a time window, a UE type, at least one data field corresponding to a UE of the corresponding UE among the number of UEs of the expected UE type at the radio cell during the time window, or a threshold number of UEs for triggering one or more resource reservation actions.

[0057] Figure 8 This is a flowchart illustrating various steps in method 800 performed by a network node according to various example implementations. The method includes receiving from another node a message indicating a prediction of at least one of: (i) the number of user equipments (UEs) expected at the radio cell during a time window; or (ii) UE resources for the number of UEs expected at the radio cell during the time window, as shown in box 802. The method also includes: based on the prediction, performing UE-related procedures for the radio cell, as shown in box 804.

[0058] In some examples, a network node is a centralized unit (CU) of a radio access network (RAN) node, and another network node is a distributed unit (DU) of a RAN node.

[0059] In some examples, the message includes or indicates a time window, and at least one data field corresponding to a corresponding UE among the expected number of UEs at the radio cell during the time window, and in some examples of these examples, at least one data field includes the UE type for the corresponding UE among the expected UEs at the radio cell during the time window.

[0060] In some examples, at least one data field also includes a cell identifier for the corresponding UE in the UE expected at the radio cell.

[0061] In some examples, receiving a message at box 802 includes receiving a continuous message for a corresponding prediction in a continuous forecast: (i) the number of UEs expected at the radio cell during a continuous time window, or (ii) the UE resources expected at the radio cell during a continuous time window. In some of these examples, the continuous message includes a corresponding message for a corresponding prediction in the continuous forecast, and the corresponding message is received when a timer expires, the timer having a duration corresponding to the corresponding time window and indicating the validity period of the corresponding prediction.

[0062] In some examples, method 800 also includes sending a request for the prediction. In some of these examples, in response to the request, a message indicating the prediction is received at box 802.

[0063] In some examples, method 800 further includes determining that the number of UEs at the radio cell exceeds a threshold number, and that the change in the number of UEs exceeding the threshold number exceeds a threshold change. In some of these examples, based on this determination, a request for prediction is sent.

[0064] In some examples, method 800 further includes determining a time window for prediction based on the number of UEs exceeding a threshold number at the radio cell and the change in the number of UEs exceeding the threshold number above the threshold number. In some of these examples, the request indicates the determined time window.

[0065] In some examples, the request for prediction includes a UE type indicating the UE service type, and the prediction is a prediction of at least one of the following: (i) the number of UEs of the expected UE type at the radio cell during the time window, or (ii) UE resources for the number of UEs of the expected UE type at the radio cell during the time window.

[0066] In some examples, the message includes or indicates at least one of the following: a time window, a UE type, at least one data field corresponding to a UE of the corresponding UE among the number of UEs of the expected UE type at the radio cell during the time window, or a threshold number of UEs for triggering one or more resource reservation actions.

[0067] According to the example implementations of this disclosure, the telecommunications system 100 or PLMN 102 and its components (such as UE 110, CN 106, RAN 108, RAN node 202, CU 204, and / or DU 206) can be implemented by various parts. The parts used to implement the system and its components can include hardware, firmware, software, or a combination thereof. In some examples, one or more devices can be configured to serve as or otherwise implement the system and its components shown and described herein. In examples involving more than one device, the respective devices can be connected to or otherwise communicate with each other in a variety of different ways, such as directly or indirectly via wired or wireless networks.

[0068] Based on some example implementations, regarding Figure 7 At least some of the described methods 700 can be performed by means including components for performing the method. Similarly, regarding Figure 8 At least some of the methods 800 described can be performed by means including components for performing the methods. Examples of suitable means may include RAN nodes (e.g., DU, CU) or any suitable means such as servers, hosts, or nodes.

[0069] Figure 9 An apparatus 900 is shown according to some example implementations of the present disclosure, wherein components perform various functions individually or under the guidance of one or more computer programs from a computer-readable storage medium or other memory, such as computer memory. The apparatus may include one or more of each of a plurality of components, such as processing circuitry 902 connected to a computer-readable storage medium or other memory 904.

[0070] Processing circuitry 902 may be comprised of one or more processors individually or in combination with one or more computer-readable storage media. Processing circuitry is typically any computer hardware capable of processing information (e.g., data, computer programs, and / or other suitable electronic information). Processing circuitry consists of a collection of electronic circuits, some of which may be packaged as integrated circuits or multiple interconnected integrated circuits (sometimes more commonly referred to as "chips"). Processing circuitry may be configured to execute computer programs, which may be stored on the processing circuitry or otherwise stored in memory 904 (of the same or another device).

[0071] Depending on the specific implementation, the processing circuitry 902 may be multiple processors, a multi-core processor, or some other type of processor. Furthermore, the processing circuitry may be implemented using multiple heterogeneous processor systems, where the main processor resides on a single chip along with one or more auxiliary processors. As another illustrative example, the processing circuitry may be a symmetric multiprocessor system comprising multiple processors of the same type. In yet another example, the processing circuitry may be embodied as or otherwise include one or more ASICs, FPGAs, etc. Therefore, while the processing circuitry is capable of executing a computer program to perform one or more functions, the various examples of processing circuitry are capable of performing one or more functions without the assistance of a computer program. In any case, the processing circuitry may be appropriately programmed to perform functions or operations according to the exemplary implementations of this disclosure.

[0072] Memory 904 is typically any computer hardware capable of temporarily and / or permanently storing information (e.g., data, computer programs, instructions 906 (e.g., computer-readable program code), and / or other suitable information). Memory may include volatile and / or non-volatile memory and may be fixed or removable. Examples of suitable memory include recording media, random access memory (RAM), read-only memory (ROM), hard disk drives, flash memory, thumb drives, removable computer disks, optical disks, or some combination thereof.

[0073] Memory 904 is a non-transitory device capable of storing information. An example of a suitable memory is a computer-readable storage medium, distinguished from a computer-readable transport medium capable of carrying information from one location to another. Examples of suitable computer-readable transport media include electronic carrier signals, telecommunication signals, or some combination thereof. As used herein, the term "non-transitory" is a limitation of the medium itself (i.e., tangible, not signaling), not a limitation of the persistence of data storage (e.g., RAM versus ROM). As described herein, computer-readable media generally refers to either computer-readable storage media or computer-readable transport media. A computer-readable medium is any entity or device capable of storing and carrying information such as one or more computer programs or portions thereof.

[0074] In addition to memory 904 (e.g., a computer-readable storage medium), processing circuitry 902 may also be connected to one or more interfaces for displaying, sending, and / or receiving information. Interfaces may include communication interface 908 and / or one or more user interfaces (e.g., a display, a user input interface). Communication interfaces may be configured to send and / or receive information to and / or from other devices, networks, etc. Communication interfaces may be configured to send and / or receive information via physical (wired) and / or wireless communication links. Examples of suitable communication interfaces include network interface controllers (NICs), wireless NICs (WNICs), etc.

[0075] The combination of operations supporting the implementation of the example implementation of this disclosure is supported by either the execution of instruction 906 by processing circuitry 902 or the storage of instructions in memory 904. In this way, apparatus 900 may include at least one processing circuit and at least one memory coupled to the at least one processing circuit, wherein the at least one processing circuit is configured to execute instructions stored in the at least one memory. It will also be understood that one or more functions, and combinations thereof, may be implemented by a dedicated hardware-based computer system and / or processing circuitry, or a combination of dedicated hardware and program code instructions, performing the specified functions.

[0076] Some example implementations of this disclosure can also be executed as a computer process defined by one or more computer programs or portions thereof. Example implementations of this disclosure can be executed by executing at least a portion of a computer program including instructions. The computer program can be in source code form, object code form, or some intermediate form. The computer program can be stored on a computer-readable medium that can be read by a computer, processing circuitry, or other suitable means. As mentioned above, for example, the computer program can be stored in memory such as a computer-readable storage medium. Additionally or alternatively, for example, the computer program can be stored on a computer-readable transmission medium. The coding of software used to perform the example implementations of this disclosure is entirely within the scope of those skilled in the art.

[0077] As will be understood, any suitable instructions can be loaded from memory or a computer-readable medium (e.g., a computer-readable storage medium, a computer-readable transmission medium) onto a computer, processing circuitry, or other programmable means to produce a particular machine, such that the particular machine becomes a component for implementing the functions specified herein. Instructions can also be stored in a computer-readable medium that can direct a computer, processing circuitry, or other programmable means to function in a particular manner to produce a particular machine or a particular article of manufacture. In some examples, instructions stored in a computer-readable medium can produce an article of manufacture, wherein the article of manufacture becomes a component for implementing the functions described herein. Instructions can be retrieved from a computer-readable medium and loaded onto a computer, processing circuitry, or other programmable means to configure the computer, processing circuitry, or other programmable means to perform operations to be performed on or by the computer, processing circuitry, or other programmable means.

[0078] Instructions, including program code instructions, can be fetched, loaded, and executed sequentially, such that one instruction is fetched, loaded, and executed at a time. In some example implementations, fetching, loading, and / or execution can be performed in parallel, such that multiple instructions are fetched, loaded, and / or executed together. The execution of program code instructions can produce computer-implemented processes, such that instructions executed by a computer, processing circuitry, or other programmable device provide operations for implementing the functions described herein.

[0079] As stated above and reiterated below, this disclosure includes, but is not limited to, the following example implementations.

[0080] Clause 1. A method performed by a network node, the method comprising: performing a machine learning (ML) operation to generate a prediction of at least one of: (i) the number of user equipments (UEs) expected at a radio cell during a time window, or (ii) UE resources for the number of UEs expected at the radio cell during the time window; and, based on the prediction, sending a message to another network node indicating the prediction of UE-related processes for the radio cell.

[0081] Clause 2. The method according to Clause 1, wherein the network node is a centralized unit (CU) of a radio access network (RAN) node, and the other network node is a distributed unit (DU) of the RAN node.

[0082] Clause 3. The method according to Clause 1 or Clause 2, wherein the message includes or indicates the time window, and at least one data field corresponding to a corresponding UE among the UEs expected at the radio cell during the time window, and wherein the at least one data field includes a UE type for the corresponding UE among the UEs expected at the radio cell during the time window.

[0083] Clause 4. The method according to Clause 3, wherein the at least one data field further includes a cell identifier for the radio cell of the corresponding UE in the UE expected at the radio cell.

[0084] Clause 5. The method according to any one of Clauses 1 to 4, wherein performing the ML operation comprises: repeatedly performing the ML operation to generate a continuous prediction for at least one of: (i) the number of UEs expected at the radio cell during a continuous time window, or (ii) UE resources for the number of UEs expected at the radio cell during the continuous time window, wherein the method further comprises: starting a timer for a corresponding prediction in the continuous prediction, the timer having a duration corresponding to a corresponding time window in the continuous time window and indicating a valid time for the corresponding prediction, and wherein sending the message comprises: sending a continuous message for the corresponding prediction in the continuous prediction, and the continuous message comprising a corresponding message for the corresponding prediction sent when the timer expires.

[0085] Clause 6. The method according to any one of Clauses 1 to 5, wherein the method further comprises receiving a request for the prediction, and wherein in response to the request, the ML operation is performed to generate the prediction, and the message instructing the prediction is sent.

[0086] Clause 7. The method according to Clause 6, wherein the request indicates the time window for the prediction, wherein the time window is based on the number of UEs exceeding a threshold number at the radio cell and the change in the number of UEs exceeding the threshold number, and wherein the ML operation is performed to generate the prediction based on the time window indicated in the request.

[0087] Clause 8. The method according to Clause 6 or Clause 7, wherein the request for the prediction includes a UE type indicating a UE service type, and wherein the ML operation is performed to generate a prediction for at least one of: (i) the number of UEs of the UE type expected at the radio cell during the time window, or (ii) UE resources for the number of UEs of the UE type expected at the radio cell during the time window.

[0088] Clause 9. The method according to Clause 8, wherein the message includes or indicates at least one of the following: the time window, the UE type, at least one data field corresponding to a corresponding UE of the number of UEs of the UE type expected at the radio cell during the time window, or a threshold number of UEs for triggering one or more resource reservation actions.

[0089] Clause 10. An apparatus comprising: at least one memory configured to store instructions; and at least one processing circuit configured to access the at least one memory and execute the instructions to cause the apparatus to perform a method according to any one of Clauses 1 to 9.

[0090] Clause 11. An apparatus comprising components for performing the method according to any one of Clauses 1 to 9.

[0091] Clause 12. A computer-readable medium comprising instructions that, in response to execution by at least one processing circuit, cause a device to perform the method according to any one of Clauses 1 to 9.

[0092] Clause 13. A computer-readable storage medium comprising instructions that, in response to execution by at least one processing circuit, cause a device to perform the method according to any one of Clauses 1 to 9.

[0093] Clause 14. A computer program comprising instructions that, in response to execution by at least one processing circuit, cause a device to perform the method according to any one of Clauses 1 to 9.

[0094] Clause 15. A method implemented by a network node, the method comprising: receiving from another node a message indicating a prediction of at least one of: (i) the number of user equipments (UEs) expected at a radio cell during a time window; or (ii) UE resources for the number of UEs expected at the radio cell during the time window; and performing UE-related procedures for the radio cell based on the prediction.

[0095] Clause 16. The method according to Clause 15, wherein the network node is a centralized unit (CU) of a radio access network (RAN) node, and the other network node is a distributed unit (DU) of the RAN node.

[0096] Clause 17. The method according to Clause 15 or Clause 16, wherein the message includes or indicates the time window, and at least one data field corresponding to a corresponding UE among the number of UEs expected at the radio cell during the time window, and wherein the at least one data field includes a UE type for the corresponding UE among the UEs expected at the radio cell during the time window.

[0097] Clause 18. The method according to Clause 17, wherein the at least one data field further includes a cell identifier for the radio cell of the corresponding UE in the UE expected at the radio cell.

[0098] Clause 19. The method according to any one of Clauses 15 to 18, wherein receiving the message comprises: receiving a continuous message for a corresponding prediction in a continuous prediction of at least one of: (i) the number of UEs expected at the radio cell during a continuous time window, or (ii) the UE resources expected at the radio cell during the continuous time window, wherein the continuous message includes a corresponding message for a corresponding prediction in the continuous prediction, and the corresponding message is received when a timer expires, the timer having a duration corresponding to the corresponding time window and indicating the validity period of the corresponding prediction.

[0099] Clause 20. The method according to any one of Clauses 15 to 19, wherein the method further comprises: sending a request for the prediction, and wherein, in response to the request, the message indicating that the prediction is received.

[0100] Clause 21. The method according to Clause 20, wherein the method further comprises: determining that the number of UEs at the radio cell exceeds a threshold number, and that the change in the number of UEs exceeding the threshold number exceeds a threshold change, and wherein, based on the determination, the request for the prediction is sent.

[0101] Clause 22. The method according to Clause 21, wherein the method further comprises: determining the time window for the prediction based on the number of UEs exceeding the threshold number at the radio cell and the change in the number of UEs exceeding the threshold number above the threshold number, wherein the request indicates the determined time window.

[0102] Clause 23. The method according to any one of Clauses 20 to 22, wherein the request for the prediction includes a UE type indicating a UE service type, and the prediction is a prediction of at least one of: (i) the number of UEs of the UE type expected at the radio cell during the time window, or (ii) UE resources for the number of UEs of the UE type expected at the radio cell during the time window.

[0103] Clause 24. The method according to Clause 23, wherein the message includes or indicates at least one of the following: the time window, the UE type, at least one data field corresponding to a corresponding UE of the number of UEs of the UE type expected at the radio cell during the time window, or a threshold number of UEs for triggering one or more resource reservation actions.

[0104] Clause 25. An apparatus comprising: at least one memory configured to store instructions; and at least one processing circuit configured to access the at least one memory and execute the instructions to cause the apparatus to perform a method according to any one of Clauses 15 to 24.

[0105] Clause 26. An apparatus comprising components for performing the method according to any one of Clauses 15 to 24.

[0106] Clause 27. A computer-readable medium comprising instructions that, in response to execution by at least one processing circuit, cause a device to perform the method according to any one of Clauses 15 to 24.

[0107] Clause 28. A computer-readable storage medium comprising instructions that, in response to execution by at least one processing circuit, cause a device to perform the method according to any one of Clauses 15 to 24.

[0108] Clause 29. A computer program comprising instructions that, in response to execution by at least one processing circuit, cause a device to perform the method according to any one of Clauses 15 to 24.

[0109] Benefiting from the teachings presented in the foregoing description and associated drawings, those skilled in the art to which this disclosure pertains will conceive of numerous modifications and other implementations of the disclosure set forth herein. Therefore, it should be understood that this disclosure is not limited to the specific implementations disclosed, and that modifications and other specific implementations are intended to be included within the scope of the appended claims. Furthermore, although the foregoing description and associated drawings describe exemplary implementations in the context of certain example combinations of elements and / or functions, it should be understood that different combinations of elements and / or functions can be provided by alternative implementations without departing from the scope of the appended claims. In this regard, for example, combinations of elements and / or functions different from those explicitly described above are also contemplated as being set forth in some of the appended claims. Although specific terminology is used herein, it is used only in a general and descriptive sense and not for limiting purposes.

Claims

1. An apparatus for implementing a network node, the apparatus comprising: At least one memory is configured to store instructions; as well as At least one processing circuit is configured to access the at least one memory and execute the instructions to cause the device to at least: Perform machine learning (ML) operations to generate predictions for at least one of the following: (i) the number of user equipment (UEs) expected at the radio cell during a time window, or (ii) UE resources for the number of UEs expected at the radio cell during the time window; as well as Based on the prediction, a message indicative of the prediction for the UE-related procedures for the radio cell is sent to another network node.

2. The apparatus of claim 1, wherein the network node is a centralized unit (CU) of a radio access network (RAN) node, and the other network node is a distributed unit (DU) of the RAN node.

3. The apparatus of claim 1, wherein the message includes or indicates the time window, and at least one data field corresponding to a corresponding UE among the UEs expected at the radio cell during the time window, and wherein the at least one data field includes a UE type for the corresponding UE among the UEs expected at the radio cell during the time window.

4. The apparatus of claim 3, wherein the at least one data field further includes a cell identifier for the radio cell of the corresponding UE in the UE expected at the radio cell.

5. The apparatus of claim 1, wherein the apparatus is caused to perform the ML operation by: The apparatus is configured to repeatedly perform the ML operation to generate continuous predictions for at least one of the following: (i) the number of UEs expected at the radio cell during a continuous time window, or (ii) UE resources for the number of UEs expected at the radio cell during the continuous time window. The at least one processing circuit is configured to execute the instructions to cause the device to further activate a timer for a corresponding prediction in the continuous prediction, the timer having a duration corresponding to a corresponding time window in the continuous time window and indicating the effective time of the corresponding prediction. The means of sending the message includes: the means of sending a continuous message for a corresponding prediction in the continuous prediction, and the continuous message includes a corresponding message for the corresponding prediction sent when the timer expires.

6. The apparatus of claim 1, wherein the at least one processing circuit is configured to execute the instructions to cause the apparatus to further receive a request for the prediction, and In response to the request, the ML operation is performed to generate the prediction, and the message instructing the prediction is sent.

7. The apparatus of claim 6, wherein the request indicates for the predicted time window, wherein the time window is based on the number of UEs exceeding a threshold number at the radio cell, and the change in the number of UEs exceeding the threshold number that exceeds the threshold change, and The ML operation is performed to generate the prediction based on the time window indicated in the request.

8. The apparatus of claim 6, wherein the request for the predicted value includes a UE type indicating a UE service type, and The ML operation is performed to generate a prediction of at least one of the following: (i) the number of UEs of the UE type expected at the radio cell during the time window, or (ii) UE resources for the number of UEs of the UE type expected at the radio cell during the time window.

9. The apparatus of claim 8, wherein the message includes or indicates at least one of the following: the time window, the UE type, at least one data field corresponding to a corresponding UE among the number of UEs of the UE type expected at the radio cell during the time window, or a threshold number of UEs for triggering one or more resource reservation actions.

10. An apparatus for implementing a network node, the apparatus comprising: At least one memory is configured to store instructions; as well as At least one processing circuit is configured to access the at least one memory and execute the instructions to cause the device to at least: Receive from another network node a message indicating a prediction of at least one of the following: (i) the number of user equipment (UEs) expected at the radio cell during a time window; or (ii) UE resources for the number of UEs expected at the radio cell during the time window; and Based on the prediction, perform UE-related procedures for the radio cell.

Images