System and method for performing condition switching
By using a machine learning model based on network analysis in conditional switching to determine the switching parameters and selecting target cells with higher signal strength, the problems of inappropriate switching parameters and service interruption in the prior art are solved, and the switching success rate and dynamics are improved Adjustment ability.
Patent Information
- Application Number
- CN202410541938.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Priority Date
- 2023-05-02
- Filing Date
- 2024-04-30
- Publication Date
- 2024-11-05
AI Technical Summary
The prior art cannot effectively provide ideal handover parameters during the conditional handover process, resulting in service interruption and failure to dynamically adjust the signal conditions of the target cell and the serving cell, affecting the handover success rate during the movement process.
Receive CHO reconfiguration of multiple target cells through the network entity, determine handover trigger parameters using a machine learning model based on network analysis, select the target cell with higher signal strength from the multiple target cells based on these parameters, and perform the handover.
It improves the success rate of conditional handover, reduces radio link failures and service interruptions, can dynamically optimize the handover process, and prioritizes the cells that support the desired service.
Smart Images

Figure CN118900440A_ABST
Abstract
Description
[0001] CROSS-REFERENCE TO RELATED APPLICATIONS
[0002] This application claims priority to Indian provisional application No. 202341031262 filed in the Indian Intellectual Property Office on May 2, 2023 and Indian application No. 202341031262 filed in the Indian Intellectual Property Office on April 29, 2024, the disclosures of which are incorporated herein by reference in their entirety. Technical Field
[0003] The present disclosure relates generally to wireless communications and, more particularly, to a system and method for performing conditional handoffs. Background Art
[0004] In 3rd Generation Partnership Project (3GPP) Release 16, Conditional Handover (CHO) is a feature introduced to improve handover robustness and reduce handover failures at cell edge scenarios. The feature is applicable to both Long Term Evolution (LTE) and New Radio (NR). The CHO feature is applied in the Radio Resource Control (RRC) connected state. The source Next Generation Node B (gNB) / evolved Node B (eNB) prepares a list of potential handover candidates and blocks radio resources at the target gNB / eNB. In addition, the user equipment (UE) receives a list of conditional reconfigurations with trigger conditions. In addition, CHO includes two operations, such as measurement evaluation of candidates and handover execution to the target cell once the trigger criteria are met.
[0005] In conventional solutions, even if CHO provides the handover configuration to the UE in advance, the UE still faces service interruption caused by radio link failure. One of the reasons for service interruption is that the gNB (also referred to as gNodeB in this article) cannot provide ideal (or accurate) handover parameters to the UE that work ideally (or well enough) under the upcoming conditions of the UE. The UE uses the CHO trigger configuration parameters calculated by the network and shared with the UE in advance before the actual handover occurs. In addition, in conventional solutions, dynamically changing target cell and serving cell signal conditions or other parameters (such as speed) that affect the mobility process are not considered. In addition, conventional schemes are also unable to give preferences (or priorities) for services supported in the target cell.
[0006] Figure 1AA sequence flow chart 102 describing a conditional handover (CHO) failure scenario according to conventional techniques is shown. In conventional techniques, mobility control information is provided by an access and mobility management function (AMF). In addition, measurement control and reporting are sent to the source gNodeB (gNB), and the network makes a decision for CHO. In addition, the handover request is shared with other potential target gNBs. In addition, admission control operations are performed. Next, the handover request is acknowledged. Therefore, the RRC reconfiguration is shared with the UE, and the RRC reconfiguration is completed. In addition, the early state is transferred to other potential target gNBs.
[0007] In addition, the CHO handover is completed. In addition, the handover is successful and the sequence number (SN) state is transferred. When the SN state is transferred, the handover is canceled.
[0008] Figure 1B A sequence flow chart 104 describing a CHO failure scenario according to another conventional technique is shown. In the prior art, a UE registers on a Next Generation Radio Access Network (NG-RAN) cell 1. In addition, a measurement report is sent to the network, and the network makes a decision for CHO and initiates a preparation phase to other cells (because the UE may switch to these cells based on matching criteria). In addition, the NG-RAN cell 1 network indicates to the UE using RRC reconfiguration the Time-to-Trigger (TTT), the Handover Margin (HOM), the candidate cells to be measured, etc. Therefore, the UE responds with RRC reconfiguration complete.
[0009] In addition, the UE evaluates CHO using TTT and HOM parameters for a given candidate cell. When the time TTT expires, the UE attempts a RACH (Random Access Channel) procedure on the CHO target cell 4 and encounters a RACH failure. To recover, the UE performs an RRC Connection Reestablishment (RRE) procedure.
[0010] Figure 1C A sequence flow chart 106 is shown describing a scenario of CHO to a wrong cell according to conventional techniques. Figure 1C As shown, the UE is registered on NG-RAN cell 1. In addition, a measurement report is sent to the network. Therefore, the network makes a decision for CHO and initiates a preparation phase towards other cells (as the UE may switch to these cells based on matching criteria). The NG-RAN cell 1 network uses RRC reconfiguration to indicate to the UE TTT, HOM, candidate cells to be measured, etc. The UE responds with RRC reconfiguration complete.
[0011] In addition, the UE that prefers (or prefers) eMBB (enhanced mobile broadband) service uses TTT and HOM parameters for a given candidate cell to evaluate the CHO condition. The UE evaluates both cell 4 (not supporting eMBB) and cell 5 (supporting eMBB). In addition, the TTT timer for cell 4 expires first. The UE performs CHO to cell 4 that does not support eMBB service. Therefore, CHO is performed on the wrong cell. Summary of the invention
[0012] Embodiments provide techniques and methods that may overcome each of the above-described challenges and limitations associated with conventional solutions.
[0013] This Summary is provided to introduce a selection of concepts in a simplified form that are further described in the Detailed Description of the present disclosure. This Summary is not intended to identify key or essential inventive concepts of the present disclosure, nor is it intended to determine the scope of the present disclosure.
[0014] According to an embodiment of the present disclosure, a method for performing conditional handover (CHO) is disclosed. The method includes: receiving a CHO reconfiguration associated with multiple target cells via a network entity; using the CHO reconfiguration to identify one or more target cells from the multiple target cells, each of the one or more target cells having a higher signal strength than a serving cell associated with the UE; using a machine learning model based on network analysis to determine one or more handover trigger parameters associated with each of the one or more target cells, wherein the one or more handover trigger parameters are determined based on one or more network parameters, historical handover data, and one or more mobility parameters; selecting a first target cell from the one or more target cells based on the one or more handover trigger parameters; and performing CHO from the serving cell to the first target cell.
[0015] According to an embodiment of the present disclosure, a system for performing conditional handover (CHO) is disclosed. The system includes: a processing circuit configured to: receive a CHO reconfiguration associated with multiple target cells via a network entity; use the CHO reconfiguration to identify one or more target cells from the multiple target cells, each of the one or more target cells having a higher signal strength than a serving cell associated with a UE; use a machine learning model based on network analysis to determine one or more handover trigger parameters associated with each of the one or more target cells, wherein the one or more handover trigger parameters are determined based on one or more network parameters, historical handover data, and one or more mobility parameters; select a first target cell from the one or more target cells based on the one or more handover trigger parameters; and perform CHO from the serving cell to the first target cell.
[0016] According to an embodiment of the present disclosure, a non-transitory computer-readable medium storing instructions is disclosed, and when the instructions are executed by at least one processor, the at least one processor performs a method for performing conditional handover (CHO). The method includes: receiving a CHO reconfiguration associated with multiple target cells via a network entity; using the CHO reconfiguration to identify one or more target cells from the multiple target cells, each of the one or more target cells having a higher signal strength than a serving cell associated with the UE; using a machine learning model based on network analysis to determine one or more handover trigger parameters associated with each of the one or more target cells, wherein the one or more handover trigger parameters are determined based on one or more network parameters, historical handover data, and one or more mobility parameters; selecting a first target cell from the one or more target cells based on the one or more handover trigger parameters; and performing CHO from the serving cell to the first target cell.
[0017] In order to further illustrate the advantages and features of the present disclosure, a more specific description of the present disclosure will be presented by referring to the specific examples of the present disclosure shown in the accompanying drawings. It is to be understood that these drawings only show typical examples of the present disclosure and therefore should not be considered as limiting the scope thereof. The present disclosure will be described and explained with additional specificity and details in conjunction with the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS
[0018] These and other features, aspects and advantages of the present disclosure will become better understood when the following detailed description is read with reference to the accompanying drawings, in which like characters refer to like parts throughout the several views, and in which:
[0019] Figure 1AA sequence flow chart describing a conditional handover (CHO) failure scenario according to conventional techniques is shown;
[0020] Figure 1B A sequence flow chart describing a scenario of a conditional handover to a wrong cell (CHO) according to conventional techniques is shown;
[0021] Figure 1C A sequence flow chart 106 is shown describing a scenario of CHO to a wrong cell according to conventional techniques;
[0022] Figure 2 A block diagram of a system for performing CHO according to an embodiment of the present disclosure is shown;
[0023] Figure 3 The embodiment according to the present disclosure is shown Figure 2 A block diagram of the multiple modules of the system shown in ;
[0024] Figure 4 A flowchart describing a process of performing CHO according to an embodiment of the present disclosure is shown;
[0025] Figure 5 A sequence flow chart describing the operation of a system for performing CHO according to an embodiment of the present disclosure is shown;
[0026] Figure 6 shows a sequence flow chart describing a CHO success scenario according to an embodiment of the present disclosure;
[0027] Figure 7 A sequence flow chart describing a scenario of CHO to a serving support cell according to an embodiment of the present disclosure is shown; and
[0028] Figure 8 An example process flow describing a method for performing CHO according to an embodiment of the present disclosure is shown.
[0029] Furthermore, those skilled in the art will appreciate that those elements in the drawings are illustrated for simplicity and may not necessarily be drawn to scale. For example, a flow chart illustrates the method in terms of the most salient operations involved to help improve understanding of various aspects of the present disclosure. Furthermore, with respect to the construction of the device, one or more components of the device may have been represented in the drawings by conventional symbols, and the drawings may show only those specific details relevant to understanding the embodiments of the present disclosure so as not to obscure the drawings with details that would be readily apparent to one of ordinary skill in the art having the benefit of the description herein. DETAILED DESCRIPTION
[0030] To promote an understanding of the principles of the present disclosure, reference will now be made to various examples, and specific language will be used to describe them. It will be understood, however, that no limitation of the scope of the present disclosure is intended thereby, and such changes and further modifications in the illustrated systems, and such further applications of the principles of the present disclosure as illustrated therein are contemplated as would normally occur to one skilled in the art to which the present disclosure relates.
[0031] Those skilled in the art will understand that both the foregoing general description and the following detailed description are illustrative of the present disclosure and are not intended to be restrictive thereof.
[0032] Reference throughout this specification to "one aspect," "another aspect," or similar language means that a particular feature, structure, or characteristic described in connection with the example is included in an embodiment of the present disclosure.
[0033] The terms "include", "comprises", or any other variations thereof are intended to cover a non-exclusive inclusion, such that a process or method that includes a list of operations includes not only those operations but may also include other operations not expressly listed or inherent to such process or method. Similarly, one or more devices or subsystems or elements or structures or components beginning with "includes..." do not exclude the presence of other devices or other subsystems or other elements or other structures or other components or additional devices or additional subsystems or additional elements or additional structures or additional components without more limitations.
[0034] Figure 2 A block diagram of a system for performing CHO according to an embodiment of the present disclosure is shown. In an embodiment of the present disclosure, a system 200 is implemented in a user equipment (UE) 202. In various embodiments of the present disclosure, the UE 202 may correspond to a smart phone, a camera, a laptop computer, a desktop computer, a wearable device, or any other device. In an embodiment of the present disclosure, CHO is a process in telecommunications in which the UE 202 switches its connection from one base station (or cell) to another base station (or cell) while maintaining an ongoing call or data session. The switching occurs conditionally based on certain criteria (such as signal strength, quality, or network congestion).
[0035] System 200 may include one or more processors / controllers 204 , input / output (I / O) interfaces 206 , multiple modules 208 , and / or memory 210 .
[0036] In an embodiment, one or more processors / controllers 204 may be operably coupled to each of the corresponding I / O interfaces, the plurality of modules 208, and / or the memory 210. In an embodiment, the one or more processors / controllers 204 may include at least one data processor for executing a process in a virtual storage area network. The one or more processors / controllers 204 may include a dedicated processing unit, such as an integrated system (bus) controller, a memory management control unit, a floating point unit, a graphics processing unit, a digital signal processing unit, etc. In an embodiment, the one or more processors / controllers 204 may include a central processing unit (CPU), a graphics processing unit (GPU), or both. The one or more processors / controllers 204 may be one or more general-purpose processors, digital signal processors, application-specific integrated circuits, field programmable gate arrays, servers, networks, digital circuits, analog circuits, combinations thereof, or other now known or later developed devices for analyzing and processing data. The one or more processors / controllers 204 may execute code of a software program (such as, manually generated (e.g., programmed)) to perform the desired operation. In an embodiment of the present disclosure, one or more processors / controllers 204 may be a general-purpose processor (such as a CPU, an application processor (AP), etc.), a graphics processing unit (such as a GPU), a vision processing unit (VPU), and / or an artificial intelligence (AI) dedicated processor (such as a neural processing unit (NPU)).
[0037] In addition, one or more processors / controllers 204 can control the processing of input data according to predefined (or optionally, given) operating rules or machine learning (ML) models stored in non-volatile memory and volatile memory. Predefined (or optionally, given) operating rules or ML models can be provided by training or learning.
[0038] Here, providing by learning means making a ML model of predefined (or optionally, given) operation rules or desired characteristics by applying learning techniques to a plurality of learning data. The learning may be performed in the UE 202 itself executing ML according to the embodiment, and / or may be implemented by a separate server / system.
[0039] In addition, the ML model may include multiple neural network layers. Each layer has multiple weight values, and the layer operation is performed by the calculation of the previous layer and the operation of multiple weights. Examples of neural networks include, but are not limited to, convolutional neural networks (CNNs), deep neural networks (DNNs), recurrent neural networks (RNNs), restricted Boltzmann machines (RBMs), deep belief networks (DBNs), bidirectional recurrent deep neural networks (BRDNNs), generative adversarial networks (GANs), and deep Q networks.
[0040] A learning technique is a method of using a plurality of learning data to train a predetermined (or optionally, a given) target device (e.g., a robot) to enable, allow, or control the target device to make decisions or predictions. Examples of learning techniques include, but are not limited to, supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning.
[0041] The one or more processors / controllers 204 may be configured to communicate with one or more input / output (I / O) devices via corresponding I / O interfaces 206. The I / O interfaces 206 may employ communication code division multiple access (CDMA), high speed packet access (HSPA+), global system for mobile communications (GSM), long term evolution (LTE), world interoperability for microwave access (WiMAX), etc.
[0042] One or more processors / controllers 204 may be configured to communicate with a communication network via a network interface. In an embodiment, the network interface may be an I / O interface 206. The network interface may be connected to a communication network to enable connection of the UE 202 with other devices. The network interface may employ connection protocols including but not limited to direct connection, Ethernet (e.g., twisted pair 10 / 100 / 1000 baseband-T), transmission control protocol / Internet protocol (TCP / IP), token ring, IEEE 802.11a / b / g / n / x, etc. The communication network may include but is not limited to direct interconnection, a local area network (LAN), a wide area network (WAN), a wireless network (e.g., using a wireless application protocol), the Internet, etc.
[0043] In an embodiment, the memory 210 may be communicatively coupled to one or more processors / controllers 204. The memory 210 may be configured to store data and instructions executable by one or more processors / controllers 204. The memory 210 may include, but is not limited to, non-transitory computer-readable storage media, such as various types of volatile and non-volatile storage media including, but not limited to, random access memory, read-only memory, programmable read-only memory, electrically programmable read-only memory, electrically erasable read-only memory, flash memory, tape or disk, optical media, etc. In one example, the memory 210 may include a cache or random access memory for one or more processors / controllers 204. In an alternative or additional example, the memory 210 may be part of one or more processors / controllers 204, such as a cache memory, system memory, or other memory of a processor. In an embodiment, the memory 210 may be an external storage device or database for storing data. The memory 210 may be operable to store instructions executable by one or more processors / controllers 204. The functions, actions, operations, or tasks shown or described in the figures may be performed by a programmed processor / controller for executing instructions stored in the memory 210. The functions, actions, operations, or tasks are independent of a particular type of instruction set, storage medium, processor, or processing strategy, and may be performed by software, hardware, integrated circuits, firmware, microcode, etc., operating alone or in combination. Likewise, processing strategies may include multi-processing, multi-tasking, parallel processing, etc.
[0044] In an embodiment, a plurality of modules 208 may be included in the memory 210. The memory 210 may also include a system database 212 for storing data. The plurality of modules 208 may include an instruction set that may be executed to cause the system 200 to perform any one or more of the methods / processes disclosed herein. As discussed herein, the plurality of modules 208 may be configured to perform the operations of the present disclosure using the data stored in the system database 212 to perform CHO. In an embodiment, each of the plurality of modules 208 may be a hardware unit that may be external to the memory 210. In addition, the memory 210 may include an operating system 214 for executing one or more tasks of the system 200 as performed by a general-purpose operating system in a communication domain. In an embodiment, the system database 212 may be configured to store information as needed by the plurality of modules 208 and one or more processors / controllers 204 or to store information for use by the plurality of modules 208 and one or more processors / controllers 204 to perform CHO.
[0045] In an embodiment of the present disclosure, at least one of the plurality of modules 208 may be implemented by an ML model. Functions associated with ML may be executed by non-volatile memory, volatile memory, and one or more processors / controllers 204.
[0046] In an embodiment, the I / O interface 206 may enable input to and output from the system 200 using suitable devices such as, but not limited to, a display, keyboard, mouse, touch screen, microphone, speaker, etc.
[0047] In addition, the present disclosure also proposes a non-temporary computer-readable medium including instructions or receiving and executing instructions in response to a propagation signal. In addition, instructions can be sent or received through a network via a communication port or interface or using a bus (not shown). The communication port or interface can be a part of one or more processors / controllers 204, or can be a separate component. The communication port can be created in software, or can be a physical connection of hardware. The communication port can be configured to be connected to any other component or combination thereof in a network, an external medium, a display, or UE 202. The connection to the network can be a physical connection (e.g., a wired Ethernet connection), or can be established wirelessly. Similarly, additional connections to other components of UE 202 can be physical or can be established wirelessly. The network can optionally be directly connected to the bus. For the sake of brevity, the architecture and standard operation of the operating system 214, the memory 210, the system database 212, one or more processors / controllers 204, and the I / O interface 206 are not discussed in detail.
[0048] Figure 3 The embodiment according to the present disclosure is shown Figure 2 . In an embodiment of the present disclosure, the plurality of modules 208 may include, but are not limited to, a receiving module 302, an identifying module 304, a determining module 306, a selecting module 308, and / or an executing module 310. The plurality of modules 208 may be implemented by suitable hardware and / or software applications.
[0049] In an embodiment of the present disclosure, the receiving module 302 may be configured to receive CHO reconfigurations associated with multiple target cells via a network entity. The network entity refers to any element within a cellular network infrastructure that interacts with the UE 202, such as a base station, an eNodeB, etc. In an embodiment of the present disclosure, CHO reconfiguration refers to the adjustment or modification of conditions under which a handover occurs in a telecommunications network. CHO reconfiguration involves changing criteria or parameters that trigger a handover from one base station to another for a user equipment.
[0050] In addition, the identification module 304 can be configured to: identify one or more target cells having a greater signal strength than the serving cell associated with the UE 202 (e.g., having a signal strength greater than the signal strength of the serving cell associated with the UE 202) from the multiple target cells by using the received CHO reconfiguration.
[0051] In addition, the determination module 306 may be configured to determine one or more handover trigger parameters associated with each of the identified one or more target cells based on one or more network parameters, historical handover data, and / or one or more mobile parameters affecting mobility by using a machine learning (ML) model based on network analysis. According to an embodiment, for example, the ML model based on network analysis may output one or more handover trigger parameters based on being applied (e.g., or based on input) one or more network parameters, historical handover data, and / or one or more mobile parameters affecting mobility. In an embodiment of the present disclosure, the one or more network parameters include a slice type, a serving cell signal condition, a target cell signal condition, a service type, one or more other network capabilities, or any combination thereof. For example, a slice type may be enhanced mobile broadband (eMBB), ultra-reliable low latency communication (uRLLC), etc. In addition, the service type refers to the type or category of service that the network is designed to provide, such as data service, voice service, video service, messaging service, security service, etc. In an embodiment of the present disclosure, the one or more mobile parameters affecting mobility include the speed of UE 202.
[0052] In an embodiment of the present disclosure, the historical handover data corresponds to one or more post-handover observations after (or based on) performing a previous CHO to a previous target cell in a plurality of target cells associated with the UE 202. The one or more post-handover observations include ping-pong, radio link failure, throughput drop, or any combination thereof. In an embodiment of the present disclosure, the one or more handover trigger parameters include a handover margin (HOM) between a source cell and a target cell, a source cell threshold, a target cell threshold, a time to trigger (TTT), or any combination thereof.
[0053] According to an embodiment, a network analysis-based ML model may be generated by applying a learning technique to learning data (e.g., by UE 202 or an external server). The learning data may include, for example, learning input data associated with learning output data, respectively. The learning input data may include one or more learning network parameters, learning historical switching data, and / or one or more learning movement parameters. The learning output data may include one or more learning switching trigger parameters. In each learning iteration, the network analysis-based ML model may be applied to the learning input data to output one or more switching trigger parameters. The output one or more switching trigger parameters may be compared with the one or more learning switching trigger parameters associated with the learning input data, and at least one parameter of the network analysis-based ML model may be adjusted based on the comparison. For example, the comparison may include determining the difference between the output one or more switching trigger parameters and the one or more learned switching trigger parameters, and at least one parameter of the network analysis-based ML model may be adjusted to minimize (or reduce) the difference (e.g., using a loss function). According to an embodiment, for example, the network analysis-based ML model may be trained as described above to minimize (or reduce) ping-pong, radio link failure, throughput degradation, etc., preferably provide a target cell of the selected (or configured) slice type and / or service type, maximize (or increase) a target cell signal condition (e.g., target cell signal strength) or a difference between a target cell signal condition and a source cell signal condition (e.g., source cell signal strength), etc. According to an embodiment, the learning technique may continue during operation of the UE 202 to adjust at least one parameter of the network analysis-based ML model, for example, based on historical handover data generated when the UE 202 performs CHO (e.g., each time it occurs).
[0054] The selection module 308 may be configured to select a best (or improved) target cell from among the one or more target cells based on the determined one or more handover triggering parameters.
[0055] Furthermore, the execution module 310 may be configured to perform CHO from the serving cell to the selected best (or improved) target cell.
[0056] Figure 4 A flowchart describing the process of performing CHO according to an embodiment of the present disclosure is shown. Figure 3 The details of performing CHO are explained in detail.
[0057] like Figure 4As shown in , the present disclosure allows UE 202 to calculate optimal (or improved) switching parameters based on existing conditions and previous switching results, and apply them to potential CHO target cells. At operation 402, in the RRC connected state, UE 202 is configured to receive a CHO configuration with target candidates and no switching trigger details from the network. Additionally, the network may choose to specify the capabilities of each CHO candidate (e.g., the slice types supported by the cell). At operation 404, UE 202 may monitor all CHO candidates and only select candidates (C1, C2, ..., Cm) whose measurements are better than the serving cell / source cell (e.g., candidates with higher signal strength). If the target candidate measurement is lower than (or equal to) the source cell, then at operation 406, the evaluation continues. Optionally, if at least one target candidate measurement is higher than the source cell (in Figure 4 ), the process proceeds to operation 408.
[0058] In addition, at operation 408, UE 202 uses reinforcement learning to determine the HOM (handover margin) / offset and TTT (trigger time) of each target candidate Cx. For example, based on the environment, UE 202 selects appropriate handover parameters (TTT, HOM) for each target cell from a database derived from previous results. In an embodiment of the present disclosure, the input of reinforcement learning is slice type, source / target signal conditions, UE 202 moving speed, etc. For example, the source / target signal conditions can be reference signal received power (RSRP), signal to interference plus noise ratio (SINR), reference signal received quality (RSRQ), etc. The output is TTT and offset for handover triggering.
[0059] At operation 410, the UE 202 performs a handover on a target that satisfies the handover parameters. In an embodiment of the present disclosure, the system 200 assigns rewards to the selected parameters based on observations after (and / or based on) the handover (e.g., ping-pong, radio link failure, throughput drop, etc.). In an embodiment of the present disclosure, Q-learning is employed to study the performance of the system 200. In addition, at operation 412, the system 200 updates a database based on various observations after (and / or based on) the handover (e.g., ping-pong, radio link failure, throughput drop, etc.). According to an embodiment, the information in the database may be used to perform or re-perform the learning techniques discussed above.
[0060] Figure 5 A sequence flow chart describing the operation of the system 200 for performing CHO according to an embodiment of the present disclosure is shown.
[0061] like Figure 5As shown in , at operation 502, UE 202 receives an RRC UE capability query from a serving gNodeB. In addition, at operation 504, an RRC UE capability response message is shared by UE 202 to the serving gNodeB. In an embodiment of the present disclosure, UE 202 supports system 200 to perform an early conditional handover, and requests the network to mention a list of functions supported on a target CHO candidate. In addition, at operation 506, a CHO decision is made.
[0062] At operation 508, an Xn Application Protocol (XnAP) handover request is shared from the serving gNodeB to the target gNodeB-1. At operation 510, an XnAP handover request is shared from the serving gNodeB to the target gNodeB-2. In addition, at operation 512, an admission control process is performed. At operation 514, the serving gNodeB receives an XnAP handover request confirmation from the target gNodeB-2. For example, the functions supported by the cell include Multimedia Broadcast Multicast Service (MBMS), uRLLC, etc. In addition, at operation 516, the serving gNodeB receives an XnAP handover request confirmation from the target gNodeB-1. At operation 518, UE 202 receives an RRC reconfiguration from the serving gNodeB, for example, a conditional reconfiguration of the cell and the supported functions. At operation 520, the RRC reconfiguration is completed. At operation 522, the CHO cell is evaluated and a handover is performed.
[0063] Figure 6 A sequence flow chart describing a CHO success scenario according to an embodiment of the present disclosure is shown. Figure 3 The details of the CHO success scenario are explained in detail.
[0064] like Figure 6 As shown in FIG. 6 , at operation 602, UE 202 is registered on NG-RAN cell 1. In addition, at operation 604, a measurement report is sent to the network. At operation 606, the network makes a decision for CHO. In addition, at operation 608, a preparation phase is initiated for other cells (because UE 202 may switch to these cells based on matching criteria). At operation 610, the NG-RAN cell 1 network indicates to the UE the candidate cells to be measured using RRC reconfiguration.
[0065] In addition, at operation 612, UE 202 responds with RRC reconfiguration complete. At operation 614, UE 202 generates TTT and HOM parameters using current signaling conditions, slice type (service), mobility parameters, learning from previous handover results, etc. At operation 616, UE 202 evaluates CHO using these UE-generated TTT and HOM parameters for a given candidate cell. In addition, at operation 618, UE 202 initiates a random access channel (RACH) procedure with the target cell. At operation 620, as the current cell condition deteriorates and a longer TTT value cannot be maintained, UE 202 generates a smaller TTT and performs CHO based on the smaller TTT.
[0066] Figure 7 A sequence flow chart describing a scenario of CHO to a serving support cell according to an embodiment of the present disclosure is shown. Figure 3 Details about the CHO procedure to the serving support cell are explained in detail.
[0067] like Figure 7 As shown in FIG. 7 , at operation 702, UE 202 is registered on NG-RAN cell 1. In an embodiment of the present disclosure, UE 202 is registered to the network and is in a connected state on cell 1. In addition, cells 1 and 5 are linked to AMF1 and support eMBB. At operation 704, cell 4 supports uRLLC and is linked to AMF2. In addition, at operations 706, 708, and 710, measurement reports are sent to the network so that the network makes a decision for CHO and initiates a preparation phase to other cells (because UE 202 may switch to these cells based on matching criteria).
[0068] At operation 712, the NG-RAN cell 1 network indicates to the UE 202 the candidate cells to be measured using RRC reconfiguration. At operation 714, the UE 202 responds with RRC reconfiguration complete. At operation 716, the UE 202 generates TTT and HOM parameters using current signaling conditions, slice type (service), mobility parameters, etc. At operation 718, the UE 202 evaluates CHO using these UE-generated TTT and HOM parameters and service types for given candidate cells (e.g., cells 4 and 5). At operation 720, the UE 202 detects that cell 4 does not support eMBB and cell 5 supports eMBB. When multiple cells are evaluated or being evaluated, at operation 722, the UE 202 considers the service and also measures cell 5 until its TTT expires. At operations 724 and 726, the UE 202 performs a handover to cell 5 when it matches the service and the evaluation for handover.
[0069] Figure 8An example process flow describing a method 800 for performing a conditional handover (CHO) according to an embodiment of the present disclosure is shown. The method 800 may be performed by Figure 2 and Figure 3 The system 200 shown in FIG. 1 is implemented in the UE 202 .
[0070] At operation 802, method 800 includes receiving, via a network entity, a CHO reconfiguration associated with a plurality of target cells.
[0071] At operation 804, method 800 includes identifying one or more target cells having a stronger signal strength than a serving cell associated with UE 202 from among the plurality of target cells by using the received CHO reconfiguration.
[0072] At operation 806, method 800 includes: determining one or more handover trigger parameters associated with each of the identified one or more target cells based on one or more network parameters, historical handover data, and one or more mobile parameters affecting mobility by using a machine learning (ML) model based on network analysis. In an embodiment of the present disclosure, the one or more network parameters include slice type, serving cell signal condition, target cell signal condition, service type, one or more other network capabilities, or any combination thereof. The one or more mobile parameters affecting mobility include the speed of UE 202. In addition, the historical handover data corresponds to one or more post-handover observations associated with UE 202 after performing a previous CHO to a previous target cell in a plurality of target cells. In an embodiment of the present disclosure, the one or more post-handover observations include ping-pong, radio link failure, throughput drop, or any combination thereof. In an embodiment of the present disclosure, the one or more handover trigger parameters include a handover margin (HOM) between a source cell and a target cell, a source cell threshold, a target cell threshold, and a trigger time (TTT).
[0073] Furthermore, at operation 808, method 800 includes selecting a best (or improved) target cell from the one or more target cells based on the determined one or more handover triggering parameters.
[0074] At operation 810, method 800 includes performing CHO from the serving cell to the selected best (or improved) target cell. According to an embodiment, after performing CHO to the selected target cell (and / or based on performing CHO to the selected target cell), UE 202 may perform network communication with the target cell. For example, UE 202 may generate a first signal, process the first signal to perform one or more of modulation, up-conversion, filtering, amplification and / or encryption on the first signal, and send the processed first signal to the selected target cell via one or more antennas of UE 202. Additionally or optionally, UE 202 may receive a second signal from the selected target cell via one or more antennas of UE 202, process the second signal to perform one or more of demodulation, down-conversion, filtering, amplification and / or decryption on the second signal, and perform additional operations based on the processed second signal. For example, the additional operations may include one or more of the following: providing the processed second signal to a corresponding application executed on UE 202, storing the processed second signal, sending a response signal to the selected target cell, etc.
[0075] Although described in a specific order Figure 8 The above operations shown in , however, according to the embodiments of the present disclosure, the operations may occur in a modified order. In addition, for the sake of brevity, the operations already described in . Figure 2-7 The descriptions covered Figure 8 Details related to various operations.
[0076] The present disclosure provides various technical advances based on the key features discussed above. The present disclosure allows UE 202 to calculate optimal (or improved) handover parameters based on existing conditions and previous handover results, and apply them to potential CHO target cells. In the RRC connected state, it is proposed that UE 202 receives a CHO configuration without handover trigger details. In addition, the network can specify the capabilities of each CHO candidate (e.g., the slice types supported by the cell). For example, the system 200 performs CHO using conditional handover execution parameters (TTT and HO margin) independently inferred by UE 202 through reinforcement learning using inputs such as source cell channel conditions, CHO target cell channel conditions, network slices, mobility parameters, and previous results.
[0077] The plurality of modules 208 may be implemented by any suitable hardware and / or instruction set. Figure 8 The sequence flows shown in are examples, and embodiments may include adding / omitting operations therein. In an embodiment, one or more operations performed by the plurality of modules 208 may be performed by a processor / controller.
[0078] Conventional devices and methods for performing conditional handover (CHO) involve receiving a handover configuration including handover parameters (such as time to trigger (TTT) and handover margin (HOM)) from a base station at a UE. However, the conditions on which such handover parameters are based may change between the moment when the base station determines the handover parameters and the moment when CHO is performed due to, for example, a changing environment at the UE. For example, a change in the moving speed of the UE and / or a change in conditions at a serving cell or a target cell (e.g., reference signal received power (RSRP), signal to interference plus noise ratio (SINR), reference signal received quality (RSRQ), etc.) may make the handover parameters determined by the base station inappropriate. For example, in a scenario where a base station provides a larger TTT and conditions at a serving cell or a target cell deteriorate, CHO using a larger TTT may not be feasible and / or may result in a radio link failure. In addition, conventionally, the base station does not provide any indication of the service capabilities of a candidate cell using handover parameters. Therefore, conventional devices and methods cannot give priority to candidate cells that provide desired services (e.g., enhanced mobile broadband) when performing CHO. Therefore, conventional apparatuses and methods do not consider situations where UE and / or service priorities change, thereby resulting in excessive radio link failures and / or CHOs to less desirable cells.
[0079] However, according to an embodiment, an improved apparatus and method for performing CHO is provided. For example, the improved apparatus and method may involve determining switching parameters at the UE (e.g., using a machine learning model based on network analysis), thereby taking into account the changing situation at the UE to obtain more appropriate switching parameters. In addition, the improved apparatus and method may involve receiving an indication of the service capabilities of candidate cells for performing CHO from a base station, thereby enabling priority selection of candidate cells that provide the desired service. Therefore, the improved apparatus and method overcome the shortcomings of conventional apparatus and methods to at least reduce radio link failures and / or increase the possibility of CHO to a desired cell.
[0080] According to an embodiment, the operations described herein as being performed by the UE 202, the system 200, the one or more processors / controllers 204, the I / O interface 206, the multiple modules 208, the operating system 214, the receiving module 302, the identifying module 304, the determining module 306, the selecting module 308, the executing module 310, the serving gNodeB, the target gNodeB-1, the target gNodeB-2, the NG-RAN cell 1, the NG-RAN cell 4, the NG-RAN cell 5, the AMF, the AMF1 and / or the AMF2 may be performed by a processing circuit. The term "processing circuit" as used in the present disclosure may refer to, for example, hardware including logic circuits; a hardware / software combination, such as a processor that executes software; or a combination thereof. For example, the processing circuit may more specifically include, but is not limited to, a central processing unit (CPU), an arithmetic logic unit (ALU), a digital signal processor, a microcomputer, a field programmable gate array (FPGA), a system on a chip (SoC), a programmable logic unit, a microprocessor, an application specific integrated circuit (ASIC), etc.
[0081] In an embodiment, the processing circuit may perform some operations (e.g., operations described herein as being performed by a machine learning model based on network analysis) through artificial intelligence and / or machine learning. As an example, the processing circuit may implement an artificial neural network (e.g., a machine learning model based on network analysis) that is trained on a set of training data through, for example, supervised, unsupervised, and / or reinforcement learning models, and wherein the processing circuit may process feature vectors to provide outputs based on the training. Such an artificial neural network may utilize various artificial neural network organizations and processing models, such as convolutional neural networks (CNNs), recurrent neural networks (RNNs) that optionally include long short-term memory (LSTM) units and / or gated recurrent units (GRUs), stacked deep neural networks (S-DNNs), state-space dynamic neural networks (S-SDNNs), deconvolutional networks, deep belief networks (DBNs), and / or restricted Boltzmann machines (RBMs). Alternatively or additionally, the processing circuitry may include other forms of artificial intelligence and / or machine learning, such as, for example, linear and / or logistic regression, statistical clustering, Bayesian classification, decision trees, dimensionality reduction (such as, principal component analysis), and expert systems; and / or combinations thereof, including ensembles such as random forests.
[0082] In this article, a machine learning model (e.g., a machine learning model based on network analysis) can have any structure that can be trained, for example, using training data. For example, a machine learning model can include an artificial neural network, a decision tree, a support vector machine, a Bayesian network, a genetic algorithm, etc. The machine learning model can be described by mainly referring to an artificial neural network, but the embodiment is not limited thereto. Non-limiting examples of artificial neural networks can include convolutional neural networks (CNNs), region-based convolutional neural networks (R-CNNs), region proposal networks (RPNs), recursive neural networks (RNNs), stacked deep neural networks (S-DNNs), state space dynamic neural networks (S-SDNNs), deconvolution networks, deep belief networks (DBNs), restricted Boltzmann machines (RBMs), fully convolutional networks, long short-term memory (LSTM) networks, classification networks, etc.
[0083] The various operations of the above methods may be performed by any suitable device capable of performing the operations (such as the processing circuits discussed above). For example, as discussed above, the operations of the above methods may be performed by various hardware and / or software implemented in some form of hardware (e.g., processor, ASIC, etc.).
[0084] The software may include an ordered listing of executable instructions for implementing logical functions and may be implemented in any "processor-readable medium" for use by or in conjunction with an instruction execution system, device or apparatus (such as a single-core or multi-core processor or a system containing a processor).
[0085] The blocks or operations of the methods or algorithms and functions described in conjunction with the embodiments disclosed herein may be implemented directly in hardware, software modules executed by a processor, or a combination of the two. If implemented in software, the functions may be stored as one or more instructions or codes on a tangible non-transitory computer-readable medium or transmitted via a tangible non-transitory computer-readable medium. The software module may be present in a random access memory (RAM), flash memory, read-only memory (ROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), registers, hard disks, removable disks, CD ROMs, or any other form of storage medium known in the art.
[0086] Although specific language has been used to describe the subject matter, any limitation caused thereby is not intended. As will be apparent to those skilled in the art, various work modifications may be made to the method to achieve the inventive concept as taught herein. The accompanying drawings and the foregoing description provide examples of embodiments. It will be appreciated by those skilled in the art that one or more of the elements described may be appropriately combined into a single functional element. Alternatively, some elements may be divided into multiple functional elements. Elements from one example may be added to another example.
Claims
1. A method for performing conditional handover CHO implemented in a user equipment UE, the method include: receiving, via a network entity, a CHO reconfiguration associated with a plurality of target cells; identifying one or more target cells from the plurality of target cells using the CHO reconfiguration, each of the one or more target cells having a higher signal strength than a serving cell associated with the UE; determining one or more handover trigger parameters associated with each of the one or more target cells using a network analysis-based machine learning model, wherein determining the one or more handover trigger parameters is based on one or more network parameters, historical handover data, and one or more mobility parameters; selecting a first target cell from the one or more target cells based on the one or more handover triggering parameters; and The CHO is performed from the serving cell to a first target cell.
2. The method according to claim 1, in, The one or more network parameters include at least one of the following: slice type, serving cell signal condition, target cell signal condition, service type, or one or more other network capabilities.
3. The method according to claim 1, in, The one or more mobility parameters include a speed of the UE.
4. The method according to claim 1, in, The historical handover data corresponds to one or more post-handover observations associated with the UE based on a previous CHO performed to a previous target cell among the plurality of target cells, the one or more post-handover observations comprising at least one of a ping-pong, a radio link failure, or a throughput degradation.
5. The method according to claim 1 or 2, in, The one or more handover triggering parameters include a handover margin HOM, a serving cell threshold, a target cell threshold, or a triggering time TTT between the serving cell and each of the one or more target cells.
6. The method according to claim 1, further comprising: include: generating a communication signal based on executing the CHO; as well as The communication signal is sent to the first target cell.
7. A system associated with a user equipment UE for performing conditional handover CHO, the system include: The processing circuit is configured to: receiving, via a network entity, a CHO reconfiguration associated with a plurality of target cells, identifying one or more target cells from the plurality of target cells using the CHO reconfiguration, each of the one or more target cells having a higher signal strength than a serving cell associated with the UE, determining one or more handover trigger parameters associated with each of the one or more target cells using a machine learning model based on network analysis, wherein determining the one or more handover trigger parameters is based on one or more network parameters, historical handover data, and one or more mobility parameters, selecting a first target cell from the one or more target cells based on the one or more handover triggering parameters, and The CHO is performed from the serving cell to a first target cell.
8. The system according to claim 7, in, The one or more network parameters include at least one of the following: slice type, serving cell signal condition, target cell signal condition, service type, or one or more other network capabilities.
9. The system according to claim 7, in, The one or more mobility parameters include a speed of the UE.
10. The system according to claim 7, in, The historical handover data corresponds to one or more post-handover observations associated with the UE based on a previous CHO performed to a previous target cell among the plurality of target cells, the one or more post-handover observations comprising at least one of a ping-pong, a radio link failure, or a throughput degradation.
11. The system according to claim 7 or 8, in, The one or more handover triggering parameters include a handover margin HOM, a serving cell threshold, a target cell threshold, or a triggering time TTT between the serving cell and each of the one or more target cells.
12. The system according to claim 7, in, The processing circuit is configured to: generating a communication signal based on executing the CHO; and The communication signal is sent to the first target cell.
13. A non-transitory computer readable medium storing instructions, which when executed by at least one processor of a user equipment (UE) causes the at least one processor to perform a method for performing a conditional handover (CHO), the method include: receiving, via a network entity, a CHO reconfiguration associated with a plurality of target cells; identifying one or more target cells from the plurality of target cells using the CHO reconfiguration, each of the one or more target cells having a higher signal strength than a serving cell associated with the UE; determining one or more handover trigger parameters associated with each of the one or more target cells using a network analysis-based machine learning model, wherein determining the one or more handover trigger parameters is based on one or more network parameters, historical handover data, and one or more mobility parameters; selecting a first target cell from the one or more target cells based on the one or more handover triggering parameters; and The CHO is performed from the serving cell to a first target cell.
14. The non-transitory computer readable medium of claim 13, in, The one or more network parameters include at least one of the following: slice type, serving cell signal condition, target cell signal condition, service type, or one or more other network capabilities.
15. The non-transitory computer readable medium of claim 13, in, The one or more mobility parameters include a speed of the UE.
16. The non-transitory computer readable medium of claim 13, in, The historical handover data corresponds to one or more post-handover observations associated with the UE based on a previous CHO performed to a previous target cell among the plurality of target cells, the one or more post-handover observations comprising at least one of a ping-pong, a radio link failure, or a throughput degradation.
17. The non-transitory computer readable medium of claim 13, in, The one or more handover triggering parameters include a handover margin HOM, a serving cell threshold, a target cell threshold, or a triggering time TTT between the serving cell and each of the one or more target cells.
18. The non-transitory computer readable medium of claim 13, in, The method further comprises: generating a communication signal based on executing the CHO; and The communication signal is sent to the first target cell.
Citation Information
Cited By
Switching method and device based on TTT, communication system and storage medium
CN120358555A
Ttt-based handover method, apparatus, communication system, and storage medium
CN120358555B
