Prediction algorithms for predicting the location of user devices for network optimization

Abstract

A method and apparatus for artificial intelligence (AI) for a communication network is provided. In one embodiment, a method implemented in a core network node includes collecting location information associated with movement of at least one user device within the network; making a prediction based on at least a portion of the collected location information; and transmitting an indication of the prediction.

Description

Technical Field

[0001] The present disclosure relates to communication networks, and in particular to artificial intelligence (AI) for communication networks. Background Art

[0002] Communication networks, such as wireless communication systems, are widely deployed to provide various services such as, for example, data, messaging, telephony, video streaming, etc. As the demand for mobile broadband continues to increase, technologies for improving the efficiency of communication networks and / or enhancing the user experience are being considered. Summary of the invention

[0003] Some embodiments of the present disclosure advantageously provide methods, devices, and systems for artificial intelligence (AI) for communication networks, such as fifth generation (5G) networks.

[0004] According to a first aspect of the present disclosure, a method implemented in a core network node is provided. The method includes collecting location information associated with movement of at least one user equipment within the network. The method includes making a prediction based on at least a portion of the collected location information. The method includes transmitting an indication of the prediction.

[0005] In some embodiments of this aspect, predicting further comprises predicting according to a prediction algorithm, the prediction algorithm associating each of a plurality of different time windows with a different weight. In some embodiments of this aspect, the plurality of different time windows comprises at least one of the following: time of day, day of the week, week of the year, month of the year, and season, each time window being associated with a different weight in the prediction algorithm. In some embodiments of this aspect, predicting according to the prediction algorithm further comprises determining at least one probability based at least in part on a weighted current prediction probability value and a weighted historical probability prediction value. In some embodiments of this aspect, results of previous predictions determine a weight value applied to the current probability prediction value and a weight value applied to the historical prediction value. In some embodiments of this aspect, collecting the location information further comprises collecting path information and corresponding time information, the path information and the time information indicating the movement of the at least one user equipment between at least two radio network areas in the network.

[0006] In some embodiments of this aspect, predicting further comprises predicting a movement path of the at least one user equipment relative to the network, the prediction being based at least in part on the collected path information and the time information. In some embodiments of this aspect, delivering the indication further comprises delivering the indication of the predicted movement path of the at least one user equipment. In some embodiments of this aspect, the at least two radio network areas comprise at least two tracking areas and at least two cells. In some embodiments of this aspect, the indication of the predicted movement path comprises at least one cell global identifier CGI, the at least one CGI indicating at least one cell to which the at least one user equipment is expected to move according to the predicted movement path. In some embodiments of this aspect, the predicting further comprises determining at least one probability of at least one movement path of the at least one user equipment, the at least one movement path comprising at least one of a cell of a base station and a neighboring cell. In some embodiments of this aspect, the indication of the predicted movement path is configured to be included in a paging request for the at least one user equipment, the paging request indicating a probability prediction of the at least one user equipment in the at least one cell for at least one cell in the paging request. In some embodiments of this aspect, the indication of the predicted moving path is configured to initiate a pre-allocation of resources for the at least one user equipment in the cell included in the predicted moving path. In some embodiments of this aspect, the pre-allocation of resources for the at least one user equipment is a pre-allocation of a contention-free preamble, the contention-free preamble being preconfigured and stored in a persistent memory at the at least one user equipment. In some embodiments of this aspect, collecting further comprises collecting the path information and the corresponding time information from at least one of the following items: the at least one user equipment, a mobility management entity, and a base station. In some embodiments of this aspect, collecting further comprises collecting historical path information from at least one of at least one initial attachment and at least one mobility process of the at least one user equipment, the historical path information comprising a cell identifier, a timestamp, a positioning coordinate, and a user equipment identifier. In some embodiments of this aspect, collecting further comprises receiving a tracking area update TAU message, the TAU message comprising a timestamp and a positioning coordinate indicating a current location of the at least one user equipment.

[0007] In some embodiments of this aspect, collecting the location information further comprises collecting the location information and corresponding time information, the collected location information and the corresponding time information being associated with the movement of a plurality of user devices within the network. In some embodiments of this aspect, predicting further comprises predicting a network characteristic based at least in part on the collected location information and the time information. In some embodiments of this aspect, delivering the indication further comprises delivering the indication of the predicted network characteristic. In some embodiments of this aspect, the predicting the network characteristic further comprises predicting at least one of the following items for a future time period based at least in part on the collected location information and the time information: the amount of user devices served by at least one cell and the amount of bearer used for services in the at least one cell. In some embodiments of this aspect, the prediction is used for resource planning in the at least one cell for the future time period. In some embodiments of this aspect, the prediction is used to determine one of a time division duplex TDD mode and a frequency division duplex FDD resource to be used in the at least one cell for the future time period.

[0008] According to a second aspect of the present disclosure, there is provided a core network node configured to facilitate communication of a user device in a communication system. The core network node comprises a processing circuit. The processing circuit is configured to cause the core network node to collect location information, the collected location information being associated with movement of at least one user device within a network. The processing circuit is configured to cause the core network node to make a prediction based on at least a portion of the collected location information. The processing circuit is configured to cause the core network node to transmit an indication of the prediction.

[0009] In some embodiments of this aspect, the processing circuit is further configured to cause the core network node to make a prediction by being configured to cause the core network node to perform the following operations: make a prediction according to a prediction algorithm, and the prediction algorithm associates each time window of a plurality of different time windows with a different weight. In some embodiments of this aspect, the plurality of different time windows include at least one of the following items: time of day, day of the week, week of the year, month of the year, and season, and each time window is associated with a different weight in the prediction algorithm. In some embodiments of this aspect, the processing circuit is further configured to cause the core network node to make a prediction according to the prediction algorithm by being configured to cause the core network node to perform the following operations: determine at least one probability based at least in part on a weighted current prediction probability value and a weighted historical probability prediction value. In some embodiments of this aspect, the results of the previous prediction determine the weight value applied to the current probability prediction value and the weight value applied to the historical prediction value.

[0010] In some embodiments of this aspect, the processing circuit is further configured to cause the core network node to collect the location information by being configured to cause the core network node to perform the following operations: collect path information and corresponding time information, the path information and the time information indicating the movement of the at least one user equipment between at least two radio network areas in the network. In some embodiments of this aspect, the processing circuit is further configured to cause the core network node to perform the following operations: predict a movement path of the at least one user equipment relative to the network, the prediction being based at least in part on the collected path information and the time information.

[0011] In some embodiments of this aspect, the processing circuit is further configured to cause the core network node to communicate the indication by being configured to cause the core network node to perform the following operations: communicate the indication of the predicted moving path of the at least one user equipment. In some embodiments of this aspect, the at least two radio network areas include at least two tracking areas and at least two cells. In some embodiments of this aspect, the indication of the predicted moving path includes at least one cell global identifier CGI, the at least one CGI indicating at least one cell to which the at least one user equipment is expected to move according to the predicted moving path. In some embodiments of this aspect, the processing circuit is further configured to cause the core network node to predict by being configured to cause the core network node to perform the following operations: determine at least one probability of at least one moving path of the at least one user equipment, the at least one moving path including at least one of a cell of a base station and a neighboring cell. In some embodiments of this aspect, the indication of the predicted moving path is configured to be included in a paging request for the at least one user equipment, the paging request indicating a probability prediction of the at least one user equipment in the at least one cell for at least one cell in the paging request. In some embodiments of this aspect, the indication of the predicted mobile path is configured to initiate a pre-allocation of resources for the at least one user equipment in a cell included in the predicted mobile path. In some embodiments of this aspect, the pre-allocation of resources for the at least one user equipment is a pre-allocation of a contention-free preamble, the contention-free preamble being pre-configured and stored in a persistent memory at the at least one user equipment.

[0012] In some embodiments of this aspect, the processing circuit is further configured to cause the core network node to collect by being configured to cause the core network node to perform the following operations: collecting the path information and the corresponding time information from at least one of the following items: the at least one user equipment, the mobility management entity, and the base station. In some embodiments of this aspect, the processing circuit is further configured to cause the core network node to collect by being configured to cause the core network node to perform the following operations: collecting historical path information from at least one of at least one initial attachment and at least one mobility process of the at least one user equipment, the historical path information including a cell identifier, a timestamp, a positioning coordinate, and a user equipment identifier. In some embodiments of this aspect, the processing circuit is further configured to cause the core network node to collect by being configured to cause the core network node to perform the following operations: receiving a tracking area update TAU message, the TAU message including a timestamp and a positioning coordinate indicating the current location of the at least one user equipment. In some embodiments of this aspect, the processing circuit is further configured to cause the core network node to collect the location information by being configured to cause the core network node to perform the following operations: collect the location information and corresponding time information, the collected location information and the corresponding time information being associated with the movement of multiple user devices within the network.

[0013] In some embodiments of this aspect, the processing circuit is further configured to cause the core network node to predict by being configured to cause the core network node to perform the following operations: predicting a network characteristic based at least in part on the collected location information and the time information. In some embodiments of this aspect, the processing circuit is further configured to cause the core network node to transmit the indication by being configured to cause the core network node to perform the following operations: transmitting the indication of the predicted network characteristic. In some embodiments of this aspect, the processing circuit is further configured to cause the core network node to predict the network characteristic by being configured to cause the core network node to perform the following operations: predicting at least one of the following items for a future time period based at least in part on the collected location information and the time information: the amount of user equipment served by at least one cell and the amount of bearer used for services in the at least one cell. In some embodiments of this aspect, the prediction is used for resource planning in the at least one cell for the future time period. In some embodiments of this aspect, the prediction is used to determine one of a time division duplex TDD mode and a frequency division duplex FDD resource to be used in the at least one cell for the future time period. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] A more complete understanding of the present embodiments and the attendant advantages and features thereof will be more readily appreciated by reference to the following detailed description when considered in conjunction with the accompanying drawings, in which:

[0015] Figure 1 is a schematic diagram of an example communication system according to one embodiment of the present disclosure, the example communication system comprising a radio access network (RAN) including a network node and a user equipment (UE) and a gateway connected to a core network, the core network including a network node operating as a data collection node;

[0016] Figure 2 is a block diagram of another example communication system including a UE and a network node according to one embodiment of the present disclosure;

[0017] Figure 3 is a flow chart of an example method for a network node according to one embodiment of the present disclosure;

[0018] Figure 4 is a schematic diagram showing an example of UE path record between network nodes according to one embodiment of the present disclosure;

[0019] Figure 5 is a schematic diagram showing an example of UE path recording between cells according to one embodiment of the present disclosure;

[0020] Figure 6 is a schematic diagram showing an example of UE path record for an idle UE according to one embodiment of the present disclosure;

[0021] Figure 7 is a schematic diagram showing an example of UE tracking according to one embodiment of the present disclosure;

[0022] Figure 8 is a flow chart showing an example of UE path retrieval initiated by a serving cell according to one embodiment of the present disclosure;

[0023] Fig. 9 is a flow chart showing an example of UE path resource pre-allocation according to one embodiment of the present disclosure;

[0024] Fig.10 is a flow chart illustrating an example of network-initiated UE path establishment according to one embodiment of the present disclosure;

[0025] Fig.11 is a schematic diagram illustrating example probabilities and predictions for UE tracking according to one embodiment of the present disclosure;

[0026] Fig.12is a schematic diagram showing an example of predicting UE mobility from cell_i according to one embodiment of the present disclosure;

[0027] Fig.13 is a schematic diagram showing an example of UE path prediction based on independent probability events according to an embodiment of the present disclosure;

[0028] Fig.14 is a schematic diagram showing an example path prediction for a UE based on user habits according to an embodiment of the present disclosure;

[0029] Fig.15 is a schematic diagram showing an example of prediction of UE mobility from cell i to cell j according to one embodiment of the present disclosure;

[0030] Fig.16 is a schematic diagram showing an example of predicting the number of UEs in a cell according to one embodiment of the present disclosure;

[0031] Fig.17 is a flow chart showing an example of periodic update of cell data according to one embodiment of the present disclosure;

[0032] Fig.18 is a flowchart illustrating an example of periodic update of UE data according to one embodiment of the present disclosure; and

[0033] Fig.19 is a schematic diagram showing an example hierarchical arrangement for past statistics according to one embodiment of the present disclosure. DETAILED DESCRIPTION

[0034] Wireless communication networks do not currently use AI to predict behavior to optimize resource allocation. Wireless communication networks do not currently use AI to predict user equipment (UE) routes to optimize mobility, or to predict where the UE is most likely to be when paging the UE. Some embodiments of the present disclosure propose techniques for utilizing AI in order to predict behavior to optimize resource allocation and / or optimize UE paging.

[0035] Some embodiments of the present disclosure provide arrangements for a radio access network node (and / or related nodes) to collect data from different UEs and scenarios during different times of the day, different days of the year, different months, different seasons, etc. to predict future behavior in one or more of the following aspects:

[0036] -Predicting load at different times for load-based time division duplex (TTD) mode selection. In some embodiments, load prediction may cause changes or selections of TDD modes for different days and times based on learned resource types and loads to be used for different days and times. For example, if the expected traffic is mainly downlink, some cells may be assigned a higher downlink timeslot ratio. The fifth generation (5G, also known as New Radio (NR)) 3rd Generation Partnership Project (3GPP) standard may allow flexible combinations of downlink and uplink timeslots to form TDD modes.

[0037] - Predicting aggregate resources and services that are likely to be used based on learned behavior (e.g., machine-learned behavior and / or prediction algorithms) for a particular day and / or time. For example, predicting expected resources for control channels versus data channels.

[0038] - Predicting services and resources to be used for specific UEs (eg, gold users) based on learned behavior (eg, machine learned behavior and / or prediction algorithms) relative to specific days and / or times.

[0039] - Predicting the route of a specific UE (e.g., a golden user) based on learned behavior (e.g., machine-learned behavior and / or prediction algorithms) with respect to different days and times. For example, the next node in the predicted UE path can be prepared in advance for the UE based on the expected path and expected services and / or resources.

[0040] - Based on the learned behavior, predict the tracking area and possibly also the MME and base station (e.g. gNB) where the UE is most likely to be located when paging the UE.

[0041] Data collected for different days and times that may assist the AI ​​algorithm to predict future UE and / or network behavior may include one or more of the following:

[0042] -The number of UEs connected to an access network (eg, radio access network) at a particular day and / or time.

[0043] - Average number of new attachments per cell and per network node.

[0044] - Average number of UEs moving from non-neighboring cells and non-neighboring nodes.

[0045] - For all UEs in the network, average the routes followed by all (one or more) UEs at a particular day and time.

[0046] - For a route followed by a particular UE(s) at a particular day and time.

[0047] - Improvements to UE mobility procedures by predicting paths.

[0048] - Type of services activated for the cell and for the network node.

[0049] - Aggregate uplink (UL) and downlink (DL) bit rates for cells and network nodes.

[0050] - Average speed of the UE path.

[0051] -Signal quality on different routes for different days and / or times.

[0052] - Positioning coordinates of the UE from Tracking Area Update (TAU) and from the recorded path. The expected / predicted position / location of the UE can be used for a more accurate paging procedure.

[0053] The output and / or resulting decisions of one or more of the techniques disclosed herein may include one or more of the following:

[0054] - Improved resource allocation to match expected demand over different days and / or times.

[0055] - Predicting routes for specific users at specific times and / or days of the week to optimize resources and optimize mobility processes. For example, a gold user may subscribe to a service that optimizes mobility of routes by allowing the network to learn the path(s) of the route(s) taken by the UE and / or enabling network nodes (e.g., gNBs) to prepare in advance for the expected service type at the expected day and time.

[0056] -TDD mode may be selected and / or used by a network node (e.g. gNB) based on expected load levels for different resource types and based on uplink versus downlink resource usage predictions.

[0057] -Resources can be assigned to network slices based on expected / predicted load.

[0058] - Pre-allocated resources may be used for the expected service. For example, transport bearers may be pre-allocated between a network node (e.g., a gNB) and a gateway based on the expected service.

[0059] - The most likely expected service type may be computed for a set of network nodes (e.g., gNBs) for different times of day and / or for different days.

[0060] -Optimizes the paging process by allowing AI algorithms to predict the location of the UE at any given time.

[0061] It should be understood that although this disclosure may discuss optimizing for different times and / or days, optimization may be for any defined time period.

[0062] Some embodiments of the present disclosure may provide one or more of the following advantages:

[0063] -Optimize resource allocation per network node (e.g., gNB), per cell, and / or per network slice based on learning algorithms applied to data continuously collected from different scenarios.

[0064] -Optimize UE mobility by predicting the UE path and preparing network nodes (e.g., gNB) in the predicted UE path in advance by taking into account one or more of the following:

[0065] O days and / or time;

[0066] Special events in the area where the OUE is located;

[0067] O The expected bandwidth / throughput requirements at different points in the path;

[0068] o Radio frequency (RF) signal strength for the expected / predicted path;

[0069] o Network impact on the UE's preferred path when, for example, a better path (e.g., in terms of signal strength, bandwidth / throughput, etc.) than the path the UE attempted to take is available.

[0070] - Optimizing the UE paging process, including selecting the beam to use by tracking the UE position not only during idle mode but also when the UE is connected to the network and following a path (beamforming case).

[0071] - Optimizing the choice of TDD mode for different days, times and when there are special events in the area by predicting the load on the cell for two different directions from data collected in the past.

[0072] Before describing the exemplary embodiments in detail, it is noted that the embodiments lie primarily in a combination of device components and processing steps related to artificial intelligence (AI) for communication networks. Therefore, in the accompanying drawings, where appropriate, components have been represented by conventional symbols, thereby showing only those specific details relevant to understanding the embodiments, so as not to obscure the present disclosure due to details that are readily apparent to those skilled in the art having the benefit of the description herein. Throughout the specification, the same numerals represent the same elements.

[0073] As used herein, relational terms such as "first" and "second", "top" and "bottom", etc. may be used solely to distinguish one entity or element from another entity or element, without necessarily requiring or implying any physical or logical relationship or order between such entities or elements. The terms used herein are for the purpose of describing specific embodiments only and are not intended to limit the concepts described herein. As used herein, the singular forms "a", "an", and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will also be understood that when used herein, the terms "comprise", "comprising", and / or "include", "including", specify the presence of stated features, integers, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof.

[0074] In the embodiments described herein, connection terms "in communication with..." and the like may be used to indicate electrical or data communication, which may be achieved, for example, by physical contact, induction, electromagnetic radiation, radio signals, infrared signals, or optical signals. Those skilled in the art will appreciate that multiple components may interoperate, and modifications and variations may be made to achieve electrical and data communication.

[0075] In some embodiments described herein, the terms "coupled," "connected," and the like may be used herein to indicate a connection (although not necessarily a direct one) and may include wired and / or wireless connections.

[0076] The term "network node" used herein may be any kind of network node included in a radio network, and may also include any of the following items: a base station (BS), a radio base station, a base transceiver station (BTS), a base station controller (BSC), a radio network controller (RNC), a g-node B (gNB), an evolved node B (eNB or eNodeB), a node B, a multi-standard radio (MSR) radio node (such as an MSR BS), a multi-cell / multicast coordination entity (MCE), a relay node, an integrated access and return (IAB), a donor node controlling a relay, a radio access point (AP), a transmission point, a transmission node, a remote radio unit (RRU), a remote radio head (RRH), an external node (e.g., a third-party node, a node outside the current network), a node in a distributed antenna system (DAS), a spectrum access system (SAS) node, an element management system (EMS), etc. The network node may also include test equipment. The term "radio node" used herein may also be used to represent a user equipment (UE), such as a wireless device (WD) or a radio network node. In some embodiments, the network node includes a mobility management entity (MME), an access and mobility management function (AMF), a self-organizing network (SON) node, a coordination node, a positioning node, an MDT node, etc.

[0077] In some embodiments, the network node may be a "core network node," such as, for example, a database that collects and / or predicts according to the techniques disclosed herein.

[0078] In some embodiments, the non-limiting terms wireless device (WD) or user equipment (UE) are used interchangeably. The UE herein may be any type of wireless device capable of communicating with a network node or another UE via a radio signal, such as a wireless device (WD). The UE may also be a radio communication device, a target device, a device-to-device (D2D) UE, a machine type UE, or a UE capable of machine-to-machine communication (M2M), a low-cost and / or low-complexity WD, a sensor equipped with a UE, a tablet computer, a mobile terminal, a smart phone, a laptop embedded device (LEE), a laptop mounted device (LME), a USB dongle, a customer premises equipment (CPE), an Internet of Things (IoT) device, or a narrowband IoT (NB-IOT) device, etc.

[0079] Furthermore, in some embodiments, the general term "radio network node" is used. It may be any kind of radio network node, which may include any of the following: base station, radio base station, base transceiver station, base station controller, network controller, RNC, evolved Node B (eNB), Node B, gNB, multi-cell / multicast coordination entity (MCE), IAB, relay node, access point, radio access point, remote radio unit (RRU), remote radio head (RRH).

[0080] As used herein, the term "collect" is used in a broad sense and may include receiving and storing received data.

[0081] As used herein, the term "pre-configured" may refer to information that is available (e.g., stored in a memory, e.g., independent of being configured) without a specific configuration from a network or network node. Configured or configurable may be considered to relate to corresponding information set / configured, e.g., by a network or network node.

[0082] Any two or more embodiments described in this disclosure may be combined with each other in any manner.

[0083] A cell may generally be a communication cell provided by a node, such as a communication cell of a cellular or mobile communication network. A serving cell may be a cell on which or via which a network node (a node providing or associated with the cell, such as a base station or eNodeB) transmits and / or transmits data (the data may be data other than broadcast data), in particular control and / or user or payload data) to a WD, and / or may be a cell on which or via which a WD transmits and / or transmits data to a node; a serving cell may be a cell on which or on which a WD is configured and / or synchronized with and / or a WD has performed an access procedure (e.g., a random access procedure) to the WD, and / or, for example, when the node and / or the WD and / or the network follows the LTE standard, the WD is in an RRC_connected or RRC_idle state associated therewith. One or more carriers (e.g., uplink and / or downlink carriers and / or carriers for both uplink and downlink) may be associated with a cell.

[0084] For cellular communication, it may be considered that at least one uplink (UL) connection and / or channel and / or carrier and at least one downlink (DL) connection and / or channel and / or carrier are provided, for example, via and / or defining a cell (which may be provided by a network node (particularly a base station or eNodeB)). The uplink direction may refer to the direction of data transmission from a terminal to a network node (e.g., a base station and / or a relay station). The downlink direction may refer to the direction of data transmission from a network node (e.g., a base station and / or a relay node) to a terminal. UL and DL may be associated with different frequency resources (e.g., carriers and / or frequency bands). A cell may include at least one uplink carrier and at least one downlink carrier, which may have different frequency bands. A network node (e.g., a base station or an eNodeB) may be suitable for providing and / or defining and / or controlling one or more cells, such as an MTC cell and / or a conventional cell.

[0085] The term "signaling" as used herein may include any of the following: high-layer signaling (e.g., via radio resource control (RRC), etc.), low-layer signaling (e.g., via a physical control channel or a broadcast channel), or a combination thereof. Signaling may be implicit or explicit. Signaling may further be unicast, multicast, or broadcast. Signaling may also be directly to another node or via a third node.

[0086] In general, it can be considered that the network (e.g., a signaling radio node and / or a node arrangement) configures the WD 22 (in particular, with transmission resources). In general, resources can be configured with one or more messages. Different resources can be configured with different messages and / or with messages about different layers or layer combinations. The size of the resource can be expressed in symbols and / or subcarriers and / or resource elements and / or physical resource blocks (depending on the domain) and / or in the number of bits (e.g., information or payload bits) that it can carry or the total number of bits. Resource sets and / or resources of a set can be related to the same carrier and / or bandwidth portion, and / or can be located in the same time slot, or in adjacent time slots.

[0087] Signaling may generally include one or more symbols and / or signals and / or messages. A signal may include or represent one or more bits. An indication may represent signaling and / or be implemented as a signal or as multiple signals. One or more signals may be included in a message and / or represented by a message. Signaling (particularly control signaling) may include multiple signals and / or messages, which may be transmitted on different carriers and / or associated with different signaling processes, for example, representing one or more such processes and / or corresponding information and / or related to one or more such processes and / or corresponding information. An indication may include signaling and / or multiple signals and / or messages, and / or may be included therein, which may be transmitted on different carriers and / or associated with different confirmation signaling processes, for example, representing one or more such processes and / or related to one or more such processes. Signaling associated with a channel may be transmitted so that the signaling and / or information for the channel is represented, and / or the signaling is interpreted by the transmitter and / or receiver as belonging to the channel. Such signaling may generally conform to the transmission parameters and / or format(s) of the channel.

[0088] A channel may generally be a logical, transport or physical channel. A channel may include and / or be arranged on one or more carriers (particularly multiple subcarriers). A channel that carries and / or is used to carry control signaling / control information may be considered a control channel, particularly when it is a physical layer channel and / or when it carries control plane information. Similarly, a channel that carries and / or is used to carry data signaling / user information may be considered a data channel, particularly when it is a physical layer channel and / or when it carries user plane information. A channel may be defined for a specific communication direction or for two complementary communication directions (e.g., UL and DL, or side links in both directions), in which case it may be considered to have at least two component channels (one in each direction). Examples of channels include a physical uplink shared channel (PUSCH), a physical uplink control channel (PUCCH), a physical downlink control channel (PDCCH), and a physical uplink shared channel (PUSCH).

[0089] Note that although terminology from one particular wireless system may be used in the present disclosure, such as, for example, 3rd Generation Partnership Project (3GPP) Long Term Evolution (LTE) and / or New Radio (NR, also referred to as fifth generation or 5G), this should not be viewed as limiting the scope of the present disclosure to only the aforementioned systems. Other wireless systems, including but not limited to Wideband Code Division Multiple Access (WCDMA), Worldwide Interoperability for Microwave Access (WiMax), Ultra Mobile Broadband (UMB), and Global System for Mobile Communications (GSM), may also benefit from utilizing the concepts covered within the present disclosure.

[0090] It is further noted that the functions described herein as being performed by a user equipment or a network node may be distributed across multiple user equipments and / or network nodes. In other words, it is contemplated that the functions of the network nodes and user equipment described herein are not limited to being performed by a single physical device and may in fact be distributed across several physical devices.

[0091] Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which the present disclosure belongs. It will be further understood that the terms used herein should be interpreted as having a meaning consistent with their meaning in the context of this specification and the relevant art, and will not be interpreted in an idealized or overly formal sense unless explicitly defined as such herein.

[0092] Referring now to the drawings, wherein like elements are referred to by like reference numerals, Figure 1 , there is shown a schematic diagram of a communication system 10 according to an embodiment, such as a 3GPP type cellular network that may support standards such as LTE and / or NR (5G), the communication system 10 including an access network 12, such as a radio access network (RAN), and a core network 14. The core network 14 includes a core network node 16a, which may implement one or more of the data collection and / or prediction techniques disclosed herein.

[0093] The access network 12 includes a network node 16b (e.g., a NB, eNB, gNB, or other type of wireless access point) that defines a corresponding coverage area 18 (such as a cell). The access network node 16b is connectable to the core network 14 via a wired or wireless connection 20, for example, via a gateway 21 (e.g., a user plane function (UPF)). A user equipment (UE) 22a located in the coverage area 18 is configured to be wirelessly connected to or paged by the corresponding network node 16b. Although a single UE is shown in this example, the disclosed embodiments are also applicable to situations where multiple UEs 22 are in the coverage area 18 or multiple UEs 22 are connected to the corresponding network node 16b. Note that although a single access network node 16b and a single core network node 16a are shown for convenience, the communication system 10 may include many more access network nodes 16b and many more core network nodes 16a.

[0094] Furthermore, it is contemplated that the UE 22 may communicate simultaneously and / or be configured to communicate with more than one network node 16 and more than one type of network node 16, respectively. For example, the UE 22 may have dual connectivity with a network node 16 supporting LTE and the same or different network nodes 16 supporting NR. As an example, the UE 22 may communicate with an eNB for LTE / E-UTRAN and a gNB for NR / NG-RAN.

[0095] The network node 16 is configured to include a collection unit 32 configured to collect location information associated with the movement of at least one user equipment within the network. The network node 16 may also be configured to include a prediction unit 34 configured to make a prediction based on at least a portion of the collected location information and / or to communicate an indication of the prediction.

[0096] Now refer to Figure 2 An example implementation according to an embodiment of the UE 22 and the network node 16 (eg, network node 16a) discussed in the preceding paragraphs will be described.

[0097] refer to Figure 2 In the communication system 10, a network node 16 (e.g., network node 16a or 16b) is arranged in the communication system 10 and includes hardware that enables it to communicate with UE 22 and other devices in the communication system 10. The hardware may include a communication interface 40 for establishing and maintaining wired and / or wireless connections of interfaces with different communication devices of the communication system 10, such as, for example, access network node 16b, gateway 21, core network node 16 and / or other devices of the communication system 10 (e.g., AMF / MME). In some embodiments, the communication interface 40 may include a radio interface for establishing and maintaining at least a wireless connection with UE 22. The radio interface may be formed as or may include, for example, one or more RF transmitters, one or more RF receivers, and / or one or more RF transceivers.

[0098] In the illustrated embodiment, the hardware of the network node 16 also includes a processing circuit 42. The processing circuit 42 may include a memory 44 and a processor 46. In particular, in addition to or in place of a processor (such as a central processing unit) and a memory, the processing circuit 42 may also include an integrated circuit for processing and / or control, for example, one or more processors and / or processor cores and / or an FPGA (field programmable gate array) and / or an ASIC (application-specific integrated circuit) adapted to execute instructions. The processor 46 may be configured to access the memory 44 (e.g., write to it and / or read from it), which may include any kind of volatile and / or non-volatile memory, for example, a cache and / or buffer memory and / or a RAM (random access memory) and / or a ROM (read-only memory) and / or an optical memory and / or an EPROM (erasable programmable read-only memory).

[0099] Thus, the network node 16 also has software that is stored internally, for example, in the memory 44, or in an external memory (e.g., a database, a storage array, a network storage device, etc.) accessible by the network node 16 via an external connection. The software may be executed by the processing circuit 42. The processing circuit 42 may be configured to control any of the methods and / or processes described herein, and / or cause these methods and / or processes to be performed, for example, by the network node 16. The processor 46 corresponds to one or more processors 46 for performing the network node 16 functions described herein. The memory 44 is configured to store data, program software code, and / or other information described herein. In some embodiments, the software may include instructions that, when executed by the processor 46 and / or the processing circuit 42, cause the processor 46 and / or the processing circuit 42 to perform the processes described herein with respect to the network node 16. For example, the processing circuit 42 of the network node 16 may include a processor configured to perform the network node processes discussed herein (such as, for example, as described in reference to Figure 3 The collection unit 32 and / or prediction unit 34 (as discussed in the flowchart and other figures in FIG. 1 ) may be a collection unit 32 and / or a prediction unit 34.

[0100] The communication system 10 further includes the already mentioned UE 22. The UE 22 may have hardware that may include a communication interface 50 configured to establish and maintain a wireless connection with a network node 16 that serves the coverage area 18 in which the UE 22 is currently located. The communication interface 50 may be formed as or may include, for example, one or more RF transmitters, one or more RF receivers and / or one or more RF transceivers. The communication interface 50 may include an interface for establishing and maintaining a wired and / or wireless connection with different communication devices of the communication system 10, such as, for example, an interface of a mobility management node (e.g., AMF / MME).

[0101] The hardware of the UE 22 also includes a processing circuit 52. The processing circuit 52 may include a memory 54 and a processor 56. In particular, in addition to or instead of a processor (such as a central processing unit) and a memory, the processing circuit 52 may also include an integrated circuit for processing and / or control, for example, one or more processors and / or processor cores and / or an FPGA (field programmable gate array) and / or an ASIC (application-specific integrated circuit) suitable for executing instructions. The processor 56 may be configured to access the memory 54 (e.g., write to it and / or read from it), which may include any kind of volatile and / or non-volatile memory, for example, a cache and / or buffer memory and / or a RAM (random access memory) and / or a ROM (read-only memory) and / or an optical memory and / or an EPROM (erasable programmable read-only memory).

[0102] Thus, the UE 22 may also include software stored, for example, in a memory 54 at the UE 22, or in an external memory (e.g., a database, a storage array, a network storage device, etc.) accessible by the UE 22. The software may be executed by the processing circuit 52. The software may include a client application. The client application may be operable to provide services to human or non-human users via the UE 22. When providing services to users, the client application may receive request data and provide user data in response to the request data. The client application may interact with the user to generate the user data it provides.

[0103] The processing circuit 52 may be configured to control any of the methods and / or processes described herein, and / or cause the methods and / or processes to be performed, for example, by the UE 22. The processor 56 corresponds to one or more processors 56 for performing the functions of the UE 22 described herein. The UE 22 includes a memory 54 configured to store data, program software code, and / or other information described herein. In some embodiments, the software and / or client application may include instructions that, when executed by the processor 56 and / or the processing circuit 52, cause the processor 56 and / or the processing circuit 52 to perform the processes described herein with respect to the UE 22.

[0104] In some embodiments, the internal workings of the network node 16 and the UE 22 may be as described in Figure 2 , and independently, the surrounding network topology can be Figure 1 The surrounding network topology.

[0105] exist Figure 2In FIG, the connection between the user equipment 22 and the network node 16 is shown without explicit reference to any intermediate devices and the precise routing of messages via these devices. The network infrastructure can determine the routing, which can be configured to hide the routing from the UE 22 or from the service provider or both. The network infrastructure can further take decisions by which the network infrastructure dynamically changes the routing (e.g., based on a reconfiguration of the network or load balancing considerations).

[0106] although Figure 1 and Figure 2 Various "units" such as collection unit 32 and prediction unit 34 are shown as being within respective processors, but it is contemplated that these units may be implemented such that a portion of the unit is stored in a corresponding memory within the processing circuitry. In other words, the units may be implemented within the processing circuitry in hardware or in a combination of hardware and software.

[0107] Figure 3 is a flowchart of an exemplary process for AI optimization techniques in a network node 16 (e.g., network node 16a) according to some embodiments of the present disclosure. According to the example method, one or more blocks and / or functions and / or methods performed by the network node 16 may be performed by one or more elements of the network node 16, such as by the collection unit 32 and / or prediction unit 34 in the processing circuit 42, the processor 46, the communication interface 40, etc. The example method includes collecting (block S100) location information, such as via the collection unit 32, the prediction unit 34, the processing circuit 42, the processor 46, and / or the communication interface 40, the collected location information is associated with the movement of at least one user device 22 within the network. The method includes predicting (block S102) location information based on at least a portion of the collected location information, such as via the collection unit 32, the prediction unit 34, the processing circuit 42, the processor 46, and / or the communication interface 40. The method includes transmitting (block S104) the location information, an indication of the prediction, such as via the collection unit 32, the prediction unit 34, the processing circuit 42, the processor 46, and / or the communication interface 40.

[0108] In some embodiments, prediction further includes such as via collection unit 32, prediction unit 34, processing circuit 42, processor 46 and / or communication interface 40 according to the prediction algorithm, the prediction algorithm associates each time window in a plurality of different time windows with different weights. In some embodiments, a plurality of different time windows include at least one of the following items: time of day, day of the week, week of the year, month of the year, and season, each time window is associated with a different weight in the prediction algorithm. In some embodiments, prediction according to the prediction algorithm further includes such as via collection unit 32, prediction unit 34, processing circuit 42, processor 46 and / or communication interface 40 at least partially based on the weighted current prediction probability value and the weighted historical probability prediction value to determine at least one probability. In some embodiments, the results of the previous prediction determine the weight value applied to the current probability prediction value and the weight value applied to the historical prediction value.

[0109] In some embodiments, collecting location information further includes collecting path information and corresponding time information, such as via the collection unit 32, the prediction unit 34, the processing circuit 42, the processor 46 and / or the communication interface 40, the path information and the time information indicating the movement of at least one user device between at least two radio network areas in the network. In some embodiments, the prediction further includes predicting the movement path of at least one user device relative to the network, such as via the collection unit 32, the prediction unit 34, the processing circuit 42, the processor 46 and / or the communication interface 40, the prediction being based at least in part on the collected path information and time information. In some embodiments, delivering the indication further includes delivering the indication of the predicted movement path of at least one user device 22, such as via the collection unit 32, the prediction unit 34, the processing circuit 42, the processor 46 and / or the communication interface 40. In some embodiments, the at least two radio network areas include at least two tracking areas and at least two cells.

[0110] In some embodiments, the indication of the predicted mobile path includes at least one cell global identifier CGI, the at least one CGI indicating at least one cell to which the at least one user equipment is expected to move according to the predicted mobile path. In some embodiments, the prediction further includes determining at least one probability of at least one mobile path of the at least one user equipment 22, such as via the collection unit 32, the prediction unit 34, the processing circuit 42, the processor 46 and / or the communication interface 40, the at least one mobile path including at least one of the cell of the base station and the neighboring cell. In some embodiments, the indication of the predicted mobile path is configured to be included in a paging request for the at least one user equipment, the paging request indicating a probability prediction of the at least one user equipment 22 in the at least one cell for at least one cell in the paging request. In some embodiments, the indication of the predicted mobile path is configured to initiate a pre-allocation of resources for at least one user equipment 22 in a cell included in the predicted mobile path.

[0111] In some embodiments, the pre-allocation of resources for at least one user equipment 22 is a pre-allocation of a contention-free preamble, which is pre-configured and stored in a persistent memory at the at least one user equipment 22. In some embodiments, collecting further includes collecting path information and corresponding time information from at least one of the at least one user equipment, the mobility management entity, and the base station, such as via the collecting unit 32, the predicting unit 34, the processing circuit 42, the processor 46, and / or the communication interface 40. In some embodiments, collecting further includes collecting historical path information from at least one of at least one initial attachment and at least one mobility process of the at least one user equipment 22, such as via the collecting unit 32, the predicting unit 34, the processing circuit 42, the processor 46, and / or the communication interface 40, the historical path information includes a cell identifier, a timestamp, a positioning coordinate, and a user equipment identifier.

[0112] In some embodiments, collecting further comprises receiving a tracking area update TAU message, such as via the collection unit 32, the prediction unit 34, the processing circuit 42, the processor 46, and / or the communication interface 40, the TAU message comprising a location coordinate and a timestamp indicating a current location of at least one user equipment 22. In some embodiments, collecting location information further comprises collecting location information and corresponding time information, such as via the collection unit 32, the prediction unit 34, the processing circuit 42, the processor 46, and / or the communication interface 40, the collected location information and corresponding time information being associated with the movement of multiple user equipment 22 within the network. In some embodiments, predicting further comprises predicting a network characteristic based at least in part on the collected location information and time information, such as via the collection unit 32, the prediction unit 34, the processing circuit 42, the processor 46, and / or the communication interface 40. In some embodiments, delivering an indication further comprises delivering an indication of the predicted network characteristic, such as via the collection unit 32, the prediction unit 34, the processing circuit 42, the processor 46, and / or the communication interface 40.

[0113] In some embodiments, predicting network characteristics further includes predicting at least one of the following items in a future time period based at least in part on the collected location information and time information, such as via the collection unit 32, the prediction unit 34, the processing circuit 42, the processor 46 and / or the communication interface 40: the amount of user equipment 22 served by at least one cell and the amount of bearer for services in at least one cell. In some embodiments, the prediction is used for resource planning for the future time period in at least one cell. In some embodiments, the prediction is used to determine one of the time division duplex TDD mode and the frequency division duplex FDD resource to be used in the future time period in at least one cell.

[0114] Having generally described arrangements for optimization and / or artificial intelligence (AI) of communication networks, functions and processes are provided below and may be implemented by one or more network nodes 16 and / or user equipment 22 .

[0115] TTD mode activation / deactivation

[0116] In some embodiments, the AI ​​algorithm uses the collected information, such as, for example, via the network node 16a, to estimate the load in the uplink and downlink directions for different days and / or different time periods and / or based on different service types (e.g., short message service, voice, streaming, etc.). Different services may require different mixes of uplink / downlink resources. For example, video-centric applications such as YouTube, Netflix, and broadcast / multicast video services require much higher downlink throughput than uplink. On the other hand, services such as Voice over Internet Protocol (VoIP) tend to be generally symmetrical about uplink and downlink throughput. Therefore, in some embodiments, the optimal TDD mode can be selected based on the expected, estimated, and / or predicted UL-DL resources to be used by, for example, a cell during a certain time period / day, such as, for example, via the network node 16b (e.g., a base station). For example, for a time period (e.g., a high streaming service time period) when the network node 16 expects or predicts a large amount of DL resources, a TDD mode with more DL resources than UL resources can be selected. For time periods where the network node 16 expects or predicts symmetric UL and DL throughput, a TDD mode with equal or nearly equal amounts of UL and DL resources may be selected.

[0117] In some embodiments, the predicted / expected UL-DL resource usage may be sent to the cell's network node 16b (e.g., a base station) (e.g., by the core network node 16a, which may collect data and calculate the prediction), and the network node 16b may determine the TDD mode based at least in part on such prediction. In other embodiments, the core network node 16a may suggest a TDD mode based on its own prediction and send such information to the access network node 16b (e.g., a base station).

[0118] Collect data on UE paths

[0119] In some embodiments, predictions may be made regarding the most likely path that a UE 22 may take during a particular day (e.g., day of the week) and / or time period (e.g., morning commute time, afternoon, evening commute time, evening time, sleep time, etc.). These predictions may be calculated by an AI algorithm at a network node 16 (e.g., core network node 16a) and may be based on UE-specific data collected in the past (e.g., historical UE 22 data for a particular UE 22). The granularity of the UE 22 path prediction may be, for example, at a base station (e.g., eNB / gNb) level, at a cell level, etc. In some embodiments, if the UE 22 positioning coordinates are used when data is logged / collected (e.g., stored at a database corresponding to the core network node 16a) daily for the UE 22, a more accurate UE 22 path prediction may be determined. In some embodiments, the data collection / logging process may be performed according to one or more of the following:

[0120] 1. Initial attachment: Figure 4 As depicted in , when a UE 22 attaches to a network (e.g., an initially attached network node 16d (e.g., a serving eNB / gNB)), the used cells and / or UE 22 positioning coordinates are collected and stored / recorded for the UE 22 (e.g., by the network node 16d) and reported to a centralized database, such as a core network node 16a. Included in the collected and recorded data may be, for example, a UE identifier associated with the collected data and one or more of the services being used by the UE 22 at the initial attach, RF signal related data, (one or more) timestamps, positioning (e.g., global positioning coordinates), etc. The UE 22 may be stored / recorded when the UE 22 is switched from one cell to the next within a network node 16 (e.g., a base station) and across multiple network nodes 16 (e.g., a base station). Figure 4 Such information may be collected and recorded when a network node 16 (e.g., a base station) is used to route a UE 22 from a serving network node 16d to a target network node 16b as shown in FIG. 1 . A network node 16 (e.g., a base station) may report such collected and recorded information to a centralized database (e.g., a core network node 16a) so that, for example, learning may be done from the data and / or UE 22 path predictions may be made from the data, for example, by an AI algorithm. In some embodiments, the speed of the UE 22 path, as well as the time spent in the serving cell and (one or more) serving nodes and the services provided to the UE 22 may also be collected, recorded, and updated.

[0121] 2. Mobility at the cell level: e.g. Figure 5As depicted in , when a UE 22 moves from one serving cell to a target cell during a mobility procedure, the identifier of the target cell and the corresponding network node 16 (e.g., a target gNB) may be logged for the UE 22 and reported to a centralized database, such as a core network node 16a. Included in the collected and logged data may be one or more of time stamps, RF signal related data, services being used by the UE 22, etc. during the mobility procedure, and a UE identifier associated with the collected data. Furthermore, positioning data may be logged and reported to the database if available. The speed of the UE 22 path during mobility, the time spent in the serving cell and connected to the serving network node 16, the services provided to the UE 22, etc. may also be reported to the core network node 16a.

[0122] 3. Mobility at the beam level: When beamforming is used, the selected beam, the configuration of the beam (e.g., direction of the beam, transmit power, RF strength, etc.), and the location coordinates of the UE 22 (if available) can be collected and recorded by the serving network node 16 (e.g., base station) for the UE 22 and reported to the core network node 16a.

[0123] 4. Carrier aggregation: If the UE 22 is using carrier aggregation and / or dual connectivity, the data collected and logged for the UE 22 may include the number of carriers, primary and secondary cells used for carrier aggregation, LTE cells and 5G / NR cells used by the UE 22, etc.

[0124] 5. Positioning coordinates: The positioning coordinates of the UE 22 (if available) may be collected and recorded by the network node 16 for the UE 22 and reported to the core network node 16a. To enable the recording of the UE 22 coordinates, the UE 22 may have location features such as a global positioning system (GPS) or 3GPP RAN UE positioning information (e.g., cell ID, enhanced cell ID, observed time difference of arrival (OTDOA), etc.).

[0125] 6. Path record for IDLE UE: Figure 6An example of a path record for an IDLE UE 22 is shown. Some embodiments may include combining a Tracking Area Update (TAU) with a learned UE 22 path, for example by a core network node 16a, to improve predictions about where the UE 22 can be found on different days and / or at different time periods. The Tracking Area Update (TAU) may be enhanced with a timestamp and location coordinates, which may be transmitted by the UE 22 to the core network node 16a via a mobility network node 16c such as an access and mobility management function (AMF) and / or a mobility management entity (MME). Some embodiments of the present disclosure may include adding multiple new interfaces to a centralized database (e.g., a core network node 16a) to enable collection and recording of collected data from multiple network nodes 16 (e.g., base station nodes, mobility management nodes, gateway nodes, network function nodes, etc.) and / or providing data in a form that can be used for an AI algorithm (e.g., characterization) and / or obtaining expected values / predictions calculated by the AI ​​algorithm. In some embodiments, data is collected and predictions are made at one network node 16. In some embodiments, data is initially collected at one or more network nodes 16 and then sent to one or more other network nodes 16 where predictions are made.

[0126] Figure 8 An example process of UE 22 path retrieval initiated by a serving cell according to one embodiment of the present disclosure is shown. In block S200, the UE 22 may perform an initial access or mobility procedure. In block S202, the serving network node 16b (e.g., a gNB) may send a request message to the mobility network node 16c (e.g., an MME, an AMF, etc.) to request a UE 22 path. In some embodiments, the request may include a UE 22 identifier that identifies a specific UE 22 (whose path is being requested). The request may also include a cell global identifier (CGI) or other identifier of the serving network node 16b. In block S204, the mobility network node 16c (e.g., an MME, an AMF, etc.) sends a request to the core 14. In block S206, the request is sent to the core network node 16a. In steps S208-S212, the core network node 16a may predict the UE 22 path and send the prediction back toward the initiating serving network node 16a. The core network node 16a may predict the UE 22 path based on historical location and time information collected for the UE 22 and the current time and location of the UE 22 (eg, based on the CGI and the time the request was sent).

[0127] Data collection for predicting future behavior

[0128] a.UE route prediction

[0129] In some embodiments, when the network node 16 has collected enough information to predict (e.g., using a machine learning algorithm, etc.) the most likely route that a particular UE 22 will follow, the UE 22 mobility process may be optimized. For example, one or more neighboring cells that are most likely to be the next serving cell for the UE 22 may be prepared before the UE 22 moves to it. For neighboring cells that are co-located with the serving cell, the network node 16 may establish resources for the UE 22 as soon as the UE 22 attaches to the serving cell / network node 16. For neighboring cells that are located in a network node 16 (e.g., a gNodeB) that is different from the network node of the serving cell, the serving network node 16 (e.g., a gNodeB) may send a resource allocation request to a potential target network node 16 (e.g., a gNodeB) via, for example, a base station to base station interface (e.g., an Xn / X2 interface). Resource preparation in the potential target cell and / or a request for allocation to the potential target cell may be sent (in advance) as a result of the prediction rather than as a result of a typical mobility process.

[0130] Fig. 9 An example process (serving cell initiated) for UE 22 path resource pre-allocation for optimizing mobility process according to one embodiment of the present disclosure is shown. In block S220, the network node 16b of the serving cell 1 may request the predicted UE 22 path (e.g., see Figure 8 In block S222, based on the predicted path, the network node 16b of the serving cell 1 may send a request to the network node 16b of the target cell 2 (which may be in the predicted path of the UE 22). The request to the target cell may include a request to pre-allocate resources to the UE 22 using pre-configured resources. The pre-configured resources may include a pre-allocated contention-free preamble. Fig. 9 As shown in block S222 of , the request to the target cell may include an identifier of the UE 22, a CGI of the serving network node 16b, and UE 22 data required to establish the pre-allocated resources. In block S224, the network node 16d of the target cell 2 may send a response to the serving network node 16b. The response may indicate the pre-allocated resources. In block S226, the UE 22 may perform a mobility procedure to switch to the target cell 2 using the pre-allocated resources (e.g., the pre-allocated contention-free preamble (which may be stored in a persistent memory at the UE 22)).

[0131] Fig.10An example process (network initiated) for UE 22 path resource pre-allocation for optimizing mobility process according to another embodiment of the present disclosure is shown. In block S230, a request for a predicted UE 22 path may be sent to the core network node 16a. In block S232, the core network node 16a may send a response including the UE 22 predicted path data. In block S234, a UE 22 path establishment request may be sent to the mobility network node 16c (e.g., MME, AMF, etc.). The request may include the UE 22 predicted path data and UE 22 context information. In block S236, based on the UE 22 predicted path data, the mobility network node 16c may identify the network node 16b (e.g., gNB) of the target cell (to which the UE 22 is predicted to move), and send the UE 22 predicted path data and UE 22 context information to the identified network node 16b (e.g., gNB). In block S238, the network node 16b of the target cell may allocate or pre-allocate resources for the UE 22 indicated in the request. In block S240, the network node 16b of the target cell may report the UE 22 path establishment result to the core 14. In block S242, the UE 22 may use the allocated or pre-allocated resources (e.g., a pre-allocated contention-free preamble (which may be stored in a persistent memory at the UE 22)) to perform an initial access or mobility procedure attached to the network node 16b of the target cell.

[0132] b. UE service requirement prediction

[0133] A service requirement prediction for the UE 22 may also be determined based on the UE 22 data collected according to the techniques in the present disclosure. In some embodiments, resources may be pre-allocated for the expected service. For example, a transport bearer may be pre-allocated between a network node 16 (e.g., a gNB) and a gateway based on the expected service.

[0134] c. Cell resource prediction

[0135] In some embodiments, as discussed in more detail herein above, the TDD mode to be used by the network node 16 of the cell may be selected based on the prediction. In some embodiments, the numerology and slot type (which may be based on the numerology) may also be selected based on the prediction made.

[0136] d. Paging: UE location prediction

[0137] In some embodiments, the UE 22 location tracking and prediction discussed herein may be used for paging purposes. For example, when there is a paging request for the UE 22, the location of the UE 22 may be unknown to the network. When such use cases occur, existing network procedures for attempting to locate the UE 22 are relatively inefficient and generally include searching each cell in a long list of potential cells. In some embodiments of the present disclosure, the UE 22 location information collected according to the techniques disclosed herein may be used to more efficiently locate the UE 22. For example, in some embodiments, when there is a paging request for the UE 22, the location of the UE 22 may be predicted based on previously collected data and time information, such as, for example, the date, day of the week and time of the year that the UE 22 is served by the cell and the corresponding network node 16 (e.g., gNB), any special events programmed at the UE 22 location, etc. The UE 22 location information may include the expected / predicted RAN / MME of the UE 22, the expected / predicted network node 16 (e.g., base station) and cell, and the expected / predicted location coordinates of the UE 22 (if available). This information may supplement data that the paging procedure typically uses to locate the UE 22, such as the last tracking area reported by the UE 22 when in idle mode, and / or the RAN Notification Area (RNA) when the UE 22 is in an inactive state.

[0138] UE paging request

[0139] In some embodiments, there may be modifications to, for example, 3GPP Technical Specification (TS) 38.413 Version 15 regarding UE paging requests, such as, for example, as shown in Table 1 below, associating existing paging request signaling with new probabilities, which are calculated based on, for example, user habits (past statistics, collected historical data, etc.) to predict the cell(s) in which the UE 22 can be found during any time.

[0140] For example, from TS 38.413 version 15 (see Table 1 below), recommended cells for paging are signaled from the network to the Radio Access Network (RAN), such as network node 16. Recommended cells are divided into "visited cells" and "non-visited cells".

[0141]

[0142] Table 1: Recommended cells for paging.

[0143] Table 1 shows (see boldface) that a percentage prediction may be signaled as part of the recommended cells for paging. In some embodiments, the percentage prediction may indicate, for example, the probability of finding the UE 22 at the recommended cell(s) during the current time (which corresponds to the paging request). In one embodiment (see, for example, Figure 7 ), the mobility network node 16 (e.g., AMF / MME, etc.) can use the prediction information to select the order in which the recommended cells can be contacted for the paging request. For example, the network node 16 (e.g., base station) corresponding to the cell with the highest probability can be contacted first by the UE 22 paging request. The cells can be selected in order according to decreasing probability values. In other embodiments, the network node 16 can use the probability information in other ways to more efficiently page the UE 22.

[0144] Fig.11 One example of how to predict which cell a UE 22 will be in at any given time is shown. Fig.11 A graph showing past statistics and future predictions corresponding to the probability that a UE1 22 is camped on or connected to a radio resource control (RRD) of a particular cell at any given time is shown. Fig.11 As can be seen in the figure of FIG. 1 , at any time t1 (where t may be in any time unit, such as minutes, hours, days, etc.), example probabilities that UE1 22 may be found in different cells (e.g., CGI a, b, or d) and / or different tracking areas (TA1, 3, or 7) may include one or more of the following:

[0145] -10% probability = (t1, 0.1) = TA1 / Cell-CGI a;

[0146] -20% probability = (t1, 0.2) = TA3 / Cell-CGI b;

[0147] -70% probability = (t1, 0.7) = TA7 / Cell-CGI d; and / or

[0148] -100% probability = (t1, 1.00) = 0.

[0149] In some embodiments, such probabilities may be signaled along with the recommended cells for paging signaling discussed above with reference to Table 1. The probabilities may be used to select the cell(s) for paging. In some embodiments, the probabilities may be signaled and used for other types of UE 22 path prediction scenarios discussed in this disclosure (e.g., initial attach, mobility, resource pre-allocation, service prediction, etc.).

[0150] Fig.12An example of predicting the mobility of UE 22 from a specific cell (cell i) to other cells in a given future time period according to one embodiment of the present disclosure is shown. Fig.12 It shows that UE 22 will move to cell 1 with a probability of 38%, UE 22 will move to cell m with a probability of 5%, UE 22 will move to cell j with a probability of 32%, UE 22 will move to cell k with a probability of 15%, and UE 22 will move to another cell with a probability of 10%.

[0151] Fig.13 An example of yet another UE 22 path prediction arrangement according to some embodiments of the present disclosure is shown. Fig.13 An example UE 22 route prediction arrangement including a series of cells in a potential route / path is shown. For example, assuming UE 22 is located at cell_i, the probability of UE 22's next movement and the average time spent in cell_i can be used to predict the next cell that UE 22 will move to. Fig.13 An embodiment is shown in which UE 22 path prediction may be based on independent probability events, and in particular, for example, path 1 (UE path including cell i to cell l, to cell n, and to cell m) has probability P1 = 0.38x0.29x0.9 = 9.92%.

[0152] Fig.14 An example path prediction for UE 22 based on user habits is shown. For example, a complete path may be predicted for UE 22 based on historical data. Fig.14 An example is shown including three paths P1, P2 and P3, each path starting from an initial cell (cell i). The three paths of UE1 22 from the initial cell (cell i) include the following values:

[0153] -UE1.P1(cell_i,t0).prediction = 0.40 = 40%;

[0154] -UE1.P2(cell_i,t0).prediction = 0.35 = 35%; and

[0155] -UE1.P3(cell_i,t0).prediction = 0.25 = 25%.

[0156] Thus, each potential cell path from the initial cell may be associated with a probability value. Each potential path may be defined by the cells in the path and the corresponding time period (in which the UE 22 may be expected to attach or connect to the corresponding cell in the path). An example of how a cell path may be defined for each of the potential paths P1, P2, and P3 is shown below:

[0157] -UE1.P1(cell_i,t0).cells = {{cell_a,t1},{cell_b,t4},{cell_c,t7},…};

[0158] -UE1.P2(cell_i,t0).cells = {{cell_d,t3},{cell_e,t6},{cell_f,t8},…}; and

[0159] -UE1.P3(cell_i,t0).cells = {{cell_g,t2},{cell_h,t5},…}.

[0160] It should be noted that different paths may share some cells.

[0161] Resource Planning

[0162] In some embodiments, as an alternative or in addition to path prediction for a specific UE 22, the collected data may be used to predict overall UE activity within or between cells for resource planning purposes. Fig.15 As shown in , historical data is used to predict the amount of UEs 22 that will move from cell i to cell j at a particular time (eg, 90 UEs or 25 UEs). These estimates can assist the network in planning resources related to UE mobility. Fig.15 An example probability graph of the amount of UEs 22 that will move from cell i to cell k is shown, predicted for time t1 (where t may be in any time unit, such as minutes, hours, days, etc.). The probabilities in the graph include the following values:

[0163] -10% probability = (t1, 0.1) = 90 UEs;

[0164] -20% probability = (t1, 0.2) = 70 UEs;

[0165] -90% probability = (t1, 0.9) = 40 UEs; and

[0166] -100% probability = (t1, 1.0) = 25 UEs.

[0167] Fig.16 An example prediction graph is shown representing a prediction that may assist the network in cell resource planning by estimating the number of UEs 22 expected in a given cell at any given time period. Fig.16It is shown that for time t1, the probability that cell 1 will have 2000 UE 22 is 10%, the probability that cell 1 will have 1200 UE 22 is 50%, the probability that cell 1 will have 800 UE 22 is 90%, and the probability that cell 1 will have 200 UE 22 is 100%. In some embodiments, the statistics of the number of UEs 22 may also include the average number of bearers for different services to further assist the network in resource planning, such as identifying the TDD mode and / or parameter set to be used based on the predicted uplink and downlink loads and the predicted quality of service requirements such as latency and throughput. For example, if the downlink direction is expected to have 50% more traffic, a TDD mode with approximately 50% more downlink transmission opportunities than the uplink is selected.

[0168] Data collection for resource planning

[0169] In some embodiments, overall cell and network node data (e.g., from multiple UEs, network nodes, etc., aggregated data, etc.) may be collected and used for various probability and prediction calculations. Statistics may be calculated, updated, and / or maintained as probabilities at the core 14 (e.g., core network node 16). In some embodiments, the network node 16 (e.g., gNB) collects the data and forwards it to the core 14. For example, Fig.17 An example signaling diagram is shown in which the network node 16b (e.g., a base station) sends a request to update data of a cell in box S250. The request may include cell data and a CGI identifying a cell corresponding to the cell data. Examples of cell data are described in more detail below. In box S252, the mobility network node 16c may forward the request to update the cell data to the core 14, and in box S254, the request may be received by the core network node 16a (e.g., an AI database). Then, as a result of the request, the core network node 16a may update the information of the cell, and in box S256, return a response message that may indicate the result (e.g., the cell data has been updated). In box S258, the mobility network node 16c may receive the result of the cell data update, and in box S260, the response message indicating the result may be forwarded to the network node 16b (e.g., a gNB). In some embodiments, the cell data may be aggregated UE data for the cell.

[0170] Fig.18An example signaling diagram for collecting / updating UE 22 specific data according to some embodiments is shown. In block S270, the network node 16b (e.g., a gNB) sends a request to update data for the UE 22. The request may include the UE 22 data and a UE identifier identifying the UE 22 corresponding to the data. In block S272, the mobility network node 16c may forward the request to update the UE 22 data to the core 14, and in block S274, the request may be received by the core network node 16a (e.g., an AI database). As a result of the request, the core network node 16a may then update the information of the UE 22 and return a response message in block S276 that may indicate the result (e.g., that the UE 22 data has been updated). In block S278, the mobility network node 16c may receive the result of the UE 22 data update, and in block S280, the response message indicating the result may be forwarded to the network node 16b (e.g., a gNB). Non-limiting examples of the collected / updated cell and node data include, for example:

[0171] - the minimum, average and / or maximum number of UEs 22 served by the network node 16 (eg, gNodeB) during the period since the last update was sent;

[0172] - the average number of UEs 22 served by each cell in the network node 16 (eg, gNodeB) during the period since the last update was sent;

[0173] - the minimum, average and / or maximum number of radio bearers for different connection types (VoIP, Video, Best Effort, MTM, etc.) in each cell of the network node 16 (eg, gNodeB) during the period since the last update was sent;

[0174] - minimum, average and / or maximum duration of calls for different connection types (VoIP, Video, Best Effort, MTM, etc.) in each cell of the network node 16 (eg, gNodeB) during the period since the last update was sent;

[0175] - the minimum, average and / or maximum number of new UEs 22 served by the network node 16 (eg, gNodeB) during the period since the last update was sent;

[0176] - the minimum, average and / or maximum number of new UEs 22 served by each cell at the network node 16 (eg, gNodeB) during the period since the last update was sent; and / or

[0177] - Minimum, average and / or maximum resource utilization levels (since the last update) of different types of resources (such as air interface bandwidth, physical resource blocks (PRBs), control channel elements (CCEs), memory, etc.).

[0178] Non-limiting examples of UE 22 data collected / updated include, for example:

[0179] - the cells that have served the UE 22 (when in the connected state), including the timestamp and duration at each cell, and the access type (initial access, mobility, dual connectivity, etc.);

[0180] - the types of services and resources, and the duration of each service used by the UE 22 during the period since the last update;

[0181] - parameters recorded for the UE 22 for different connections / services (such as bit rate, RF signal strength, retransmissions, etc.);

[0182] - the serving cell and target cell for each successful move of the UE 22, and the associated timestamp; and / or

[0183] - Statistics associated with the data, and for example statistics for tracking the probability of a UE 22 moving from one cell to another (eg cell 1 to cell 2) or statistics for the load of the cells at any time.

[0184] like Fig.19 As shown in , by way of example, statistics at different levels may be maintained, such as hour of day, day of week, etc. Predictions discussed throughout this document may be calculated based on past statistics, as described in more detail below. In some embodiments, statistics may be continuously and / or periodically and / or dynamically updated. For example, a network node 16 (e.g., a gNB) may send periodic updates to the core 14, and the updates may include data collected since the last update. When an update is received (e.g., based on Fig.17 and 18 ), the received data is stored at the core network node 16a and the probabilities can be updated with the new data.

[0185] According to one embodiment, past statistics are used to calculate current probabilities. The following are the statistics that can be used to predict P pred An example formula for :

[0186] P pred = (w pred * P pred ) + (w prob * ((v1 * P h ) + (v2 * P d) + (v3 * P w ) +(v4 * P m ) + (v5 * P s ) + … + (v n * P other ))), where the initial conditions include:

[0187] -P pred = 0,

[0188] -w pred = 0, and

[0189] -w prob = 1- w pred ; and wherein:

[0190] -v n is the weight value for the statistical type;

[0191] -v n in the range [0...1] and sum(v1+…+v n ) = 1;

[0192] -P pred is a prediction that a particular event will occur (e.g., any of the various predictions discussed in this article);

[0193] -w pred =Last predicted weight value (range: [0..1]);

[0194] -w prob = weight value of past statistics (range: [0..1]); and

[0195] -w pred + w prob = 1.

[0196] Learning Algorithms

[0197] In some embodiments, prediction unit 34 may use a learning algorithm to make and / or adjust predictions based on, for example, data collected by collection unit 32. For example, in some embodiments, the learning algorithm may include a feedback loop configured to adjust for inaccuracies in the prediction algorithm. The feedback loop may adjust the prediction based on at least four situations, such as, for example, one or more of the following situations.

[0198] - Case 1: occurs when the last prediction of the event is correct. In this case, future predictions are calculated with a higher weight on the last prediction and a lower weight on past statistics. For case 1, the actual predicted event E1 can be calculated according to, for example, actual = E1 = predicted:

[0199] w pred = w pred + ((1-w pred ) / k),

[0200] where k is in [0.. maxValueCase1], and where maxValueCase1 is a configurable positive integer, and w prob = 1-w pred .

[0201] - Case 2: occurs when the last prediction of an event is incorrect. In this case, future predictions are calculated with lower weights on the last predictions and more weights on past statistics. For case 2, the actual predicted event E1 can be calculated according to, for example, actual = E1 = predicted:

[0202] w pred = w pred -(w pred / l),

[0203] where l is in [0..maxValueCase2], and where maxValueCase2 is a configurable positive integer, and w prob = 1-w pred .

[0204] - Case 3: For an event that occurs when it is not the predicted event. In this case, future predictions for this event are increased by increasing the prediction weight for the last prediction and having a lower weight for past statistics. For case 3, the actual predicted event E1 can be calculated according to, for example, actual = E1 = predicted:

[0205] -w pred = w pred + ((1-w pred ) / k),

[0206] where k is in [0.. maxValueCase3], and where maxValueCase3 is a configurable positive integer, and w prob = 1-w pred .

[0207] - Case 4: An event that we did not predict and did not occur. For case 4, the actual predicted event E1 can be calculated according to, for example, actual = E1 = predicted:

[0208] w pred = w pred -(w pred / l),

[0209] where l is in [0 ..maxValueCase4], and where maxValueCase4 is a configurable positive integer, and w prob = 1- w pred .

[0210] In further embodiments, other types of learning algorithms may be used to increase the accuracy of the predictions.

[0211] Some embodiments of the present disclosure provide arrangements for a radio access network node (and / or related nodes) to collect data associated with different UEs and scenarios during different times of the day, different days of the year, different months, different seasons, etc. to predict future behavior in one or more of the aspects discussed herein (e.g., TDD UL-DL mode selection, aggregated resources and services, resources and services for specific UEs, UE path prediction, UE tracking and paging requests, etc.).

[0212] As will be appreciated by those skilled in the art, the concepts described herein may be embodied as methods, data processing systems, computer program products, and / or computer storage media storing executable computer programs. Therefore, the concepts described herein may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects, all of which are generally referred to herein as "circuits" or "modules". Any process, step, action, and / or functionality described herein may be performed and / or associated with a corresponding module, which may be implemented in software and / or firmware and / or hardware. In addition, the present disclosure may take the form of a computer program product on a tangible computer-usable storage medium having a computer program code embodied in the medium that may be executed by a computer. Any suitable tangible computer-readable medium may be utilized, including a hard disk, a CD-ROM, an electronic storage device, an optical storage device, or a magnetic storage device.

[0213] Some embodiments are described herein with reference to the flowchart illustration and / or block diagram of method, system and computer program product. It will be understood that each frame of flowchart illustration and / or block diagram and the combination of frames in flowchart illustration and / or block diagram can be realized by computer program instructions. These computer program instructions can be provided to the processor of general-purpose computer (so as to create a special-purpose computer), special-purpose computer or other programmable data processing equipment to produce a machine, so that the instructions executed by the processor of computer or other programmable data processing equipment create the parts for realizing the function / action specified in one or more frames of flowchart and / or block diagram.

[0214] These computer program instructions may also be stored in a computer-readable memory or storage medium, which may direct a computer or other programmable data processing device to function in a specific manner so that the instructions stored in the computer-readable memory produce an article of manufacture including instruction components that implement the functions / actions specified in one or more boxes of the flowchart and / or block diagram.

[0215] The computer program instructions may also be loaded onto a computer or other programmable data processing device to cause a series of operational steps to be performed on the computer or other programmable device to produce a computer-implemented process, so that the instructions executed on the computer or other programmable device provide steps for implementing the functions / actions specified in one or more boxes of the flowchart and / or block diagram.

[0216] It should be understood that the functions / actions indicated in the blocks may not occur in the order indicated in the operational diagram. For example, two blocks shown in succession may actually be executed substantially simultaneously, or the blocks may sometimes be executed in the reverse order, depending on the functionality / actions involved. Although some diagrams include arrows on communication paths to illustrate the primary direction of communication, it should be understood that communication may occur in the opposite direction of the arrows depicted.

[0217] The computer program code for implementing the operation of the concepts described herein can be written in an object-oriented programming language (such as Java® or C++). However, the computer program code for implementing the operation of the present disclosure can also be written in a conventional process programming language (such as the "C" programming language). The program code can be executed entirely on the user's computer, partially on the user's computer, executed as an independent software package, partially on the user's computer and partially on a remote computer, or completely on a remote computer. In the latter case, the remote computer can be connected to the user's computer through a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (e.g., using an Internet service provider through the Internet).

[0218] Many different embodiments have been disclosed herein in conjunction with the above description and accompanying drawings. It will be understood that it would be unduly repetitive and confusing to literally describe and illustrate every combination and subcombination of these embodiments. Therefore, all embodiments may be combined in any manner and / or combination, and this specification including the accompanying drawings should be interpreted as constituting a complete written description of all combinations and subcombinations of the embodiments described herein and the manner and process of making and using them, and should support claims to any such combination or subcombination.

[0219] Those skilled in the art will appreciate that the embodiments described herein are not limited to what has been specifically shown and described herein above. In addition, unless otherwise mentioned above, it should be noted that all drawings are not drawn to scale. Various modifications and variations are possible according to the above teachings without departing from the scope of the appended claims.

Claims

1. A method implemented in a core network node (16), the method comprising: collecting (S100) location information, the collected location information being associated with movement of at least one user equipment (22) within the network; Making a prediction based on at least a portion of the collected location information (S102); as well as transmitting (S104) an indication of the prediction, The forecasts further include: Making a prediction according to a prediction algorithm that associates each of a plurality of different time windows with a different weight, The plurality of different time windows include at least one of the following: time of day, day of week, week of year, month of year, and season, each time window being associated with a different weight in the prediction algorithm.

2. The method according to claim 1, wherein making predictions according to the prediction algorithm further comprises: At least one probability is determined based at least in part on the weighted current predicted probability value and the weighted historical probability predicted values.

3. The method of claim 2, wherein the results of previous predictions determine the weight values ​​applied to the current probability prediction value and the weight values ​​applied to the historical prediction values.

4. The method according to any one of claims 1 to 3, wherein: Collecting the location information further includes: collecting path information and corresponding time information, said path information and said time information indicating said movement of said at least one user equipment (22) between at least two radio network areas in said network; The forecast further includes: predicting a movement path of the at least one user device (22) relative to the network, the prediction being based at least in part on the collected path information and the time information; and Transmitting the instruction further comprises: The indication of the predicted movement path of the at least one user equipment (22) is communicated. The method according to claim 4 , wherein the at least two radio network areas include at least two tracking areas and at least two cells.

6. The method of claim 4, wherein the indication of the predicted moving path comprises at least one cell global identifier (CGI), the at least one CGI indicating at least one cell to which the at least one user equipment (22) is expected to move according to the predicted moving path.

7. The method of claim 4, wherein the predicting further comprises: At least one probability of at least one moving path of the at least one user equipment (22) is determined, the at least one moving path including at least one of a cell of a base station and a neighboring cell.

8. A method according to claim 4, wherein the indication of the predicted moving path is configured to be included in a paging request for the at least one user equipment (22), the paging request indicating a probability prediction of the at least one user equipment (22) in the at least one cell in the paging request.

9. The method of claim 4, wherein the indication of the predicted moving path is configured to initiate a pre-allocation of resources for the at least one user equipment (22) in a cell included in the predicted moving path.

10. The method of claim 9, wherein the pre-allocation of resources for the at least one user equipment (22) is a pre-allocation of a contention-free preamble, the contention-free preamble being pre-configured and stored in a persistent memory at the at least one user equipment (22).

11. The method of claim 4, wherein collecting further comprises: The path information and the corresponding time information are collected from at least one of: the at least one user equipment (22), a mobility management entity, and a base station.

12. The method of claim 4, wherein collecting further comprises: Historical path information is collected from at least one of at least one initial attach and at least one mobility process of the at least one user equipment (22), the historical path information comprising a cell identifier, a timestamp, a positioning coordinate and a user equipment identifier.

13. The method of claim 4, wherein collecting further comprises: A tracking area update (TAU) message is received, the TAU message comprising a timestamp and location coordinates indicating a current location of the at least one user equipment (22).

14. The method according to any one of claims 1 to 3, wherein: Collecting the location information further includes: collecting the location information and corresponding time information, the collected location information and the corresponding time information being associated with the movement of a plurality of user devices (22) within the network; and The forecast further includes: predicting a network characteristic based at least in part on the collected location information and the temporal information; and Transmitting the instruction further comprises: The indication of the predicted network characteristic is communicated.

15. The method according to claim 14, wherein the predicting the network characteristic further comprises: At least one of the following items: the amount of user equipment (22) served by at least one cell and the amount of bearer used for services in the at least one cell is predicted for a future time period based at least in part on the collected location information and the time information.

16. The method of claim 15, wherein the prediction is used for resource planning in the at least one cell for the future time period.

17. The method of claim 15, wherein the prediction is used to determine one of a time division duplex (TDD) mode and a frequency division duplex (FDD) resource to be used in the at least one cell for the future time period.

18. A core network node (16) configured to facilitate communication of a user equipment (22) in a communication system, the core network node (16) comprising processing circuitry (42), the processing circuitry (42) configured to cause the core network node (16) to: collect location information, the collected location information being associated with movement of at least one user equipment (22) within the network; making a prediction based on at least a portion of the collected location information; as well as conveying an indication of said forecast, The processing circuit (42) is further configured to cause the core network node (16) to make a prediction by causing the core network node (16) to: Making a prediction according to a prediction algorithm that associates each of a plurality of different time windows with a different weight, The plurality of different time windows include at least one of the following: time of day, day of week, week of year, month of year, and season, each time window being associated with a different weight in the prediction algorithm.

19. The core network node (16) of claim 18, wherein the processing circuit (42) is further configured to cause the core network node (16) to make predictions according to the prediction algorithm by being configured to cause the core network node (16) to: At least one probability is determined based at least in part on the weighted current predicted probability value and the weighted historical probability predicted values.

20. The core network node (16) of claim 19, wherein results of previous predictions determine weight values ​​applied to the current probabilistic prediction value and weight values ​​applied to the historical prediction values.

21. The core network node (16) according to any one of claims 18 to 20, wherein the processing circuit (42) is further configured to cause the core network node (16): The location information is collected by configuring the core network node (16) to: collecting path information and corresponding time information, said path information and said time information indicating said movement of said at least one user equipment (22) between at least two radio network areas in said network; The prediction is performed by configuring the core network node (16) to: predicting a movement path of the at least one user device (22) relative to the network, the prediction being based at least in part on the collected path information and the time information; and The indication is communicated by being configured to cause the core network node (16) to: The indication of the predicted movement path of the at least one user equipment (22) is communicated.

22. The core network node (16) of claim 21, wherein the at least two radio network areas comprise at least two tracking areas and at least two cells.

23. The core network node (16) of claim 21, wherein the indication of the predicted moving path comprises at least one cell global identifier (CGI), the at least one CGI indicating at least one cell to which the at least one user equipment (22) is expected to move according to the predicted moving path.

24. A core network node (16) according to claim 21, wherein the processing circuit (42) is further configured to cause the core network node (16) to make a prediction by being configured to cause the core network node (16) to perform the following operations: determine at least one probability of at least one mobile path of the at least one user equipment (22), the at least one mobile path including at least one of a cell of a base station and a neighboring cell.

25. A core network node (16) according to claim 21, wherein the indication of the predicted mobile path is configured to be included in a paging request for the at least one user equipment (22), the paging request indicating a probability prediction of the at least one user equipment (22) in the at least one cell in the paging request.

26. The core network node (16) of claim 21, wherein the indication of the predicted moving path is configured to initiate a pre-allocation of resources for the at least one user equipment (22) in a cell included in the predicted moving path.

27. A core network node (16) according to claim 26, wherein the pre-allocation of resources for the at least one user equipment (22) is a pre-allocation of a contention-free preamble, and the contention-free preamble is pre-configured and stored in a persistent memory at the at least one user equipment (22).

28. The core network node (16) of claim 21, wherein the processing circuit (42) is further configured to cause the core network node (16) to collect by configuring the core network node (16) to perform the following operations: collecting the path information and the corresponding time information from at least one of the following items: the at least one user equipment (22), a mobility management entity, and a base station.

29. The core network node (16) of claim 21, wherein the processing circuit (42) is further configured to cause the core network node (16) to collect by being configured to cause the core network node (16) to perform the following operations: collecting historical path information from at least one of at least one initial attachment and at least one mobility process of the at least one user equipment (22), the historical path information comprising a cell identifier, a timestamp, a positioning coordinate, and a user equipment identifier.

30. The core network node (16) of claim 21, wherein the processing circuit (42) is further configured to cause the core network node (16) to collect by being configured to cause the core network node (16) to perform the following operations: receive a tracking area update (TAU) message, the TAU message comprising a timestamp and positioning coordinates indicating a current location of the at least one user equipment (22).

31. The core network node (16) according to any one of claims 18-20, wherein the processing circuit (42) is further configured to cause the core network node (16): The location information is collected by configuring the core network node (16) to: collecting the location information and corresponding time information, the collected location information and the corresponding time information being associated with the movement of a plurality of user devices (22) within the network; and The prediction is performed by configuring the core network node (16) to: predicting a network characteristic based at least in part on the collected location information and the temporal information; and The indication is communicated by being configured to cause the core network node (16) to: The indication of the predicted network characteristic is communicated.

32. The core network node (16) of claim 31, wherein the processing circuit (42) is further configured to cause the core network node (16) to predict the network characteristic by being configured to cause the core network node (16) to: At least one of the following items: the amount of user equipment (22) served by at least one cell and the amount of bearer used for services in the at least one cell is predicted for a future time period based at least in part on the collected location information and the time information.

33. The core network node (16) according to claim 32, wherein the prediction is used for resource planning in the at least one cell for the future time period.

34. The core network node (16) of claim 32, wherein the prediction is used to determine one of a time division duplex (TDD) mode and a frequency division duplex (FDD) resource to be used in the at least one cell for the future time period.

Images