Method and apparatus for handover management

Abstract

Embodiments of the present disclosure provide methods and apparatuses for handover management. A method performed by a handover management entity includes receiving a handover request from a network node. The handover request indicates that a first terminal device is to be handed over from a source cell to a target cell. The method further includes obtaining a location of the first terminal device. The method further includes predicting a handover outcome for the first terminal device by a classifier. The location of the first terminal device is used as an input to the classifier, and the classifier is trained for handover from the source cell to the target cell. The method further includes generating a handover decision based on the predicted handover outcome. The method further includes sending a handover response including the handover decision to the network node.

Description

TECHNICAL FIELD

[0001] The non-limiting and exemplary embodiments of the present disclosure generally relate to the field of communication technology, and in particular to methods and apparatuses for handover management. BACKGROUND

[0002] This section introduces aspects that can be helpful in further understanding the present disclosure. Thus, the statements made in this section are not to be read as an admission that anything in the prior art is related to what is presented in this section or that what is presented in this section is what is in the prior art.

[0003] Communication service providers and network operators have been facing challenges in delivering value and convenience to consumers, for example, by providing compelling network services and performance. With the rapid development of network and communication technologies, wireless communication networks such as Long Term Evolution (LTE) / Fourth Generation (4G) networks and New Radio (NR) / Fifth Generation (5G) networks are expected to achieve high traffic capacity and end-user data rates with low latency. To meet the diverse needs of new services across various industries, the Third Generation Partnership Project (3GPP) is developing various network function services for various communication networks.

[0004] The ability to perform handover between cells can be a requirement for any wireless network such as a cellular network. Mobility can remove location-based anchors, improve user experience, and reduce hardware installation constraints.

[0005] Providing quality mobility services can rely on network operators' calibration and configuration of mobility parameters. To reduce network configuration efforts and allow networks to adapt to changing environments, the concept of self-organizing networks (SON) has been introduced into a series of 3GPP protocols.

[0006] In the context of SON, mobility robustness optimization (MRO) is one of the techniques in SON. MRO can refer to a class of procedures that allow a cellular network to select its own set of optimal mobility parameters. Such procedures can be run autonomously across domains of the network in a centralized or non-centralized manner without human intervention.

[0007] As described in 3GPP TS 36.300 V16.2.0 (the disclosure of which is incorporated herein by reference in its entirety), one of the functions of MRO is to detect connection failures that occur due to too early handover or too late handover or handover to a wrong cell. These handover problems are defined as follows:

[0008] Too late handover: Radio link failure (RLF) occurs after the user equipment (UE) has stayed in a cell for a long time. The UE attempts to reestablish a radio link connection in a different cell.

[0009] Too early handover: RLF occurs shortly after a successful handover from a source cell to a target cell, or handover failure occurs during the handover procedure. The UE attempts to reestablish a radio link connection in a cell other than the source cell and the target cell.

[0010] Handover to wrong cell: RLF occurs shortly after a successful handover from a source cell to a target cell, or handover failure occurs during the handover procedure. The UE attempts to reestablish a radio link connection in a cell other than the source cell and the target cell. SUMMARY

[0011] This summary is provided in simplified form to present selected concepts, which will be further described below in the detailed description. This summary is neither intended nor is it to be construed as identifying key or essential features, nor as

[0012] As mentioned above, there are some issues in handover, such as too late handover, too early handover, handover to wrong cell, etc. However, some existing solutions for these handover issues can also have some problems.

[0013] For example, an existing MRO solution can rely on adjusting CIO (cell individual offset) according to, for example, the proportion of the identified connection failure types. The CIO parameter can be applicable to a specific cell and can be used as an offset in cell reselection. For example, a CIO value of dB-24 corresponds to -24 dB, dB-22 corresponds to -22 dB, and so on. For example, if the number of “too early handover” is greater than the number of “too late handover”, the CIO of a neighboring cell can be decreased by one step in an MRO period, and vice versa. For handover from a source cell to a target cell, some UEs can have a “too late handover” issue, some UEs can have a “too early handover” issue, and some UEs can have a “handover to wrong cell” issue. Therefore, it can be difficult to satisfy all UEs with the same CIO adjustment. In addition, for example, depending on the frequency of different handover issues, the CIO adjustment can oscillate in different optimization periods.

[0014] It can be difficult to determine handover trigger parameters, such as CIO adjustment parameters. The handover trigger parameters, such as CIO adjustment upper limit, CIO adjustment lower limit, CIO adjustment step, etc., can be manually input at a cell deployment stage. Suitable handover trigger parameters can depend on the rich experience of a network operator. However, in some cases, the network operator can not have rich network adjustment experience.

[0015] It can be necessary to tailor handover trigger parameters to suit a specific cell. However, there can not be a default set of mobility parameters that can be best performed in different cells.

[0016] Small cell networks in enterprise scenarios can involve a large number of cells to guarantee coverage. In dense multi-cell scenarios, it can be necessary for a network operator to configure each cell individually. However, the number of low-cost small cells to be deployed means that this configuration can not be practical.

[0017] If the above handover problems are not addressed, the network can handle many radio resource control (RRC) connection setups and re-establishments for UEs. These RRC connection setups and re-establishments can not always be successful, breaking the connectivity of the UEs, degrading the user experience, and increasing the network signaling load.

[0018] To overcome or alleviate at least one of the above problems or other problems, embodiments of the present disclosure propose improved solutions for handover management.

[0019] In a first aspect of the present disclosure, a method performed by a handover management entity is provided. The method comprises receiving a handover request from a network node. The handover request indicates that a first terminal device is to be handed over from a source cell to a target cell. The method further comprises obtaining a location of the first terminal device. The method further comprises predicting a handover outcome for the first terminal device by a classifier. The location of the first terminal device is used as an input to the classifier, and the classifier is trained for handovers from the source cell to the target cell. The method further comprises generating a handover decision based on the predicted handover outcome. The method further comprises sending a handover response comprising the handover decision to the network node.

[0020] In one embodiment, the classifier can be trained by a training set, and the training set comprises historical handover outcome data about handovers from the source cell to the target cell.

[0021] In one embodiment, the training set can further comprise handover outcome data about handovers from the source cell to the target cell generated by a generative adversarial network.

[0022] In one embodiment, for a specific type of handover outcome, a corresponding type of generative adversarial network is trained by using historical handover outcome data of the corresponding type about the handover from the source cell to the target cell.

[0023] In one embodiment, the handover outcome data can comprise a location of a terminal device, a handover outcome, a source cell identifier, a target cell identifier, an error cell identifier when the terminal device is handed over to an error cell.

[0024] In one embodiment, the handover result data can further comprise at least one of: antenna information of the source cell, antenna information of the target cell, antenna information of the error cell, relative position of the terminal device to the antenna of the source cell, relative position of the terminal device to the antenna of the target cell, or relative position of the terminal device to the antenna of the error cell.

[0025] In one embodiment, the handover result can comprise at least one of: too late handover; too early handover; handover to an error cell; or handover success.

[0026] In one embodiment, when the predicted handover result indicates too late handover, the handover decision can instruct the network node to lower handover trigger difficulty.

[0027] In one embodiment, when the predicted handover result indicates handover success, the handover decision can instruct the network node to immediately perform handover.

[0028] In one embodiment, when the predicted handover result indicates too early handover or handover to an error cell, the handover decision can be further generated based on movement information of the first terminal device.

[0029] In one embodiment, the method can further comprise obtaining movement information of the first terminal device.

[0030] In one embodiment, the movement information of the first terminal device can comprise at least one of: moving speed of the first terminal device; moving direction of the first terminal device; or acceleration of the first terminal device.

[0031] In the embodiment of generating the handover decision further based on the movement information of the first terminal device, when the first terminal device will enter a handover success area at a specific time point, the handover decision can instruct the network node a specific time point for performing handover; or when the first terminal device will enter a handover success area at a specific time point, the handover decision can instruct the network node to perform handover, wherein the response comprising the handover decision is sent to the network node at or after the specific time point; or when the first terminal device is moving away from the handover success area, the handover decision can comprise at least one recommended target cell and instruct the network node to perform cell reselection based on the at least one recommended target cell.

[0032] In one embodiment, the method can further comprise determining at least one handover result area regarding handover from the source cell to the target cell.

[0033] In one embodiment, the method can further comprise receiving at least a part of the historical handover result data from the network node.

[0034] In one embodiment, the handover management entity can be deployed into an open radio access network.

[0035] In a second aspect of the disclosure, a method performed by a network node is provided. The method comprises sending a handover request to a handover management entity. The handover request indicates that a first terminal device is to be handed over from a source cell to a target cell. The method further comprises receiving a handover response comprising a handover decision from the handover management entity. The handover decision is generated based on a predicted handover outcome for the first terminal device, and the predicted handover outcome for the first terminal device is predicted by a classifier. A location of the first terminal device is used as input to the classifier, and the classifier is trained for handover from the source cell to the target cell.

[0036] In one embodiment, the method can further comprise sending at least a portion of historical handover outcome data to the handover management entity.

[0037] In a third aspect of the disclosure, a handover management entity is provided. The handover management entity comprises a processor; and a memory storing instructions executable by the processor, whereby the handover management entity is operative to receive a handover request from a network node. The handover request indicates that a first terminal device is to be handed over from a source cell to a target cell. The handover management entity is further operative to obtain a location of the first terminal device. The handover management entity is further operative to predict a handover outcome for the first terminal device by a classifier. The location of the first terminal device is used as input to the classifier, and the classifier is trained for handover from the source cell to the target cell. The handover management entity is further operative to generate a handover decision based on the predicted handover outcome. The handover management entity is further operative to send a handover response comprising the handover decision to the network node.

[0038] In one embodiment, the handover management entity can be further operative to obtain mobility information for the first terminal device.

[0039] In one embodiment, the handover management entity can be further operative to determine at least one handover outcome region with respect to handover from the source cell to the target cell.

[0040] In one embodiment, the handover management entity can be further operative to receive at least a portion of historical handover outcome data from the network node.

[0041] In a fourth aspect of the disclosure, a network node is provided. The network node comprises a processor; and a memory storing instructions executable by the processor, whereby the network node is operative to send a handover request to a handover management entity. The handover request indicates that a first terminal device is to be handed over from a source cell to a target cell. The network node is further operative to receive a handover response from the handover management entity comprising a handover decision. The handover decision is generated based on a predicted handover outcome for the first terminal device, and the predicted handover outcome for the first terminal device is predicted by a classifier. A location of the first terminal device is used as input to the classifier, and the classifier is trained for handover from the source cell to the target cell.

[0042] In one embodiment, the network node is further operative to send at least a portion of historical handover outcome data to the handover management entity.

[0043] In a fifth aspect of the disclosure, a computer program product comprising instructions which, when executed on at least one processor, cause the at least one controller to carry out the method according to any of the first and second aspects of the disclosure is provided.

[0044] In a sixth aspect of the disclosure, a computer-readable storage medium storing instructions which, when executed on at least one processor, cause the at least one controller to carry out the method according to any of the first and second aspects of the disclosure is provided.

[0045] Another aspect of the disclosure provides a communication system including a host computer comprising processing circuitry configured to provide user data, and a communication interface configured to forward the user data to a cellular network for transmission to a terminal device. The cellular network comprises the network node and / or the terminal device described above.

[0046] In embodiments of the disclosure, the system further comprises the terminal device, wherein the terminal device is configured to communicate with the network node.

[0047] In embodiments of the disclosure, the processing circuitry of the host computer is configured to execute a host application, thereby providing the user data; and the terminal device comprises processing circuitry configured to execute a client application associated with the host application.

[0048] Another aspect of the disclosure provides a communication system including a host computer comprising a communication interface configured to receive user data originating from a terminal device. The network node is as described above.

[0049] In embodiments of the disclosure, the processing circuitry of the host computer is configured to execute a host application. The terminal device is configured to execute a client application associated with the host application, thereby providing user data received from the host computer.

[0050] A further aspect of the disclosure provides a method implemented in a communication system that can include a host computer, a network node and a terminal device. The method can include at the host computer, providing user data. Optionally, the method can include at the host computer, initiating a transmission carrying the user data to the terminal device via a cellular network that includes the network node, which can perform any of the steps of the method according to the second aspect of the disclosure.

[0051] A further aspect of the disclosure provides a communication system including a host computer. The host computer can include processing circuitry configured to provide user data and a communication interface configured to forward the user data to a cellular network for transmission to a terminal device. The cellular network can include a network node having a radio interface and processing circuitry. The network node's processing circuitry can be configured to perform any of the steps of the method according to the second aspect of the disclosure.

[0052] A further aspect of the disclosure provides a method implemented in a communication system that can include a host computer, a network node and a terminal device. The method can include at the host computer, providing user data. Optionally, the method can include at the host computer, initiating a transmission carrying the user data to the terminal device via a cellular network that includes the network node.

[0053] A further aspect of the disclosure provides a communication system including a host computer. The host computer can include processing circuitry configured to provide user data and a communication interface configured to forward the user data to a cellular network for transmission to a terminal device. The terminal device can include a radio interface and processing circuitry.

[0054] A further aspect of the disclosure provides a method implemented in a communication system that can include a host computer, a network node and a terminal device. The method can include at the host computer, receiving user data transmitted from a terminal device to a network node.

[0055] A further aspect of the disclosure provides a communication system including a host computer. The host computer can include a communication interface configured to receive user data originating from a transmission from a terminal device to a network node. The terminal device can include a radio interface and processing circuitry.

[0056] Another aspect of the disclosure provides a method implemented in a communication system that can include a host computer, a network node, and a terminal device. The method can include at the host computer, receiving user data that originated from a transmission by the terminal device to the network node. The network node can perform any of the steps of the method according to the second aspect of the disclosure.

[0057] Another aspect of the disclosure provides a communication system that can include a host computer. The host computer can include a communication interface configured to receive user data that originated from a transmission by a terminal device to a network node. The network node can include a radio interface and processing circuitry. The processing circuitry of the network node can be configured to perform any of the steps of the method according to the second aspect of the disclosure.

[0058] Various embodiments herein provide various advantages, the following is a non-exhaustive list of examples of advantages. In some embodiments herein, the proposed solution can not require intervention of network operators. The proposed solution can not rely on any existing MRO parameter settings that can only be provided by network operators with rich network adjustment experience. For example, initial CIO parameters can be set randomly. Alternatively, MRO related work such as deciding handover timing, adjusting HO trigger thresholds, etc. can be done automatically by a handover management entity. In some embodiments herein, the proposed solution can satisfy most or all UEs with different handover issues. For example, unlike conventional MRO solutions, where each parameter (e.g., CIO) adjustment can only satisfy part of UEs in a network but not most UEs in the network with different handover issues. Alternatively, the proposed solution can satisfy most or all UEs. In some embodiments herein, the proposed solution can solve or mitigate the oscillation problem of the optimized parameter (e.g., CIO). For example, in conventional MRO solutions, the optimized parameter (e.g., CIO) can oscillate depending on the percentage of each handover issue in different adjustment periods, while the proposed solution can solve or mitigate the oscillation problem of the optimized parameter. Embodiments herein are not limited to the above-mentioned features and advantages. Additional features and advantages will be recognized by those skilled in the art upon reading the following detailed description. BRIEF DESCRIPTION OF DRAWINGS

[0059] The above and other aspects, features, and advantages of various embodiments of the disclosure will become more fully apparent from the following detailed description, by way of example, with reference to the accompanying drawings, in which like reference numerals or letters are used to denote like elements throughout and wherein:

[0060] Figure 1aSystem architecture in a 4G network is schematically illustrated;

[0061] Figure 1b System architecture in a 5G network is schematically illustrated;

[0062] Figure 2 A flowchart of a method according to embodiments of the disclosure is shown;

[0063] Figure 3 An example of an architecture of a GAN is shown;

[0064] Figure 4 A flowchart of a method according to another embodiment of the disclosure is shown;

[0065] Figure 5 A flowchart of a method according to another embodiment of the disclosure is shown;

[0066] Figure 6 An example of handover region partitioning according to embodiments of the disclosure is shown;

[0067] Figure 7a An example of an architecture of GAN-based MRO according to embodiments of the disclosure is shown;

[0068] Figure 7b A flowchart of GAN-based MRO according to embodiments of the disclosure is shown;

[0069] Figure 7c A flowchart of GAN-based MRO according to another embodiment of the disclosure is shown;

[0070] Figure 8 An example of a VAE-GAN workflow according to embodiments of the disclosure is shown;

[0071] Figure 9 An example of RT UE position, moving speed and direction according to embodiments of the disclosure is shown;

[0072] Figure 10 An example of a UE moving away from a handover normal segment according to embodiments of the disclosure is shown;

[0073] Figure 11 A flowchart of a GMC workflow according to embodiments of the disclosure is shown;

[0074] Figure 12 An example of input vector dimensions for a GAN model and HO result segment classifier according to embodiments of the disclosure is shown;

[0075] Figure 13 An example of a GMC deployed into ORAN to implement traffic steering according to embodiments of the disclosure is shown;

[0076] Figure 14 An example of a service steering use case flow diagram is shown in accordance with embodiments of the disclosure;

[0077] Figure 15 is a block diagram illustrating a device suitable for implementing some embodiments of the disclosure;

[0078] Figure 16 is a block diagram illustrating a handover management entity in accordance with embodiments of the disclosure; and

[0079] Figure 17 is a block diagram illustrating a network node in accordance with embodiments of the disclosure.

[0080] Figure 18 is a schematic diagram illustrating a wireless network in accordance with some embodiments;

[0081] Figure 19 is a schematic diagram illustrating a user equipment in accordance with some embodiments;

[0082] Figure 20 is a schematic diagram illustrating a virtualization environment in accordance with some embodiments;

[0083] Figure 21 is a schematic diagram illustrating a telecommunication network connected via an intermediate network to a host computer, in accordance with some embodiments;

[0084] Figure 22 is a schematic diagram illustrating a host computer communicating via a base station with a user equipment over a partially wireless connection, in accordance with some embodiments;

[0085] Figure 23 is a schematic diagram illustrating methods implemented in a communication system including a host computer, a base station and a user equipment, in accordance with some embodiments;

[0086] Figure 24 is a schematic diagram illustrating methods implemented in a communication system including a host computer, a base station and a user equipment, in accordance with some embodiments;

[0087] Figure 25 is a schematic diagram illustrating methods implemented in a communication system including a host computer, a base station and a user equipment, in accordance with some embodiments; and

[0088] Figure 26 is a schematic diagram illustrating methods implemented in a communication system including a host computer, a base station and a user equipment, in accordance with some embodiments. DETAILED DESCRIPTION

[0089] Embodiments of the present disclosure are described in detail with reference to the drawings. It should be understood that these embodiments are discussed solely for the purpose of enabling those skilled in the art to better understand and thus realize and implement the present disclosure and are not intended to be a limitation on the scope of the present disclosure. Reference throughout this specification to features, advantages or similar language does not mean that all of the features and advantages that can be achieved in accordance with the present disclosure should be or are implemented in any single embodiment of the disclosure. Rather, language referring to the features and advantages is understood to mean that a particular feature, advantage, or characteristic described in connection with an embodiment is included in at least one embodiment of the disclosure. Furthermore, it should be understood that features and advantages described in the specification and / or claims are not necessarily all-inclusive of other features and advantages that can be realized. In one or more embodiments, the features, advantages, and characteristics described can be combined in any suitable manner.

[0090] As used herein, the term “network” refers to a network that complies with any suitable wireless communication standard. For example, the wireless communication standard can include New Radio (NR), Long Term Evolution (LTE), LTE-Advanced, Wideband Code Division Multiple Access (WCDMA), High-Speed Packet Access (HSPA), Code Division Multiple Access (CDMA), Time Division Multiple Access (TDMA), Frequency Division Multiple Access (FDMA), Orthogonal Frequency Division Multiple Access (OFDMA), Single-Carrier Frequency Division Multiple Access (SC-FDMA), and other wireless networks. A CDMA network can implement a radio technology such as Universal Terrestrial Radio Access (UTRA). UTRA includes WCDMA and other variants of CDMA. A TDMA network can implement a radio technology such as Global System for Mobile Communications (GSM). An OFDMA network can implement a radio technology such as Evolved UTRA (E-UTRA), Ultra Mobile Broadband (UMB), IEEE 802.11 (Wi-Fi), IEEE 802.16 (WiMAX), IEEE 802.20, Flash-OFDMA, Ad hoc networks, Wireless Sensor Networks, and so on. In the following description, the terms “network” and “system” can be used interchangeably. Also, communication between two devices in a network can be performed according to any suitable communication protocol, including, but not limited to, wireless communication protocols defined by standards organizations such as the Third Generation Partnership Project (3GPP). For example, the wireless communication protocols can include first generation (1G), 2G, 3G, 4G, 4.5G, 5G communication protocols, and / or any other protocols currently known or developed in the future.

[0091] The term “network node” as used herein refers to a (physical or virtual) network equipment in a communications network. For example, a network node can be an access network equipment in a communications network through which terminal devices access the network and receive services therefrom. For example, a network node can include, but is not limited to, an integrated access and backhaul (IAB) node, an access point (AP), a multi-cell / multicast coordination entity (MCE), a base station (BS), and the like. An access network equipment can be, for example, a NodeB (NB or NB), an evolved NodeB (eNodeB or eNB), a next generation NodeB (gNodeB or gNB), a remote radio unit (RRU), a radio head (RH), a remote radio head (RRH), a relay, a low power node (e.g., femto, pico, etc.), and the like.

[0092] Yet another example of a network node includes a multi-standard radio (MSR) wireless device, such as a MSR BS, a network controller such as a radio network controller (RNC) or base station controller (BSC), a base transceiver station (BTS), a transmission point, a transmission node, a positioning node, and the like. However, more generally, a network node can represent any suitable device (or group of devices) capable of, configured to, arranged to, and / or operable to enable terminal devices to access a wireless communications network and / or provide certain services to terminal devices that have accessed the wireless communications network.

[0093] The term “entity” as used herein refers to a network equipment or network node or network function in a communications network. For example, a network entity can be implemented as a network element on a dedicated hardware, as a software instance running on a dedicated hardware, or as a virtual function instantiated on a suitable platform, e.g., on a cloud infrastructure.

[0094] The term "terminal device" refers to any end device that can access a communication network and receive services therefrom. By way of example, but not limitation, a terminal device refers to a mobile terminal, user equipment (UE), or other suitable device. A UE can be, for example, a subscriber station (SS), a portable user station, a mobile station (MS), or an access terminal (AT). A terminal device can include, but is not limited to, a portable computer, an image capture terminal device such as a digital camera, a game terminal device, a music storage and playback appliance, a mobile phone, a cellular phone, a smart phone, a voice over Internet Protocol (VoIP) phone, a wireless local loop phone, a tablet, a wearable device, a personal digital assistant (PDA), a portable computer, a desktop computer, a wearable terminal device, a vehicle-mounted wireless terminal device, a wireless endpoint, a mobile station, a laptop embedded equipment (LEE), a laptop mounted equipment (LME), a USB (Universal Serial Bus) dongle, a smart device, a wireless customer premises equipment (CPE), or the like. In the following description, the terms "terminal device," "terminal," "user equipment," and "UE" can be used interchangeably. As one example, a terminal device can represent a UE configured for communication in accordance with one or more communication standards promulgated by 3GPP, such as the LTE standard or the NR standard by 3GPP. As used herein, a "user equipment" or "UE" can not necessarily have a "user" in the sense of a human user that owns and / or operates the relevant device. In some embodiments, a terminal device can be configured to transmit and / or receive information without direct human interaction.

[0095] As yet another example, in an Internet of Things (IOT) scenario, a terminal device can represent a machine or other device that performs monitoring and / or measurements, and reports the results of such monitoring and / or measurements to another terminal device and / or a network device. In this case, the terminal device can be a machine-to-machine (M2M) device, which in a 3GPP context can be referred to as a machine-type communication (MTC) device. As one particular example, a terminal device can be a UE implementing the 3GPP Narrow Band-IoT (NB-IoT) standard. Particular examples of such machines or devices are sensors, metering devices (e.g., electricity meters), industrial machinery, or home or personal appliances (e.g., refrigerators, televisions), personal wearable devices (e.g., watches), etc. In other scenarios, a terminal device can represent a vehicle or other equipment that is capable of monitoring and / or reporting on its operational status or other functions related to its operation.

[0096] References in the specification to “one embodiment,” “an embodiment,” “an example embodiment,” etc. indicate that the embodiment described can include a particular feature, structure, or characteristic, but not every embodiment necessarily includes the particular feature, structure, or characteristic. Moreover, such phrases are not necessarily referring to the same embodiment. Furthermore, when a particular feature, structure, or characteristic is described in connection with an embodiment, it is submitted that it is within the knowledge of those in the art to affect such feature, structure, or characteristic in connection with other embodiments whether or not explicitly described.

[0097] It should be understood that although the terms “first” and “second” among others can be used herein to describe various elements, these elements should not be limited by these terms. These terms are only used to distinguish one element from another. For example, a first element could be termed a second element, and, similarly, a second element could be termed a first element, without departing from the scope of the example embodiments. As used herein, the term “and / or” includes any and all combinations of one or more of the associated listed terms.

[0098] As used herein, the phrases “at least one of A or B” and “at least one of A and B” should be interpreted to mean “only A, only B, or both A and B.” The phrase “A and / or B” should be interpreted to mean “only A, only B, or both A and B.”

[0099] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments. 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 be further understood that the terms “comprises,” “comprising,” “includes,” “including,” “has,” “have,” “containing” and / or “contains” specify the presence of stated features, elements and / or components, but do not preclude the presence or addition of one or more other features, elements, components and / or combinations thereof.

[0100] Note that the terms used herein are only for the convenience of description and to distinguish between nodes, devices or networks, etc. Other terms with similar / same meanings can also be used as technology evolves.

[0101] In the following description and claims, unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this disclosure belongs.

[0102] Note that some embodiments of this disclosure are described primarily with respect to non-limiting examples, such as cellular networks as defined by 3GPP, which are used as exemplary network configurations and system deployments. Therefore, the descriptions of the exemplary embodiments given herein specifically refer to terms directly related to them. Such terms are used only in the context of the presented non-limiting examples and embodiments and are not intended to limit this disclosure in any way. Rather, any other system configuration or radio technology (such as wireless sensor networks) can be used in the same way, provided that the exemplary embodiments described herein are applicable.

[0103] Figures 1a-1b Some system architectures that can implement embodiments of this disclosure are shown. For simplicity, Figures 1a-1b The system architecture described herein only depicts a few exemplary components. In practice, a communication system may also include any additional components suitable for supporting communication between terminal devices or between a wireless device and another communication device, such as a landline telephone, a service provider, or any other network node or terminal device. The communication system may provide communication and various types of services to one or more terminal devices to facilitate access to and / or use of services provided by or via the communication system.

[0104] Figure 1a The diagram schematically illustrates the system architecture in a 4G network, which is consistent with 3GPP TS 23.682V16.7.0. Figure 4 Similar to .2-1a, the public content of which is incorporated herein by reference in its entirety. Figure 1a The system architecture may include some exemplary components, such as Service Capability Server (SCS), Application Server (AS), SCEF, HSS, UE, RAN (Radio Access Network), SGSN (Serving GPRS (General Packet Radio Service) Support Node), MME, MSC (Mobile Switching Center), S-GW (Serving Gateway), GGSN / P-GW (Gateway GPRS Support Node / PDN (Packet Data Network) Gateway), MTC-IWF (Machine Type Interoperability Function), CDF / CGF (Charging Data Function / Charging Gateway Function), MTC-AAA (Machine Type Authentication, Authorization and Accounting), SMS-SC / GMSC / IWMSC (Short Message Service Center / Gateway MSC / Interoperability MSC), and IP-SM-GW (Internet Protocol Short Message Gateway). Figure 1a The network elements and interfaces shown may be the same as the corresponding network elements and interfaces described in 3GPP TS 23.682V16.7.0.

[0105] Figure 1b The diagram schematically illustrates the system architecture in a 5G network, which is consistent with 3GPP TS 23.501V16.5.1. Figure 42.3-1, the disclosure of which is incorporated by reference herein in its entirety. Figure 1b The system architecture of FIG. 1 can include some exemplary elements, such as an AMF (Access and Mobility Function), an SMF (Session Management Function), an AUSF (Authentication Service Function), a UDM (Unified Data Management), a PCF (Policy Control Function), an AF (Application Function), an NEF (Network Exposure Function), a UPF (User Plane Function), a NRF (Network Repository Function), a RAN (Radio Access Network), an SCP (Service Communication Proxy), an NSSF (Network Slice Selection Function), an NSSAAF (Network Slice Specific Authentication and Authorization Function), and the like. As shown in FIG. 1, the network elements, reference points, and interfaces can be the same as the corresponding network elements, reference points, and interfaces described in 3GPP TS 23.501 V16.5.1. Figure 1b The network elements, reference points, and interfaces shown in FIG. 1 can be the same as the corresponding network elements, reference points, and interfaces described in 3GPP TS 23.501 V16.5.1.

[0106] Figure 2 A flowchart of a method 200 according to embodiments of the disclosure is shown, which can be performed by an apparatus implemented in a handover management entity or by an apparatus implemented as a handover management entity or communicatively coupled to a handover management entity. As such, the apparatus can provide means or modules for performing various operations of the method 200, as well as means or modules for performing other operations in conjunction with other components.

[0107] The handover management entity can be implemented as a network element on a dedicated hardware, as a software instance running on a dedicated hardware, as a network function on a network element, or as a virtualized function instantiated on a suitable platform, e.g., on a cloud infrastructure. For example, the handover management entity can be implemented as a network function on any suitable network node, such as a RAN or (R)AN, as shown in FIGS. 1 and 2. Figure 1a and 1b Alternatively, the handover management entity can be implemented in two or more devices. For example, a first portion of the functionality of the handover management entity can be implemented in a first device; a second portion of the functionality of the handover management entity can be implemented in a second device; and so on. In one embodiment, the training functionality of the handover management entity can be implemented in a server, and the classification functionality of the handover control entity can be implemented in an access network node.

[0108] At block 202, the handover management entity can receive a handover request from a network node. The handover request indicates that a first terminal device is to be handed over from a source cell to a target cell.

[0109] The handover can be any suitable handover, such as an intra-system handover, an inter-system handover, etc. In one embodiment, the handover can be any handover as described in clause 5.5 of 3GPP TS 23.401 V16.6.0, the disclosure of which is incorporated by reference herein in its entirety, and clause 4.9 of 3GPP TS 23.502 V16.5.1.

[0110] The handover can be triggered for various reasons, such as new radio conditions, load balancing, or due to specific services, such as in the presence of QoS (Quality of Service) flows for voice, etc.

[0111] At block 204, the handover management entity can obtain a location of the first terminal device. The handover management entity can obtain the location of the first terminal device in various ways. For example, when the location of the first terminal device is included in the handover request, the handover management entity can obtain the location of the first terminal device from the handover request. Alternatively, the handover management entity can obtain the location of the first terminal device from another device, such as a location server. For example, the location data of the first terminal device in the location server can come from a positioning module (e.g., GPS (Global Positioning System)) of the first terminal device or from a location service of the network.

[0112] At block 206, the handover management entity can predict a handover outcome of the first terminal device by a classifier. The location of the first terminal device is used as an input to the classifier. The classifier is trained for handover from a source cell to a target cell.

[0113] The classifier can be any suitable classifier that is capable of mapping input data (e.g., the location of the first terminal device) to a particular class (e.g., a handover outcome class). The classifier can be implemented by using various techniques, such as neural networks, deep learning, etc. In one embodiment, the classifier can be a multi-class classifier. In a multi-class classifier, each input data or sample can be assigned to one and only one label or class.

[0114] In one embodiment, the classifier can be trained by a training set, and the training set can include historical handover outcome data regarding handover from a source cell to a target cell. The historical handover outcome data can be obtained by the handover management entity in various ways. For example, the handover management entity can obtain the historical handover outcome data from a network management device, which can collect the historical handover outcome data from network nodes. Further, the handover management entity can obtain the historical handover outcome data from the network nodes.

[0115] In one embodiment, the training set can further include handover outcome data regarding handover from a source cell to a target cell generated by a generative adversarial network (GAN). The GAN can be any suitable GAN currently known or developed in the future.

[0116] Figure 3 An example of a GAN architecture is shown. For example... Figure 3 As shown, the generator in a GAN learns to create fake data by incorporating feedback from a discriminator. GAN learning enables the discriminator to classify its output as real data. Compared to discriminator training, generator training may require a tighter integration between the generator and the discriminator. Training the generator can include:

[0117] Random input,

[0118] • A generator network that transforms random input into data instances.

[0119] • A discriminator network that classifies the generated data.

[0120] • Discriminator output,

[0121] • Generator loss, which penalizes the generator for failing to fool the discriminator.

[0122] GANs can take random noise as input. The generator then transforms this noise into a meaningful output. The generator loss penalizes the generator because it produces a sample that the discriminator network classifies as false. Backpropagation adjusts each weight in the correct direction by calculating the effect of the weights on the output. Both the generator and the discriminator can be neural networks.

[0123] For example, a GAN trained on a photograph can generate new photographs that appear at least superficially real to a human observer and possess many realistic features.

[0124] Note that, as Figure 3 The GAN shown is merely an example of a GAN, and any other suitable GAN can be used in other embodiments. For example, a variational autoencoder (VAE) with a generative adversarial network (GAN), designed by Anders Boesen, Lindbo Larsen, etc., can be used. Kaae Hugo Larochelle and Ole Winther proposed Autoencoding beyond pixels using a learned similarity metric, Proceedings of the 33rd International Conference on Machine Learning, Volume 48 (ICML'16), pp. 1558-1566.

[0125] In one embodiment, for a specific type of handover result, the corresponding type of generative adversarial network can be trained by using the historical handover result data of the corresponding type about the handover from the source cell to the target cell. For example, when there are four types of handover results, there can be four types of GANs, each of which can correspond to a different type of handover effect.

[0126] In one embodiment, the handover result data includes: the location of the terminal device, the handover result, the source cell identifier, the target cell identifier, the error cell identifier when the terminal device is handed over to the error cell. In other embodiments, the handover result data can also include any other suitable data, such as cell configuration information, antenna information, signal measurement data of the source cell, signal measurement data of the target cell, signal measurement data of the error cell, handover trigger conditions (or handover trigger difficulty), etc.

[0127] In one embodiment, the handover result data can also include at least one of the following: antenna information of the source cell, antenna information of the target cell, antenna information of the error cell, relative position of the terminal device and the antenna of the source cell, relative position of the terminal device and the antenna of the target cell, or relative position of the terminal device and the antenna of the error cell. The antenna information can include data of the antenna positions and tilts of all cells in a geographical area. Based on these antennas, two or more cells can be established in the geographical area. The antenna information can be manually input at the cell deployment stage, or in the case of Active Antenna System (AAS) it can be collected from reports. The relative position of the terminal device and the antenna can be represented in various ways. For example, it can be represented by the current position coordinates of the terminal device, the static antenna position coordinates of the antenna, the static antenna tilt of the antenna, the angle between the terminal device and the antenna, the distance between the terminal device and the antenna.

[0128] In one embodiment, the handover result can include at least one of the following: too late handover; too early handover; handover to an error cell; or handover success.

[0129] As described in 3GPP TS 36.300 V16.2.0, the network node can perform the detection mechanism for too late handover, too early handover, and handover to an error cell by the following ways:

[0130] [Too Late Handover]

[0131] If the UE attempts to re-establish a radio link connection in a cell belonging to eNB B, indicates a cell belonging to a different eNB A than eNB B as the last source cell, eNB B can report this event to eNB A through the RLF indication procedure. eNB A can then use the information in the RLF indication message to determine if the failure occurred in the source cell or not.

[0132] [Too early handover]

[0133] If the target cell belongs to eNB B, different from eNB A, controlling the source cell, when eNB B receives the RLF indication message from eNB A and if eNB B has sent a UE context release message to eNB A related to the completion of an incoming handover for the same UE within the last Tstore_UE_cnxt seconds or there is a prepared handover in eNB B for the same UE, eNB B can send a handover report message to eNB A indicating a too early handover event.

[0134] [Handover to wrong cell]

[0135] If the failure type is radio link failure and the target cell belongs to eNB B, different from eNB A, controlling the source cell, when eNB B receives the RLF indication message from eNB C and if eNB B has sent a UE context release message to eNB A related to the completion of an incoming handover for the same UE within the last Tstore_UE_cnxt seconds or there is a prepared handover in eNB B for the same UE, eNB B can send a handover report message to eNB A indicating a handover to wrong cell event. This also applies when eNB A and eNB C are the same. If eNB B and eNB C are the same and the RLF indication is internal to this eNB, a handover report message can also be sent.

[0136] If the failure type is a handover failure during a handover from a cell in eNB A and the UE attempts to re-establish a radio link connection to a cell in eNB C, eNB C can send an RLF indication message to eNB A.

[0137] Reference Figure 2 At block 208, the handover management entity can generate a handover decision based on the predicted handover result. For example, depending on the particular type of the predicted handover result, the handover management entity can generate different handover decisions.

[0138] As a first example, when the predicted handover result indicates too late handover, the handover decision can instruct the network node to stop the handover and perform cell reselection. Further, the handover decision can provide at least one recommended target cell for the network node to perform cell reselection.

[0139] As a second example, when the predicted handover result indicates too early handover and the handover management entity determines that the first terminal device will enter a handover success area at a certain time point, the handover decision can instruct the network node to perform handover at or after the certain time. When the handover management entity determines that the first terminal device will enter an area of handover to an error cell at a certain time point, the handover decision can instruct the network node to select the error cell and perform handover to the error cell at or after the certain time point.

[0140] As a third example, when the predicted handover result indicates handover to an error cell and the handover management entity determines that the first terminal device will enter a handover success area at a certain time point, the handover decision can instruct the network node to perform handover at or after the certain time. When the handover management entity determines that the first terminal device is moving towards an error cell, the handover decision can instruct the network node to select the error cell and perform handover to the error cell.

[0141] As a fourth example, when the predicted handover result indicates too early handover and the handover management entity can monitor the real-time location of the first terminal device, until the first terminal device enters a handover success area, the handover management entity can send a handover decision including a handover command to the network node.

[0142] In one embodiment, when the predicted handover result indicates too late handover, the handover decision instructs the network node to lower the handover trigger difficulty. For example, the handover trigger difficulty can be set according to a conventional rule. For example, the inequality A3-1 (entry condition) as described in 3GPP TS 38.331 V16.1.0 can be used.

[0143] Inequality A3-1 (entry condition):

[0144] Mn + Ofn + Ocn - Hys > Mp + Ofp + Ocp + Off

[0145] The variables in inequality A3-1 are defined as follows:

[0146] Mn is the measurement result of the neighboring cell, without considering any offset.

[0147] Ofn is the measurement object specific offset of the reference signal of the neighboring cell (i.e., corresponding to offsetMO as defined within measObjectNR).

[0148] Ocn is the cell-specific offset of the neighbor cell (i.e., the cellIndividualOffset as defined in measObjectNR corresponding to the frequency of the neighbor cell), which is set to zero if it is not configured for the neighbor cell.

[0149] Mp is the measurement result of the SpCell without considering any offset.

[0150] Ofp is the measurement object-specific offset of the SpCell (i.e., the offsetMO as defined in measObjectNR corresponding to the SpCell).

[0151] Ocp is the cell-specific offset of the SpCell (i.e., the cellIndividualOffset as defined in measObjectNR corresponding to the SpCell), which is set to zero if it is not configured for the SpCell.

[0152] Hys is the hysteresis parameter for this event (i.e., the hysteresis as defined in reportConfigNR for this event).

[0153] Off is the offset parameter for this event (i.e., the a3-Offset as defined in reportConfigNR for this event).

[0154] Mn, Mp are expressed in dBm in case of RSRP (Reference Signal Received Power), or in dB in case of RSRQ (Reference Signal Quality) and RS-SINR (Reference Signal - Signal to Interference plus Noise Ratio).

[0155] Ofn, Ocn, Ofp, Ocp, Hys, Off are expressed in dB.

[0156] In this embodiment, the Ocp parameter can be decreased when the predicted handover outcome indicates too late handover. Or, the Ocn parameter can be increased when the predicted handover outcome indicates too late handover. In this case, the handover can be more easily triggered, so that the probability of the first terminal device entering the “too late segment” can be very low.

[0157] In one embodiment, the initial parameters set in the above inequality A3-1 can be configured to make the inequality more easily achieved, which means the handover is more easily triggered, so that the probability of the UE entering the “too late segment” is very low.

[0158] In one embodiment, the initial parameters set in the above inequality A3-1 can be configured according to historical handover outcome data, for example, in the handover success area and / or the too early handover area.

[0159] In one embodiment, the handover decision indicates to the network node to immediately perform the handover when the predicted handover result indicates a successful handover.

[0160] In one embodiment, the handover decision can be further generated based on mobility information of the first terminal device when the predicted handover result indicates a too early handover or a handover to a wrong cell. In one embodiment, the mobility information of the first terminal device can comprise at least one of: a moving speed of the first terminal device; a moving direction of the first terminal device; or an acceleration of the first terminal device.

[0161] The handover management entity can use the mobility information of the first terminal device to determine whether to continue the handover. For example, when the handover management entity predicts that the first terminal device will enter a handover successful area based on the mobility information, it can determine to continue the handover. In this case, the handover management entity can determine a handover timing. For example, the handover management entity can predict a time when the first terminal device will enter the handover successful area, and then determine the handover timing. When the handover management entity predicts that the first terminal device will enter an area of a handover to a wrong cell based on the mobility information, it can determine to stop the handover. In this case, the handover decision can indicate to the network node to stop the handover and perform a cell reselection. In addition, the handover management entity can provide at least one recommended target cell to the network node.

[0162] In one embodiment, the handover decision indicates to the network node a specific time point for performing the handover when the predicted handover result indicates a too early handover or a handover to a wrong cell and the handover management entity determines that the first terminal device will enter a handover successful area at the specific time point.

[0163] In one embodiment, the handover decision indicates to the network node to perform the handover when the predicted handover result indicates a too early handover or a handover to a wrong cell and the handover management entity determines that the first terminal device will enter a handover successful area at a specific time point, wherein a response comprising the handover decision is sent to the network node at or after the specific time point.

[0164] In one embodiment, the handover decision comprises at least one recommended target cell and indicates to the network node to perform a cell reselection based on the at least one recommended target cell when the predicted handover result indicates a too early handover or a handover to a wrong cell and the handover management entity determines that the first terminal device is moving away from a handover successful area.

[0165] In block 210, the handover management entity can send a handover response comprising the handover decision to the network node.

[0166] Figure 4A flowchart of a method 400 according to another embodiment of the disclosure is shown, which can be performed by a device implemented in a handover management entity or a device implemented as or communicatively coupled to the handover management entity. For some parts that have been described in the above embodiments, their descriptions are omitted here for brevity.

[0167] At block 402, the handover management entity can receive at least a portion of historical handover result data from a network node.

[0168] At block 404, the handover management entity can receive a handover request from a network node. The handover request indicates that a first terminal device is to be handed over from a source cell to a target cell. Block 404 is the same as block 202 of Figure 2 .

[0169] At block 406, the handover management entity can obtain a location of the first terminal device. Block 406 is the same as block 204 of Figure 2 .

[0170] At block 408, the handover management entity can obtain movement information of the first terminal device. Blocks 406 and 408 can be performed in one step.

[0171] At block 410, the handover management entity can determine at least one handover result area for the handover from the source cell to the target cell. In one embodiment, the at least one handover result area for the handover from the source cell to the target cell can be determined based on the historical handover result data for the handover from the source cell to the target cell. In another embodiment, the at least one handover result area for the handover from the source cell to the target cell can be determined by using a classifier and / or a generative adversarial network.

[0172] For example, based on the handover result (e.g. normal or identified handover problem) and the location of the UE when performing the handover, the handover management entity can divide the whole handover area between the source and target cell pair into different segments (or areas), such as a “too early handover” segment, a “too late handover” segment, a “handover to wrong cell” segment, and a “handover normal (or successful)” segment.

[0173] At block 412, the handover management entity can predict a handover result of the first terminal device by a classifier. The location of the first terminal device is used as an input of the classifier, and the classifier is trained for the handover from the source cell to the target cell. Block 412 is the same as block 206 of Figure 2 .

[0174] At block 414, the handover management entity can generate a handover decision based on the predicted handover result. Block 414 is the same as block 208 of Figure 2 .

[0175] At block 416, the handover management entity can transmit a handover response including the handover decision to the network node. Block 416 is the same as block 210 of FIG. 2. Figure 2

[0176] In one embodiment, the handover management entity can be deployed into an open radio access network (O-RAN).

[0177] Figure 5 A flowchart of a method 500 according to another embodiment of the disclosure is shown, which can be performed by an apparatus implemented in a network node or a device implemented as or communicatively coupled to the network node. As such, the apparatus can provide means for performing various operations of method 500 and means for performing other operations in conjunction with other components. For some parts, descriptions thereof are omitted herein for brevity.

[0178] At block 502, the network node can optionally transmit at least a portion of the historical handover result data to the handover management entity. For example, when the network node detects a handover result, it can transmit the handover result data to the handover management entity.

[0179] At block 504, the network node can transmit a handover request to the handover management entity. The handover request indicates that the first terminal device is to be handed over from the source cell to the target cell.

[0180] At block 506, the network node can receive a handover response including a handover decision from the handover management entity. The handover decision is generated based on a predicted handover result of the first terminal device, and the predicted handover result of the first terminal device is predicted by a classifier. A location of the first terminal device is used as an input of the classifier, and the classifier is trained for a handover from the source cell to the target cell.

[0181] Figure 6 An example of handover area partitioning according to an embodiment of the disclosure is shown.

[0182] ​The detailed steps for handover area partitioning for source and target cell pairs can be as follows. When the source or serving cell decides to trigger a UE handover, it can report this event (e.g., the UE is going to be handed over from the source cell to the target cell) to the GMC (Global MRO Commander) (also referred to as the handover management entity). The GMC can immediately query the real-time UE location (e.g., at the time of handover execution). The source cell can report the handover outcome to the GMC based on the traditional MRO rules and procedures, e.g., “handover normal”, “too early handover”, “too late handover”, or “handover to wrong cell”. If the identified issue is “handover to wrong cell”, the cell identifier (CID) of the wrong cell should be attached. The GMC can label each handover location with the corresponding handover outcome as a real image (e.g., a real handover location). For the “handover to wrong cell” issue, the CID of the “wrong cell” should be part of the label, which means different wrong cells can have different labels.

[0183] After enough “real images (e.g., real handover locations)” for a certain type of handover outcome are collected (which means these “real images” share the same label), e.g., after the GMC collects 1000 “real images” for the “too early handover” issue, the GMC can start to build and train a GAN model to generate a set of “fake images (e.g., virtual handover locations)” that map to the handover outcome (i.e., too early handover).

[0184] For the images of “handover to wrong cell”, since different wrong cells can have different labels (e.g., the CID of the wrong cell), the GAN model can be built and trained separately, so that a fake image set for this type of handover issue can be generated separately and the fake image set can be mapped to different wrong cells.

[0185] For each type of handover (HO) outcome, the GMC can combine the real images and fake images together and label them with the corresponding type of HO outcome to form a training set. The GMC can use this training set to train a multi-class classifier to classify or predict the HO outcome segment. For the multi-class classifier, its input vector can be the HO location of the UE and its output vector can be the HO outcome segment. Finally, for a source and target cell pair, the HO outcome segment can be formed.

[0186] After the multi-class classifier for the source and target cells of a specific pair is trained, when a handover is triggered in the source cell, the source cell can request the GMC to provide the handover decision (e.g., handover timing) instead of making the handover decision itself. After the GMC receives the handover request, it can start to monitor the UE, e.g., query the real-time location, moving speed, and direction of the UE, and then predict the HO outcome segment, e.g., by using the multi-class classifier and / or the moving speed and moving direction.

[0187] For example, the handover trigger condition can be set according to conventional rules, such as inequality A3-1 (entry condition) as described above.

[0188] The GMC can decide the handover timing based on the prediction result (e.g., the HO result segment that the UE belongs to at the time of triggering handover). If the current location of the UE belongs to the “too early handover” segment, the GMC can not send the handover command until the UE enters the handover normal segment. If the current location of the UE belongs to the “too late handover” segment, the GMC can inform the source cell to lower the handover trigger difficulty. If the current location of the UE belongs to the “handover to wrong cell” segment, the GMC can check the moving speed and direction of the UE. If the UE is moving close to the handover normal segment according to the moving speed and direction of the UE, the handover command can not be sent until the UE enters the handover normal segment. If the UE is moving away from the handover normal segment, the GMC can return the CID list of candidate target cells to the source cell for target cell reselection. If the current location of the UE belongs to the handover normal segment, the GMC can immediately send the handover command to the source cell, which means the handover timing is now.

[0189] Figure 7a An example of an architecture of GAN-based MRO is shown, in accordance with an embodiment of the present disclosure. Figure 7b A flowchart of GAN-based MRO is shown, in accordance with an embodiment of the present disclosure. Figure 7c A flowchart of GAN-based MRO is shown, in accordance with another embodiment of the present disclosure.

[0190] As Figure 7a shown, the architecture can include a functional entity of static database (DB) of antenna locations and tilts. The functional entity of static DB of antenna locations and tilts can be used to store data of antenna locations and tilts of at least one cell in a geographical area. Based on these antennas, at least one cell can be established. As Figure 7b shown, the data of DB of antenna locations and tilts can come from manual input at the cell deployment phase or from reporting in the case of AAS. If needed, the DB of antenna locations and tilts can provide the GMC with antenna location and tilt information of a specific cell.

[0191] The architecture can also include a functional entity of dynamic DB of real-time (RT) UE locations and moving speed and direction. The functional entity of dynamic DB of RT UE locations and moving speed and direction can provide the GMC with an application programming interface (API). By using the API, the GMC can retrieve the real-time location and moving speed (i.e., speed vector ) of a UE at any time. The data of dynamic DB of RT UE locations and moving speed and direction can come from a positioning system of the UE, such as GPS.

[0192] The architecture may also include functional entities of the GMC. These functional entities can perform tasks such as collecting labeled data (e.g., real images or historical switch result data), training the GAN model, generating fake images, segmenting the switch region (segment classification), determining the switch timing, and continuously optimizing the GAN model and the HO result segment classifier.

[0193] like Figure 7b As shown, when the serving cell (i.e., the source cell) plans to activate the MRO function, it can request the GMC to perform HO area segmentation on a specific HO area defined by the source and target cells. This means that at least one of the above tasks can be performed on the source and target cell pairs.

[0194] like Figure 7b As shown, the process of collecting labeled data (real images) can be as follows.

[0195] Step 1: When the source cell performs a UE HO, it can report the UE HO event to the GMC. The UE HO event may include the source CID, the target CID, and the UE ID (identifier), etc.

[0196] Step 2: GMC can query the RT UE location from the dynamic DB of RT UE location, movement speed and direction.

[0197] Step 3: According to traditional MRO rules and definitions, after obtaining the HO result from the target cell or the wrong cell, the source cell can send a report of the HO result to the GMC. The HO result report may include the source CID, target CID, UE ID, and the HO result identified by the source cell. When the UE is handed over to the wrong cell, the HO result report may also include the incorrect CID. The HO result may include: "Handover normal", "Handover too early", "Handover too late", or "HO to wrong cell".

[0198] Step 4: The GMC can associate the RT UE location with the HO results to form a true image. The GMC can then set up separate databases to store the true images of different HO results, meaning these databases can be set up for each type of HO result.

[0199] like Figure 7b As shown, the GAN model training process can be as follows: A GAN model can be trained for each pair of source and target cells. For any database, when the number of real images required for a specific type of HO result for a specific pair of source and target cells is reached, the GMC can begin training a GAN model corresponding to the specific type of HO result for that specific pair of source and target cells. This means that the number of GAN models can match the number of HO result types.

[0200] Since the traditional GAN model can use random noise as input to generate fake images, it can make the generated fake images have greater differences with real images, which can further cause the GMC to calculate the wrong HO timing. In order to make the HO timing decision as accurate as possible (i.e., the fake image is as close to the real image as possible), a VAE-GAN (Variational Autoencoder Generative Adversarial Network) can be used.

[0201] Figure 8 An example of a VAE-GAN workflow according to embodiments of the disclosure is shown. Compared with the traditional GAN, the VAE-GAN connects an encoder before the generator, which can output an embedding code z based on the real image x. Then based on the embedding code z instead of random noise, the generator can output the final fake image x'. The fake image x' needs to be as close to the real image x as possible.

[0202] Reference Figure 7b The process of fake image generation can be as follows. The GMC can use the selected GAN model to generate a specified number of fake images for each type of HO result.

[0203] Reference Figure 7b The process of handover area segmentation can be as follows.

[0204] Step 1: The GMC can combine the real images and the generated fake images for the source and target cells of a specific pair together, and label the specific HO result to generate a training set for the HO result segment classifier. The classifier can be a multi-class classifier.

[0205] Step 2: The GMC can train the classifier with a machine learning (ML) algorithm by using the training set for the source and target cells of a specific pair.

[0206] Step 3: When the training of the classifier is completed, the GMC can notify the source cell that has requested the handover area segmentation.

[0207] Reference Figure 7c The process of determining the handover timing can be as follows.

[0208] Step 1: When the HO trigger condition of the UE is met, the source cell can request the GMC to evaluate the handover timing.

[0209] Step 2: The GMC can query the RT location, moving speed and direction of the UE from the dynamic DB of RT UE locations and moving speeds and directions.

[0210] Step 3: The GMC can predict the HO result segment for the UE by inputting the RT UE location into the HO result segment classifier.

[0211] If the current UE position belongs to the too early handover segment, GMC can calculate the hysteresis time At using the following equation. After At, the UE is able to enter the "handover normal" segment.

[0212]

[0213] where P i is the position of the i-th image in the "handover normal" segment (both real and false images), P0is the RT UE position, is the RT UE moving speed vector, θ i is the angle between .

[0214] Figure 9 An example of RT UE position, moving speed, and direction is shown according to an embodiment of the disclosure.

[0215] If the current UE position belongs to the too late handover segment, GMC can inform the source cell to lower the handover triggering difficulty as in the legacy.

[0216] If the current UE position belongs to the handover to wrong cell segment, GMC can check the UE's moving trend (e.g., moving speed and direction). If according to the UE's moving trend, the UE is moving close to the handover normal segment. GMC can follow the same procedure as the too early handover case. If the UE is moving away from the handover normal segment, GMC can return the CID list of candidate target cells to the source cell. The candidate target cells can include multiple wrong cells, e.g., due to segment overlapping.

[0217] The expected output from the HO result segment classifier can be the likelihood value of each class, thus GMC can select the N most likely wrong cells with close likelihood values as candidate target cells.

[0218] Figure 10 An example of UE moving away from the handover normal segment is shown according to an embodiment of the disclosure. According to equation (1), if the calculated At < 0, GMC can know that the UE is moving away from the handover normal segment, otherwise the UE is moving close to the handover normal segment. If the UE is moving away from the handover normal segment, the θ i in equation (1) can be greater than 90°. If the current UE position belongs to the handover normal segment, GMC can immediately send the handover command to the source cell, which means the handover timing is now.

[0219] Reference Figure 7cThe GAN model and the HO result segment classifier can be continuously optimized. For example, after HO region segmentation, real image (i.e., historical handover result data) collection can not stop. The GMC can continuously monitor various types of HO results reported from source cells. When the ratio of total real images of all types of HO problems to real images of normal handover results reaches a predefined threshold, the GMC can start to retrain the GAN model using ensemble learning, and then improve the HO region segment. During ensemble learning, the GMC can keep the original real images but discard the original fake images. After completing the new HO region segmentation, the GMC can continue to retrain the HO result segment classifier with the new training set.

[0220] Figure 11 A flowchart of a GMC workflow according to embodiments of the disclosure is shown. The GMC workflow can include GAN model setup and training, fake image generation, HO region segmentation, and handover timing decision. The detailed GMC workflow has been described in the above embodiments.

[0221] The image dimension (or feature) of the input vector of the GAN and / or classifier can be related to the location of the UE, which can include the UE coordinates (x, y, z) representing the absolute location of the UE and the distance and angle (d, θ) between the UE and the antenna location of at least one cell in the geographic area, which can represent the relative location of the UE to the antenna of at least one cell in the geographic area.

[0222] Figure 12 An example of the input vector dimension for the GAN model and the HO result segment classifier according to embodiments of the disclosure is shown.

[0223] Suppose there are a total of N deployed cells in a geographic area, then the input vector for the image of a specific pair of source cell and target cell can have the following features:

[0224]

[0225] (Xu, Yu, Zu): current location coordinates of the UE;

[0226] (Xn, Yn, Zn): static antenna location coordinates of the nth cell;

[0227] Static antenna tilt angle of the nth cell;

[0228] θn: angle between the UE and the antenna of the nth cell;

[0229] dn: distance between the UE and the antenna of the nth cell.

[0230] Both the GAN model and the HO outcome segment classifier can have the same input vector dimension.

[0231] For the GAN model, the output vector can be a set of fake images that can have the same dimension as the input vector. While for the HO outcome segment classifier, the dimension of the output vector can be the likelihood values of all the handover outcome segment categories, such as “Handover Normal Segment”, “Too Early Handover Segment”, “Too Late Handover Segment”, “Handover to Wrong Cell Segment”.

[0232] For “Handover Normal”, “Too Early Handover”, “Too Late Handover”, the GMC can use the predicted handover segment (e.g. HO outcome) with the largest likelihood value to decide the HO timing. For “Handover to Wrong Cell”, in the case that their likelihood values are very close to each other (corresponding to the case that the UE is located in the overlapping area of multiple “wrong cells”), the GMC can use the likelihood values of multiple categories to decide the recommended candidate target cell list. Then, the source cell can reselect a new target cell for UE HO based on the recommendation of the GMC and the traditional rules.

[0233] Figure 13 An example of GMC deployed into ORAN to implement traffic steering is shown according to embodiments of the present disclosure. In addition to the GMC shown in Figure 13 The network elements other than the GMC shown in FIG. 1 are the same as the corresponding network elements described in O-RAN-WG1-O-RAN Architecture Description v01.00.00, the disclosure of which is incorporated by reference herein in its entirety.

[0234] As shown in Figure 13 , the GMC can be deployed into the ORAN architecture for traffic steering. The implementation of the GMC can be distributed into the Non-RT RAN Intelligent Controller (Non-RT RIC) and the Near-RT RAN Intelligent Controller (Near-RT RIC) or the Network Management System (NMS). The Non-RT RIC can implement a part of the functions, such as antenna information acquisition; real image collection; GAN training; fake image generation; segment classifier training; and optimization for GAN and classifier. The Near-RT RIC or NMS implements a part of the functions, such as handover segment prediction and deciding handover timing.

[0235] Figure 14 An example of traffic steering use case flow chart is shown according to embodiments of the present disclosure. The traffic steering use case flow chart is the same as “ORAN-WG2. Use Case Requirements v01.00”, the disclosure of which is incorporated by reference herein in its entirety. Figure 3 .1.3-1”, the disclosure of which is incorporated by reference herein in its entirety.

[0236] Figure 15is a block diagram illustrating a device suitable for implementing some embodiments of the present disclosure. For example, any of the handover management entity and the network node as described above can be implemented as or by the device 1500.

[0237] The device 1500 comprises at least one processor 1521, e.g. a DP (Digital Processor), and at least one MEM (Memory) 1522 coupled to the processor 1521. The device 1500 can further comprise a transmitter (TX) and a receiver (RX) 1523 coupled to the processor 1521. The MEM 1522 stores a PROG (Program) 1524. The PROG 1524 can include instructions that, when executed on the associated processor 1521, enable the device 1500 to operate in accordance with the embodiments of the present disclosure. The combination of at least one processor 1521 and at least one MEM 1522 can form a processing means 1525 suitable to implement various embodiments of the present disclosure.

[0238] Various embodiments of the present disclosure can be implemented by a computer program executable by one or more of a processor 1521, software, firmware, hardware or combinations thereof.

[0239] The MEM 1522 can be of any type suitable to the local technical environment, and can be implemented using any suitable data storage technology, such as non-limiting examples semiconductor-based memory devices, magnetic memory devices and systems, optical memory devices and devices, fixed memory and removable memory.

[0240] The processor 1521 can be of any type suitable to the local technical environment, and can include one or more of a general purpose computer, a special purpose computer, a microprocessor, a digital signal processor (DSP), and a processor based on a multi-core processor architecture, as non-limiting examples.

[0241] In embodiments where the device is implemented as or at a handover management entity, the memory 1522 stores instructions executable by the processor 1521, whereby the handover management entity operates in accordance with any of the methods related to the handover management entity as described above.

[0242] In embodiments where the device is implemented as or at a network node, the memory 1522 stores instructions executable by the processor 1521, whereby the network node operates in accordance with any of the methods related to the network node as described above.

[0243] Figure 16is a block diagram illustrating a handover management entity according to an embodiment of the present disclosure. As shown in the figure, the handover management entity 1600 includes a first receiving module 1601, a first obtaining module 1602, a predicting module 1603, a generating module 1604, and a sending module 1605. The first receiving module 1601 can be configured to receive, from a network node, a handover request, wherein the handover request indicates that a first terminal device is to be handed over from a source cell to a target cell. The obtaining module 1602 can be configured to obtain a location of the first terminal device. The predicting module 1603 can be configured to predict a handover result of the first terminal device by a classifier, wherein the location of the first terminal device is used as an input of the classifier, and the classifier is trained for a handover from the source cell to the target cell. The generating module 1604 can be configured to generate a handover decision based on the predicted handover result. The sending module 1605 can be configured to send, to the network node, a handover response including the handover decision.

[0244] In one embodiment, the handover management entity 1600 can further include a second obtaining module 1606 configured to obtain mobility information of the first terminal device.

[0245] In one embodiment, the handover management entity 1600 can further include a determining module 1607 configured to determine at least one handover result area regarding the handover from the source cell to the target cell.

[0246] In one embodiment, the handover management entity 1600 can further include a second receiving module 1608 configured to receive, from the network node, at least a portion of historical handover result data.

[0247] Figure 17 is a block diagram illustrating a network node according to an embodiment of the present disclosure. As shown in the figure, the network node 1700 includes a first sending module 1701 and a receiving module 1702. The first sending module 1701 can be configured to send, to a handover management entity, a handover request, wherein the handover request indicates that a first terminal device is to be handed over from a source cell to a target cell. The receiving module 1702 can be configured to receive, from the handover management entity, a handover response including a handover decision. The handover decision is generated based on a predicted handover result of the first terminal device, and the predicted handover result of the first terminal device is predicted by a classifier. A location of the first terminal device is used as an input of the classifier, and the classifier is trained for a handover from the source cell to the target cell.

[0248] In one embodiment, the network node 1700 includes a second sending module 1703 configured to send, to the handover management entity, at least a portion of historical handover result data.

[0249] The term unit can have conventional meaning in the field of electronics, electrical, and / or electronic devices and can include, for example, electrical and / or electronic circuitry, devices, modules, processors, memories, logic solid state and / or discrete devices, computer programs or instructions that, when executed, carry out the functions, processes, computations, outputs, and / or displays described herein, and / or the like, as desired.

[0250] Using functional units, the handover management entity or network node can not need fixed processors or memories. The introduction of virtualization technology and network computing technology can improve the efficiency of the use of network resources and the flexibility of the network.

[0251] Various embodiments herein provide various advantages, the following is a non-exhaustive list of examples of advantages. In some embodiments herein, the proposed solution can not need the intervention of network operators. The proposed solution can not rely on any existing MRO parameter settings that can only be provided by network operators with rich network adjustment experience. For example, the initial CIO parameter can be set randomly. Alternatively, MRO related work such as deciding handover timing, adjusting HO trigger thresholds, etc. can be done automatically by the handover management entity. In some embodiments herein, the proposed solution can satisfy most or all UEs with different handover problems. For example, unlike traditional MRO solutions, in which each parameter (e.g., CIO) adjustment can only satisfy part of the UEs in the network and not most of the UEs in the network with different handover problems. Alternatively, the proposed solution can satisfy most or all UEs. In some embodiments herein, the proposed solution can solve or mitigate the problem of oscillation of the optimized parameter (e.g., CIO). For example, in traditional MRO solutions, the optimized parameter (e.g., CIO) can oscillate depending on the percentage of each handover problem in different adjustment periods, while the proposed solution can solve or mitigate the problem of oscillation of the optimized parameter. Embodiments herein are not limited to the above-mentioned features and advantages. Additional features and advantages will be recognized by those skilled in the art upon reading the following detailed description.

[0252] According to various embodiments, a new method of implementing intelligent MRO based on GAN is proposed. The proposed method can not need network operators to input any prior parameters (e.g., the initial CIO parameter can be set randomly). In addition, the proposed method can satisfy most or all UEs that will be handed over from a specific serving cell to a target cell.

[0253] In addition, an exemplary overall communication system including a terminal device and a network node such as a base station will be described below.

[0254] Embodiments of this disclosure provide a communication system including a host computer, the host computer comprising: processing circuitry configured to provide user data; and a communication interface configured to forward the user data to a cellular network for transmission to a terminal device. The cellular network includes the aforementioned base station and / or the aforementioned terminal device.

[0255] In embodiments of this disclosure, the system further includes a terminal device configured to communicate with the base station.

[0256] In embodiments of this disclosure, the processing circuitry of the host computer is configured to execute a host application to provide user data; the terminal device includes processing circuitry configured to execute a client application associated with the host application.

[0257] Embodiments of this disclosure also provide a communication system including a host computer and a base station. The host computer includes a communication interface configured to receive user data transmitted from a terminal device. The transmission is from the terminal device to the base station. The base station is as described above, and / or the terminal device is as described above.

[0258] In embodiments of this disclosure, the processing circuitry of the host computer is configured to execute a host application. The terminal device is configured to execute a client application associated with the host application, thereby providing user data to be received by the host computer.

[0259] Figure 18 This is a schematic diagram illustrating a wireless network according to some embodiments.

[0260] Although the subjects described herein can be implemented using any suitable components in any suitable type of system, the embodiments disclosed herein are described with respect to wireless networks, for example... Figure 18 The example wireless network shown is for simplicity. Figure 18 The wireless network depicted only includes network 1006, network nodes 1060 (corresponding to network-side nodes) and 1060b, and WDs (corresponding to terminal devices) 1010, 1010b, and 1010c. In practice, the wireless network may also include any additional elements suitable for supporting communication between wireless devices or between a wireless device and another communication device (e.g., a landline telephone, a service provider, or any other network node or terminal device). Among the components shown, network node 1060 and wireless device (WD) 1010 are depicted with additional details. The wireless network can provide communication and other types of services to one or more wireless devices to facilitate access to and / or use of services provided by or via the wireless network.

[0261] A wireless network can comprise interface and / or communicate with any type of communications, telecommunication, data, cellular and / or radio network, or other similar type of systems. In some embodiments, the wireless network can be configured to operate in accordance with specific standards or other types of predefined rules or procedures. Thus, particular embodiments of wireless network can implement communication standards, such as Global System for Mobile Communications (GSM), Universal Mobile Telecommunications System (UMTS), Long Term Evolution (LTE), and / or other suitable 2G, 3G, 4G, or 5G standards; wireless local area network (WLAN) standards, such as the IEEE 802.11 standards; and / or any other appropriate wireless communication standard, such as Worldwide Interoperability for Microwave Access (WiMax), Bluetooth, Z-Wave and / or ZigBee standards.

[0262] Network 1006 can comprise one or more backhaul networks, core networks, IP networks, public switched telephone networks (PSTNs), packet data networks, optical networks, wide-area networks (WANs), local area networks (LANs), wireless local area networks (WLANs), wired networks, wireless networks, metropolitan area networks, and other networks to enable communication among devices.

[0263] Network node 1060 and WD 1010 include various components described in more detail below. These components work together to provide network node and / or wireless device functionality, such as providing wireless connections in a wireless network. In different embodiments, the wireless network can comprise any number of wired or wireless networks, network nodes, base stations, controllers, wireless devices, relay stations, and / or any other components or systems that can facilitate or participate in the communication of data and signals between and among each other.

[0264] As used herein, network node refers to equipment capable, configured, arranged and / or operable to communicate directly or indirectly with a wireless device and / or with other equipment inside or outside a wireless network to enable and / or provide wireless access to the wireless device and / or to perform other functions (e.g., administration and / or management functions) within the wireless network. Examples of network nodes include, but are not limited to, access points (APs) (e.g., radio access points), Base Stations (BSs) (e.g., radio base stations, Node Bs, evolved Node Bs (eNBs) and NR Node Bs (gNBs)). Base stations can be categorized based on the amount of coverage they provide (or, stated differently, the transmission power of their output interfaces) as macro base stations, micro base stations, pico base stations, and / or femto base stations. Base stations can be standalone devices or can be centralized in a base station controller (BSC) or radio controller and / or centralized in a core network node. A base station can be a relay node or a relay donor node controlling relays. Network nodes can also include one or more components of a distributed radio base station, such as a centralized digital unit and / or remote radio unit (RRU), sometimes called a remote radio head (RRH). Such remote radio units can or can not be integrated with antennas. The components of a distributed radio base station can also be referred to as nodes of a distributed antenna system (DAS). Yet further examples of network nodes include multi-standard radio (MSR) equipment such as MSR BSs, network controllers (e.g., radio network controllers (RNCs) or base station controllers (BSCs)), base transceiver stations (BTSs), transmission points, transmission nodes, multi-cell / multicast coordination entities (MCEs), core network nodes (e.g., MSCs, MMEs), O&M nodes, OSS nodes, SON nodes, positioning nodes (e.g., E-SMLCs), and / or MDTs. As another example, a network node can be a virtual network node as described in more detail below. More generally, however, network nodes can represent any suitable device (or group of devices) capable, configured, arranged, and / or operable to enable, provide, and / or otherwise facilitate access to a wireless network by a wireless device, and / or to perform other functions that

[0265] In Figure 18 In some embodiments, network node 1060 includes processing circuitry 1070, device readable medium 1080, interface 1090, auxiliary equipment 1084, power source 1086, power circuitry 1087, and antenna 1062. In some embodiments, network node 1060 is a distributed Figure 18The network node 1060 illustrated in the example wireless network can represent a device that includes the illustrated combination of hardware components, but other embodiments can include network nodes with different combinations of components. It is contemplated that the network nodes include any suitable combination of hardware and / or software needed to perform the tasks, features, functions and methods disclosed herein. Moreover, while the components of the network node 1060 are depicted as single boxes located within a larger box, or single boxes nested within multiple boxes, in reality, the network node can comprise multiple different physical components constituting a single illustrated component (e.g., the device readable medium 1080 can include multiple individual disk drives as well as multiple RAM modules).

[0266] Similarly, the network node 1060 can be composed of multiple physically separate components (e.g., a NodeB component and a RNC component, or a BTS component and a BSC component, etc.), which can each have their own respective components. In certain scenarios in which the network node 1060 includes multiple separate components (e.g., BTS and BSC components), one or more separate components can be shared among several network nodes. For example, a single RNC can control multiple NodeB's. In such scenarios, each unique NodeB and RNC pair, in certain circumstances, can be considered a single separate network node. In some embodiments, the network node 1060 can be configured to support multiple radio access technologies (RATs). In such embodiments, some components (e.g., separate device readable medium 1080 for the different RATs) can be duplicated and some components can be reused (e.g., the same antenna 1062 can be shared by the RATs). The network node 1060 can also include multiple sets of the various illustrated components for different wireless technologies integrated into the network node 1060, such as GSM, WCDMA, LTE, NR, WiFi, or Bluetooth wireless technologies. These wireless technologies can be integrated into the same or different chip or set of chips and other components within the network node 1060.

[0267] The processing circuit 1070 is configured to perform any determining, calculating, or similar operations (e.g., certain obtaining operations) described herein as being provided by a network node. These operations performed by the processing circuit 1070 can include processing information obtained by the processing circuit 1070 by, for example, converting the obtained information into other information, comparing the obtained information or converted information to information stored in the network node, and / or performing one or more operations based on the obtained information or converted information, and as a result of said processing, making a determination.

[0268] The processing circuit 1070 can comprise a combination of one or more of a microprocessor, controller, microcontroller, central processing unit, digital signal processor, application-specific integrated circuit, field programmable gate array, or any other processing circuit, whether implemented in hardware, software, and / or firmware, or any combination thereof. Processing circuit 1070 can be configured to perform processing performed by network node 1060 such as any of the processing described herein as being performed by a network node. For example, processing circuit 1070 can execute an operating system (OS) 1072 and one or more software applications 1074 resident in the memory 1080 and / or storage 1082. Processing circuit 1070 can be configured to perform such processing using software, hardware, and / or other code — such as firmware or microcode — and any combinations thereof.

[0269] In some embodiments, processing circuit 1070 can include one or more of radio frequency (RF) transceiver circuitry 1072 and baseband processing circuitry 1074. In some embodiments, the RF transceiver circuitry 1072 and the baseband processing circuitry 1074 can be on separate chips (or sets of chips), boards, or units, such as radio and digital units. In alternative embodiments, part or all of the RF transceiver circuitry 1072 and the baseband processing circuitry 1074 can be on the same chip or set of chips, boards, or units.

[0270] In certain embodiments, some or all of the functionality described herein as being provided by a network node, base station, eNB or other such network device can be performed by the processing circuit 1070 executing instructions stored in the device readable medium 1080 or memory within the processing circuit 1070. In alternative embodiments, some or all of the functionality can be provided by the processing circuit 1070 without executing instructions stored in a separate or discrete device readable medium, such as in a hard-wired manner. In any of these embodiments, whether executing instructions stored in a device readable medium or not, the processing circuit 1070 can be configured to perform the described functions. The benefits provided by such functionality are not limited to the processing circuit 1070 or other components of the network node 1060 but extend to the network node 1060 as a whole and to the wireless network and its end users and operators as well.

[0271] Device readable medium 1080 can include any form of volatile or non-volatile computer readable memory including, without limitation, persistent storage, volatile memory, remote installation memory, magnetic media, optical media, random access memory (RAM), read only memory (ROM), mass storage media (for example, hard disk), removable storage media (for example, flash drive, compact disk (CD), or digital video disk (DVD)), and / or any other volatile or non-volatile, non-transitory device readable and / or computer-executable memory devices that store information, data, and / or instructions that can be used by processing circuitry 1070. Device readable medium 1080 can store any suitable instruction, data or information, including a computer program, software, including one or more of logic, rules, code, tables, etc., and / or other instructions capable of being executed by processing circuitry 1070 and used by network node 1060. Device readable medium 1080 can be used to store, among other things, any calculations made by processing circuitry 1070 and / or any data received by interface 1090. In some embodiments, processing circuitry 1070 and device readable medium 1080 can be considered to be integrated.

[0272] Interface 1090 is used in the wired or wireless communication of signaling or data between network node 1060, network 1006, and / or WDs 1010. As illustrated, interface 1090 includes ports / terminals 1094 that can be used to connect to network 1006, e.g., to establish network 1006 and / or data connections. Interface 1090 also includes radio front end circuitry 1092 that can be coupled to, or in some embodiments a part of, antenna 1062. Radio front end circuitry 1092 comprises filters 1098 and amplifiers 1096. Radio front end circuitry 1092 can be connected to antenna 1062 and processing circuitry 1070. Radio front end circuitry 1092 can be configured to condition signals from antenna 1062 for processing circuitry 1070 and / or for transmission to another network node or WD. Radio front end circuitry 1092 can also be configured to condition signals from processing circuitry 1070 for transmission by antenna 1062. Radio front end circuitry 1092 can include duplicate components that allow certain operations to be performed

[0273] In certain alternative embodiments, network node 1060 can not include separate radio front end circuitry 1092, instead, processing circuitry 1070 can comprise radio front end circuitry and can be connected to antenna 1062 without separate radio front end circuitry 1092. Similarly, in some embodiments, all or some of RF transceiver circuitry 1072 can be considered a part of interface 1090. In still other embodiments, interface 1090 can include one or more ports or terminals 1094, radio front end circuitry 1092, and RF transceiver circuitry 1072, as part of a radio

[0274] Antenna 1062 can include one or more antennas or antenna arrays configured to send and / or receive wireless signals. Antenna 1062 can be coupled to radio front end circuitry 1090 and can be any type of antenna and / or antennas in known in the art, including monopole, dipole, and / or loop antennas. In some embodiments, antenna 1062 can include one or more omnidirectional, sector or panel antennas that operate to transmit / receive radio signals between, for example, 2 GHz and 66 GHz. An omnidirectional antenna can be used to transmit / receive radio signals in any direction, a sector antenna can be used to transmit / receive radio signals to / from devices within a specific area, and a panel antenna can be a line of sight antenna used to transmit / receive radio signals in a relatively straight line. In some cases, the use of more than one antenna can be referred to as MIMO. In certain embodiments, antenna 1062 can be separate from network node 1060 and can be connectable to network node 1060 through an interface or port.

[0275] Antenna 1062, interface 1090, and / or processing circuitry 1070 can be configured to perform any receiving operations and / or certain obtaining operations described herein as being performed by a network node. Any information, data and / or signals can be received from wireless devices, another network node and / or any other network equipment. Similarly, antenna 1062, interface 1090, and / or processing circuitry 1070 can be configured to perform any transmitting operations described herein as being performed by a network node. Any information, data and / or signals can be transmitted to wireless devices, another network node and / or any other network equipment.

[0276] Power supply circuitry 1087 can comprise or be coupled to power management circuitry and is configured to supply the components of the network node 1060 with power for performing the functions described herein. Power supply circuitry 1087 can receive power from power source 1086. Power source 1086 and / or power supply circuitry 1087 can be configured to provide power to the various components of the network node 1060 in a form suitable for use by each respective component (e.g., at a voltage and current level that each respective component needs and / or is compatible with). Power source 1086 can be included in, or external to, power supply circuitry 1087 and / or network node 1060. Power source 1086 can supply power to power supply circuitry 1087 through a power source interface or bus. As an example, network node 1060 can be connected to an external power source (e.g., an electricity outlet) through an input circuitry or interface (e.g., an electrical cable) and hence the external power source can supply power to power supply circuitry 1087. As another example, power source 1086 can comprise a battery or battery pack coupled to power supply circuitry 108 or integrated with power supply circuitry 1087. The battery can provide backup power in the event of failure of the external power source. Other types of power sources, such as photovoltaic devices, can also be used.

[0277] Alternative embodiments of the network node 1060 can include additional components not shown in FIG. 10 that can be responsible for providing certain aspects of the network node’s functionality, including any of the functions described herein and / or any functionality necessary to support the subject matter described herein. For example, the network node 1060 can include user interface Figure 18 For example, the network node 1060 can include user interface devices to allow input of information into network node 1060 and to allow output of information from network node 1060. This can allow a user to perform diagnostic, maintenance, repair, and other administrative functions for network node 1060.

[0278] As used herein, wireless device (WD) refers to a device capable, configured, arranged and / or operable to communicate wirelessly with network nodes and / or other wireless devices. Unless otherwise mentioned, the term WD can be used interchangeably herein with user equipment (UE), and user equipment (UE). The wireless communication can involve sending and / or receiving wireless signals using electromagnetic waves, radio waves, infrared waves, and / or other types of signals suitable for conveying information through air. In some embodiments, a WD can be configured to transmit and / or receive information without direct human interaction (e.g., automatically). For instance, a WD can be designed to transmit information to a network node on a predetermined schedule, in response to detected events, and / or in response to requests from the network. Examples of a WD include, but are not limited to, a smart phone, a mobile phone, a cell phone, a voice over IP (VoIP) phone, a wireless local loop phone, a desktop computer, a personal digital assistant (PDA), a wireless cameras, a gaming console or device, a music storage device, a playback appliance, a wearable terminal device, a wireless endpoint, a mobile station, a tablet, a laptop, a laptop-embedded equipment (LEE), a laptop-mounted equipment (LME), a smart device, a wireless customer-premise equipment (CPE), a vehicle-mounted wireless terminal device, etc. A WD can support device-to-device (D2D) communication, e.g., using proximity services (ProSe) or traffic advertisement, as an example. D2D communication can be achieved via a direct link between WDs, e.g., without necessarily relying on a base station for information transfer. D2D communication can be through any suitable medium or media. As a particular example, in a vehicle-to-vehicle (V2V), vehicle-to-infrastructure (V2I), or vehicle-to-everything (V2X) scenario, D2D communication can be used between a WD and a road side unit (RSU). As another particular example, in an Internet of Things (IoT) scenario, a WD can represent a machine or other device that performs monitoring and / or measurements, and transmits the results of such monitoring and / or measurements to another WD and / or a network node. In this case, the WD can be implemented as an M2M device, which can be referred to as an MTC device in a 3GPP context. As a particular example, a WD can be a UE implementing the 3GPP narrow band IoT (NB-IoT) standard. Particular examples of such machines or devices are sensors, metering devices, industrial machinery, or home or personal appliances (e.g., refrigerators, televisions, etc.), personal wearables (e.g., watches, fitness trackers, etc.). In other scenarios, a WD can represent a vehicle or other equipment that is capable of monitoring and / or reporting on its operational status or other functions associated with its operation. A WD as described above can represent the endpoint of a wireless connection, in which case the device can be referred to as a wireless terminal. Furthermore, a WD as described above can be mobile, in which case it can also be referred to as a mobile device or mobile terminal.

[0279] As illustrated, wireless device 1010 includes antenna 1011, interface 1014, processing circuitry 1020, device readable medium 1030, user interface equipment 1032, auxiliary equipment 1034, power source 1036 and power circuitry 1037. WD 1010 can include multiple sets of one or more of the illustrated components for different wireless technologies supported by WD 1010, such as, for example, GSM, WCDMA, LTE, NR, WiFi, WiMAX, or Bluetooth wireless technologies, just to mention a few. These technologies can be integrated into the same or different chips or set of chips as other components within WD 1010.

[0280] Antenna 1011 can include one or more antennas or antenna arrays, configured to send and / or receive wireless signals, and is connected to interface 1014. In certain alternative embodiments, antenna 1011 can be separate from WD 1010 and be connectable to WD 1010 through an interface or port. Antenna 1011, interface 1014, and / or processing circuitry 1020 can be configured to perform any receiving or transmitting described herein as being performed by a WD. Any information, data and / or signals can be received from a network node and / or another WD. In some embodiments, radio front end circuitry and / or antenna 1011 can be considered an interface.

[0281] As illustrated, interface 1014 includes radio front end circuitry 1012 and antenna 1011. Radio front end circuitry 1012 includes one or more filters 1018 and amplifiers 1016. Radio front end circuitry 1014 is connected to antenna 1011 and processing circuitry 1020 and is configured to condition signals communicated between antenna 1011 and processing circuitry 1020. Radio front end circuitry 1012 can be coupled to or a part of antenna 1011. In some embodiments, WD 1010 can not include separate radio front end circuitry 1012; rather, processing circuitry 1020 can comprise radio front end circuitry and can be connected to antenna 1011. Similarly, in some embodiments, some or all of RF transceiver circuitry 1022 can be considered a part of interface 1014. Radio front end circuitry 1012 can receive digital data that is to be sent over a wireless connection to another network node or WD. Radio front end circuitry 1012 can convert the digital data into a wireless signal having the appropriate channel and bandwidth parameters using a combination of filters 1018 and / or amplifiers 1016. The wireless signal can then be transmitted via antenna 1011. Similarly, when receiving data, antenna 1011 can collect wireless signals, which are then converted into digital data by radio front end circuitry 1012. The digital data can be passed to processing circuitry 1020. In other embodiments, the interface can comprise different components and / or different combinations of components.

[0282] Processing circuitry 1020 can comprise a combination of one or more of a microprocessor, controller, microcontroller, central processing unit, digital signal processor, application-specific integrated circuit, field programmable gate array, or any other suitable computing device, resource, or combination of hardware, software and / or encoded logic operable to provide WD 1010 functionality either alone or in combination with other WD 1010 components (such as device readable medium 1030). Such functionality can include providing any of the various wireless features or benefits discussed herein. For example, processing circuitry 1020 can execute instructions stored in device readable medium 1030 or in memory within processing circuitry 1020 to provide the functionality disclosed herein.

[0283] As illustrated, processing circuitry 1020 includes one or more of RF transceiver circuitry 1022, baseband processing circuitry 1024, and application processing circuitry 1026. In other embodiments, the processing circuitry can comprise different components and / or different combinations of components. In certain embodiments, processing circuitry 1020 of WD 1010 can comprise a SOC. In some embodiments, RF transceiver circuitry 1022, baseband processing circuitry 1024, and application processing circuitry 1026 can be on separate chips or sets of chips. In alternative embodiments, part or all of baseband processing circuitry 1024 and application processing circuitry 1026 can be combined into one chip or set of chips, and RF transceiver circuitry 1022 can be on a separate chip or set of chips. In yet another alternative embodiment, part or all of RF transceiver circuitry 1022 and baseband processing circuitry 1024 can be on the same chip or set of chips, and application processing circuitry 1026 can be on a separate chip or set of chips. In still even another alternative embodiment, part or all of RF transceiver circuitry 1022, baseband processing circuitry 1024, and application processing circuitry 1026 can be combined in the same chip or set of chips. In some embodiments, RF transceiver circuitry 1022 can be a part of interface 1014. RF transceiver circuitry 1022 can condition signals for processing circuitry 1020.

[0284] In certain embodiments, some or all of the functionality described herein as being performed by a WD can be performed by processing circuitry 1020 executing instructions stored on device readable medium 1030, which in certain embodiments can be a computer-readable storage medium. In alternative embodiments, some or all of the functionality can be provided by processing circuitry 1020 without executing instructions stored on a separate or discrete device readable medium, such as, for example, in a hard-wired device or in a device configured with hard-wired logic and / or circuitry. In any of these particular embodiments, whether

[0285] Processing circuitry 1020 can be configured to perform any determining, calculating, or similar operations (e.g., certain obtaining operations) described herein as being performed by a WD. These operations, as performed by processing circuitry 1020, can include processing information obtained by processing circuitry 1020 by, for example, converting the obtained information into other information, comparing the obtained information or converted information to information stored by WD 1010, and / or performing one or more operations based on the obtained information or converted information, and as a result of said processing, making a determination.

[0286] Device readable medium 1030 can be operable to store a computer program, software, including one or more of logic, rules, code, tables, etc. and / or other instructions capable of being executed by processing circuitry 1020. The medium 1030 can include computer memory (e.g., Random Access Memory

[0287] User interface equipment 1032 can provide components that allow for a human user to interact with WD 1010. Such interaction can be of many forms, such as visual, auditory, verbal, tactile, etc. User interface equipment 1032 can operate to produce output to the user and to capture input from the user. The type of interaction can vary from one implementation to another, depending on the design and capabilities of WD 1010. For example, if WD 1010 is a smart phone, the interaction can be through a touch screen; if WD 1010 is a smart meter, the interaction can be through a screen providing usage (e.g., the number of gallons used) or a speaker providing auditory alerts (e.g., if smoke is detected). User interface equipment 1032 can include input interfaces, devices and circuits, and output interfaces, devices and circuits. User interface equipment 1032 is configured to allow input of information into WD 1010, and is connected to processing circuitry 1020 to allow processing circuitry 1020 to process the input information. User interface equipment 1032 can include, for example, a microphone, a proximity or other sensor, keys / buttons, a touch display, one or more cameras, a USB port or other input circuitry. User interface equipment 1032 is also configured to allow output of information from WD 1010, and to allow processing circuitry 1020 to output information from WD 1010. User interface equipment 1032 can include, for example, a speaker, a display, vibrating circuitry, a USB port, a headphone

[0288] Auxiliary equipment 1034 is operable to provide more specific functionality which can not be generally performed by WDs. This can comprise dedicated sensors for measuring

[0289] In some embodiments, power source 1036 can be in the form of a battery or battery pack. Other types of power sources, such as an external power source (e.g., an electricity outlet), photovoltaic devices or power cells, can also be used. WD 1010 can further comprise power circuitry 1037 for delivering power from power source 1036 to the various accessories of WD 1010 that require power from power source 1036 to perform their functions. In some embodiments, power circuitry 1037 can include power management circuitry. Power circuitry 1037 can additionally or alternatively be operable to receive power from an external power source; in which case WD 1010 can be connectable to the external power source (such as an electricity outlet) by an interface or port, e.g., an electrical cable, etc. In some embodiments, power circuitry 1037 can also be operable to deliver power from an external power source to power source 1036. This could be, for example, for the purpose of recharging power source 1036. Power circuitry 1037 can perform any formatting, converting, or other modification to the power from power source 1036 as is required to make the power suitable for the respective components of WD 1010 that are being powered.

[0290] Figure 19 is a schematic diagram illustrating a user equipment according to some embodiments.

[0291] Figure 19 One embodiment of a UE is illustrated in accordance with various aspects described herein. As used herein, a user equipment or UE can not necessarily have a user in the sense of a human user that owns and / or operates the relevant device. Instead, a UE can represent a device that is intended for sale to, or operation by, an end user but that can not or initially can not be associated with a specific human user (e.g., a smart sprinkler controller). Alternatively, a UE can represent a device that is not intended for sale to, or operation by, an end user but that can be associated with or operated for the benefit of a user (e.g., a smart electric meter). UE 1100 can be any UE identified by the Third Generation Partnership Project (3GPP) including a NB-IoT UE, a machine type communication (MTC) UE, and / or an enhanced MTC (eMTC) UE. As shown, UE 1100 is one example of a WD configured for communication in accordance with one or more communication standards promulgated by the Third Generation Partnership Project (3GPP), such as 3GPP's GSM, UMTS, LTE, and / or 5G standards. As Figure 19 The above-identified components can be housed in a common housing or separate housings. As described elsewhere herein, the UE 1100 is not limited to any specific combination of components. Figure 19 The components discussed above in relation to the UE are equally applicable in relation to the WD.

[0292] In Figure 19In particular embodiments, UE 1100 includes processing circuitry 1101 operatively coupled to input / output interface 1105, radio frequency (RF) interface 1109, network connection interface 1111, memory 1115 (including random access memory (RAM), read only memory (ROM), and storage medium 1121, etc.), communication subsystem 1131, power source 1133, and / or any other component, or any combination thereof. Storage medium 1121 includes operating system 1123, application program 1125, and data 1127. In other embodiments, storage medium 1121 can include other similar types of information. Certain UEs can utilize all of the components shown in FIG. 11, or only a subset of the components. The level of integration between the components can vary from one UE to another UE. Furthermore, a certain UE can contain multiple instances of a component, such as multiple processing cores, multiple transceivers, etc. Figure 19 In particular embodiments, processing circuitry 1101 can be configured to process computer instructions and data. Processing circuitry 1101 can be configured to implement any sequential state machine operative to

[0293] In particular embodiments, processing circuitry 1101 can be configured to process computer instructions and data. Processing circuitry 1101 can be configured to implement any sequential state machine operative to Figure 19 In particular embodiments, processing circuitry 1101 can be configured to process computer instructions and data. Processing circuitry 1101 can be configured to implement any sequential state machine operative to

[0294] In the depicted embodiment, input / output interface 1105 can be configured to provide a communication interface to input and output devices. UE 1100 can be configured to use output devices through input / output interface 1105. Output devices can use the same type of interface port as input devices. For example, a USB port can be used to provide input to and output from UE 1100. The output device can be a speaker, a sound card, a video card, a display, a monitor, a printer, an actuator, an emitter, a smartcard, another output device, or any combination thereof. UE 1100 can be configured to use input devices through input / output interface 1105 to allow a user to capture information into UE 1100. Input devices can include a touch-sensitive or presence-sensitive display, a camera (for example, a digital still or motion camera), a microphone, a sensor, a mouse, a trackball, a directional key, a trackpad, a scroll wheel, a smartcard, and the like. The presence-sensitive display can include a capacitive or resistive touch sensor to sense input from a user. For example, the sensor can be an accelerometer, a gyroscope, a tilt sensor, a force sensor, a magnetometer, an optical sensor, a proximity sensor, another like sensor, or any combination thereof. For example, the input device can be an accelerometer, a magnetometer, a digital camera, a microphone, and an optical sensor.

[0295] In Figure 19 RF interface 1109 can be configured to provide a communication interface to RF components such as a transmitter, a receiver, and an antenna. Network connection interface 1111 can be configured to provide a communication interface to network 1143a. Network 1143a can encompass

[0296] The RAM 1117 can be configured to interface to the processing circuitry 1101 over the bus 1102 to provide storage or caching of data or computer instructions downloaded from the network 1108 or stored on the storage medium 1121, during execution of software programs such as the operating system, application programs, and device drivers. The ROM 1119 can be configured to interface to the processing circuitry 1101 to provide storage for instructions or data, typically used by the processing circuitry 1101 to boot up or initialize the UE 1100. The storage medium 1121 can be configured to include a number of physical drive units, such as redundant array of independent disks (RAID), floppy disk drive, flash memory, USB flash drive, external hard disk drive, thumb drive, pen drive, key drive, high-density digital versatile disc (HD-DVD) optical disc drive, Blu-ray optical disc drive, holographic optical disc drive, internal hard disk drive, external mini-dual in-line memory module (DIMM), synchronous dynamic random access memory (SDRAM), external micro- DIMM SDRAM, smartcard memory such as a subscriber identity module or a removable user identity (SIM / RUIM) module, other memory, or any combination thereof. The storage medium 1121 can allow the UE 1100 to access computer-executable instructions, application programs or the like, stored on non-transitory storage media to off-load data or instructions from the processing circuitry 1101. A manufacturing

[0297] The storage medium 1121 can be configured to include a number of physical drive units, such as redundant array of independent disks (RAID), floppy disk drive, flash memory, USB flash drive, external hard disk drive, thumb drive, pen drive, key drive, high-density digital versatile disc (HD-DVD) optical disc drive, Blu-ray optical disc drive, holographic optical disc drive, internal hard disk drive, external mini-dual in-line memory module (DIMM), synchronous dynamic random access memory (SDRAM), external micro- DIMM SDRAM, smartcard memory such as a subscriber identity module or a removable user identity (SIM / RUIM) module, other memory, or any combination thereof. The storage medium 1121 can allow the UE 1100 to access computer-executable instructions, application programs or the like, stored on non-transitory storage media to off-load data or instructions from the processing circuitry 1101. A manufacturing

[0298] In Figure 19In particular embodiments, processing circuitry 1101 can be configured to communicate with network 1143b using communication subsystem 1131. Network 1143a and network 1143b can be the same network or multiple networks, or different networks, or multiple networks. Communication subsystem 1131 can be configured to include one or more transceivers used to communicate with network 1143b. For example, communication subsystem 1131 can be configured to include one or more transceivers used to communicate with one or more remote transceivers of another device capable of wireless communication such as another WD, UE, or base station of a radio access network (RAN) according to one or more communication protocols, such as IEEE 802.11, CDMA, WCDMA, GSM, LTE, UTRAN, WiMax, or the like. Each transceiver can include transmitter 1133 and / or receiver 1135 to implement transmitter or receiver functions of the transceiver, respectively, appropriate to the RAN links (e.g., frequency allocations and the like). Further, transmitter 1133 and receiver 1135 of each transceiver can share circuit components, software, or firmware, or can be fully

[0299] In the illustrated embodiment, communication functions of communication subsystem 1131 can include data communication, voice communication, multimedia communication, short-range communications, near-field communication, location-based communication such as the use of the global positioning system (GPS) to determine a location, another like function, or any combination thereof. For example, communication subsystem 1131 can include cellular communication, Wi-Fi communication, Bluetooth communication, and GPS communication. Network 1143b can encompass wired and / or wireless networks such as a local-area network (LAN), a wide-area network (WAN), a computer network, a wireless network, a telecommunications network, another like network, or any combination thereof. For example, network 1143b can be a cellular network, a Wi-Fi network, and / or a near-field network. Power source 1113 can be configured to supply AC or DC power to components of UE 1100.

[0300] The features, benefits and / or functions described herein can be implemented in one of the components of UE 1100 or divided among several components of UE 1100. Further, the features, benefits, and / or functions described herein can be implemented in any combination of hardware, software or firmware. In one example, communication subsystem 1131 can be configured to include any of the components described herein. Further, processing circuitry 1101 can be configured to communicate with any of such components over bus 1102. In another example, any of such components can be represented by program instructions stored in memory that, as executed by processing circuitry 1101, perform the corresponding functions described herein. In another example, any of the functionality of such components can be partitioned between processing circuitry 1101 and communication subsystem 1131. In another example, non-computationally intensive functions of any of such components can be implemented in software or firmware and computation-intensive functions can be implemented in hardware.

[0301] Figure 20 is a schematic diagram illustrating a virtualization environment, in accordance with some embodiments.

[0302] Figure 20 is a schematic block diagram illustrating a virtualization environment 1200 in which functions implemented by some embodiments can be virtualized. In this context, virtualization means the creation of a virtual version of a device or of a physical machine, which can include virtualization of hardware platforms, storage devices and network resources. As used herein, virtualization can apply to a node (e.g., a virtualized base station or a virtualized radio access node) or to a device (e.g., a UE, a wireless device or any other type of communication device) or components thereof, and involves the implementation of at least a portion of the functions in a virtual environment (e.g., through one or more applications, components, functions, virtual machines or containers running on one or more physical processing nodes in one or more networks).

[0303] In some embodiments, some or all of the functions described herein can be implemented as virtual components executed by one or more virtual machines implemented in one or more virtual environments 1200 hosted by one or more hardware nodes 1230. Further, in embodiments in which the virtual node is not a radio access node or does not require radio connectivity (e.g., a core network node), then the network node can be entirely virtualized.

[0304] The functions can be implemented by one or more applications 1220 (which can alternatively be called software instances, virtual appliances, network functions, virtual nodes, virtual network functions, etc.) operative to implement some of the features, functions, and / or benefits of some of the embodiments disclosed herein. The applications 1220 are run in a virtualization environment 1200 which provides hardware 1230 comprising processing circuitry 1260 and memory 1290. The memory 1290 stores instructions 1295 executable by the processing circuitry 1260, whereby the applications 1220 is operative to provide one or more features, benefits, and / or functions disclosed herein.

[0305] The virtualization environment 1200 includes general-purpose or special-purpose network hardware devices 1230 comprising a set of one or more processors or processing circuitry 1260, which can be commercial off-the-shelf (COTS) processors, dedicated Application-Specific Integrated Circuits (ASICs), or any other type of processing circuitry including digital or analog hardware components or special purpose processors. Each hardware device can include memory 1290-1 which can be non-persistent memory used for storage of instructions 1295 or software executed by the processing circuitry 1260. Each hardware device can include one or more network interface controllers (NICs) 1270, also commonly referred to as network interface cards, which include physical network interfaces 1280. Each hardware device can also include non-transitory, persistent, machine-readable storage media 1290-2 having stored therein software 1295 and / or instructions executable by processing circuitry 1260. The software 1295 can include any type of software including software allowing instance(s) of virtualization layer 1250 (also referred to as a hypervisor) to be instantiated, software allowing virtual machines 1240 to be started, and software allowing the functions, features and / or benefits of some embodiments described herein to be

[0306] Virtual machines 1240 comprise virtual processing, virtual storage, virtual networks or interfaces and virtual storage, and can be run by a corresponding virtualization layer 1250 or hypervisor. Different embodiments of the instances of virtual appliances 1220 can be implemented on one or more of virtual machines 1240 and can be implemented in different ways.

[0307] During operation, processing circuitry 1260 executes software 1295 to instantiate the hypervisor or virtualization layer 1250, which can sometimes be referred to as a virtual machine monitor (VMM). Virtualization layer 1250 can present a virtual operating platform that appears like networking hardware to virtual machine 1240.

[0308] As Figure 20As shown, hardware 1230 can be a standalone network node with generic or specific components. Hardware 1230 can comprise antenna 12225 and can implement some functions through virtualization. Alternatively, hardware 1230 can be part of a larger cluster of hardware (e.g., in a data center or customer premises equipment (CPE)) where many hardware nodes work together and are managed by management and orchestration (MANO) 12100 that, among others, oversees lifecycle management of applications 1220.

[0309] Virtualization of the hardware is in some contexts referred to as Network Function Virtualization (NFV). NFV can be used to consolidate many network equipment types onto industry standard high volume server hardware, physical switches and physical storage, which can be located in data centers, and customer premise equipment.

[0310] In the context of NFV, virtual machine 1240 can be a software implementation of a physical machine that executes programs as if they were running on the physical, non-virtualized

[0311] Still in the context of NFV, Virtual Network Function (VNF) is responsible for handling specific network functions that are executed in one or more virtual machines 1240 on top of hardware networking infrastructure 1230 and corresponds to Figure 20 application 1220 in

[0312] In some embodiments, one or more radio units 12200 that each include one or more transmitters 12220 and one or more receivers 12210 can be coupled to one or more antennas 12225. Radio units 12200 can communicate directly with hardware nodes 1230 over one or more appropriate networks and can be used in combination with virtual components to provide a virtual node with radio capabilities such as a radio access node or a base station.

[0313] In some embodiments, some signaling can be effected with the use of control system 12230 which can alternatively be used for communication between hardware nodes 1230 and radio units 12200.

[0314] Figure 21 is a schematic diagram illustrating a telecommunication network connected via an intermediate network to a host computer, according to some embodiments.

[0315] Referring to Figure 21According to an embodiment, the communication system includes a telecommunication network 1310, such as a 3GPP-type cellular network, which comprises access networks 1311, such as radio access networks, and a core network 1314. The access network 1311 comprises a plurality of base stations 1312a, 1312b, 1312c, such as NBs, eNBs, gNBs or other types of wireless access points, each defining a corresponding coverage area 1313a, 1313b, 1313c. Each base station 1312a, 1312b, 1312c can be connected to the core network 1314 via a wired or wireless connection 1315. A first UE 1391 located in coverage area 1313c is configured to wirelessly connect to, or be paged by, the corresponding base station 1312c. A second UE 1392 located in coverage area 1313a is wirelessly connectable to the corresponding base station 1312a. While a plurality of UEs 1391, 1392 are illustrated in this example, the disclosed embodiments are equally applicable to a situation where a sole UE is in the coverage area or where a sole UE is connecting to the corresponding base station 1312.

[0316] The telecommunication network 1310 is itself connected to a host computer 1330, which can be embodied in hardware and / or software and can be embodied as a standalone server, a cloud-implemented server, or a distributed server. The host computer 1330 can be controlled by a service provider or be operated by a service provider on behalf of a user. Connections 1321 and 1322 between the telecommunication network 1310 and the host computer 1330 can be direct or indirect, wired or wireless, and can involve intermediate devices. The intermediate devices can include other computers, servers, routers, and switches, among other possibilities. The intermediate devices can be owned or operated by the service provider or by a third party, and can include devices from multiple providers.

[0317] Figure 21The communication system as a whole enables connectivity between the connected UEs 1391, 1392 and the host computer 1330. The connectivity can be described as an over-the-top (OTT) connection 1350. The host computer 1330 and the connected UEs 1391, 1392 are configured to communicate data and / or signaling using the OTT connection 1350 via the base station 1312, the core network 1314, any intermediate network 1320, and possible further infrastructure (not shown) as the intermediate media for the OTT connection 1350. The OTT connection 1350 can be transparent in the sense that the participating communication devices through which the OTT connection 1350 passes are unaware of the routing of uplink and downlink communications. For example, a base station 1312 can not or need not be aware of the past routing of an incoming downlink communication with data originating from a host computer 1330 to be forwarded (e.g., handed over) to a connected UE 1391. Similarly, the base station 1312 need not be aware of the future routing of an outgoing uplink communication originating with a UE 1391 to be forwarded (e.g., handed over) to the host computer 1330.

[0318] Figure 22 is a schematic diagram illustrating a host computer communicating via a base station with a user equipment over a partially wireless connection in accordance with some embodiments.

[0319] Example implementations, in accordance with an embodiment, of the UE, base station, and host computer discussed in the preceding paragraphs will now be described with reference to the Figure 22 The example implementations of the UE, base station, and host computer discussed in the preceding paragraphs will now be described with reference to Figure 14. In a communication system 1400, a host computer 1410 is connected to a base station 1412 that in turn is connected to a UE 1430. The host computer 1410, the base station 1412, and the UE 1430 can be examples of the host computer 1330, the base station 1312, and the UE 1391, 1392, respectively, described in reference to Figure 13. The host computer 1410 and the UE 1430 are configured to set up, maintain, and release a connection 1450 (also referred to as an“RRC connection”) between them using a set of RRC messages. The connection 1450 can be a logical connection through the base station 1412. A set of RRC messages can be used to establish the connection 1450, modify the

[0320] The communication system 1400 further includes the base station 1420 provided in a telecommunication system and comprising hardware 1425 enabling it to communicate with the host computer 1410 and with the UE 1430. The hardware 1425 can include a communication interface 1426 for Figure 22 establishing and maintaining a wired or wireless connection with the different communication devices of the communication system 1400 as well as a radio interface 1427 for establishing and maintaining at least wireless connection 1470 with the UE 1430 located in a coverage area 1441 of the base station 1420 (not shown in FIG. 14). The communication interface 1426 can be configured to facilitate a connection 1460 to the host computer 1410. The connection 1460 can be direct or it can pass through the core network (not shown in FIG. 14) of the telecommunication system and / or through one or more intermediate networks outside the telecommunication system. In the embodiment shown, the hardware 1425 of the base station 1420 further includes processing circuitry 1428, which can comprise one or more programmable processors, application-specific integrated circuits, field programmable gate arrays or combinations of these (not shown) adapted to execute instructions. The base station 1420 further has software 1421 stored internally or accessible via an external connection. Figure 22

[0321] The communication system 1400 further includes the UE 1430 already referred to. Its hardware 1435 can include a radio interface 1437 configured to set up and maintain a wireless connection 1470 with a base station serving a coverage area in which the UE 1430 is currently located. The hardware 1435 of the UE 1430 further includes processing circuitry 1438, which can comprise one or more programmable processors, application-specific integrated circuits, field programmable gate arrays or combinations of these (not shown) adapted to execute instructions. The UE 1430 further comprises software 1431 stored internally or accessible via an external connection and executable by the processing circuitry 1438. The software 1431 includes a client application 1432. The client application 1432 can be for providing a service to a human or non-human user via the UE 1430, e.g., with the support of the host computer 1410. In the host computer 1410, an executing host application 1412 can communicate with the executing client application 1432 by way of the OTT connection 1450 terminating at the UE 1430 and the host computer 1410. In providing the service to the user, the client application 1432 can receive request data from the host application 1412 and provide user data in response to the request data. The OTT connection 1450 can carry both the request data and the user data. The client application 1432 can present the user data to the user of the UE 1430 and interact with the user to generate user input data in response to the presentation. The client application 1432 can provide the user input data to the host computer 1410 as user data.

[0322] Note that the base station 1420 in the embodiment shown is configured to operate in a wireless telecommunications system, but it is also capable of communicating with external networks, such as the Internet, e.g., for updating and / or receiving software updates. Figure 22 The host computer 1410, base station 1420, and UE 1430 illustrated in FIG. 14 can be in the form of a server computer, a base station, or a UE, respectively, as discussed above.​Figure 21 The host computer 1330, one of the base stations 1312a, 1312b, 1312c, and one of the UEs 1391, 1392 are respectively similar or identical to the host computer 1310, one of the base stations 1312a, 1312b, 1312c, and one of the UEs 1391, 1392 of the embodiments of Figure 22 Figs. 13 and 14. That is, the inner workings of these entities can be as shown in Figure 21 Figs. 13 and 14, and independently, the surrounding network topology can be that of

[0323] In the example of Fig. 14, the OTT connection 1450 has been drawn as a dashed line to indicate that, unlike the direct connection 1430 in the example of Fig. 13, the Figure 22 connection 1450 need not be a direct connection between the host computer 1410 and the UE 1430. That is, the OTT connection 1450 can be established via one or more

[0324] wireless connection 1470 between the UE 1430 and the base station 1420 is in accordance with the teachings of the embodiments described throughout this disclosure. One or more of the various embodiments improve the performance of OTT services provided to the UE 1430 using the OTT connection 1450, in which the wireless connection 1470 forms the last segment. More precisely, the teachings of these embodiments can improve the latency, and thereby provide benefits such as reduced user waiting time.

[0325] A measurement procedure can be provided for the purpose of monitoring data rate, latency and other factors on which the one or more embodiments improve. There can further be an optional network functionality to reconfigure OTT connection 1450 between host computer 1410 and UE 1430, in response to variations in the measurement results. The measurement procedure and / or the network functionality to reconfigure OTT connection 1450 can be implemented in software 1411 and hardware 1415 of host computer 1410 or in software 1431 and hardware 1435 of UE 1430, or both. In embodiments, sensors (not shown) can be deployed in or in association with communication devices through which OTT connection 1450 passes; the sensors can participate in the measurement procedure by supplying values of the monitored quantities exemplified above, or supplying values of other physical quantities from which software 1411, 1431 can compute or estimate the monitored quantities. The reconfiguring of OTT connection 1450 can include message format, retransmission settings, preferred routing, etc.; the reconfiguring need not affect base station 1420, and it can be unknown or invisible to the base station. Such procedures and functionalities are known in the art and put into practice. In certain embodiments, the measurement can involve proprietary UE signaling facilitating host computer 1410’s measurements of throughput, propagation times, latency and the like. The measurements can be implemented in software 1411, 1431 using OTT connection 1450 to transmit messages, especially empty or “dummy” messages, back and forth,

[0326] Figure 23 FIG. 1 is a schematic diagram illustrating a communication system in accordance with some embodiments.

[0327] Figure 23 FIG. 1 is a schematic diagram illustrating a communication system in accordance with some embodiments. Figure 23 FIG. 1 is a schematic diagram illustrating a communication system in accordance with some embodiments.

[0328] Figure 24is a schematic diagram illustrating methods implemented in a communication system including a host computer, a base station, and a user equipment according to some embodiments.

[0329] Figure 24 is a flowchart illustrating a method implemented in a communication system according to one embodiment. The communication system includes a host computer, a base station, and a UE. For simplicity and clarity, only drawing references to Figure 24 will be included in this section. In step 1610 of the method, the host computer provides user data. In an optional substep (not shown) the host computer provides the user data by executing a host application. In step 1620, the host computer initiates a transmission carrying the user data to the UE. The transmission can pass via the base station, in accordance with the teachings of the embodiments described throughout this disclosure. In step 1630 (which can be optional), the UE receives the user data carried in the transmission.

[0330] Figure 25 is a schematic diagram illustrating methods implemented in a communication system including a host computer, a base station, and a user equipment according to some embodiments.

[0331] Figure 25 is a flowchart illustrating a method implemented in a communication system according to one embodiment. The communication system includes a host computer, a base station, and a UE. For simplicity and clarity, this section includes only drawing references to Figure 25 In step 1710 (which can be optional), the UE receives input data provided by the host computer. Additionally or alternatively, in step 1720, the UE provides user data. In substep 1721 of step 1720 (which can be optional), the UE provides the user data by executing a client application. In substep 1711 of step 1710 (which can be optional), the UE executes a client application which provides the user data in reaction to the received input data provided by the host computer. In providing the user data, the executed client application can further consider user input received from the user. Regardless of the specific manner in which the user data was provided, the UE initiates, in substep 1730 (which can be optional), transmission of the user data to the host computer. In step 1740 of the method, the host computer receives the user data transmitted from the UE, in accordance with the teachings of the embodiments described throughout this disclosure.

[0332] Figure 26 is a schematic diagram illustrating methods implemented in a communication system including a host computer, a base station, and a user equipment according to some embodiments.

[0333] Figure 26is a flowchart illustrating a method implemented in a communication system, according to one embodiment. The communication system includes a host computer, a base station and a UE. For simplicity of the present disclosure, only drawing references to Figure 26 Fig. 18 will be included in this section. In step 1810 (which can be optional), in accordance with the teachings of the embodiments described throughout this disclosure, the base station receives user data from the UE. In step 1820 (which can be optional), the base station initiates transmission of the received user data to the host computer. In step 1830 (which can be optional), the host computer receives the user data carried in the transmission initiated by the base station.

[0334] According to an aspect of the present disclosure, there is provided a computer program product tangibly storing instructions and including instructions that, when executed by at least one processor, cause the at least one processor to perform any of the methods described above in relation to a network node.

[0335] According to an aspect of the present disclosure, there is provided a computer program product tangibly storing instructions and including instructions that, when executed by at least one processor, cause the at least one processor to perform any of the methods described above in relation to a network node.

[0336] According to an aspect of the present disclosure, there is provided a computer program product tangibly storing instructions and including instructions that, when executed by at least one processor, cause the at least one processor to perform any of the methods described above in relation to a network node.

[0337] According to an aspect of the present disclosure, there is provided a computer program product tangibly storing instructions and including instructions that, when executed by at least one processor, cause the at least one processor to perform any of the methods described above in relation to a network node.

[0338] Further, the present disclosure can also provide a carrier containing the aforementioned computer program which can be any of an electronic signal, optical signal, radio signal, or computer readable storage medium. The computer readable storage medium can be, for example, an optical disc, or an electronic storage device such as a RAM (Random Access Memory), ROM (Read-Only Memory), flash memory, magnetic tape, CD-ROM, DVD, Blu-ray Disc, etc.

[0339] The techniques described herein can be implemented by various means. For example, these techniques can be implemented in hardware (one or more apparatuses), firmware (one or more apparatuses), software (one or more modules), or combinations thereof. For a firmware or software implementation, the

[0340] The exemplary embodiments herein have been described with reference to the drawings, which are described above. It will be understood that each block of the block diagrams and flowchart illustrations, and combinations of blocks in the block diagrams and flowchart illustrations, can be implemented by various means, including computer program instructions. Such computer program instructions can be loaded into the general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions that execute on the computer or other programmable data processing apparatus create the means for implementing the functions specified in the flowchart block or blocks.

[0341] In addition, while operations can be depicted in the drawings in a particular order, this should not be understood as requiring that such operations be performed in the particular order shown or in sequential order, or that all illustrated operations be performed, to achieve desirable results. In certain circumstances, multitasking and parallel processing can be advantageous. Likewise, while several specific embodiments have been described, these should be considered as merely illustrative of the principles of the subject matter described herein, rather than as limitations on the scope of the subject matter described herein. Certain features that are described in the context of separate embodiments can also be implemented in combination in a single embodiment. Conversely, various features that are described in the context of a single embodiment can also be implemented in multiple embodiments separately or in any suitable sub-combination. Moreover, although the subject matter has been described in the context of particular embodiments, the subject matter described herein can be implemented in any number of ways, and is not limited to the particular embodiments described herein.

[0342] While this specification contains many specific implementation details, these should not be construed as limitations on the scope of any embodiments described herein but as descriptions of features that can be specific to particular embodiments. Certain features that are described in the context of separate embodiments can also be implemented in combination in a single embodiment. Conversely, various features that are described in the context of a single embodiment can also be implemented in multiple embodiments separately or in any suitable sub-combination. Moreover, although the subject matter has been described in the context of particular embodiments, other alternatives can occur to those skilled in the art. For example, in some embodiments, techniques suitable for use with a wired communication link can be employed in conjunction with those for a wireless link, and vice versa. Furthermore, some of the features described herein can be used to define a single embodiment. The terms "the" and "the one" and "one" and "an" and "a" and similar referents in the context of an individual embodiment are to be construed to cover both the singular and the plural, unless otherwise indicated. The indefinite articles "a" and "an" are used herein in a generic sense, and are not to be construed to be limited to a single instance of the individual item unless otherwise indicated. The terms "comprising," "having," "including," and "containing" are to be construed as open-ended terms (i.e., meaning "including, but not limited to,") unless otherwise noted. The indefinite articles "a" and "an" are used herein in a generic sense, and are not to be construed to be limited to a single instance of the individual item unless otherwise indicated. The terms "comprising," "having," "including," and "containing" are to be construed as open-ended terms (i.e., meaning "including, but not limited to,") unless otherwise noted. Recitation of ranges of values herein are not to be interpreted as expressly disclosing all values between the recited ranges. The disclosure of a single value of a parameter in the description section of this patent is not intended to discard all but one specific value. Rather, it is intended to recite "about" that single value. Furthermore, the foregoing description of various aspects of the subject matter described herein is provided for illustrative purposes only and is not intended to exhaust the possible embodiments, features, and features that can be realized and implemented.

[0343] It will be apparent to those skilled in the art that, with the progress of technology, the inventive concept can be implemented in various ways. The above-described embodiments are given for the purpose of description and not limitation of the present disclosure, and it is understood that modifications and variations can be made thereto by those skilled in the art without departing from the spirit and scope of the present disclosure as defined by the following claims. Such modifications and variations are considered to be within the scope of the present disclosure and the appended claims. The scope of protection of the present disclosure is defined by the appended claims.

Claims

1. A method (200) performed by a handover management entity, comprising: receiving (202) a handover request from a network node, wherein the handover request indicates that a first terminal device is to be handed over from a source cell to a target cell; obtaining (204) a location of the first terminal device; predicting (206) a handover outcome of the first terminal device by a classifier, wherein the location of the first terminal device is used as an input of the classifier, and the classifier is trained for the handover from the source cell to the target cell; generating (208) a handover decision based on the predicted handover outcome; and sending (210) a handover response including the handover decision to the network node, wherein the handover outcome comprises at least one of: too late handover; too early handover; handover to a wrong cell; or handover success.

2. The method of claim 1, wherein, The classifier is trained by a training set, and the training set comprises historical handover outcome data about the handover from the source cell to the target cell.

3. The method of claim 2, wherein, The training set further comprises handover outcome data about the handover from the source cell to the target cell generated by a generative adversarial network.

4. The method of claim 3, wherein, For a specific type of handover outcome, a corresponding type of generative adversarial network is trained by using a corresponding type of historical handover outcome data about the handover from the source cell to the target cell.

5. The method of any one of claims 2-4, wherein, The handover outcome data comprises: a location of a terminal device, a handover outcome, a source cell identifier, a target cell identifier, a wrong cell identifier when the terminal device is handed over to a wrong cell.

6. The method of claim 5, wherein, The handover outcome data further comprises at least one of: antenna information of the source cell, antenna information of the target cell, antenna information of the wrong cell, a relative position of the terminal device to an antenna of the source cell, a relative position of the terminal device to an antenna of the target cell, or a relative position of the terminal device to an antenna of the wrong cell. 7.The method of any one of claims 1-4 and 6, wherein when the predicted handover outcome indicates too late handover, the handover decision indicates the network node to lower handover trigger difficulty; or when the predicted handover outcome indicates handover success, the handover decision indicates the network node to immediately perform the handover; or when the predicted handover outcome indicates too early handover or handover to a wrong cell, the handover decision is further generated based on movement information of the first terminal device. 8.The method of claim 7, further comprising: obtaining (408) the movement information of the first terminal device.

9. The method of claim 8, wherein, The movement information of the first terminal device comprises at least one of: a moving speed of the first terminal device; a moving direction of the first terminal device; or an acceleration of the first terminal device.

10. The method of claim 7, wherein, When the handover decision is further generated based on the movement information of the first terminal device, when the first terminal device is to enter a handover success area at a specific time point, the handover decision indicates the specific time point for performing the handover to the network node; or when the first terminal device is to enter a handover failure area at a specific time point, the handover decision indicates the specific time point for postponing the handover to the network node. when the first terminal device is about to enter a handover success area at a certain point in time, the handover decision instructs the network node to perform the handover, wherein the response comprising the handover decision is sent to the network node at or after the certain point in time; or when the first terminal device is moving away from a handover success area, the handover decision comprises at least one recommended target cell and instructs the network node to perform a cell reselection based on the at least one recommended target cell.

11. The method of any one of claims 1-4, 6, and 8-10, further comprising: determining (410) at least one handover outcome area regarding the handover from the source cell to the target cell.

12. The method of any one of claims 1-4, 6, and 8-10, further comprising: receiving (402) at least a portion of historical handover outcome data from the network node.

13. The method of any one of claims 1-4, 6, and 8-10, wherein, the handover management entity is deployed into an open radio access network.

14. A method (500) performed by a network node, comprising: sending (504) a handover request to a handover management entity, wherein the handover request indicates a first terminal device is to be handed over from a source cell to a target cell; and receiving (506) a handover response comprising a handover decision from the handover management entity, wherein the handover decision is generated based on a predicted handover outcome of the first terminal device, and the predicted handover outcome of the first terminal device is predicted by a classifier, wherein a location of the first terminal device is used as an input to the classifier, and the classifier is trained for the handover from the source cell to the target cell, wherein the handover outcome comprises at least one of: too late handover; too early handover; handover to a wrong cell; or handover success.

15. The method of claim 14, wherein, the classifier is trained by a training set, and the training set comprises historical handover outcome data regarding the handover from the source cell to the target cell.

16. The method of claim 15, wherein, the training set further comprises handover outcome data regarding the handover from the source cell to the target cell generated by a generative adversarial network.

17. The method of claim 16, wherein, for a certain type of handover outcome, the corresponding type of generative adversarial network is trained by using a corresponding type of historical handover outcome data regarding the handover from the source cell to the target cell.

18. The method of any one of claims 15-17, wherein, the handover outcome data comprises: a location of a terminal device, a handover outcome, a source cell identifier, a target cell identifier, a wrong cell identifier when the terminal device is handed over to a wrong cell.

19. The method of claim 18, wherein, the handover outcome data further comprises at least one of: antenna information of the source cell, antenna information of the target cell, antenna information of the wrong cell, a relative position of the terminal device to an antenna of the source cell, a relative position of the terminal device to an antenna of the target cell, or a relative position of the terminal device to an antenna of the wrong cell.

20. The method of any one of claims 14-17 and 19, wherein when the predicted handover outcome indicates too late handover, the handover decision instructs the network node to lower handover trigger difficulty; or when the predicted handover outcome indicates handover success, the handover decision instructs the network node to immediately perform the handover; or when the predicted handover outcome indicates too early handover or handover to a wrong cell, the handover decision is further generated based on mobility information of the first terminal device.

21. The method of claim 20, wherein, The mobility information of the first terminal device comprises at least one of: a moving speed of the first terminal device; a moving direction of the first terminal device; or an acceleration of the first terminal device.

22. The method of claim 20, wherein, When the handover decision is generated further based on the mobility information of the first terminal device, when the first terminal device will enter a handover success area at a certain time point, the handover decision instructs the network node the certain time point for performing the handover; or when the first terminal device will enter a handover success area at a certain time point, the handover decision instructs the network node to perform the handover, wherein the response comprising the handover decision is sent to the network node at or after the certain time point; or when the first terminal device is moving away from a handover success area, the handover decision comprises at least one recommended target cell and instructs the network node to perform cell reselection based on the at least one recommended target cell.

23. The method of any one of claims 14-17, 19, and 21-22, further comprising: sending (502) at least a portion of historical handover outcome data to the handover management entity.

24. The method of any one of claims 14-17, 19, and 21-22, wherein, The handover management entity is deployed into an open radio access network.

25. A handover management entity, comprising: a processor; and a memory storing instructions executable by the processor, whereby the handover management entity is operative to: receive a handover request from a network node, wherein the handover request indicates that a first terminal device is to be handed over from a source cell to a target cell; obtain a location of the first terminal device; predict a handover outcome of the first terminal device by a classifier, wherein the location of the first terminal device is used as an input to the classifier and the classifier is trained for the handover from the source cell to the target cell; generate a handover decision based on the predicted handover outcome; and send a handover response comprising the handover decision to the network node, wherein the handover outcome comprises at least one of: too late handover; too early handover; handover to a wrong cell; or handover success. The handover management entity is operative to perform the method of any one of claims 2 to 13.

26. The handover management entity of claim 25, wherein, 27. A network node, comprising: a processor; and a memory storing instructions executable by the processor, whereby the network node is operative to: send a handover request to a handover management entity, wherein the handover request indicates that a first terminal device is to be handed over from a source cell to a target cell; and receive a handover response comprising a handover decision from the handover management entity, ​ ​ wherein the handover decision is generated based on a predicted handover outcome for the first terminal device, and the predicted handover outcome for the first terminal device is predicted by a classifier, wherein a location of the first terminal device is used as input to the classifier, and the classifier is trained for the handover from the source cell to the target cell, wherein the handover outcome comprises at least one of: too late handover; too early handover; handover to a wrong cell; or handover success.

28. The network node of claim 27, wherein, The network node is operative to perform the method according to any of claims 15-24.

29. A computer-readable storage medium storing instructions that, when executed by at least one processor, cause the at least one processor to perform the method according to any of claims 1-24.

30. A computer program product comprising instructions that, when executed by at least one processor, cause the at least one processor to perform the method according to any of claims 1-24.

Images