Devices and methods of communication
By integrating AI-based mobility management in terminal devices to assess the necessity of cell switches, the solution addresses the incompleteness of current AI-based mobility management, enhancing mobility and network performance in 5G networks.
Patent Information
- Application Number
- PCT/CN2023/126007
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2023-10-23
- Publication Date
- 2025-05-01
AI Technical Summary
Current AI-based mobility management in 5G networks is incomplete and requires further development to optimize key performance indicators such as latency, reliability, and user experience.
The implementation of AI-based mobility management in terminal devices, which determines whether a cell switch to a target cell is necessary based on an AI model, and performs appropriate operations such as cancelling measurement reports or deactivating evaluation processes.
This approach enhances mobility management by avoiding unnecessary cell switches, improving terminal device mobility, and potentially optimizing network performance.
Smart Images

Figure CN2023126007_01052025_PF_FP_ABST
Abstract
Description
DEVICES AND METHODS OF COMMUNICATIONTECHNICAL FIELD
[0001] Embodiments of the present disclosure generally relate to the field of telecommunication, and in particular, to devices and methods of communication for artificial intelligence (AI) -based mobility management.BACKGROUND
[0002] The fifth generation (5G) networks are expected to meet challenges of consistent optimization of increasing numbers of key performance indicators (KPIs) including latency, reliability, connection density, user experience, energy efficiency, etc.. AI provides a powerful tool to help operators to improve network management and user experience, by analyzing data collected and autonomously processed that can yield further insights. Currently, AI-based mobility management is still incomplete and needs to be further developed.SUMMARY
[0003] In general, embodiments of the present disclosure provide methods, devices and computer storage media of communication for AI-based mobility management.
[0004] In a first aspect, there is provided a terminal device. The terminal device comprises a processor. The processor is configured to cause the terminal device to: determine, based on an artificial intelligence model, that a cell switch to a target cell is unnecessary; and perform a first operation of mobility management. The first operation of mobility management comprises at least one of the following: in accordance with a determination that a measurement report is to be initiated by an evaluation for the cell switch to the target cell, cancelling the measurement report; or in accordance with a determination that a command indicating the cell switch to the target cell is received from a network device providing a serving cell, cancelling the cell switch.
[0005] In a second aspect, there is provided a terminal device. The terminal device comprises a processor. The processor is configured to cause the terminal device to: determine, based on an artificial intelligence model, that a cell switch to a target cell is unnecessary; and perform a third operation of mobility management. The third operation of mobility management comprises at least one of the following: deactivating an evaluation for the cell switch to the target cell; or in accordance with a determination that the target cell fulfills a condition for the cell switch, cancelling the cell switch.
[0006] In a third aspect, there is provided a terminal device. The terminal device comprises a processor. The processor is configured to cause the terminal device to: determine, based on an output of an artificial intelligence model, predicted information of whether a cell switch to a cell is unnecessary; and transmit the predicted information to a network device.
[0007] In a fourth aspect, there is provided a method of communication. The method comprises: determining, at a terminal device and based on an artificial intelligence model, that a cell switch to a target cell is unnecessary; and performing a first operation of mobility management. The first operation of mobility management comprises at least one of the following: in accordance with a determination that a measurement report is to be initiated by an evaluation for the cell switch to the target cell, cancelling the measurement report; or in accordance with a determination that a command indicating the cell switch to the target cell is received from a network device providing a serving cell, cancelling the cell switch.
[0008] In a fifth aspect, there is provided a method of communication. The method comprises: determining, at a terminal device and based on an artificial intelligence model, that a cell switch to a target cell is unnecessary; and performing a third operation of mobility management. The third operation of mobility management comprises at least one of the following: deactivating an evaluation for the cell switch to the target cell; or in accordance with a determination that the target cell fulfills a condition for the cell switch, cancelling the cell switch.
[0009] In a sixth aspect, there is provided a method of communication. The method comprises: determining, based on an output of an artificial intelligence model, predicted information of whether a cell switch to a cell is unnecessary; and transmitting the predicted information to a network device.
[0010] In a seventh aspect, there is provided a computer readable medium having instructions stored thereon. The instructions, when executed on at least one processor, cause the at least one processor to perform the method according to the fourth or sixth aspect of the present disclosure.
[0011] Other features of the present disclosure will become easily comprehensible through the following description.BRIEF DESCRIPTION OF THE DRAWINGS
[0012] Through the more detailed description of some embodiments of the present disclosure in the accompanying drawings, the above and other objects, features and advantages of the present disclosure will become more apparent, wherein:
[0013] FIG. 1 illustrates an example communication network in which some embodiments of the present disclosure can be implemented;
[0014] FIG. 2 illustrates a schematic diagram of an AI model inference and monitoring in which some embodiments of the present disclosure can be implemented;
[0015] FIG. 3 illustrates a signaling chart illustrating an example process of communication for an AI-based cell switch according to embodiments of the present disclosure;
[0016] FIG. 4A illustrates a signaling chart illustrating an example AI-based handover (HO) procedure according to embodiments of the present disclosure;
[0017] FIG. 4B illustrates a signaling chart illustrating another example AI-based HO procedure according to embodiments of the present disclosure;
[0018] FIG. 5A illustrates a signaling chart illustrating an example AI-based layer 1 (L1) / layer 2 (L2) triggered mobility (LTM) procedure according to embodiments of the present disclosure;
[0019] FIG. 5B illustrates a signaling chart illustrating another example AI-based LTM procedure according to embodiments of the present disclosure;
[0020] FIG. 6 illustrates a signaling chart illustrating an example process of communication for an AI-based conditional cell switch according to embodiments of the present disclosure;
[0021] FIG. 7A illustrates a signaling chart illustrating an example AI-based conditional handover (CHO) procedure according to embodiments of the present disclosure;
[0022] FIG. 7B illustrates a signaling chart illustrating another example CHO procedure according to embodiments of the present disclosure;
[0023] FIG. 8 illustrates a signaling chart illustrating an example process of communication for AI-based mobility management at a network (NW) side according to embodiments of the present disclosure;
[0024] FIG. 9 illustrates an example method of communication implemented at a terminal device in accordance with some embodiments of the present disclosure;
[0025] FIG. 10 illustrates another example method of communication implemented at a terminal device in accordance with some embodiments of the present disclosure;
[0026] FIG. 11 illustrates still another example method of communication implemented at a terminal device in accordance with some embodiments of the present disclosure; and
[0027] FIG. 12 is a simplified block diagram of a device that is suitable for implementing embodiments of the present disclosure.
[0028] Throughout the drawings, the same or similar reference numerals represent the same or similar element.DETAILED DESCRIPTION
[0029] Principle of the present disclosure will now be described with reference to some embodiments. It is to be understood that these embodiments are described only for the purpose of illustration and help those skilled in the art to understand and implement the present disclosure, without suggesting any limitations as to the scope of the disclosure. The disclosure described herein can be implemented in various manners other than the ones described below.
[0030] In the following description and claims, unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skills in the art to which this disclosure belongs.
[0031] As used herein, the term ‘terminal device’ refers to any device having wireless or wired communication capabilities. Examples of the terminal device include, but not limited to, user equipment (UE) , personal computers, desktops, mobile phones, cellular phones, smart phones, personal digital assistants (PDAs) , portable computers, tablets, wearable devices, internet of things (IoT) devices, Ultra-reliable and Low Latency Communications (URLLC) devices, Internet of Everything (IoE) devices, machine type communication (MTC) devices, device on vehicle for V2X communication where X means pedestrian, vehicle, or infrastructure / network, devices for Integrated Access and Backhaul (IAB) , Space borne vehicles or Air borne vehicles in Non-terrestrial networks (NTN) including Satellites and High Altitude Platforms (HAPs) encompassing Unmanned Aircraft Systems (UAS) , eXtended Reality (XR) devices including different types of realities such as Augmented Reality (AR) , Mixed Reality (MR) and Virtual Reality (VR) , the unmanned aerial vehicle (UAV) commonly known as a drone which is an aircraft without any human pilot, devices on high speed train (HST) , or image capture devices such as digital cameras, sensors, gaming devices, music storage and playback appliances, or Internet appliances enabling wireless or wired Internet access and browsing and the like. The ‘terminal device’ can further has ‘multicast / broadcast’ feature, to support public safety and mission critical, V2X applications, transparent IPv4 / IPv6 multicast delivery, IPTV, smart TV, radio services, software delivery over wireless, group communications and IoT applications. It may also incorporate one or multiple Subscriber Identity Module (SIM) as known as Multi-SIM. The term “terminal device” can be used interchangeably with a UE, a mobile station, a subscriber station, a mobile terminal, a user terminal or a wireless device.
[0032] The term “network device” may refer to a device which is capable of providing or hosting a cell or coverage where terminal devices can communicate. Examples of an access network device include, but not limited to, a satellite, a unmanned aerial systems (UAS) platform, a Node B (NodeB or NB) , an evolved NodeB (eNodeB or eNB) , a next generation NodeB (gNB) , a transmission reception point (TRP) , a remote radio unit (RRU) , a radio head (RH) , a remote radio head (RRH) , an IAB node, a low power node such as a femto node, a pico node, a reconfigurable intelligent surface (RIS) , and the like.
[0033] The terminal device or the network device may have AI or machine learning (ML) capability. It generally includes a model which has been trained from numerous collected data for a specific function, and can be used to predict some information.
[0034] The terminal or the network device may work on several frequency ranges, e.g. FR1 (410 MHz to 7125 MHz) , FR2 (24.25GHz to 71GHz) , frequency band larger than 100GHz as well as Tera Hertz (THz) . It can further work on licensed / unlicensed / shared spectrum. The terminal device may have more than one connection with the network devices under Multi-Radio Dual Connectivity (MR-DC) application scenario. The terminal device or the network device can work on full duplex, flexible duplex and cross division duplex modes.
[0035] The embodiments of the present disclosure may be performed in test equipment, e.g. signal generator, signal analyzer, spectrum analyzer, network analyzer, test terminal device, test network device, channel emulator.
[0036] In one embodiment, the terminal device may be connected with a first network device and a second network device. One of the first network device and the second network device may be a master node and the other one may be a secondary node. The first network device and the second network device may use different radio access technologies (RATs) . In one embodiment, the first network device may be a first RAT device and the second network device may be a second RAT device. In one embodiment, the first RAT device is eNB and the second RAT device is gNB. Information related with different RATs may be transmitted to the terminal device from at least one of the first network device or the second network device. In one embodiment, first information may be transmitted to the terminal device from the first network device and second information may be transmitted to the terminal device from the second network device directly or via the first network device. In one embodiment, information related with configuration for the terminal device configured by the second network device may be transmitted from the second network device via the first network device. Information related with reconfiguration for the terminal device configured by the second network device may be transmitted to the terminal device from the second network device directly or via the first network device.
[0037] As used herein, the singular forms ‘a’ , ‘an’ and ‘the’ are intended to include the plural forms as well, unless the context clearly indicates otherwise. The term ‘includes’ and its variants are to be read as open terms that mean ‘includes, but is not limited to. ’ The term ‘based on’ is to be read as ‘at least in part based on. ’ The term ‘one embodiment’ and ‘an embodiment’ are to be read as ‘at least one embodiment. ’ The term ‘another embodiment’ is to be read as ‘at least one other embodiment. ’ The terms ‘first, ’ ‘second, ’ and the like may refer to different or same objects. Other definitions, explicit and implicit, may be included below.
[0038] In some examples, values, procedures, or apparatus are referred to as ‘best, ’ ‘lowest, ’ ‘highest, ’ ‘minimum, ’ ‘maximum, ’ or the like. It will be appreciated that such descriptions are intended to indicate that a selection among many used functional alternatives can be made, and such selections need not be better, smaller, higher, or otherwise preferable to other selections.
[0039] In the context of the present disclosure, the term “AI” may be interchangeably used with “machine learning (ML) ” or “AI / ML” . The term “AI model” may be interchangeably used with “ML model” or “AI / ML model” . In the context of the present disclosure, the term “above” herein may be interchangeably used with “higher than or equal to” or “greater than or equal to” . The term “below” herein may be interchangeably used with “lower than or equal to” or “smaller than or equal to” . The term “a neighbor cell” herein may be interchangeably used with “a target cell” or “a candidate cell” .
[0040] Embodiments of the present disclosure provide a solution of AI-based mobility management. In one aspect, upon determination that a cell switch to a target cell is unnecessary based on an AI model, a terminal device performs a first operation of mobility management comprising at least one of the following: if a measurement report is to be initiated by an evaluation for the cell switch to the target cell, cancelling the measurement report; or if a command indicating the cell switch to the target cell is received from a network device providing a serving cell, cancelling the cell switch. In this way, a cell switch procedure such as HO or LTM may be enhanced based on AI prediction.
[0041] In another aspect, upon determination that a cell switch to a target cell is unnecessary based on an AI model, a terminal device performs a third operation of mobility management comprising at least one of the following: deactivating an evaluation for the cell switch to the target cell; or if the target cell fulfills a condition for the cell switch, cancelling the cell switch. In this way, a conditional cell switch procedure such as CHO may be enhanced based on AI prediction.
[0042] In still another aspect, a terminal device determines predicted information of whether a cell switch to a cell is unnecessary and transmits the predicted information to a network device. In this way, AI-based mobility management at a NW side may be facilitated.
[0043] Principles and implementations of the present disclosure will be described in detail below with reference to the figures.
[0044] EXAMPLE OF COMMUNICATION NETWORK
[0045] FIG. 1 illustrates a schematic diagram of an example communication network 100 in which some embodiments of the present disclosure can be implemented. As shown in FIG. 1, the communication network 100 may include a terminal device 110 and network devices 120, 130 and 140. The network device 120 may provide a cell 121 to serve one or more terminal devices, the network device 130 provides a cell 131 to serve one or more terminal devices, and the network device 140 provides a cell 141 to serve one or more terminal devices. It is to be understood that more cells may be provided by any of the network devices 120, 130 or 140.
[0046] In some embodiments, the network device 120, 130 and 140 may be different network devices. In some embodiments, any two or all of the network device 120, 130 and 140 may be the same network device.
[0047] It is to be understood that the number of devices or cells in FIG. 1 is given for the purpose of illustration without suggesting any limitations to the present disclosure. The communication network 100 may include any suitable number of network devices and / or terminal devices and / or cells adapted for implementing implementations of the present disclosure.
[0048] As shown in FIG. 1, the terminal device 110 and each of the network devices 120, 130 and 140 may communicate with each other via a channel such as a wireless communication channel. The communications in the communication network 100 may conform to any suitable standards including, but not limited to, Global System for Mobile Communications (GSM) , Long Term Evolution (LTE) , LTE-Evolution, LTE-Advanced (LTE-A) , New Radio (NR) , Wideband Code Division Multiple Access (WCDMA) , Code Division Multiple Access (CDMA) , GSM EDGE Radio Access Network (GERAN) , Machine Type Communication (MTC) and the like. The embodiments of the present disclosure may be performed according to any generation communication protocols either currently known or to be developed in the future. Examples of the communication protocols include, but not limited to, the first generation (1G) , the second generation (2G) , 2.5G, 2.75G, the third generation (3G) , the fourth generation (4G) , 4.5G, the fifth generation (5G) communication protocols, 5.5G, 5G-Advanced networks, or the sixth generation (6G) networks.
[0049] It is assumed that the cell 121 serves as a serving cell of the terminal device 110, and the cells 131 and 141 serve as candidate cells of the terminal device 110.
[0050] In some scenarios, the terminal device 110 may perform L3 measurements on the serving cell and the candidate cells and evaluate the measurement results. The terminal device 110 may transmit a measurement report indicating L3 measurement result (s) of the cell (s) fulfilling a condition (e.g., an event A3) to the network device 120 (e.g., source gNB) . Based on the measurement report, the network device 120 may make a HO decision for one (e.g., the cell 131) of the candidate cells. After negotiation with the network device 130 (e.g., target gNB) , the network device 120 may transmit a HO command to initiate a HO of the terminal device 110 to the cell 131. Based on the HO command, the terminal device 110 may detach from the cell 121 and synchronize to the cell 131. This procedure may be called as a HO procedure.
[0051] In some scenarios, the terminal device 110 may perform L3 measurements on the serving cell and the candidate cells and evaluate the measurement results. The terminal device 110 may transmit a measurement report indicating L3 measurement result (s) of the cell (s) fulfilling a condition (e.g., an event A3) to the network device 120 (e.g., source gNB) . Based on the measurement report, the network device 120 may negotiate with the network devices 130 and 140 (e.g., candidate gNBs) providing the candidate cells, and obtain configurations of CHO conditions for the candidate cells. The network device 120 may transmit the configurations of CHO conditions for the candidate cells to the terminal device 110. The terminal device 110 may evaluate the CHO conditions. Upon one of the CHO conditions (e.g., for the cell 131) is satisfied, the terminal device 110 may detach from the cell 121 and synchronize to the cell 131. This procedure may be called as a CHO procedure.
[0052] In some scenarios, the terminal device 110 may perform L3 measurements on the serving cell and the candidate cells and evaluate the measurement results. The terminal device 110 may transmit a measurement report indicating L3 measurement result (s) of the cell (s) fulfilling a condition (e.g., an event A3) to the network device 120 (e.g., source gNB) . Based on the measurement report, the network device 120 may decide to use LTM and initiate LTM candidate preparation. The network device 120 may transmit, to the terminal device 110, a configuration (also referred to as an LTM candidate configuration herein) of one or multiple LTM candidate cells. The terminal device 110 may store the configuration of LTM candidate cell (s) . The terminal device 110 may perform downlink (DL) and uplink (UL) synchronization with candidate cell (s) before receiving a cell switch command. Then the terminal device 110 may perform L1 measurements on the configured LTM candidate cell (s) and transmit a measurement report indicating results of the L1 measurements. The network device 120 may decide to execute an LTM cell switch to a target cell (e.g., the cell 131) , and transmits a medium access control control element (MAC CE) triggering the LTM cell switch to the target cell. The terminal device 110 may detach from the cell 121 and apply a configuration of the cell 131. This procedure may be called as an LTM procedure.
[0053] In the context of the present disclosure, the term “a cell switch” herein may refer to a HO procedure, a CHO procedure, an LTM cell switch procedure or any other cell switch procedures existing or to be developed in future. The term “a cell switch” herein may be interchangeably used with “HO” , “CHO” , “LTM cell switch” , or “RRCReconfigurationwithSync” . The term “a conditional cell switch” herein may refer to a CHO procedure, a conditional LTM cell switch procedure or any other conditional cell switch procedures existing or to be developed in future. The term “a conditional cell switch” herein may be interchangeably used with “CHO” , “conditional LTM cell switch” or “cell switch” .
[0054] FIG. 2 illustrates a schematic diagram 200 of an AI model inference and monitoring in which some embodiments of the present disclosure can be implemented. As shown in FIG. 2, model training may be performed based on training data. An AI model may be deployed or updated by the model training. With an input data set as an input of the AI model, an output data set may be obtained by model inference. This is an AI model inference procedure.
[0055] With reference to FIG. 2, a model monitoring may be performed to monitor performance of the model inference of the AI model. The model monitoring may be classified into three types: comparison between inference results and ground-truth results; evaluation for system performance (e.g., throughout, block error rate (BLER) , reference signal receiving power (RSRP) , positive acknowledgement (ACK) / NACK) ; distribution detection for the input or output data set.
[0056] Returning to FIG. 1, in some scenarios, the terminal device 110 may move from the cell 121 to the cell 141 across the cell 131 along a trajectory 150. During the movement, a measurement result of the cell 131 may fulfill a cell switch criterion configured for the terminal device 110 no matter the criterion is from any cell switch procedure. Conventionally, the terminal device 110 may probably connect with the cell 131 without considering residence time in the cell 131. If the terminal device 110 only stays in the cell 131 for few seconds, actually there is no need to perform a cell switch. Otherwise, unnecessary cell switch happens.
[0057] Mobility management such as a cell switch may be performed based on AI prediction of an AI model. For example, moving or staying information (e.g., the trajectory 150) of the terminal device 110 may be predicted. Based on the predicted information, a cell switch may be enhanced.
[0058] Thus, embodiments of the present disclosure provide a solution of AI-based mobility management so as to avoid an unnecessary cell switch and improve terminal device mobility robust. In the solution, a terminal device determines information of whether a cell switch to a cell is unnecessary based on an AI model, and performs mobility management based on the determined information. More details of the solution will be described below.
[0059] EXAMPLE IMPLEMENTATION OF DETERMINATION OF UNNECESSARY CELL SWITCH
[0060] Embodiments of the present disclosure provide a solution of determining whether a cell switch to a cell (e.g., target cell) is unnecessary. In the solution, a terminal device may obtain predicted information for the cell from an output of an AI model, and determine whether the cell switch to the cell is unnecessary at least based on the predicted information.
[0061] In some embodiments, an input and an output of the AI model may be defined for AI-based cell switch from cell prediction point of view. In some embodiments, the input of the AI model may comprise location information of the terminal device 110. For example, the location information of the terminal device 110 may comprise a positioning parameter of the terminal device 110 such as longitude, latitude, or altitude with different time instances. It is to be understood that any other suitable location information may also be feasible.
[0062] In some embodiments, the input of the AI model may comprise location information of a cell (e.g., the cell 121, 131 or 141) . For example, the location information of the cell may comprise a positioning parameter of the cell such as a fixed longitude, latitude, or altitude. It is to be understood that any other suitable location information may also be feasible.
[0063] In some embodiments, the input of the AI model may comprise an identity (ID) of a serving cell (e.g., the cell 121) and ID (s) of one or more neighbor cells (e.g., the cell 131 and / or 141) . For example, the ID of the serving or neighbor cell may comprise at least one of physical cell identity (PCI) , cell ID, a public land mobile network (PLMN) ID, or a network device ID (e.g., gNB ID) . It is to be understood that any other suitable ID information may also be feasible.
[0064] In some embodiments, the input of the AI model may comprise a measurement result of the serving cell and measurement result (s) of the one or more neighbor cells. For example, the measurement result may comprise reference signal received power (RSRP) , reference signal received quality (RSRQ) , signal to interference plus noise ratio (SINR) or any other suitable metrics.
[0065] In some embodiments, the input of the AI model may comprise velocity information of the terminal device 110. For example, a unit of a velocity may be km / h, m / s or any other units.
[0066] In some embodiments, the input of the AI model may comprise angle information of a moving direction of the terminal device 110. For example, an angle (e.g., 15°or 30°) with respect to a predetermined direction (e.g., the north or east) . It is to be understood that any other suitable angle information may also be feasible.
[0067] In some embodiments, the input of the AI model may comprise a type of the terminal device 110. For example, the type may indicate enhanced mobile broadband (eMBB) device, reduced capability (RedCap) device, an IoT device, or any combination of them.
[0068] In some embodiments, the input of the AI model may comprise a history of a cell switch of the terminal device 110. For example, the history may comprise a record of a cell for a previous cell switch, e.g., a cell ID of the cell and a corresponding residence time of the terminal device 110 in the cell. It is to be understood that the record may have any other suitable forms. It is also to be understood that any combination of the above input information of the AI model may also be feasible.
[0069] In some embodiments, the output of the AI model may indicate an ID of a predicted cell. For example, the ID of the predicted cell may comprise at least one of PCI, cell ID, a PLMN ID, or a network device ID (e.g., gNB ID) . It is to be understood that any other suitable ID information may also be feasible.
[0070] In some embodiments, the output of the AI model may indicate a residence time for the predicted cell. For example, the residence time may comprise a predicted time duration for which the terminal device 110 will stay in the predicted cell. The unit of the predicted time duration may be second. It is to be understood that any other suitable forms of the residence time may also be feasible.
[0071] In some embodiments, the output of the AI model may indicate a trajectory (i.e., a predicted trajectory) of the terminal device 110. For example, the predicted trajectory may comprise a positioning parameter of the terminal device 110 such as a predicted longitude, latitude, or altitude with different time instances. It is to be understood that any other suitable trajectory information may also be feasible.
[0072] In some embodiments, the output of the AI model may indicate a location (i.e., a predicted location) of the predicted cell. For example, the predicted location may comprise a positioning parameter of the predicted cell such as a fixed longitude, latitude, or altitude. It is to be understood that any other suitable location information may also be feasible.
[0073] In some embodiments, the output of the AI model may comprise an indication of whether the cell switch to the predicted cell is unnecessary. In some embodiments, if the output of the AI model indicates a cell (e.g., comprise an ID of the cell) , the terminal device 110 may consider the cell as a necessary cell. In some embodiments, if the output of the AI model indicates the cell, the terminal device 110 may consider the cell as an unnecessary cell.
[0074] In the context of the present disclosure, the term “a necessary cell” may refer to a cell to which a cell switch is necessary, and the term “an unnecessary cell” may refer to a cell to which a cell switch is unnecessary.
[0075] For illustration, an example output of the AI model may be described in Table 1.
[0076] Table 1
[0077] It is to be understood that any combination of the above output information of the AI model may also be feasible.
[0078] Based on the output of the AI model, the terminal device 110 may determine whether a cell switch to a target cell is worth to be performed, i.e., whether the target cell is an unnecessary cell or a necessary cell.
[0079] In some embodiments, if the residence time for the target cell is above a time threshold, the terminal device 110 may determine that the cell switch to the target cell is necessary. In some embodiments, if the residence time for the target cell is below the time threshold, the terminal device 110 may determine that the cell switch to the target cell is unnecessary.
[0080] In an example of Table 1, based on the AI model, the terminal device 110 predicts 2 cells as candidate cells for cell switch. It is assumed that a time threshold is 5s. Thus, the cell 131 will be considered as an unnecessary cell (as 4s < the time threshold) , and the cell 141 will be considered as a necessary cell (as 39s > the time threshold) .
[0081] For illustration, an example procedure may be described as below.
[0082] 1> For each predicted / candidate cell:
[0083] 2> If the residence time for this cell is lower than the threshold_residenceTime:
[0084] 3> Consider this cell as an unnecessary cell;
[0085] 2> If the residence time for this cell is greater than the threshold_residenceTime:
[0086] 3> Consider this cell as a necessary cell.
[0087] In this example, “threshold_residenceTime” denotes the time threshold.
[0088] Besides the residence time, a confidence of model inference of the AI model may also be considered in determination of whether the target cell is an unnecessary cell or a necessary cell. For example, if AI inference outputs a predicted cell ID with a residence time of 20s and a confidence of 80%, it means that a prediction accuracy of 20s is 80%. In some embodiments, the confidence of model inference may be obtained as an output of the AI model together with the predicted information. It is to be understood that the confidence of model inference may be determined in any suitable ways, and the present disclosure does not limit this aspect.
[0089] In some embodiments, if the residence time for the target cell is above the time threshold (e.g., denoted as threshold_residenceTime) and the confidence of model inference is above a confidence threshold (e.g., denoted as threshold_confidence) , the terminal device 110 may determine that the cell switch to the target cell is necessary. If the residence time for the target cell is below the time threshold and the confidence of model inference is above the confidence threshold, the terminal device 110 may determine that the cell switch to the target cell is unnecessary.
[0090] In some embodiments, if the residence time for the target cell is above the time threshold and the confidence of model inference is below the confidence threshold, the terminal device 110 may perform mobility management without considering whether the cell switch to the target cell is unnecessary, e.g., perform a cell switch based on a conventional procedure without a special handling for the target cell. In some embodiments, if the residence time for the target cell is below the time threshold and the confidence of model inference is below the confidence threshold, the terminal device 110 may perform mobility management without considering whether the cell switch to the target cell is unnecessary, e.g., perform a cell switch based on a conventional procedure without a special handling for the target cell.
[0091] So far, prediction or determination of the information whether a cell switch to a cell is unnecessary is described. Mobility management based on the determined information will be described with reference to FIGs. 3 to 8 below.
[0092] EXAMPLE IMPLEMENTATION OF AI-BASED CELL SWITCH
[0093] Embodiments of the present disclosure provide a solution of managing a cell switch based on the determined information of whether a cell switch to a cell is unnecessary. The solution will be described in connection with FIGs. 3 to 5B.
[0094] FIG. 3 illustrates a signaling chart illustrating an example process 300 of communication for an AI-based cell switch according to embodiments of the present disclosure. For the purpose of discussion, the process 300 will be described with reference to FIG. 1. The process 300 may involve the terminal device 110 and the network device 120 as illustrated in FIG. 1. It is to be understood that the steps and the order of the steps in FIG. 3 are merely for illustration, and not for limitation. For example, the order of the steps may be changed. Some of the steps may be omitted or any other suitable additional steps may be added. It is assumed that model training and deployment of the AI model is finished, and the AI model is deployed at the terminal device 110. The terminal device 110 is served by the network device 120.
[0095] As shown in FIG. 3, the terminal device 110 may determine 310 that a cell switch to a target cell (e.g., the cell 131) is unnecessary based on the AI model. In this case, the terminal device 110 may perform 320 an operation (for convenience, also referred to as a first operation herein) of mobility management.
[0096] With reference to FIG. 3, in some embodiments, an evaluation for the cell switch to the target cell may trigger a measurement report. As the cell switch is predicted to be unnecessary, the terminal device 110 may cancel 321 the measurement report so as to avoid the unnecessary cell switch. In some embodiments, the evaluation may be based on an L3 measurement result for the target cell. In some embodiments, the evaluation may be based on an L1 measurement result for the target cell.
[0097] In some embodiments, the terminal device 110 may receive 322, from the network device 120, a command indicating the cell switch to the target cell. As the cell switch is predicted to be unnecessary, the terminal device 110 may cancel 323 the cell switch so as to avoid the unnecessary cell switch. In some embodiments, the command may be carried in an RRC signaling such as RRCReconfigurationwithSync. In some embodiments, the command may be carried in a MAC CE such as an LTM cell switch MAC CE.
[0098] Continuing to refer to FIG. 3, the terminal device 110 may determine 330 that the cell switch to the target cell (e.g., the cell 131) is necessary based on the AI model. In this case, the terminal device 110 may perform 340 an operation (for convenience, also referred to as a second operation herein) of mobility management.
[0099] With reference to FIG. 3, in some embodiments, an evaluation for the cell switch to the target cell may trigger a measurement report. As the cell switch is predicted to be necessary, the terminal device 110 may transmit 341 the measurement report so as to facilitate the necessary cell switch. In some embodiments, the evaluation may be based on an L3 measurement result for the target cell. In some embodiments, the evaluation may be based on an L1 measurement result for the target cell.
[0100] In some embodiments, the terminal device 110 may receive 342, from the network device 120, a command indicating the cell switch to the target cell. As the cell switch is predicted to be necessary, the terminal device 110 may perform 343 the cell switch so as to facilitate the necessary cell switch. In some embodiments, the command may be carried in an RRC signaling. In some embodiments, the command may be carried in a MAC CE.
[0101] For illustration, some example embodiments will be further described in connection with FIGs. 4A to 5B. FIG. 4A illustrates a signaling chart illustrating an example AI-based HO procedure 400A according to embodiments of the present disclosure. For the purpose of discussion, the procedure 400A will be described with reference to FIG. 1.
[0102] With reference to FIG. 4A, the terminal device 110 may perform 410 an evaluation for HO by L3 measurements on a serving cell and one or more neighbor cells. In some embodiments, the terminal device 110 may perform the evaluation based on an event A3. It is to be understood that any other suitable events existing or to be developed in future may also be feasible. As a result of the evaluation (e.g., the event A3 is fulfilled) , a measurement report may be triggered by the L3 measurement result of the target cell.
[0103] Continuing to refer to FIG. 4A, the terminal device 110 may determine 420 whether to initiate the measurement report based on the information of whether the cell switch (i.e., HO) to the target cell is unnecessary. If HO to the target cell is unnecessary, the terminal device 110 may not initiate 421 the measurement report. That is, the measurement report is cancelled. In this way, an unnecessary HO to the target cell may be avoided.
[0104] Continuing to refer to FIG. 4A, if HO to the target cell is necessary, the terminal device 110 may transmit 422 the measurement report to the network device 120. The network device 120 may make 423 a HO decision. In this way, a necessary HO to the target cell may be facilitated.
[0105] It is to be understood that more details in the AI-based HO procedure 400A are similar as that in a conventional HO procedure, and thus are omitted here for conciseness.
[0106] For illustration, an example procedure may be described as below.
[0107] 2> if the reportType is set to eventTriggered and if the entry condition applicable for this event, i.e. the event corresponding with the eventId of the corresponding reportConfig within VarMeasConfig, is fulfilled for one or more applicable cells for all measurements after layer 3 filtering taken during timeToTrigger defined for this event within the VarMeasConfig, while the VarMeasReportList does not include a measurement reporting entry for this measId (a first cell triggers the event) :
[0108] 3> if AI information (e.g., predicted / candidate cell ID and the corresponding residence time, threshold_residenceTime) is available, for the triggered cell:
[0109] 4> if, for the triggered cell, the corresponding residence time is lower than threshold_residenceTime:
[0110] 5> not include the concerned cell (s) in the cellsTriggeredList defined within the VarMeasReportList for this measId.
[0111] 5> not initiate the measurement reporting procedure, which the procedure is end.
[0112] 4> else if for the triggered cell, the corresponding residence time is greater than threshold_residenceTime (i.e., as legacy) :
[0113] 5> include a measurement reporting entry within the VarMeasReportList for this measId;
[0114] 5> set the numberOfReportsSent defined within the VarMeasReportList for this measId to 0;
[0115] 5> include the concerned cell (s) in the cellsTriggeredList defined within the VarMeasReportList for this measId;
[0116] 5> if useT312 is set to true in reportConfig for this event:
[0117] 6> if T310 for the corresponding SpCell is running; and
[0118] 6> if T312 is not running for corresponding SpCell:
[0119] 7> start timer T312 for the corresponding SpCell with the value of T312 configured in the corresponding measObjectNR;
[0120] 5> initiate the measurement reporting procedure;
[0121] 2> else if the reportType is set to eventTriggered and if the entry condition applicable for this event, i.e. the event corresponding with the eventId of the corresponding reportConfig within VarMeasConfig, is fulfilled for one or more applicable cells not included in the cellsTriggeredList for all measurements after layer 3 filtering taken during timeToTrigger defined for this event within the VarMeasConfig (a subsequent cell triggers the event) :
[0122] 3> if AI information (e.g., predicted / candidate cell ID and the corresponding residence time, threshold_residenceTime) is available, for each triggered cell:
[0123] 4> if, for each triggered cell, the corresponding residence time is lower than threshold_residenceTime:
[0124] 5> not include the concerned cell (s) in the cellsTriggeredList defined within the VarMeasReportList for this measId.
[0125] 4> else if for each triggered cell, the corresponding residence time is greater than threshold_residenceTime (i.e., as legacy) :
[0126] 5> set the numberOfReportsSent defined within the VarMeasReportList for this measId to 0;
[0127] 5> include the concerned cell (s) in the cellsTriggeredList defined within the VarMeasReportList for this measId;
[0128] 5> if useT312 is set to true in reportConfig for this event:
[0129] 6> if T310 for the corresponding SpCell is running; and
[0130] 6> if T312 is not running for corresponding SpCell:
[0131] 7> start timer T312 for the corresponding SpCell with the value of T312 configured in the corresponding measObjectNR;
[0132] 5> initiate the measurement reporting procedure.
[0133] In this example, reportType denotes a type of a measurement report, eventTriggered denotes the measurement report is triggered by an event, eventId denotes an ID of the event, VarMeasConfig denotes a configuration of the measurement report, reportConfig denotes a report configuration, VarMeasReportList denotes a list of configurations of measurement reports, threshold_residenceTime denotes a threshold for a residence time, cellsTriggeredList denotes a list of cells triggered with a measurement report, measId denotes an ID of a measurement configuration, numberOfReportsSent denotes the number of sent measurement reports, and measObjectNR denotes a measurement object for NR.
[0134] FIG. 4B illustrates a signaling chart illustrating another example AI-based HO procedure 400B according to embodiments of the present disclosure. For the purpose of discussion, the procedure 400B will be described with reference to FIG. 1.
[0135] With reference to FIG. 4B, the terminal device 110 may perform 450 an evaluation for HO by L3 measurements on a serving cell and one or more neighbor cells. In some embodiments, the terminal device 110 may perform the evaluation based on an event A3. It is to be understood that any other suitable events existing or to be developed in future may also be feasible. As a result of the evaluation (e.g., the event A3 is fulfilled) , a measurement report may be triggered by the L3 measurement result of the target cell.
[0136] Continuing to refer to FIG. 4B, the terminal device 110 may transmit 451 the measurement report to the network device 120. Based on the measurement report, the network device 120 may make 452 a HO decision for the cell 131 provided by the network device 130. The network device 120 (i.e., source gNB) may transmit 453 a HO request to the network device 130 (i.e., target gNB) . The network device 130 may perform 454 admission control and transmit 455 an acknowledgement for the HO request to the network device 120. Then the network device 120 may transmit 456 a HO command (e.g., an RRC message) to initiate a HO of the terminal device 110 to the cell 131.
[0137] Upon reception of the HO command, the terminal device 110 may determine 460 whether to perform the HO. If the HO to the target cell is unnecessary, the terminal device 110 may not perform the HO. In some embodiments, the terminal device 110 may ignore 461 the HO command, i.e., may not make a response to the HO command. In this way, an unnecessary HO may be avoided.
[0138] In some embodiments, the terminal device 110 may transmit 462 a response to the HO command. The response indicates a rejection for the HO. In some embodiments, the terminal device 110 may transmit the response indicating the rejection via an RRC message. In some embodiments, the terminal device 110 may transmit the response indicating the rejection via a MAC CE. In some embodiments, the terminal device 110 may transmit the response indicating the rejection via uplink control information (UCI) .
[0139] In some embodiments, if the HO is rejected or ignored, the network device 120 (e.g., source gNB) may transmit 463, to the network device 130 (e.g., target gNB) , an indication that the HO is cancelled. It is to be understood that the indication may be transmitted via any suitable Xn messages.
[0140] If the HO to the target cell is necessary, the terminal device 110 may perform 464 the HO. For example, the terminal device 110 may detach from the cell 121 and synchronize to the cell 131.
[0141] It is to be understood that more details in the AI-based HO procedure 400B are similar as that in a conventional HO procedure, and thus are omitted for conciseness.
[0142] For illustration, an example procedure may be described as below.
[0143] UE performs the following actions based on a received CellGroupConfig IE:
[0144] 1> if the CellGroupConfig contains the spCellConfig with reconfigurationWithSync:
[0145] 2> if AI information (e.g., predicted / candidate cell ID and the corresponding residence time, threshold_residenceTime) is available, for the triggered cell:
[0146] 3> if, for the triggered cell, the corresponding residence time is lower than threshold_residenceTime:
[0147] 4> not perform Reconfiguration with sync, upon which the procedure (i.e., sync) ends;
[0148] 3> else if for the triggered cell, the corresponding residence time is greater than threshold_residenceTime:
[0149] 4> perform Reconfiguration with sync to the corresponding cell.
[0150] In this example, CellGroupConfig denotes a configuration of a cell group, spCellConfig denotes a configuration of a special cell (SpCell) of the cell group, and threshold_residenceTime denotes a threshold for a residence time.
[0151] FIG. 5A illustrates a signaling chart illustrating an example AI-based LTM procedure 500A according to embodiments of the present disclosure. For the purpose of discussion, the procedure 500A will be described with reference to FIG. 1.
[0152] With reference to FIG. 5A, the terminal device 110 may perform 510 an evaluation for a cell switch by L3 measurements on a serving cell and one or more neighbor cells. In some embodiments, the terminal device 110 may perform the evaluation based on an event A3. It is to be understood that any other suitable events existing or to be developed in future may also be feasible. As a result of the evaluation (e.g., the event A3 is fulfilled) , a measurement report may be triggered by the L3 measurement result of the target cell.
[0153] Continuing to refer to FIG. 5A, the terminal device 110 may transmit 511 the measurement report to the network device 120. Based on the measurement report, the network device 120 may decide to use LTM and initiate 512 LTM candidate preparation. The network device 120 may transmit 513, to the terminal device 110, an LTM candidate configuration of one or multiple LTM candidate cells. The terminal device 110 may store the configuration of LTM candidate cell (s) . As shown in FIG. 5A, the terminal device 110 may perform 514 DL and UL synchronization with candidate cell (s) before receiving a cell switch command.
[0154] Based on the LTM candidate configuration, the terminal device 110 may perform L1 measurements on the configured LTM candidate cell (s) . With reference to FIG. 5A, the terminal device 110 may determine 520 whether an L1 measurement is to be performed on a candidate cell. If the candidate cell is an unnecessary cell, the terminal device 110 may not perform the L1 measurement on the candidate cell and may not transmit 521 an L1 measurement report for the candidate cell. In this way, an unnecessary LTM cell switch to the candidate cell may be avoided.
[0155] If the candidate cell is a necessary cell, the terminal device 110 may perform the L1 measurement on the candidate cell and may transmit 522 the L1 measurement report for the candidate cell. Based on the L1 measurement report, the network device 120 may decide to execute an LTM cell switch to the candidate cell. In this way, a necessary LTM cell switch to the candidate cell may be facilitated.
[0156] It is to be understood that more details in the AI-based LTM procedure 500A are similar as that in a conventional LTM procedure, and thus are omitted here for conciseness.
[0157] For illustration, an example procedure may be described as below.
[0158] When the reception of CSI-MeasConfig within RRCReconfiguration, the UE shall:
[0159] 1> if LTM-CSI-ReportConfig is included:
[0160] 2> if, for the candidate cell indicated by LTM cell switch command MAC CE, the corresponding residence time is lower than threshold_residenceTime:
[0161] 3> may not perform the CSI measurements based on LTM-CSI-ResourceConfig for this candidate cell;
[0162] 3> may not perform L1 measurement report for this candidate cell;
[0163] 2> if, for the candidate cell indicated by LTM cell switch command MAC CE, the corresponding residence time is greater than threshold_residenceTime:
[0164] 3> perform CSI measurements and L1 measurement report.
[0165] In this example, CSI-MeasConfig denotes a configuration of a channel status information (CSI) measurement, LTM-CSI-ReportConfig denotes a configuration of a CSI report for LTM, LTM-CSI-ResourceConfig denotes a configuration of a resource of a CSI measurement for LTM, and threshold_residenceTime denotes a threshold for a residence time.
[0166] FIG. 5B illustrates a signaling chart illustrating another example AI-based LTM procedure 500B according to embodiments of the present disclosure. For the purpose of discussion, the procedure 500B will be described with reference to FIG. 1.
[0167] With reference to FIG. 5B, the terminal device 110 may perform 550 an evaluation for a cell switch by L3 measurements on a serving cell and one or more neighbor cells. In some embodiments, the terminal device 110 may perform the evaluation based on an event A3. It is to be understood that any other suitable events existing or to be developed in future may also be feasible. As a result of the evaluation (e.g., the event A3 is fulfilled) , a measurement report may be triggered by the L3 measurement result of the target cell.
[0168] Continuing to refer to FIG. 5B, the terminal device 110 may transmit 551 the measurement report to the network device 120. Based on the measurement report, the network device 120 may decide to use LTM and initiate 552 LTM candidate preparation. The network device 120 may transmit 553, to the terminal device 110, an LTM candidate configuration of one or multiple LTM candidate cells. The terminal device 110 may store the configuration of LTM candidate cell (s) . As shown in FIG. 5B, the terminal device 110 may perform 554 DL and UL synchronization with candidate cell (s) before receiving a cell switch command.
[0169] Based on the LTM candidate configuration, the terminal device 110 may perform L1 measurements on the configured LTM candidate cell (s) and transmit 555 an L1 measurement report indicating results of the L1 measurements. The network device 120 may decide 556 to execute an LTM cell switch to a target cell (e.g., the cell 131) , and transmits 557 a MAC CE triggering the LTM cell switch to the target cell.
[0170] With reference to FIG. 5B, upon reception of the MAC CE, the terminal device 110 may determine 560 whether to perform an LTM cell switch. If the LTM cell switch to the target cell is unnecessary, the terminal device 110 may not perform the LTM cell switch. In some embodiments, the terminal device 110 may ignore 561 the MAC CE, i.e., may not make a response to the MAC CE. In this way, an unnecessary LTM cell switch may be avoided.
[0171] In some embodiments, the terminal device 110 may transmit 562 a response to the MAC CE. The response indicates a rejection for the LTM cell switch. In some embodiments, the terminal device 110 may transmit the response indicating the rejection via an RRC message. In some embodiments, the terminal device 110 may transmit the response indicating the rejection via a MAC CE. In some embodiments, the terminal device 110 may transmit the response indicating the rejection via UCI.
[0172] In some embodiments, if the LTM cell switch is rejected or ignored, the network device 120 (e.g., source gNB) may transmit, to the network device 130 (e.g., target gNB) , an indication that the LTM cell switch is cancelled. It is to be understood that the indication may be transmitted via any suitable Xn messages.
[0173] If the LTM cell switch to the target cell is necessary, the terminal device 110 may perform 563 the LTM cell switch. For example, the terminal device 110 may detach from the cell 121 and apply a configuration of the cell 131.
[0174] It is to be understood that more details in the AI-based LTM procedure 500B are similar as that in a conventional LTM procedure, and thus are omitted for conciseness.
[0175] For illustration, an example procedure may be described as below.
[0176] Upon the indication by lower layers that an LTM cell switch procedure is triggered, the UE shall:
[0177] 1> if the AI information (e.g., predicted / candidate cell ID and the corresponding residence time, threshold_residenceTime) is available:
[0178] 2> if, for the candidate cell indicated by LTM cell switch command MAC CE, the corresponding residence time is lower than threshold_residenceTime: (Option 1)
[0179] 3> ignore this LTM cell switch command, i.e., not apply the LTM candidate configuration, not perform RA / synchronization to this candidate cell, upon which the procedure ends;
[0180] (Option 2)
[0181] 3> indicate a rejection for this LTM cell switch command to network by UCI / MAC CE / RRC;
[0182] 3> not apply the LTM candidate configuration, not perform RA / synchronization to this candidate cell, upon which the procedure ends;
[0183] 2> else if, for the candidate cell indicated by LTM cell switch command MAC CE, the corresponding residence time is greater than threshold_residenceTime:
[0184] 3> perform LTM cell switch execution as legacy, e.g., release / clear configuration, timer control, apply L1 / L2 configuration based on specific indication, transmission of RRCReconfigurationComplete.
[0185] In this example, threshold_residenceTime denotes a threshold for a residence time.
[0186] So far, an AI-based cell switch is described. It is to be understood that the procedures 400A, 400B, 500A and 500B are merely examples of the process 300, and do not limit the present disclosure. The process 300 may also be applied to any other suitable cell switch procedures.
[0187] EXAMPLE IMPLEMENTATION OF AI-BASED CONDITIONAL CELL SWITCH
[0188] Embodiments of the present disclosure provide a solution of managing a conditional cell switch based on the determined information of whether a cell switch to a cell is unnecessary. The solution will be described in connection with FIGs. 6 to 7B.
[0189] FIG. 6 illustrates a signaling chart illustrating an example process 600 of communication for an AI-based conditional cell switch according to embodiments of the present disclosure. For the purpose of discussion, the process 600 will be described with reference to FIG. 1. The process 600 may involve the terminal device 110 and the network device 120 as illustrated in FIG. 1. It is to be understood that the steps and the order of the steps in FIG. 6 are merely for illustration, and not for limitation. For example, the order of the steps may be changed. Some of the steps may be omitted or any other suitable additional steps may be added. It is assumed that model training and deployment of the AI model is finished, and the AI model is deployed at the terminal device 110. The terminal device 110 is served by the network device 120.
[0190] As shown in FIG. 6, the terminal device 110 may determine 610 that a cell switch to a target cell (e.g., the cell 131) is unnecessary based on the AI model. In this case, the terminal device 110 may perform 620 an operation (for convenience, also referred to as a third operation herein) of mobility management.
[0191] With reference to FIG. 6, the terminal device 110 may receive 621 a configuration for an evaluation for the cell switch. The configuration comprises a condition for the cell switch. The terminal device 110 may perform the evaluation based on the condition for the cell switch.
[0192] In some embodiments, as the cell switch is predicted to be unnecessary, the terminal device 110 may deactivate 622 the evaluation for the cell switch to the target cell so as to avoid unnecessary cell evaluation and unnecessary cell switch. In some embodiments, the evaluation may be based on an L3 measurement result for the target cell. In some embodiments, the evaluation may be based on an L1 measurement result for the target cell.
[0193] In some embodiments, the terminal device 110 may determine 623 that the target cell fulfills the condition for the cell switch. As the cell switch to the target cell is predicted to be unnecessary, the terminal device 110 may cancel 624 the cell switch so as to avoid the unnecessary cell switch.
[0194] Continuing to refer to FIG. 6, the terminal device 110 may determine 630 that the cell switch to the target cell (e.g., the cell 131) is necessary based on the AI model. In this case, the terminal device 110 may perform 640 an operation (for convenience, also referred to as a fourth operation herein) of mobility management.
[0195] With reference to FIG. 6, upon reception of the configuration for the evaluation for the cell switch, as the cell switch to the target cell is predicted to be necessary, the terminal device 110 may activate 641 the evaluation for the target cell so as to facilitate a necessary cell evaluation and a necessary cell switch. In some embodiments, the evaluation may be based on an L3 measurement result for the target cell. In some embodiments, the evaluation may be based on an L1 measurement result for the target cell.
[0196] In some embodiments, after the evaluation based on the condition of the cell switch, the terminal device 110 may determine 642 that the target cell fulfills the condition for the cell switch. As the cell switch to the target cell is predicted to be necessary, the terminal device 110 may perform 643 the cell switch so as to facilitate the necessary cell switch. In some embodiments, the terminal device 110 may perform UL synchronization to the target cell, e.g., by initiating a random access to the target cell. In some embodiments, the terminal device 110 may perform DL synchronization to the target cell, e.g., by receiving and processing a synchronization signal block (SSB) .
[0197] For illustration, some example embodiments will be further described in connection with FIGs. 7A and 7B. FIG. 7A illustrates a signaling chart illustrating an example AI-based CHO procedure 700A according to embodiments of the present disclosure. For the purpose of discussion, the procedure 700A will be described with reference to FIG. 1.
[0198] With reference to FIG. 7A, the terminal device 110 may perform 710, based on a measurement and report configuration, L3 measurements on a serving cell and one or more neighbor cells and transmit a measurement report indicating L3 measurement result (s) of the cell (s) to the network device 120.
[0199] Upon reception of the measurement report, the network device 120 may negotiate 711 with network devices (e.g., candidate gNBs) providing the candidate cells, and obtain configurations of CHO conditions for the candidate cells. The network device 120 may transmit 712 the configurations of CHO conditions for the candidate cells to the terminal device 110. In some embodiments, a CHO condition may be an event A3 or any other suitable events.
[0200] Continuing to refer to FIG. 7A, the terminal device 110 may determine 720 whether to evaluate a CHO condition for a candidate cell. If a CHO to the candidate cell is unnecessary, the terminal device 110 may deactivate 721 the evaluation for the candidate cell. In this way, an unnecessary CHO may be avoided.
[0201] If a CHO to a candidate cell is necessary, the terminal device 110 may evaluate 722 for the CHO to the candidate cell based on the CHO condition for the candidate cell. When the CHO condition for the candidate cell (e.g., for the cell 131) is satisfied, the terminal device 110 may detach from the cell 121 and synchronize 723 to the cell 131. In this way, a CHO to a candidate cell may be facilitated.
[0202] It is to be understood that more details in the AI-based CHO procedure 700A are similar as that in a conventional CHO procedure, and thus are omitted here for conciseness.
[0203] For illustration, an example procedure may be described as below.
[0204] 2> if the AI information (e.g., predicted / candidate cell ID and the corresponding residence time, threshold_residenceTime) is available:
[0205] 2> for each measId included in the measIdList within VarMeasConfig indicated in the condExecutionCond or condExecutionCondSCG associated to condReconfigId:
[0206] 3> if, for each applicable cell configured by this measId, the corresponding residence time is lower than threshold_residenceTime:
[0207] 3> stop evaluation for theses applicable cell configured by this measId.
[0208] 3> else if, for each applicable cell configured by this measId, the corresponding residence time is greater than threshold_residenceTime:
[0209] 4> if the condEventId is associated with condEventT1, and if the entry condition applicable for this event associated with the condReconfigId, i.e. the event corresponding with the condEventId (s) of the corresponding condTriggerConfig within VarConditionalReconfig, is fulfilled for the applicable cell; or
[0210] 4> if the condEventId is associated with condEventD1, and if the entry conditions applicable for this event associated with the condReconfigId, i.e. the event corresponding with the condEventId (s) of the corresponding condTriggerConfig within VarConditionalReconfig, is fulfilled for the applicable cell during the corresponding timeToTrigger defined for this event within the VarConditionalReconfig; or
[0211] 4> if the condEventId is associated with condEventA3, condEventA4 or condEventA5, and if the entry condition (s) applicable for this event associated with the condReconfigId, i.e. the event corresponding with the condEventId (s) of the corresponding condTriggerConfig within VarConditionalReconfig, is fulfilled for the applicable cells for all measurements after layer 3 filtering taken during the corresponding timeToTrigger defined for this event within the VarConditionalReconfig:
[0212] 5> consider the event associated to that measId to be fulfilled.
[0213] In this example, VarMeasConfig denotes a configuration of a measurement report, measIdList denotes a list of measurement configuration IDs, condExecutionCond denotes an execution condition, condExecutionCondSCG denotes an execution condition for secondary cell group (SCG) , condReconfigId denotes a conditional reconfiguration ID, measId denotes a measurement configuration ID, threshold_residenceTime denotes a threshold for a residence time, condEventId denotes an event ID of an execution condition, condTriggerConfig denotes a configuration of a triggered condition, and VarConditionalReconfig denotes a conditional reconfiguration.
[0214] FIG. 7B illustrates a signaling chart illustrating another example AI-based CHO procedure 700B according to embodiments of the present disclosure. For the purpose of discussion, the procedure 700B will be described with reference to FIG. 1.
[0215] With reference to FIG. 7B, the terminal device 110 may perform 750, based on a measurement and report configuration, L3 measurements on a serving cell and one or more neighbor cells and transmit a measurement report indicating L3 measurement result (s) of the cell (s) to the network device 120.
[0216] Upon reception of the measurement report, the network device 120 may negotiate 751 with network devices (e.g., candidate gNBs) providing the candidate cells, and obtain configurations of CHO conditions for the candidate cells. The network device 120 may transmit 752 the configurations of CHO conditions for the candidate cells to the terminal device 110. In some embodiments, a CHO condition may be an event A3 or any other suitable events.
[0217] Continuing to refer to FIG. 7B, the terminal device 110 may evaluate 753 the CHO conditions for the candidate cells, and determine that a CHO condition for a candidate cell (i.e., a target cell) is fulfilled.
[0218] Then the terminal device 110 may determine 760 whether to perform the CHO. If the CHO to the candidate cell is predicted to be unnecessary, the terminal device 110 may not perform 761 a synchronization to the candidate cell. In this way, an unnecessary CHO may be avoided.
[0219] In some embodiments, if the CHO to the candidate cell is predicted to be unnecessary, the terminal device 110 may transmit 762, to the network device 120, an indication indicating that the CHO to the candidate cell fulfilling the condition is cancelled due to AI prediction. In some embodiments, the terminal device 110 may transmit the indication via an RRC message. In some embodiments, the terminal device 110 may transmit the indication via a MAC CE. In some embodiments, the terminal device 110 may transmit the indication via UCI.
[0220] Continuing to refer to FIG. 7B, if the CHO to the candidate cell is predicated to be necessary, the terminal device 110 may perform 763 the HO. For example, the terminal device 110 may detach from the cell 121 and synchronize to the cell 131.
[0221] It is to be understood that more details in the AI-based CHO procedure 700B are similar as that in a conventional CHO procedure, and thus are omitted here for conciseness.
[0222] For illustration, an example procedure may be described as below.
[0223] 2> for each measId included in the measIdList within VarMeasConfig indicated in the condExecutionCond or condExecutionCondSCG associated to condReconfigId:
[0224] 3> if the condEventId is associated with condEventT1, and if the entry condition applicable for this event associated with the condReconfigId, i.e. the event corresponding with the condEventId (s) of the corresponding condTriggerConfig within VarConditionalReconfig, is fulfilled for the applicable cell; or
[0225] 3> if the condEventId is associated with condEventD1, and if the entry conditions applicable for this event associated with the condReconfigId, i.e. the event corresponding with the condEventId (s) of the corresponding condTriggerConfig within VarConditionalReconfig, is fulfilled for the applicable cell during the corresponding timeToTrigger defined for this event within the VarConditionalReconfig; or
[0226] 3> if the condEventId is associated with condEventA3, condEventA4 or condEventA5, and if the entry condition (s) applicable for this event associated with the condReconfigId, i.e. the event corresponding with the condEventId (s) of the corresponding condTriggerConfig within VarConditionalReconfig, is fulfilled for the applicable cells for all measurements after layer 3 filtering taken during the corresponding timeToTrigger defined for this event within the VarConditionalReconfig:
[0227] 4> consider the event associated to that measId to be fulfilled;
[0228] 2> if event (s) associated to all measId (s) within condTriggerConfig for a target candidate cell within the stored condRRCReconfig are fulfilled:
[0229] 3> if the AI information (e.g., predicted / candidate cell ID and the corresponding residence time, threshold_residenceTime) is available:
[0230] 4> if, for the target candidate cell, the corresponding residence time is lower than threshold_residenceTime:
[0231] (Option 1)
[0232] 5> not consider this tartget candidate cell within the stored condRRCReconfig, associated to that condReconfigId, as a triggered cell;
[0233] 5> not initiate the conditional reconfiguration execution;
[0234] (Option 2)
[0235] 5> indicate network that the target candidate cell fulfilling the CHO conditions is cancelled for conditional reconfiguration execution;
[0236] 4> else if, for the target candidate cell, the corresponding residence time is greater than threshold_residenceTime:
[0237] 5> consider the target candidate cell within the stored condRRCReconfig, associated to that condReconfigId, as a triggered cell;
[0238] 5> initiate the conditional reconfiguration execution.
[0239] In this example, VarMeasConfig denotes a configuration of a measurement report, measIdList denotes a list of measurement configuration IDs, condExecutionCond denotes an execution condition, condExecutionCondSCG denotes an execution condition for SCG, condReconfigId denotes a conditional reconfiguration ID, measId denotes a measurement configuration ID, threshold_residenceTime denotes a threshold for a residence time, condEventId denotes an event ID of an execution condition, condTriggerConfig denotes a configuration of a triggered condition, VarConditionalReconfig denotes a conditional reconfiguration, and condRRCReconfig denotes a conditional RRC reconfiguration.
[0240] EXAMPLE IMPLEMENTATION OF CELL SWITCH EVALUATION
[0241] Embodiments of the present disclosure provide a solution of evaluating a cell switch such as HO or CHO. In the solution, if a cell switch to a target cell (e.g., a neighbor cell) is necessary, the terminal device 110 may perform an evaluation for the cell switch based on a first configuration for an event for the evaluation. If the cell switch to the target cell is unnecessary, the terminal device 110 may perform the evaluation based on a second configuration for the event. The first configuration and the second configuration may be associated with at least one of a time to trigger (TTT) parameter or a hysteresis parameter.
[0242] In some embodiments, the first configuration may ignore the at least one of the TTT parameter or the hysteresis parameter in the event, and the second configuration may maintain the TTT parameter and the hysteresis parameter in the event. In other words, if the target cell is an unnecessary cell, the terminal device 110 may evaluate the cell switch based on the event considering the TTT parameter and the hysteresis parameter, as in a conventional solution. If the target cell is a necessary cell, the terminal device 110 may ignore the at least one of the TTT parameter or the hysteresis parameter in the event for the evaluation. In this way, the terminal device 110 may perform the cell switch more quickly.
[0243] For example, the event is an event A3. When a neighbor cell fulfills the following equation (1) within a duration TTT, an entering condition of the event A3 is fulfilled.
[0244] Mn + Ofn + Ocn –Hys > Mp +Ofp +Ocp + Off (1)
[0245] where Mn denotes a measurement result of the neighbor cell, Ofn denotes an object-specific offset of a reference signal measurement of the neighbor cell, Ocn denotes a cell-specific offset of the neighbor cell, Hys denotes a hysteresis parameter of the event, Mp denotes a measurement result of a serving cell, Ofp denotes an object-specific offset of a reference signal measurement of the serving cell, Ocp denotes a cell-specific offset of the serving cell, Off denotes an offset parameter of the event, and TTT denotes a TTT parameter of the event.
[0246] If there is one cell considered as a necessary cell, and is configured with the event A3 by a report configuration (e.g., reportConfig) , the terminal device 110 may just ignore the parameters TTT and Hys. For example, once RSRP of a neighbor cell is greater than RSRP of a serving cell, the terminal device 110 may initiate a measurement report to network for HO without waiting for the duration TTT, or the terminal device 110 may initiate a random access or synchronization to the neighbor cell for CHO without waiting for the duration TTT.
[0247] In some embodiments, the first configuration may comprise at least one of a reduced value of the TTT parameter or a reduced value of the hysteresis parameter in the event, and the second configuration may comprise at least one of an increased value of the TTT parameter or an increased value of the hysteresis parameter in the event. In other words, if the neighbor cell is a necessary cell, the terminal device 110 may evaluate the cell switch based on the event considering a shorter TTT and a smaller Hys. If the neighbor cell is an unnecessary cell, the terminal device 110 may evaluate the cell switch based on the event considering a longer TTT and a larger Hys. In this way, the terminal device 110 may perform the necessary cell switch more quickly, and make sure that the unnecessary cell switch is not performed.
[0248] For illustration, an example procedure may be described as below.
[0249] 1> if the AI information (such as predicted / candidate cell ID and corresponding residence time, threshold_residenceTime) is available:
[0250] 2> if, for each predicted / candidate cell, the residence time is greater than threshold_residenceTime:
[0251] 3> if the reportType is set to eventTriggered and if the entry condition applicable for this event, i.e. the event corresponding with the eventId of the corresponding reportConfig within VarMeasConfig, but the hysteresis is ignored, is fulfilled for one or more applicable cells for all measurements after layer 3 filtering taken, while the VarMeasReportList does not include a measurement reporting entry for this measId (a first cell triggers the event) :
[0252] 4> include a measurement reporting entry within the VarMeasReportList for this measId;
[0253] 4> set the numberOfReportsSent defined within the VarMeasReportList for this measId to 0;
[0254] 4> include the concerned cell (s) in the cellsTriggeredList defined within the VarMeasReportList for this measId;
[0255] 4> if useT312 is set to true in reportConfig for this event:
[0256] 5> if T310 for the corresponding SpCell is running; and
[0257] 5> if T312 is not running for corresponding SpCell:
[0258] 6> start timer T312 for the corresponding SpCell with the value of T312 configured in the corresponding measObjectNR;
[0259] 4> initiate the measurement reporting procedure.
[0260] In this example, reportType denotes a type of a measurement report, eventTriggered denotes the measurement report is triggered by an event, eventId denotes an ID of the event, VarMeasConfig denotes a configuration of the measurement report, reportConfig denotes a report configuration, VarMeasReportList denotes a list of configurations of measurement reports, threshold_residenceTime denotes a threshold for a residence time, cellsTriggeredList denotes a list of cells triggered with a measurement report, measId denotes an ID of a measurement configuration, numberOfReportsSent denotes the number of sent measurement reports, and measObjectNR denotes a measurement object for NR.
[0261] So far, a solution of an evaluation of a cell switch may be described. The solution may be applied to the step 410 in FIG. 4A, the step 450 in FIG. 4B, the step 722 in FIG. 7A, or the step 753 in FIG. 7B.
[0262] EXAMPLE IMPLEMENTATION OF NETWORK MANAGEMENT
[0263] Embodiments of the present disclosure provide a solution of facilitating NW mobility management. In the solution, the terminal device may transmit predicted information of whether a cell switch to a cell is unnecessary to a network device for mobility management. The solution will be detailed in connection with FIG. 8.
[0264] FIG. 8 illustrates a signaling chart illustrating an example process 800 of communication for AI-based mobility management at a NW side according to embodiments of the present disclosure. For the purpose of discussion, the process 800 will be described with reference to FIG. 1. The process 800 may involve the terminal device 110 and the network device 120 as illustrated in FIG. 1. It is assumed that model training and deployment of the AI model is finished, and the AI model is deployed at the terminal device 110. The terminal device 110 is served by the network device 120.
[0265] As shown in FIG. 8, the terminal device 110 may determine 810, based on an output of an AI model, predicted information of whether a cell switch to a cell is unnecessary. In some embodiments, the predicted information may indicate at least one of the following: an ID of the cell, a residence time for the cell, a trajectory of the terminal device 110, a location of the cell, or an indication of whether the cell switch to the cell is unnecessary. Other details are similar as that described above in section “EXAMPLE IMPLEMENTATION OF DETERMINATION OF UNNECESSARY CELL SWITCH” , and thus are not repeated here for conciseness.
[0266] Continuing to refer to FIG. 8, the terminal device 110 may transmit 820 the predicted information to the network device 120. In some embodiments, the terminal device 110 may transmit the predicted information via an RRC message. For example, the terminal device 110 may transmit the predicted information via a UEAssistanceInformation message. It is to be understood that any other similar RRC messages may also be feasible. In some embodiments, the terminal device 110 may transmit the predicted information via a MAC CE. In some embodiments, the terminal device 110 may transmit the predicted information via UCI.
[0267] The predicted information may help the network device 120 to facilitate mobility management for a cell switch such as HO, CHO or LTM. As shown in FIG. 8, the network device 120 may perform 830 the mobility management based on the predicted information. This is dependent on network implementation.
[0268] It is to be understood that operations or processes or procedures described above in connection with FIGs. 1 to 8 may be performed separately or in any suitable combination.
[0269] EXAMPLE IMPLEMENTATION OF METHODS
[0270] Corresponding to the above processes, embodiments of the present disclosure provide methods of communication implemented at a terminal device. These methods will be described below with reference to FIGs. 9 to 11.
[0271] FIG. 9 illustrates an example method 900 of communication implemented at a terminal device in accordance with some embodiments of the present disclosure. For example, the method 900 may be performed at the terminal device 110 as shown in FIG. 1. For the purpose of discussion, in the following, the method 900 will be described with reference to FIG. 1. It is to be understood that the method 900 may include additional blocks not shown and / or may omit some blocks as shown, and the scope of the present disclosure is not limited in this regard.
[0272] At block 910, the terminal device 110 determines, based on an AI model, that a cell switch to a target cell is unnecessary.
[0273] In some embodiments, the terminal device 110 may obtain, from an output of the AI model, predicted information for the target cell, and determine whether the cell switch to the target cell is unnecessary at least based on the predicted information. In some embodiments, the predicted information may indicate at least one of the following: an identity of the target cell, a residence time for the target cell, a trajectory of the terminal device 110, a location of the target cell, or an indication of whether the cell switch to the target cell is unnecessary.
[0274] In some embodiments, if the residence time for the target cell is above a time threshold, the terminal device 110 may determine that the cell switch to the target cell is necessary. In some embodiments, if the residence time for the target cell is below the time threshold, the terminal device 110 may determine that the cell switch to the target cell is unnecessary. In some embodiments, if the residence time for the target cell is above the time threshold and a confidence of model inference of the artificial intelligence model is above a confidence threshold, the terminal device 110 may determine that the cell switch to the target cell is necessary. In some embodiments, if the residence time for the target cell is below the time threshold and the confidence of model inference is above the confidence threshold, the terminal device 110 may determine that the cell switch to the target cell is unnecessary.
[0275] In some embodiments, if the residence time for the target cell is above the time threshold and the confidence of model inference is below the confidence threshold, the terminal device 110 may perform mobility management without considering whether the cell switch to the target cell is unnecessary. In some embodiments, if the residence time for the target cell is below the time threshold and the confidence of model inference is below the confidence threshold, the terminal device 110 may perform mobility management without considering whether the cell switch to the target cell is unnecessary.
[0276] At block 920, the terminal device 110 performs a first operation of mobility management.
[0277] In some embodiments for the first operation, if a measurement report is to be initiated by an evaluation for the cell switch to the target cell, the terminal device 110 may cancel the measurement report. In some embodiments, the evaluation is based on an L3 measurement result for the target cell. In some embodiments, the evaluation is based on an L1 measurement result for the target cell.
[0278] In some embodiments for the first operation, if a command indicating the cell switch to the target cell is received from the network device 120 providing a serving cell, the terminal device 110 may cancel the cell switch.
[0279] In some embodiments, the command is carried in an RRC message. In some embodiments, the terminal device 110 may ignore the RRC message so as to cancel the cell switch. In some embodiments, the terminal device 110 may transmit, to the network device 120, a response to the RRC message that indicates a rejection for the cell switch. In some embodiments, the terminal device 110 may transmit the response via at least one of the following: an RRC signaling, a MAC CE or UCI.
[0280] In some embodiments, the command is carried in a MAC CE. In some embodiments, the terminal device 110 may transmit, to the network device 120, a response to the MAC CE that indicates a rejection for the cell switch. In some embodiments, the terminal device 110 may transmit the response via at least one of the following: an RRC signaling, a MAC CE or UCI.
[0281] In some embodiments, the terminal device 110 may determine, based on the AI model, that the cell switch to the target cell is necessary, and perform a second operation of mobility management. In some embodiments for the second operation, if the measurement report is to be initiated by the evaluation for the cell switch, the terminal device 110 may transmit the measurement report to the network device 120. In some embodiments for the second operation, if the cell switch to the target cell is to be performed, the terminal device 110 may perform the cell switch.
[0282] In some embodiments, if the cell switch to the target cell is necessary, the terminal device 110 may perform the evaluation based on a first configuration for an event for the evaluation. If the cell switch to the target cell is unnecessary, the terminal device 110 may perform the evaluation based on a second configuration for the event. The first configuration and the second configuration are associated with at least one of a TTT parameter or a hysteresis parameter.
[0283] In some embodiments, the first configuration may ignore the at least one of the TTT parameter or the hysteresis parameter in the event, and the second configuration may maintain the TTT parameter and the hysteresis parameter in the event.
[0284] In some embodiments, the first configuration may comprise at least one of a reduced value of the TTT parameter or a reduced value of the hysteresis parameter in the event, and the second configuration comprises at least one of an increased value of the TTT parameter or an increased value of the hysteresis parameter in the event.
[0285] With the method 900, an AI-based cell switch may be carried out, and unnecessary cell switch may be avoided.
[0286] FIG. 10 illustrates an example method 1000 of communication implemented at a terminal device in accordance with some embodiments of the present disclosure. For example, the method 1000 may be performed at the terminal device 110 as shown in FIG. 1. For the purpose of discussion, in the following, the method 1000 will be described with reference to FIG. 1. It is to be understood that the method 1000 may include additional blocks not shown and / or may omit some blocks as shown, and the scope of the present disclosure is not limited in this regard.
[0287] At block 1010, the terminal device 110 determines, based on an AI model, that a cell switch to a target cell is unnecessary.
[0288] In some embodiments, the terminal device 110 may obtain, from an output of the AI model, predicted information for the target cell, and determine whether the cell switch to the target cell is unnecessary at least based on the predicted information. In some embodiments, the predicted information may indicate at least one of the following: an identity of the target cell, a residence time for the target cell, a trajectory of the terminal device 110, a location of the target cell, or an indication of whether the cell switch to the target cell is unnecessary.
[0289] In some embodiments, if the residence time for the target cell is above a time threshold, the terminal device 110 may determine that the cell switch to the target cell is necessary. In some embodiments, if the residence time for the target cell is below the time threshold, the terminal device 110 may determine that the cell switch to the target cell is unnecessary. In some embodiments, if the residence time for the target cell is above the time threshold and a confidence of model inference of the artificial intelligence model is above a confidence threshold, the terminal device 110 may determine that the cell switch to the target cell is necessary. In some embodiments, if the residence time for the target cell is below the time threshold and the confidence of model inference is above the confidence threshold, the terminal device 110 may determine that the cell switch to the target cell is unnecessary.
[0290] In some embodiments, if the residence time for the target cell is above the time threshold and the confidence of model inference is below the confidence threshold, the terminal device 110 may perform mobility management without considering whether the cell switch to the target cell is unnecessary. In some embodiments, if the residence time for the target cell is below the time threshold and the confidence of model inference is below the confidence threshold, the terminal device 110 may perform mobility management without considering whether the cell switch to the target cell is unnecessary.
[0291] At block 1020, the terminal device 110 performs a third operation of mobility management.
[0292] In some embodiments for the third operation, the terminal device 110 may deactivate an evaluation for the cell switch to the target cell. In some embodiments, the evaluation is based on an L3 measurement result for the target cell. In some embodiments, the evaluation is based on an L1 measurement result for the target cell.
[0293] In some embodiments for the third operation, if the target cell fulfills a condition for the cell switch, the terminal device 110 may cancel the cell switch. In some embodiments, the terminal device 110 may not perform a synchronization to the target cell. In some embodiments, the terminal device 110 may transmit, to the network device 120, an indication indicating that the cell switch to the target cell fulfilling the condition is cancelled. In some embodiments, the terminal device 110 may transmit the indication via at least one of the following: an RRC signaling, a MAC CE or UCI.
[0294] In some embodiments, the terminal device 110 may determine, based on the AI model, that the cell switch to the target cell is necessary, and perform a fourth operation of mobility management. In some embodiments for the fourth operation, the terminal device 110 may activate the evaluation for the cell switch to the target cell. In some embodiments for the fourth operation, if the target cell fulfills the condition for the cell switch, the terminal device 110 may perform the cell switch. In some embodiments for the cell switch, the terminal device 110 may perform a synchronization to the target cell.
[0295] In some embodiments, if the cell switch to the target cell is necessary, the terminal device 110 may perform the evaluation based on a first configuration for an event for the evaluation. If the cell switch to the target cell is unnecessary, the terminal device 110 may perform the evaluation based on a second configuration for the event. The first configuration and the second configuration are associated with at least one of a TTT parameter or a hysteresis parameter.
[0296] In some embodiments, the first configuration may ignore the at least one of the TTT parameter or the hysteresis parameter in the event, and the second configuration may maintain the TTT parameter and the hysteresis parameter in the event.
[0297] In some embodiments, the first configuration may comprise at least one of a reduced value of the TTT parameter or a reduced value of the hysteresis parameter in the event, and the second configuration comprises at least one of an increased value of the TTT parameter or an increased value of the hysteresis parameter in the event.
[0298] With the method 1000, an AI-based conditional cell switch may be carried out, and unnecessary conditional cell switch may be avoided.
[0299] FIG. 11 illustrates an example method 1100 of communication implemented at a terminal device in accordance with some embodiments of the present disclosure. For example, the method 1100 may be performed at the terminal device 110 as shown in FIG. 1. For the purpose of discussion, in the following, the method 1100 will be described with reference to FIG. 1. It is to be understood that the method 1100 may include additional blocks not shown and / or may omit some blocks as shown, and the scope of the present disclosure is not limited in this regard.
[0300] At block 1110, the terminal device 110 determines, based on an AI model, predicted information of whether a cell switch to a cell is unnecessary. In some embodiments, the predicted information may indicate at least one of the following: an identity of the target cell, a residence time for the target cell, a trajectory of the terminal device 110, a location of the target cell, or an indication of whether the cell switch to the target cell is unnecessary.
[0301] At block 1120, the terminal device 110 transmits the predicted information to the network device 120. In some embodiments, the terminal device 110 may transmit the predicted information via an RRC message. In some embodiments, the terminal device 110 may transmit the predicted information via a MAC CE. In some embodiments, the terminal device 110 may transmit the predicted information via UCI.
[0302] It is to be understood that operations of the methods 900 to 1100 correspond to that described in connection with FIGs. 3 to 8, and thus other details are not repeated here for conciseness.
[0303] EXAMPLE IMPLEMENTATION OF DEVICES
[0304] FIG. 12 is a simplified block diagram of a device 1200 that is suitable for implementing embodiments of the present disclosure. The device 1200 can be considered as a further example implementation of the terminal device 110 or the network device 120 as shown in FIG. 1. Accordingly, the device 1200 can be implemented at or as at least a part of the terminal device 110 or the network device 120.
[0305] As shown, the device 1200 includes a processor 1210, a memory 1220 coupled to the processor 1210, a suitable transceiver 1240 coupled to the processor 1210, and a communication interface coupled to the transceiver 1240. The memory 1210 stores at least a part of a program 1230. The transceiver 1240 may be for bidirectional communications or a unidirectional communication based on requirements. The transceiver 1240 may include at least one of a transmitter 1242 or a receiver 1244. The transmitter 1242 and the receiver 1244 may be functional modules or physical entities. The transceiver 1240 has at least one antenna to facilitate communication, though in practice an Access Node mentioned in this application may have several ones. The communication interface may represent any interface that is necessary for communication with other network elements, such as X2 / Xn interface for bidirectional communications between eNBs / gNBs, S1 / NG interface for communication between a Mobility Management Entity (MME) / Access and Mobility Management Function (AMF) / SGW / UPF and the eNB / gNB, Un interface for communication between the eNB / gNB and a relay node (RN) , or Uu interface for communication between the eNB / gNB and a terminal device.
[0306] The program 1230 is assumed to include program instructions that, when executed by the associated processor 1210, enable the device 1200 to operate in accordance with the embodiments of the present disclosure, as discussed herein with reference to FIGs. 1 to 11. The embodiments herein may be implemented by computer software executable by the processor 1210 of the device 1200, or by hardware, or by a combination of software and hardware. The processor 1210 may be configured to implement various embodiments of the present disclosure. Furthermore, a combination of the processor 1210 and memory 1220 may form processing means 1250 adapted to implement various embodiments of the present disclosure.
[0307] The memory 1220 may be of any type suitable to the local technical network and may be implemented using any suitable data storage technology, such as a non-transitory computer readable storage medium, semiconductor based memory devices, magnetic memory devices and systems, optical memory devices and systems, fixed memory and removable memory, as non-limiting examples. While only one memory 1220 is shown in the device 1200, there may be several physically distinct memory modules in the device 1200. The processor 1210 may be of any type suitable to the local technical network, and may include one or more of general purpose computers, special purpose computers, microprocessors, digital signal processors (DSPs) and processors based on multicore processor architecture, as non-limiting examples. The device 1200 may have multiple processors, such as an application specific integrated circuit chip that is slaved in time to a clock which synchronizes the main processor.
[0308] In some embodiments, a terminal device comprises a circuitry configured to: determine, based on an AI model, that a cell switch to a target cell is unnecessary; and perform a first operation of mobility management. The first operation of mobility management comprises at least one of the following: in accordance with a determination that a measurement report is to be initiated by an evaluation for the cell switch to the target cell, cancelling the measurement report; or in accordance with a determination that a command indicating the cell switch to the target cell is received from a network device providing a serving cell, cancelling the cell switch.
[0309] In some embodiments, a terminal device comprises a circuitry configured to: determine, based on an AI model, that a cell switch to a target cell is unnecessary; and perform a third operation of mobility management. The third operation of mobility management comprises at least one of the following: deactivating an evaluation for the cell switch to the target cell; or in accordance with a determination that the target cell fulfills a condition for the cell switch, cancelling the cell switch.
[0310] In some embodiments, a terminal device comprises a circuitry configured to: determine, based on an output of an AI model, predicted information of whether a cell switch to a cell is unnecessary; and transmit the predicted information to a network device.
[0311] The term “circuitry” used herein may refer to hardware circuits and / or combinations of hardware circuits and software. For example, the circuitry may be a combination of analog and / or digital hardware circuits with software / firmware. As a further example, the circuitry may be any portions of hardware processors with software including digital signal processor (s) , software, and memory (ies) that work together to cause an apparatus, such as a terminal device or a network device, to perform various functions. In a still further example, the circuitry may be hardware circuits and or processors, such as a microprocessor or a portion of a microprocessor, that requires software / firmware for operation, but the software may not be present when it is not needed for operation. As used herein, the term circuitry also covers an implementation of merely a hardware circuit or processor (s) or a portion of a hardware circuit or processor (s) and its (or their) accompanying software and / or firmware.
[0312] Generally, various embodiments of the present disclosure may be implemented in hardware or special purpose circuits, software, logic or any combination thereof. Some aspects may be implemented in hardware, while other aspects may be implemented in firmware or software which may be executed by a controller, microprocessor or other computing device. While various aspects of embodiments of the present disclosure are illustrated and described as block diagrams, flowcharts, or using some other pictorial representation, it will be appreciated that the blocks, apparatus, systems, techniques or methods described herein may be implemented in, as non-limiting examples, hardware, software, firmware, special purpose circuits or logic, general purpose hardware or controller or other computing devices, or some combination thereof.
[0313] The present disclosure also provides at least one computer program product tangibly stored on a non-transitory computer readable storage medium. The computer program product includes computer-executable instructions, such as those included in program modules, being executed in a device on a target real or virtual processor, to carry out the process or method as described above with reference to FIGs. 1 to 11. Generally, program modules include routines, programs, libraries, objects, classes, components, data structures, or the like that perform particular tasks or implement particular abstract data types. The functionality of the program modules may be combined or split between program modules as desired in various embodiments. Machine-executable instructions for program modules may be executed within a local or distributed device. In a distributed device, program modules may be located in both local and remote storage media.
[0314] Program code for carrying out methods of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the program codes, when executed by the processor or controller, cause the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may execute entirely on a machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.
[0315] The above program code may be embodied on a machine readable medium, which may be any tangible medium that may contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine readable medium may be a machine readable signal medium or a machine readable storage medium. A machine readable medium may include but not limited to an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of the machine readable storage medium would include an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM) , a read-only memory (ROM) , an erasable programmable read-only memory (EPROM or Flash memory) , an optical fiber, a portable compact disc read-only memory (CD-ROM) , an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
[0316] Further, while operations are depicted in a particular order, this should not be understood as requiring that such operations be performed in the particular order shown or in sequential order, or that all illustrated operations be performed, to achieve desirable results. In certain circumstances, multitasking and parallel processing may be advantageous. Likewise, while several specific implementation details are contained in the above discussions, these should not be construed as limitations on the scope of the present disclosure, but rather as descriptions of features that may be specific to particular embodiments. Certain features that are described in the context of separate embodiments may also be implemented in combination in a single embodiment. Conversely, various features that are described in the context of a single embodiment may also be implemented in multiple embodiments separately or in any suitable sub-combination.
[0317] Although the present disclosure has been described in language specific to structural features and / or methodological acts, it is to be understood that the present disclosure defined in the appended claims is not necessarily limited to the specific features or acts described above. Rather, the specific features and acts described above are disclosed as example forms of implementing the claims.
Claims
1.A terminal device, comprising:a processor configured to cause the terminal device to:determine, based on an artificial intelligence model, that a cell switch to a target cell is unnecessary; andperform a first operation of mobility management comprising at least one of the following:in accordance with a determination that a measurement report is to be initiated by an evaluation for the cell switch to the target cell, cancelling the measurement report; orin accordance with a determination that a command indicating the cell switch to the target cell is received from a network device providing a serving cell, cancelling the cell switch.2.The terminal device of claim 1, wherein the evaluation is based on a layer 3 measurement result for the target cell, orwherein the evaluation is based on a layer 1 measurement result for the target cell.3.The terminal device of claim 1, wherein the terminal device is further caused to:receive, from a network device providing a serving cell, a radio resource control, RRC, message indicating the cell switch to the target cell.4.The terminal device of claim 3, wherein the terminal device is caused to cancel the cell switch by:ignoring the RRC message; ortransmitting, to the network device, a response to the RRC message that indicates a rejection for the cell switch.5.The terminal device of claim 1, wherein the terminal device is further caused to:receive, from a network device providing a serving cell, a medium access control control element, MAC CE, indicating the cell switch to the target cell.6.The terminal device of claim 5, wherein the terminal device is caused to cancel the cell switch by:ignoring the MAC CE; ortransmitting, to the network device, a response to the MAC CE that indicates a rejection for the cell switch.7.The terminal device of claim 1, wherein the terminal device is further caused to:determine, based on the artificial intelligence model, that the cell switch to the target cell is necessary; andperform a second operation of mobility management comprising at least one of the following:in accordance with a determination that the measurement report is to be initiated by the evaluation for the cell switch, transmitting the measurement report to the network device; orin accordance with a determination that the cell switch to the target cell is to be performed, performing the cell switch.8.A terminal device, comprising:a processor configured to cause the terminal device to:determine, based on an artificial intelligence model, that a cell switch to a target cell is unnecessary; andperform a third operation of mobility management comprising at least one of the following:deactivating an evaluation for the cell switch to the target cell; orin accordance with a determination that the target cell fulfills a condition for the cell switch, cancelling the cell switch.9.The terminal device of claim 8, wherein the terminal device is caused to cancel the cell switch by:performing no synchronization to the target cell; ortransmitting, to a network device providing a serving cell, an indication indicating that the cell switch to the target cell fulfilling the condition is cancelled.10.The terminal device of claim 8, wherein the terminal device is further caused to:determine, based on the artificial intelligence model, that the cell switch to the target cell is necessary; andperform a fourth operation of mobility management comprising at least one of the following:activating the evaluation for the cell switch to the target cell; orin accordance with a determination that the target cell fulfills the condition for the cell switch, performing the cell switch.11.The terminal device of claim 10, wherein the terminal device is caused to perform the cell switch by:performing a synchronization to the target cell.12.The terminal device of claim 7 or 10, wherein the terminal device is caused to perform the evaluation for the cell switch by:in accordance with a determination that the cell switch to the target cell is necessary, performing the evaluation based on a first configuration for an event for the evaluation; orin accordance with a determination that the cell switch to the target cell is unnecessary, performing the evaluation based on a second configuration for the event,wherein the first configuration and the second configuration are associated with at least one of a time to trigger parameter or a hysteresis parameter.13.The terminal device of claim 12, wherein the first configuration ignores the at least one of the time to trigger parameter or the hysteresis parameter in the event, and the second configuration maintains the time to trigger parameter and the hysteresis parameter in the event.14.The terminal device of claim 12, wherein the first configuration comprises at least one of a reduced value of the time to trigger parameter or a reduced value of the hysteresis parameter in the event, and the second configuration comprises at least one of an increased value of the time to trigger parameter or an increased value of the hysteresis parameter in the event.15.The terminal device of claim 1 or 8, wherein the terminal device is further caused to:obtain, from an output of the artificial intelligence model, predicted information for the target cell, the predicted information indicating at least one of the following:an identity of the target cell,a residence time for the target cell,a trajectory of the terminal device,a location of the target cell, oran indication of whether the cell switch to the target cell is unnecessary; anddetermine whether the cell switch to the target cell is unnecessary at least based on the predicted information.16.The terminal device of claim 15, wherein the terminal device is caused to determine whether the cell switch to the target cell is unnecessary by at least one of the following:in accordance with a determination that the residence time for the target cell is above a time threshold, determining that the cell switch to the target cell is necessary;in accordance with a determination that the residence time for the target cell is below the time threshold, determining that the cell switch to the target cell is unnecessary;in accordance with a determination that the residence time for the target cell is above the time threshold and a confidence of model inference of the artificial intelligence model is above a confidence threshold, determining that the cell switch to the target cell is necessary; orin accordance with a determination that the residence time for the target cell is below the time threshold and the confidence of model inference is above the confidence threshold, determining that the cell switch to the target cell is unnecessary.17.The terminal device of claim 16, wherein the terminal device is further caused to:perform mobility management without considering whether the cell switch to the target cell is unnecessary based on one of the following:the residence time for the target cell is above the time threshold and the confidence of model inference is below the confidence threshold; orthe residence time for the target cell is below the time threshold and the confidence of model inference is below the confidence threshold.18.A terminal device, comprising:a processor configured to cause the terminal device to:determine, based on an output of an artificial intelligence model, predicted information of whether a cell switch to a cell is unnecessary; andtransmit the predicted information to a network device.19.The terminal device of claim 18, wherein the predicted information indicates at least one of the following:an identity of the cell,a residence time for the cell,a trajectory of the terminal device,a location of the cell, oran indication of whether the cell switch to the cell is unnecessary.20.The terminal device of claim 18, wherein the terminal device is caused to transmit the predicted information by at least one of the following:transmitting the predicted information via a radio resource control, RRC, message;transmitting the predicted information via a medium access control control element, MAC CE; ortransmitting the predicted information via uplink control information, UCI.
Citation Information
Patent Citations
Switching method and device in communication network
CN116782323A
Method and apparatus for support of machine learning or artificial intelligence techniques for handover management in communication systems
US20220286927A1
Method, device and computer readable medium for communications
WO2023108470A1