Allocation of contention-free random access preamble resources

Abstract

A method is disclosed, the method comprising: for each beam of a plurality of beams of a target cell, generating a metric indicating a probability that a user equipment performs a random access via the respective beam; and sending a handover message to a target access node of the target cell, wherein the handover message comprises at least one of the metrics.

Description

Technical Field

[0001] The following exemplary embodiments relate to cellular communication and performing a handover process. Background Technology

[0002] In cellular communication, user equipment (UE) can be served by the access node of the cell where the UE resides. Due to changes, such as cell deactivation or UE relocation making it unsuitable for service by that cell, a handover process can be performed, allowing the UE to be served by another cell. It is beneficial to execute this process as smoothly as possible. Summary of the Invention

[0003] The scope of protection sought by the various embodiments of the present invention is stated by the independent claims. Exemplary embodiments and features (if any) described in this specification that are not outside the scope of the independent claims are to be interpreted as examples useful for understanding the various embodiments of the invention. Then, a base station or any other suitable radio unit in a wireless digital communication network including multiple antennas for wireless communication to implement data transmission can use cross-polarized antennas to implement independent transmission paths for data transmission.

[0004] According to a first aspect, an apparatus is provided, the apparatus including components for performing the following operations: generating a metric for each of a plurality of beams of a target cell, indicating the probability that a user equipment performs random access via the respective beam; and sending a handover message to a target access node of the target cell, wherein the handover message includes at least one of the metrics.

[0005] In some example embodiments according to the first aspect, the component includes at least one processor and at least one memory storing instructions that, when executed by the at least one processor, are configured to cause execution of the means.

[0006] According to a second aspect, an apparatus is provided, comprising: at least one processor and at least one memory storing instructions that, when executed by the at least one processor, cause the apparatus to at least: generate, for each of a plurality of beams of a target cell, a metric indicating the probability of a user equipment performing random access via the corresponding beam; and send a handover message to a target access node of the target cell, wherein the handover message includes at least one of the metrics.

[0007] According to a third aspect, a method is provided, the method comprising: generating, for each of a plurality of beams in a target cell, a metric indicating the probability that a user equipment performs random access via the corresponding beam; and sending a handover message to a target access node in the target cell, wherein the handover message includes at least one of the metrics.

[0008] In some example embodiments according to the third aspect, the method is a computer-implemented method.

[0009] According to a fourth aspect, a computer program including instructions is provided that, when executed by a device, causes the device to perform at least the following operations: for each of a plurality of beams in a target cell, generating a metric indicating the probability of a user equipment performing random access via the corresponding beam; and sending a handover message to a target access node in the target cell, wherein the handover message includes at least one of the metrics.

[0010] According to a fifth aspect, a computer program is provided, the computer program including instructions stored thereon for at least performing the following operations: generating a metric for each of a plurality of beams of a target cell, indicating the probability of a user equipment performing random access via the corresponding beam; and sending a handover message to a target access node of the target cell, wherein the handover message includes at least one of the metrics.

[0011] According to a sixth aspect, a non-transitory computer-readable medium is provided comprising program instructions that, when executed by an apparatus, cause the apparatus to perform at least the following operations: for each of a plurality of beams of a target cell, generating a metric indicating the probability of a user equipment performing random access via the corresponding beam; and sending a handover message to a target access node of the target cell, wherein the handover message includes at least one of the metrics.

[0012] According to a seventh aspect, a non-transitory computer-readable medium is provided, the non-transitory computer-readable medium including program instructions stored thereon for at least performing the following operations: generating a metric indicating the probability of a user equipment performing random access via the corresponding beam for each of a plurality of beams of a target cell; and sending a handover message to a target access node of the target cell, wherein the handover message includes at least one of the metrics.

[0013] According to an eighth aspect, a computer-readable medium including program instructions is provided, which, when executed by an apparatus, cause the apparatus to perform at least the following operations: for each of a plurality of beams of a target cell, generating a metric indicating the probability of a user equipment performing random access via the respective beam; and sending a handover message to a target access node of the target cell, wherein the handover message includes at least one of the metrics.

[0014] According to a ninth aspect, a computer-readable medium is provided, the computer-readable medium storing thereon program instructions for at least performing the following operations: generating a metric indicating the probability of a user equipment performing random access via the corresponding beam for each of a plurality of beams of a target cell; and sending a handover message to a target access node of the target cell, wherein the handover message includes at least one of the metrics.

[0015] According to a tenth aspect, an apparatus is provided, comprising components for performing the following operations: receiving a handover message from a source access node, wherein the handover message includes: a metric for each of a plurality of beams of a target cell provided by the apparatus, the metric indicating the probability that a user equipment performs random access via the respective beam; allocating contention-free random access resources to the plurality of beams based on the metric; and sending an acknowledgment to the source access node regarding the handover message, wherein the acknowledgment includes the allocation of contention-free random access resources to the plurality of beams.

[0016] In some example embodiments according to the tenth aspect, the component includes at least one processor and at least one memory storing instructions that, when executed by the at least one processor, cause the device to perform.

[0017] According to an eleventh aspect, an apparatus is provided, the apparatus including at least one processor and at least one memory storing instructions, the instructions being configured, when executed by the at least one processor, to cause the apparatus to at least: receive a handover message from a source access node, wherein the handover message includes: a metric for each of a plurality of beams of a target cell provided by the apparatus, the metric indicating the probability that a user equipment performs random access via the respective beam; allocate contention-free random access resources to the plurality of beams based on the metric; and send an acknowledgment to the source access node regarding the handover message, wherein the acknowledgment includes the allocation of contention-free random access resources to the plurality of beams.

[0018] According to the twelfth aspect, a method is provided, the method comprising: receiving a handover message from a source access node, wherein the handover message includes: a metric for each of a plurality of beams of a target cell provided by a device, the metric indicating the probability that a user equipment performs random access via the respective beam; allocating contention-free random access resources to the plurality of beams based on the metric; and sending an acknowledgment to the source access node regarding the handover message, wherein the acknowledgment includes the allocation of contention-free random access resources to the plurality of beams.

[0019] In some example embodiments according to the twelfth aspect, the method is a computer-implemented method.

[0020] According to a thirteenth aspect, a computer program including instructions is provided that, when executed by an apparatus, causes the apparatus to perform at least the following operations: receiving a handover message from a source access node, wherein the handover message includes: a metric for each of a plurality of beams of a target cell provided by the apparatus, the metric indicating the probability that a user equipment will perform random access via the respective beam; allocating contention-free random access resources to the plurality of beams based on the metric; and sending an acknowledgment to the source access node regarding the handover message, wherein the acknowledgment includes the allocation of contention-free random access resources to the plurality of beams.

[0021] According to the fourteenth aspect, a computer program is provided, the computer program including instructions stored thereon for at least performing the following operations: receiving a handover message from a source access node, wherein the handover message includes: a metric for each of a plurality of beams of a target cell provided by a device, the metric indicating the probability that a user equipment performs random access via the respective beam; allocating contention-free random access resources to the plurality of beams based on the metric; and sending an acknowledgment to the source access node regarding the handover message, wherein the acknowledgment includes the allocation of contention-free random access resources to the plurality of beams.

[0022] According to a fifteenth aspect, a non-transitory computer-readable medium including program instructions, which, when executed by an apparatus, cause the device to perform at least the following operations: receiving a handover message from a source access node, wherein the handover message includes: a metric for each of a plurality of beams of a target cell provided by the device, the metric indicating the probability that a user equipment performs random access via the respective beam; allocating contention-free random access resources to the plurality of beams based on the metric; and sending an acknowledgment to the source access node regarding the handover message, wherein the acknowledgment includes the allocation of contention-free random access resources to the plurality of beams.

[0023] According to a sixteenth aspect, a non-transitory computer-readable medium is provided, the non-transitory computer-readable medium including program instructions stored thereon for at least performing the following operations: receiving a handover message from a source access node, wherein the handover message includes: a metric for each of a plurality of beams of a target cell provided by a device, the metric indicating the probability that a user equipment performs random access via the corresponding beam; allocating contention-free random access resources to the plurality of beams based on the metric; and sending an acknowledgment to the source access node regarding the handover message, wherein the acknowledgment includes the allocation of contention-free random access resources to the plurality of beams.

[0024] According to a seventeenth aspect, a computer-readable medium including program instructions is provided, which, when executed by an apparatus, cause the apparatus to perform at least the following operations: receiving a handover message from a source access node, wherein the handover message includes: a metric for each of a plurality of beams of a target cell provided by the apparatus, the metric indicating the probability that a user equipment performs random access via the respective beam; allocating contention-free random access resources to the plurality of beams based on the metric; and sending an acknowledgment to the source access node regarding the handover message, wherein the acknowledgment includes the allocation of contention-free random access resources to the plurality of beams.

[0025] According to the eighteenth aspect, a computer-readable medium is provided, the computer-readable medium including program instructions stored thereon for at least performing the following operations: receiving a handover message from a source access node, wherein the handover message includes: a metric for each of a plurality of beams of a target cell provided by a device, the metric indicating the probability that a user equipment performs random access via the respective beam; allocating contention-free random access resources to the plurality of beams based on the metric; and sending an acknowledgment to the source access node regarding the handover message, wherein the acknowledgment includes the allocation of contention-free random access resources to the plurality of beams.

[0026] List of Attachments The invention will now be described in more detail with reference to embodiments and accompanying drawings, in which: Figure 1 An example embodiment of a radio access network is shown.

[0027] Figure 2A A signaling diagram is shown according to an example embodiment of contention-based random access.

[0028] Figure 2B A signaling diagram is shown based on an example embodiment of contention-free random access.

[0029] Figure 3 An example embodiment of the condition switching process is shown.

[0030] Figure 4 An example embodiment of selecting a random access channel preamble is shown.

[0031] Figure 5 An example implementation of using a machine learning model to select contention-free random access resources to be allocated is shown.

[0032] Figure 6 A block diagram of an example embodiment selected based on the execution preamble is shown.

[0033] Figure 7 An example embodiment of a supervised learning autoencoder machine learning model is shown.

[0034] Figure 8 An example implementation of a training cycle of a supervised machine learning model is shown.

[0035] Figure 9 An example embodiment of the device is shown. Detailed Implementation

[0036] The following embodiments are exemplary. Although the specification may refer to "a," "an," or "some" embodiments in several places in the text, this does not necessarily mean that every reference is made to the same embodiment, or that a particular feature is applicable only to a single embodiment. Individual features of different embodiments may also be combined to provide other embodiments.

[0037] As used herein, the term "circuit system" refers to all of the following: (a) hardware circuit implementations only, such as implementations only in analog and / or digital circuit systems; and (b) combinations of circuits and software (and / or firmware), such as (where applicable): (i) combinations of (one or more) processors or (ii) portions of (one or more) processors / software, including (one or more) digital signal processors, software, and (one or more) memories working together to enable the device to perform various functions; and (c) circuits, such as (one or more) microprocessors or portions of (one or more) microprocessors, which require software or firmware to operate, even if the software or firmware is not physically present. This definition of "circuit system" applies to all uses of the term in this application. As another example, as used herein, the term "circuit system" will also cover implementations only of processors (or processors) or portions of processors and their accompanying software and / or firmware. For example, and if applicable to a particular element, the term "circuit system" will also cover baseband integrated circuits or application processor integrated circuits for use in mobile phones or servers, cellular network devices, or other network devices. The above embodiments of the circuit system can also be considered as embodiments of components providing embodiments for performing the methods or processes described in this document.

[0038] The techniques and methods described herein can be implemented by various means. For example, these techniques can be implemented in hardware (one or more devices), firmware (one or more devices), software (one or more modules), or a combination thereof. For hardware embodiments, the devices of the embodiments may be implemented in one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), graphics processing units (GPUs), processors, controllers, microcontrollers, microprocessors, other electronic units designed to perform the functions described herein, or combinations thereof. For firmware or software, implementation may be performed by modules of at least one chipset (e.g., processes, functions, etc.) that perform the functions described herein. Software code may be stored in memory cells and executed by a processor. Memory cells may be implemented within or outside the processor. In the latter case, it may be communicatively coupled to the processor via any suitable component. Furthermore, as those skilled in the art will appreciate, the components of the systems described herein may be rearranged and / or supplemented by additional components to facilitate the achievement of various aspects of their description, and are not limited to the precise configuration illustrated in the given figures.

[0039] The embodiments described herein can be implemented in communication systems, such as at least one of the following: Long Term Evolution (LTE), LTE Advanced, 5G mobile or cellular communication systems, 5G Advanced, and / or 6G. However, the embodiments are not limited to the systems given as examples, but those skilled in the art can apply this solution to other communication systems with the necessary properties.

[0040] Figure 1 An example of a simplified system architecture is depicted, showing some components and functional entities, all of which are logical units whose implementations may differ from those shown. Figure 1 The connections shown are logical connections; the actual physical connections may differ. It will be apparent to those skilled in the art that the system may also include, in addition to... Figure 1 Other functions and structures besides those shown. Figure 1 The example illustrates a portion of an example embodiment of a radio access network.

[0041] Figure 1Terminal devices 100 and 102 are illustrated, configured to wirelessly connect to an access node (e.g., (e / g)NodeB) 104 providing the cell on one or more communication channels within a cell. Terminal devices 100 and 102 may also be referred to as mobile devices, user equipment (UE), user terminals, user equipment, etc. Access node 104 may also be referred to as a node, base station, or any other type of interface device including relay stations capable of operating in a wireless environment. The physical link from the terminal device to the (e / g)NodeB is referred to as an uplink (UL) or backward link, and the physical link from the (e / g)NodeB to the terminal device is referred to as a downlink (DL) or forward link. It should be understood that the (e / g)B node or its functionality can be implemented using any entity suitable for such use, such as an access node, host, server, or access point. It should be noted that although one cell is discussed in this exemplary embodiment, for simplicity, in some example embodiments, multiple cells may be provided by one access node.

[0042] A communication system may include more than one (e / g)NodeB, in which case the (e / g)NodeBs may also be configured to communicate with each other via wired or wireless links designed for the purpose. These links may be used for signaling purposes. An (e / g)NodeB is a computing device configured to control the radio resources of the communication system to which it is coupled. An (e / g)NodeB includes or is coupled to a transceiver. From the transceiver of the (e / g)NodeB, a connection is provided to antenna elements that establish a bidirectional radio link to the user equipment. The antenna elements may include multiple antennas or antenna elements. The (e / g)NodeB is also connected to the core network 110 (CN or Next Generation Core NGC). Depending on the system, the CN-side counterpart may be a Serving Gateway (S-GW, routing and forwarding user data packets), a Packet Data Network Gateway (P-GW), or something similar, used to provide connectivity from terminal equipment to external packet data networks or Mobility Management Entities (MMEs).

[0043] The User Equipment (UE) illustrates a type of apparatus to which resources on the air interface are allocated and assigned, and therefore any features relating to the UE described herein can be implemented using corresponding apparatuses, such as relay nodes. An example of such a relay node is a Layer 3 relay (self-backhaul relay) oriented towards a base station. Another example of such a relay node is a Layer 2 relay. Such a relay node may include a UE portion and a Distributed Unit (DU) portion. For example, the CU (Centralized Unit) can coordinate DU operations via the F1AP interface.

[0044] UE can refer to a portable computing device that operates with or without a Subscriber Identity Module (SIM) or embedded SIM, eSIM, or wireless mobile communication device. UE can also be a device capable of operating in an Internet of Things (IoT) network, a scenario in which the ability to deliver data over a network to objects is provided without human-to-human or human-to-computer interaction is required. UE can also utilize cloud computing. UE (or, in some embodiments, a Layer 3 relay node) is configured to perform one or more user equipment functions. It should be noted that UE can also be a vehicle or home appliance capable of using cellular communications.

[0045] Furthermore, although the device has been described as a single entity, different units, processors, and / or memory units can be implemented. Figure 1 (Not shown in the image).

[0046] 5G enables the use of multiple-input multiple-output (MIMO) antennas, far more base stations or nodes than LTE (the so-called small cell concept), including macro sites cooperating with smaller stations, and employing a variety of radio technologies depending on service requirements, use cases, and / or available spectrum. 5G mobile communications support a wide range of use cases and related applications, including video streaming, augmented reality, different data sharing methods, and various forms of machine-type applications, such as (massive) machine-type communications (mMTC), including vehicle safety, various sensors, and real-time control. 5G is expected to have multiple radio interfaces: sub-6GHz, cmWave, and mmWave, and can also integrate with existing legacy radio access technologies such as LTE. Integration with LTE can be implemented as a system where macro coverage is provided by LTE, and 5G radio interface access originates from small cells via aggregation to LTE. In other words, 5G can support inter-RAT operability (such as LTE-5G) and inter-RI operability (inter-radio interface operability, such as sub-6GHz - cmWave, sub-6GHz - cmWave - mmWave). One of the concepts believed to be used in 5G networks is network slicing, in which multiple independent and dedicated virtual subnetworks (network instances) can be created within the same infrastructure to run services with different requirements for latency, reliability, throughput, and mobility.

[0047] The architecture in LTE networks is entirely distributed across the radio and entirely centralized in the core network. Low-latency applications and services in 5G may require content to be closer to the radio, potentially leading to local outages and multi-access edge computing (MEC). 5G enables analytics and knowledge generation to occur at the data source. MEC provides a distributed computing environment for application and service hosting. It also has the ability to store and process content near cellular subscribers for faster response times. Edge computing encompasses a wide range of technologies such as wireless sensor networks, mobile data acquisition, mobile signature analytics, collaborative distributed peer-to-peer self-organizing networking and processing, and can also be categorized as local cloud / fog computing and grid / mesh computing, dew computing, mobile edge computing, micro-cloud, distributed data storage and retrieval, autonomous self-healing networks, remote cloud services, augmented and virtual reality, data caching, the Internet of Things (massive connectivity and / or latency critical), and critical communications (autonomous vehicles, traffic safety, real-time analytics, time-critical control, healthcare applications).

[0048] The communication system is also capable of communicating with other networks (such as the public switched telephone network or the Internet 112) and / or utilizing services provided by them. The communication network can also support the use of cloud services; for example, at least a portion of the core network operation can be performed as a cloud service (this is in...). Figure 1 (Described by “Cloud” 114). Communication systems may also include a central control entity, etc., to provide facilities for different operators’ networks to collaborate, for example, in spectrum sharing.

[0049] By leveraging Network Functions Virtualization (NFV) and Software-Defined Networking (SDN), edge cloud can be brought into the Radio Access Network (RAN). Using edge cloud means performing access node operations, at least partially, within servers, hosts, or nodes operatively coupled to remote radio heads or base stations, including the radio portion. Node operations can also be distributed across multiple servers, nodes, or hosts. The application of the cloudRAN architecture enables real-time RAN functions to be executed on the RAN side (in the distributed unit DU 104), while non-real-time functions are executed centrally (in the centralized unit CU 108).

[0050] It should also be understood that the division of labor between core network operations and base station operations may differ from, or even not exist in, LTE. Some other technologies that can be used include, for example, big data and all-IP, which could change the way networks are being constructed and managed. 5G (or New Radio) networks are designed to support multiple tiers, where MEC servers can be placed between the core and base stations or nodeBs (gNBs). It should be understood that MEC can also be applied to 4G networks.

[0051] It should be noted that the depicted system is an example of a radio access system, and the system may include multiple (e / g) NodeBs, the UE may access multiple radio cells, and the system may also include other devices such as physical layer relay nodes or other network elements. Furthermore, multiple different types of radio cells and multiple radio cells may be provided within the geographical area of ​​the radio communication system. A radio cell can be a macrocell (or umbrella cell), which is a large cell, typically with a diameter of up to tens of kilometers, or a smaller cell, such as a microcell, femtocell, or picocell. Figure 1 The (e / g)NodeB can provide any type of these cells. A cellular radio system can be implemented as a multi-layered network comprising several types of cells. In some exemplary embodiments, in a multi-layered network, one access node provides one or more cells of one type, and therefore multiple (e / g)NodeBs are required to provide such a network structure.

[0052] The access node (such as a gNB) of the cell providing services to the UE can be understood as the serving access node of the providing cell, or the source access node of the providing source cell. When a UE handover is performed, the cell to which the UE is to hand over can be understood as the target cell provided by the target access node. Any suitable handover procedure (e.g., baseline handover procedure, conditional handover (CHO), or dual active protocol stack (DAPS)) can be used to trigger and execute the handover. During the handover procedure, a random access channel (RACH) procedure is performed. The RACH procedure can be contention-based random access (CBRA) or contention-free random access (CFRA).

[0053] Figure 2AAn example implementation of CBRA is shown. In this example implementation, for UE 200, the target cell is provided by access node 205, which is a gNB in ​​this example implementation, but it can also be any other suitable access node. First, UE 200 selects a RACH preamble from a configured set and sends the preamble 210 at one of the predetermined RACH timings. In response, access node 205 then sends 215 a Random Access Response (RAR) generated by the Medium Access Control (MAC) layer. The RAR can be used to provide the UE with information such as timing advance (TA), initial uplink (UL) grant, and assignment of a temporary cell-radio network temporary identifier (C-RNTI). Based on the received RAR, UE 200 then sends 220 a scheduled Physical Uplink Shared Channel (PUSCH) transmission to access node 205 using msg 3 (message 3). Access node 205 can then send 225 contention resolution to UE 200 using msg 4 (message 4). For example, if UE 200 loses contention due to, for example, a collision in preamble transmission, UE 200 will repeat the RACH procedure.

[0054] Figure 2B An example embodiment of CFRA is shown, in which UE 200 has access node 205 as its target access node, as in Figure 2A In an example embodiment, access node 205 configures UE 200 with a dedicated RACH preamble by sending 230 (Random Access Preamble Assignment). This can alternatively be performed via a source cell configured with a target cell including the dedicated RACH preamble. UE 200 then sends 240 (Dedicated RACH Preamble) at one of the pre-configured RACH timings. In response, access node 205 subsequently sends 250 (RAR). The RACH procedure is then completed when UE 200 successfully receives the RAR.

[0055] If the TA is known in the network or acquired before cell handover, the UE can send a Layer 3 (L3) message acknowledging a handover-related reconfiguration, such as a Radio Resource Control (RRC) reconfiguration that occurs immediately after receiving lower-layer signaling that triggered the cell change. The UE uses the acquired TA to send the L3 message acknowledging the reconfiguration to the target cell. To obtain the UL grant for sending the L3 message, two options can be used, for example. In the first option, the target cell can provide a semi-persistent PUSCH grant as part of the handover preparation. The target cell can then specify the UL TCI state that the UE will use to send the L3 message on the UL grant. Assuming the target cell may not know in advance which Quasi-Coexistence (QCL) Source Reference Signal (RS) indices are associated with the UL transmission during handover, the target cell can indicate multiple UL TCI states, each corresponding to the PUSCH grant. In the second option, the UE can monitor the UL grant provided by the selected target cell for handover execution. Based on the received measurements, the serving DU can then instruct the UE that it will perform a TCI state change on another prepared cell. Based on the received instruction, the UE then applies the configuration of the selected target cell and uses the QCL information of the indicated TCI state to monitor the UL-granted PDCCH from another ready cell that is now the new target cell. However, if the selected new target cell is under the control of another DU, the serving DU notifies the other DU of the TCI state that the UE will use to monitor the PDCCH. Using this information, the target DU can then use the QCL information of the indicated TCI state to transmit the PDCCH.

[0056] The switching process can be a conditional switching process (CHO). Figure 3 An example embodiment of CHO is shown. In this example embodiment, UE 300 is triggered by a configured event to send a measurement report 320 to the access node 310, which is its source access node. Based on this report, source access node 310 can then, in response to a decision 330, execute a CHO to prepare one or more target cells for handover. Source access node 310 then sends a CHO request 332 to target access node 312. Source access node 310 also sends a CHO request 334 to one or more other potential target access nodes 314. Target access node 312 then performs admission control 336, and additionally, other possible target nodes 314 perform admission control 338. In response, source access node 310 receives a first CHO request acknowledgment 340 from target access node 312. Accordingly, source access node 310 can also receive a second CHO request acknowledgment 342 from other target access nodes 314. Source access node 310 then sends an RRC reconfiguration 344 to the UE. RRC reconfiguration can be understood as a handover command.

[0057] In response, UE 300 then evaluates the 350 CHO condition, sends and receives 355 user data with the source access node 310 if possible, and accesses the target access node 312 once the CHO execution condition is met. In other words, the preparation for the handover phase and the execution phase are decoupled. This condition can be configured, for example, by the source access node 312 in the handover command. This allows UE 300 to send the handover command early while it is still safe in the source cell, and to postpone the execution of access to the target cell when it is stable, which in turn provides mobility robustness. Once UE 300 determines that the 360 ​​CHO condition is met, it stops sending to and receiving from the source access node 310.

[0058] Then, UE 300 sends a Physical Random Access Channel (PRACH) preamble (362) to target access node 312, receives 364 in response to the RACH response, and then sends an RRC reconfiguration completion (366) to target access node 312. Next, target access node 312 sends a handover success signaling (368) to source access node 310, which responds by stopping data transmission and reception from UE 300 (370) and initiating data forwarding, and sends a sequence number (SN) status indication (372) to target access node 312. Therefore, if source access node 310 receives 374 data from User Plane Function (UPF) 316, it forwards it to target access node 312. Source access node 310 can then send a 376 CHO indication of readiness to release to other potential target access nodes 314. Then, the source access node 310, the target access node 312, other target access nodes 314, UPF 316 and access management function (AMF) 318 perform the 380 path handover.

[0059] During a handover procedure, the UE can be configured to perform a CFRA towards the target cell. To do this, the target cell can indicate to the UE in the handover command a dedicated RACH preamble to be used for accessing the target cell. The RACH preamble can be associated with a corresponding beam of the target cell, and the beam can be identified via, for example, a synchronization signal block (SSB) and / or a channel state information-reference signal (CSI-RS). However, since the radio conditions of the target cell may change between the time the UE receives the CFRA preamble and the time the UE transmits the RACH preamble, a procedure for selecting the RACH preamble can be utilized. Figure 4An example embodiment of the process for selecting a RACH preamble is shown. First, in block 410, it is determined whether the UE has been configured by the network with a CFRA resource associated with a beam, which can be identified via their respective SSB / CSI-RS indices, using, for example, a handover command or another RRC message. The UE can then measure such beams, and if at least one of these SSB / CSI RSs has an L1-reference received signal strength (RSRP) higher than a certain threshold T1, then in block 412, the UE selects the beam with the associated SSB / CSI RS among those with an L1-RSRP higher than the threshold T1, and performs random access using the dedicated CFRA resource corresponding to the selected beam. If not, the UE can fall back to perform CBRA, as shown in block 420, and the UE first checks whether at least one beam associated with an SSB having an L1-RSRP higher than another threshold rsrp-ThresholdSSB is available. If so, in box 422, the UE selects a beam with an SSB having an L1-RSRP higher than the threshold; otherwise, the UE selects any beam, as shown in box 424. In both cases, the UE performs CBRA on the selected beam.

[0060] In summary, once the CFRA preamble has been received from the source access node, if the measurement indication signal quality is higher than the threshold T1, the UE can first measure the CFRA preamble resources, such as the corresponding SSB / CSI RS, and perform contention-free random access. Therefore, the UE can fall back to contention-based random access only if it is detected that the measurement indication CFRA preamble resources are not associated with signal quality above the threshold.

[0061] Therefore, in an example embodiment where a fallback from CFRA to CBRA is used in conjunction with a CHO, a beam associated with an SSB or CSI-RS is provided within the cell for the candidate target cell. The source cell receives a measurement report from the UE when the UE is served by the first beam of the source cell associated with, for example, SSB 1 (1 indicates the corresponding index), and forwards the measurement report to the target access node for handover. Using the measurement report, the target cell with the strongest DL reception measurement then prepares a CFRA preamble associated with, for example, a beam associated with SSB 8. The target cell then provides CFRA resources to the UE using a CHO command sent by the source access node. After receiving the CHO command, the UE moves, and the CHO execution is satisfied when the UE is served by, for example, a beam associated with SSB 3. When performing random access, the UE discards the prepared CFRA preamble associated with the beam associated with SSB 8 when its L1-RSRP falls below a threshold T1, and performs CBRA by selecting a CBRA preamble associated with another beam associated with another SSB (e.g., SSB 6), which has a much stronger L1-RSRP than SSB 8. It should be noted that in a CHO, the time difference between CHO preparation and execution can be at most a few seconds, which increases the likelihood of CBRA compared to a baseline handover where the UE performs RACH access shortly after receiving a handover command containing the prepared CFRA preamble. Therefore, allocating CFRA preambles during handover to maximize the likelihood of CFRA and minimize the likelihood of falling back to CBRA would be beneficial. It should be understood that this is a simplified embodiment with one SSB having CFRA resources. The target cell can assign CFRA resources on multiple beams based on measurement reports. In this scenario, the UE can use L1-RSRP measurements to search for multiple beams for CFRA resources that provide signal quality above a threshold T1 and use one of such CFRA resources for CFRA.

[0062] Machine learning (ML) can be used for CFRA allocation during handover, and a trained ML model can be run by the source access node, with the results then provided to the target access node to assist in allocating CFRA resources to the UE. An example of CFRA resources is the RACH preamble. The source access node can receive periodic L1 RSRP measurement reports from the UE for reference signaling, such as the SSB or CSI-RS of the serving cell and neighboring cells, enabling L1-triggered inter-cell mobility. This means the source access node will have more knowledge than the target access node, which receives the measurement reports when the measurement event is triggered. Furthermore, the source access node can configure periodic L3 RSRP measurements, including beam measurements, which can be used for CFRA resource allocation and also for other use cases such as predictive handover, load balancing, beam optimization meshes, etc. Therefore, in an example embodiment, the source access node can provide the target access node with metrics (such as a list of values ​​for each beam) provided by the target access node and identified via their respective SSBs and / or CSI-RS, indicating their expected superiority for random access. The superiority of random access can be understood as the probability, indicated by a metric, that a UE will perform random access via the beam indicating the superiority. Using this information, the target access node can then configure CFRA resources and allocate them to beams identified via their respective SSBs and / or CSI RSs. The target access node can then provide feedback on the accuracy of the capture superiority information regarding how the allocated CFRA resources corresponding to the beams perform. It should be noted that the generated metric can be based on a measurement report provided by the UE, as described above, or alternatively, based on the UE's location and motion trajectory. In some example embodiments, a combination of measurement reports and location and motion trajectory can also be used as the basis for generating the metric, which can be a metric for each beam.

[0063] Sequence-to-sequence supervised ML can be used to predict future measurements that may determine the future beams to which the UE will connect. These future predictions can also capture possible common trajectories of UEs in that geographic area (streets, train tracks, bus routes, etc.).

[0064] Figure 5An example embodiment is shown in which an ML model is used to select CFRA resources to be allocated. In this example embodiment, the ML model is used to generate a metric that indicates the probability that the UE will perform random access via a beam. In other words, the ML model outputs a prediction of the beam's superiority. In this example embodiment, the UE 500 sends a measurement report 520 to its source access node (such as gNB 510). Upon receiving the measurement report, the source access node 510 then performs ML inference and thus obtains a prediction of the superiority of multiple beams provided by a target access node (such as gNB 515). The beams included in the multiple beams can be identified via their respective SSBs and / or CSI-RS. The source access node 510 then sends a handover message 535 to the target access node 515, which may include a handover request or a CHO request. Along with the request, the prediction of superiority may also be provided. In other words, at least one generated metric is included in the handover message. Then, the target access node 515 can allocate 540 CFRA-related resources based on the received prediction and send 542 an acknowledgment of the handover request to the source access node 510. This acknowledgment can indicate the allocated CFRA resources to the source access node 510. In response, the source access node 510 can send 544 RRC reconfiguration to the UE 500, indicating the allocated CFRA resources to the UE 500. Then, if possible, the UE 500 provides the target cell with the random access procedure provided by the target access node 515 in the allocated CFRA resources or as a fallback in the CBRA resources. After random access, the target access node 515 can also send 560 feedback on how to utilize the configured CFRA resources. For example, the feedback can indicate whether the UE uses CFRA or CBRA resources for random access, and if CFRA resources are used, indicate the beam used for random access (via SSB and / or CSI-RS index). Based on this feedback, the ML can be further trained by the source access node 510 or by any other suitable entity.

[0065] The prediction (which can also be understood as a metric indicating the probability that the UE will perform random access on the corresponding beam) indicates the estimated superiority of each SSB or CSI RS provided by the target access node 515 for random access. It should be noted that the metric can be generated based on measurement reports provided by the UE 500, or alternatively or additionally, based on the location and motion trajectory of the UE 500. Superiority can be indicated, for example, by assigning a priority value to each beam to be configured for CFRA, e.g., 1 is the highest. The priority value can be based on a prediction of future signal levels obtained from an ML model, and the prediction can be based on previously reported measurements. Alternatively, the source access node 510 can indicate superiority by providing predicted RSRP / RSRQ / SINR measurements for at least some of the beam measurements (which may include SSB measurements and / or CSI RS measurements) in the next time period of the selected duration. The source access node 510 can provide predictive measurements for different times (such as 40ms, 80ms, 160ms, or 200ms) because the RACH period configured by the target cell can be changed for CHO, for example, 1s or 2s.

[0066] However, in another alternative, the source access node 510 can indicate the superiority by providing the target access node 515 with a list of beams identified by the SSB index or CSI RS index to be configured for the CFRA based on the predicted future signal level.

[0067] Source access node 510 may also provide candidate configurations of RACH-related thresholds for selecting CFRA or CBRA, such as threshold T1 for each beam or at least some beams of the target cell. These thresholds may be predicted by source access node 510. In this example embodiment, source access node 510 provides the prediction as part of a handover request. In the case that the handover request is a CHO request, source access node 510 may update the prediction provided to target access node 515 by sending a new CHO request to target access node 515 after preparing the target cell. This may be useful if the prediction has changed since the last update. Target access node 515 may then select which threshold(s) to apply and indicate the selected thresholds back to source access node 510 as part of a handover request confirmation message. Source access node 510 then delivers the selected thresholds to UE 500 in an RRC reconfiguration message for use in random access.

[0068] Handover messages, such as handover requests, may also include information about whether feedback is requested. Alternatively, such requests for feedback may be sent in a separate feedback configuration message. If the source access node 510 requests feedback, the target access node 515 will report the feedback to the source access node 510. The source access node 510 may specify the feedback information that the target access node 515 should report in the handover message. The feedback information may include, for example, one or more of the following: whether the UE 500 has performed CBRA or CFRA, the beams on which CBRA or CFRA has been performed, the average signal measurement of the beams over a period of time, and the average throughput of each beam in the downlink and / or uplink.

[0069] Alternatively, the source access node 510 may notify the target access node 515 whether deviation from policy reinforcement learning (RL) is permitted. Deviation from policy RL allows the target access node 510 to not select the beam determined by the source access node 510 as the optimal beam or recommended for CFRA. For example, the target access node 515 may choose the next optimal beam or even a random beam for CFRA. This allows exploration of whether a better solution exists, or whether the environment has changed and requires updates in the ML model. On the other hand, policy RL requires the target access node 515 to follow the beam selection for CFRA made by the source access node 510. This may be beneficial, for example, for training the ML model used by the source access node 510.

[0070] If deviation from the strategy RL is permitted, the target access node 515 can add exploration on top of the prediction of CFRA resources. The source access node 510 can, for example, implement a value function to evaluate the superiority of each beam of the CFRA, while the target access node 515 implements a strategy selected based on the value of the value function. For example, the target access node 515 can select an exploration strategy based on the value function of the beam (e.g., different exploration strategies for different sets of value functions).

[0071] Optionally, the target access node 515 may define feedback that is reported back to the source access node 510. In this case, the source access node 510 is training an ML model based on the feedback without specifying the requested feedback type. Feedback can be understood to include labels or parameters that can be used to train the ML model. For example, the target access node 515 may report one or more of the following as feedback: whether the UE 500 has performed CBRA or CFRA, the beam on which CFRA or CBRA is performed, and the average throughput of the beam in the downlink and / or uplink. For example, feedback may be aggregated into a single message. In an embodiment, the target access node collects feedback through multiple random accesses. In this case, feedback may include the number, ratio, or percentage of backoffs from CFRA to CBRA, which can be understood as the CBRA ratio. For CHO, feedback may be provided by the target access node 515 as part of a "handover successful" message sent to the source access node 510 as an indication that the handover is complete.

[0072] The ML model used can be any suitable ML model. For example, a reinforcement learning-based model can be used to map measurement reports and optionally other information related to the user experience (UE) into metrics. In an example embodiment of reinforcement learning (RL), a context-based multi-armed slot algorithm, which is a type of reinforcement learning algorithm, can be used. In RL, the environment can be described as a Markov decision process (MDP), and the algorithm learns to maximize the cumulative expected reward by selecting appropriate action sequences from the underlying MDP. Utilizing a context-based multi-armed slot, a context is used, and the algorithm selects actions from multiple actions with the aim of maximizing the average reward given the context. Therefore, the solution algorithm is similar to a supervised learning algorithm, but since the agent can observe the reward only for taking an action, the algorithm adds an exploration element that makes it a reinforcement learning algorithm.

[0073] In this example embodiment, the most relevant input data is considered to be a sequence of beam measurements, such as RSRP sequences, performed and reported by the UE in time from the source cell and / or neighboring cells. Beam measurements can, for example, come from N strongest beams or a specific beam. Therefore, the input is a two-dimensional matrix with both time and beam domains. This state representation implicitly includes information about location, orientation, and velocity, or the UE itself. Additionally or alternatively, any other type of information different from the RSRP sequence may be used.

[0074] In this example embodiment, the inference output and training depend on the ML scheme and the feedback is provided by the target cell. For example, the source access node 510 may not even know the meaning of the feedback, except that higher values ​​are better. If deviation policy inference is used, supervised learning ML at the source access node 510 can be used, for example. The ML can, for example, minimize the loss between the prediction and the feedback. The target access node 515 can add exploration on top of the prediction, for example, random exploration with decreasing probability as the reward increases. If a policy is used, a policy gradient algorithm can be used. In the policy gradient algorithm, the output is a probability distribution for different actions. The source access node 510 can sample from the predicted distribution and transmit a selected beam for the target access node 515. During training, the feedback can be used with a cross-entropy loss function to increase or decrease the probability of taking an action.

[0075] Figure 6 A block diagram of an example embodiment selected based on a preamble is shown. Blocks can be understood as logical units for performing actions, and their actual implementation can be done in any suitable manner. In this example embodiment, UE 600 switches from source cell 610 to target cell 615. First, in this example embodiment, UE 600 optionally provides a measurement report including a beam measurement sequence to block 635, which includes a trained ML model hosted by the source access node providing source cell 610. The ML model may include, for example, a contextual multi-armed slot machine model that predicts the average reward for each beam, optionally taking into account other information such as the UE's motion trajectory and / or velocity. This is performed via air interface 620. The source access node then performs ML inference and provides prediction 640 as output from the ML model, for example, in the form of the aforementioned metric. The prediction is then provided to the target access node providing target cell 615 using the Xn interface. The target access node then performs action selection, which includes: selecting at least one beam with CFRA resources in box 650, running the selected action by preparing the selected beam with CFRA resources in box 655, and finally evaluating the action (random access performed by the UE) in box 660. Based on the evaluation, the aforementioned feedback 670 can be provided for retraining the ML model.

[0076] When the target access node selects an action in box 650, it can decide to perform an exploration with random probability. If an exploration is performed, the target access node can prepare a random beam weighted by predictions, where the random beam can be any beam other than the one with the highest prediction value (which is most likely for random access). If no exploration is performed, the target access node can select the beam with the highest prediction value. When evaluating the action in box 660, the target access node can evaluate whether the beam preparation resulted in a successful CFRA handover. If so, the reward is 1; otherwise, the reward is 0. For example, if the UE has successfully performed CFRA to the target cell and no radio link failure (RLF) occurs after the handover within a predetermined time period (such as T seconds), a successful CFRA handover can be determined. If the reward is fed back to the source access node, the source access node associates the reward with the input and action and can use it as part of training. The source access node can use the mean squared error (MSE) loss function to minimize the difference between the predicted action performance and the observed action performance.

[0077] The above example embodiments can benefit from reduced signaling overhead on Xn because only the output of the ML algorithm can be provided to the target cell instead of the entire dataset. Another benefit is that the above example embodiments allow the use of measurement traces available in the source cell and used in other use cases such as L1-triggered inter-cell mobility, predictive handover, load balancing, beam-optimized grids, etc. Furthermore, the ability of the target access node to define how to train the ML model running at the source access node can have the benefit of allowing for target cell-specific configurations.

[0078] Figure 7 An example embodiment of a supervised learning autoencoder (ML) model is illustrated. In this example embodiment, a signal level 700 for a historical window 710 is shown, which takes previous UE measurements of the serving cell and target cell and / or beam signal levels as input 720 and provides a multi-step prediction of the signal level for a future window 715 as output 740. For example, input 720 may include N beams and X steps, and output 740 may include N beams and Y steps. The input is processed by encoder 730, followed by decoder 735 for providing output 740. Output 740 is also provided to post-processing 750, after which target cell 755 can be identified. Post-processing of the prediction window by the serving access node allows it to identify future multi-step signal levels and select the best possible future target cell for the UE.

[0079] Figure 8An example embodiment of a training cycle of a supervised ML model is shown, where ground truth values ​​(in other words, labels) are obtained during training. In this example embodiment, RSRP levels 800 are shown for cells 810, 812, and 814 at a given time 805. An input sequence K x N 830 from a history window 835 is provided as input to ML training 840. The corresponding estimate of the best cell 850 for labeling and obtaining the sequence K x M during training time window 855 is provided to ML training as labels.

[0080] Figure 9 Example embodiments of a device, which may be an access node or included in an access node such as a gNB, are shown. The device may be, for example, a circuit system or chipset suitable for an access node to implement the described embodiments. Device 900 may be an electronic device including one or more electronic circuit systems. Device 900 may include a communication control circuitry 910 (such as at least one processor) and at least one memory 920 including computer program code (software) 922, wherein the at least one memory and the computer program code (software) 922 are configured, together with the at least one processor, to cause device 900 to perform any of the example embodiments of the access node described above. The device may be suitable for operation as a source access node and / or a target access node.

[0081] The memory 920 can be implemented using any suitable data storage technology, such as semiconductor-based memory devices, flash memory, magnetic memory devices and systems, optical memory devices and systems, fixed memory, and removable memory. The memory may include a configuration database for storing configuration data. For example, the configuration database may store a current list of neighboring cells, and in some example embodiments, it may store the structure of frames used in detected neighboring cells.

[0082] The apparatus 900 may further include a communication interface 930, which includes hardware and / or software for implementing a communication connection according to one or more communication protocols. The communication interface 930 may provide the apparatus with radio communication capabilities for communication within a cellular communication system. The communication interface may, for example, provide a radio interface to a terminal device to transmit RRC messages to the UE and receive measurement reports. For example, the apparatus 900 may also include another interface toward a core network such as a network coordinator device and / or to an access node in the cellular communication system, to, for example, transmit the above-mentioned combined... Figure 5 The described switching message. The device 900 may also include a scheduler 940 configured to allocate resources.

[0083] Although the invention has been described above with reference to examples and the accompanying drawings, it is clear that the invention is not limited thereto, but can be modified in several ways within the scope of the appended claims. Therefore, all words and expressions should be interpreted broadly, and they are intended to illustrate rather than limit the embodiments. It will be apparent to those skilled in the art that the inventive concept can be implemented in various ways as technology advances. Furthermore, it will be understood by those skilled in the art that the described embodiments can, but are not required to, be combined with other embodiments in various ways.

Claims

1. An apparatus comprising at least one processor and at least one memory, the at least one memory storing instructions, the instructions being configured, when executed by the at least one processor, to cause the apparatus to at least: For each of the multiple beams in the target cell, generate a metric indicating the probability that the user equipment will perform random access via the corresponding beam; and A handover message is sent to the target access node of the target cell, wherein the handover message includes at least one of the metrics.

2. The apparatus of claim 1, wherein the measurement is generated based on a measurement report received from a user equipment, wherein the measurement report includes measurements of the plurality of beams of the target cell.

3. The apparatus of claim 1, wherein the metric is generated based on the position and motion trajectory of the user equipment.

4. The apparatus according to any one of the preceding claims, wherein the apparatus is configured to associate the metric with the beam via a synchronization signal block or channel state information reference signal of the respective beam.

5. The apparatus according to any one of the preceding claims, wherein the apparatus is further configured to receive feedback information from a target access node providing the target cell, the feedback information including at least one of the following: an indication of the beam for which the user equipment performs the random access, and whether the user equipment uses contention-free random access or contention-based random access.

6. The apparatus of claim 5, wherein the apparatus is further configured to use a machine learning model to generate the metric and to train the machine learning model based on the feedback.

7. The apparatus of claim 5 or 6, wherein the apparatus is further configured to send a feedback configuration message to the target access node, the feedback configuration message including at least one information element enabling the target access node to send the feedback and at least one information element indicating the content of the feedback information.

8. The apparatus according to any one of the preceding claims, wherein the switching message is a switching request or a conditional switching request.

9. The apparatus according to any one of the preceding claims, wherein the handover message further includes a threshold for the user equipment to select between contention-free random access or contention-based random access at the target cell.

10. The apparatus according to any one of the preceding claims, wherein the metric includes one of: a priority value assigned to each beam, a predictive measurement for each beam for the next time period, or a list of beams that the target cell should be configured for contention-free random access.

11. The apparatus according to any one of the preceding claims, wherein the switching message further indicates whether a deviation policy is permitted, wherein the deviation policy allows the target access node to not follow at least one of the at least one metrics.

12. An apparatus comprising at least one processor and at least one memory, the at least one memory storing instructions, the instructions being configured, when executed by the at least one processor, to cause the apparatus to at least: Receive a handover message from the source access node, wherein the handover message includes: The device provides a metric for each of a plurality of beams in a target cell, the metric indicating the probability that a user equipment will perform random access via the corresponding beam; Based on the metric, contention-free random access resources are allocated to the plurality of beams; as well as Send an acknowledgment to the source access node regarding the handover message, wherein the acknowledgment includes the allocation of the contention-free random access resources to the plurality of beams.

13. The apparatus of claim 12, wherein the beam is identified via a synchronization signal block or a channel state information reference signal.

14. The apparatus according to claim 12 or 13, wherein the apparatus is further configured to: Contention-free random access or contention-based random access is performed with the user equipment via one of the plurality of beams; The user equipment sends feedback information to the source access node, the feedback information including at least one of the following: an indication of the beam used by the user equipment for the random access, and whether the user equipment uses the contention-free random access or the contention-based random access.

15. The apparatus of claim 14, wherein the feedback information further comprises one or more of the following: average throughput of each beam over a time period; average signal measurement of each beam over a time period.

16. The apparatus according to any one of claims 12 to 15, wherein the handover message further includes configuration information for the user equipment to select between contention-free random access or contention-based random access to the target cell.

17. The apparatus of any one of claims 12 to 16, wherein the metric comprises one of: a priority value assigned to each beam, a predictive measurement for each beam for the next time period, or a list of beams for contention-free random access.

18. The apparatus according to any one of the preceding claims, wherein the switching message further indicates whether a deviation policy is permitted, and wherein if the switching message indicates that the deviation policy is permitted, the apparatus is caused to not follow at least one of the received metrics.

19. A method comprising: For each of the multiple beams in the target cell, a metric is generated indicating the probability that the user equipment will perform random access via the corresponding beam; as well as A handover message is sent to the target access node of the target cell, wherein the handover message includes at least one of the metrics.

20. A method comprising: The device receives a handover message from the source access node, wherein the handover message includes a metric for each of a plurality of beams of a target cell provided by the device, the metric indicating the probability that the user equipment will perform random access via the corresponding beam; Based on the metric, contention-free random access resources are allocated to the plurality of beams; and Send an acknowledgment to the source access node regarding the handover message, wherein the acknowledgment includes the allocation of the contention-free random access resources to the plurality of beams.

21. A computer-readable medium comprising program instructions that, when executed by a device, cause the device to perform at least the following operations: For each of the multiple beams in the target cell, generate a metric indicating the probability that the user equipment will perform random access via the corresponding beam; and A handover message is sent to the target access node of the target cell, wherein the handover message includes at least one of the metrics.

22. A computer-readable medium comprising program instructions that, when executed by a device, cause the device to perform at least the following operations: Receive a handover message from the source access node, wherein the handover message includes: The device provides a metric for each of a plurality of beams in a target cell, the metric indicating the probability that a user equipment will perform random access via the corresponding beam; Based on the metric, contention-free random access resources are allocated to the plurality of beams; as well as Send an acknowledgment to the source access node regarding the handover message, wherein the acknowledgment includes the allocation of the contention-free random access resources to the plurality of beams.

Images