A method for ai / ML based measurement and mobility management
AI-assisted mobility management in wireless networks predicts future network conditions to optimize resource allocation and handover processes, addressing inefficiencies in current reactive systems.
Patent Information
- Application Number
- PCT/CN2024/085856
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2024-04-03
- Publication Date
- 2025-07-31
AI Technical Summary
Current mobility management in wireless communication networks requires lengthy and resource-intensive measurements of current network conditions, which are reactive and do not consider potential future variations, leading to inefficient resource allocation and potential handover failures.
Utilizing Artificial Intelligence (AI) models on the network side or terminal side to predict future network conditions, allowing for proactive mobility management by configuring wireless terminal devices with AI-predicted measurement results and actual measurements to assist in handover decisions.
Enhances mobility management by reducing measurement overhead, improving handover efficiency, and preventing failures through proactive decision-making based on predicted network conditions.
Smart Images

Figure CN2024085856_31072025_PF_FP_ABST
Abstract
Description
A METHOD FOR AI / ML BASED MEASUREMENT AND MOBILITY MANAGEMENTTECHNICAL FIELD
[0001] This disclosure is directed generally to wireless communication networks and particularly to configuration and provisioning of mobility of wireless terminal devices assisted by Artificial Intelligence (AI) models residing either on the network side or the terminal side.BACKGROUND
[0002] In a wireless communication system, mobility management and provisioning of wireless terminals may require lengthy and resource-intensive measurement of current network conditions as well as reporting of a large amount of such measurement. Such mobility management and provisioning may only be reactive in that it derives resource allocation and other network configuration for the mobility based on current network conditions without considering potential future variation of the network conditions from the current measurement.SUMMARY
[0003] This disclosure is directed generally to wireless communication networks and particularly to configuration and provisioning of mobility of wireless terminal devices assisted by Artificial Intelligence (AI) models residing either on the network side or the terminal side. For example, a configuration may be provided by the network to a terminal device with respect to such mobility management. Such a configuration may specify information related to actual measurements and reporting of measurement objects as well as generation and reporting of AI-predicted measurement results. The actual measurements and AI-predicted results may be identified and used to assist with mobility management, such as a handover, of the terminal device via adapted messaging in a mobility management procedure.
[0004] In one example implementation, a method performed by a base station in radio communication with a terminal in a wireless access network is disclosed. The method may include transmitting a configuration message to the terminal for mobility management of the terminal, the configuration message comprising at least one information item pertaining to artificial intelligence (AI) prediction of a measurement object (MO) among a plurality of MOs; receiving a measurement report from the terminal, the measurement report being generated by the terminal pertaining to the plurality of the MOs in accordance with the configuration message; and performing a handover procedure for the terminal in collaboration with a target base station based on the measurement report.
[0005] In the example implementation above, the configuration message comprises at least one of: a beam and / or cell list to indicate beams and / or cells that are expected to be measured and / or reported by the terminal; one or more first indications specifying whether the beams, the cells, and / or the plurality of MOs are predicted by AI predictions; one or more second indications for specifying types of the AI predictions; a first set of measurement threshold values to set conditions for the terminal to report measurement results of the beams, the cells, and / or the MOs to the base station; one or more second measurement threshold values below which the terminal is disallowed from reporting the measurement results of the beams, the cells, and / or the MOs to the base station; or one or more information elements to indicate MOs whose actual measurement results that can be used for predictions of other MOs.
[0006] In any one of the example implementations above, the configuration message comprises a list of information items for configuring the plurality of MOs; and at least one of the information items comprise a configuration data field for indicating whether a corresponding MO is to be predicted by AI.
[0007] In any one of the example implementations above, the configuration message comprises: a first list of information items for configuring the plurality of MOs; and a second list of information items separate from the first list of information items for specifying one or more prediction objects for the terminal to generate by AI prediction.
[0008] In any one of the example implementations above, the types of the AI predictions comprise at least spatial domain AI prediction type, temporal domain AI prediction type, and frequency domain AI prediction type.
[0009] In any one of the example implementations above, the types of AI predictions are indicated in the configuration message on a per frequency, per MO, or per cell level.
[0010] In any one of the example implementations above, the first set of measurement threshold values and the one or more second measurement threshold values pertain to Reference Signal Receive Power (RSRP) , Reference Signal Received Quality (RSRQ) , or Signal to Interference Noise Ratio (SINR) value.
[0011] In any one of the example implementations above, the first set of measurement threshold values comprise a measurement report enablement threshold value and a measurement disablement threshold value; the measurement report enablement threshold value is lower than the measurement disablement threshold value; and the terminal is allowed to report the measurement results of the beams, the cells, and / or the MOs only after the measurement results drops below the measurement report enablement threshold value and before the measurement raises back above the measurement report disablement threshold value.
[0012] In any one of the example implementations above, the first set of measurement threshold values comprise a single measurement report threshold value; and the terminal is allowed to report the measurement results of the beams, the cells, and / or the MOs only when the measurement results drops below the single measurement report threshold value.
[0013] In any one of the example implementations above, when the measurement results of one of the beams, the cells, and the MOs falls below a corresponding second measurement threshold value, a third indication therefor is included the measurement report.
[0014] In any one of the example implementations above, the handover procedure comprises: selecting, by the base station, the target base station based on the measurement report; sending a handover request to the target base station; and sending a handover command to the terminal for the terminal to complete the handover procedure with the target base station.
[0015] In any one of the example implementations above, the handover request comprises at least one of: AI information associated with features / functions / models of the AI predictions; AI related additional information; data items comprising the measurement results and / or the AI predictions of the beams, the cells, and / or the MOs; or one or more third indications for indicating whether the data items are measured or AI predicted.
[0016] In any one of the example implementations above, the data items are included in a list in the handover request and each data item comprises one of the one or more third indications.
[0017] In any one of the example implementations above, the handover request comprises at least one of: AI information associated with features / functions / models of the AI predictions; AI related additional information; and data items included in a first list and a second list, wherein the first list is identified as measured, and the second list is identified as AI predicted.
[0018] In any one of the example implementations above, the handover command comprises at least one of: AI predicted target cell information; reference information indicating measured information as a reference for identifying and accessing the target base station; an SSB index over which the terminal is expected to perform a random access procedure; a preamble path loss for a physical random access channel (PRACH) associated with the random access procedure; or a configured uplink grant for the terminal to send a handover complete message.
[0019] In any one of the example implementations above, the AI predictions are performed by the base station.
[0020] In any one of the example implementations above, the AI predictions are performed by the terminal.
[0021] In another example implementation, a method performed by a terminal in radio communication with a base station in a wireless access network is disclosed. The method may include receiving a configuration message from the base station for mobility management of the terminal, the configuration message comprising at least one information item pertaining to artificial intelligence (AI) prediction of a measurement object (MO) among a plurality of MOs; generating a measurement report comprising measurement results of the plurality of the MOs in accordance with the configuration message; and performing a handover procedure from the base station to a target base station based on the measurement report.
[0022] In any one of the example implementations above, the configuration message comprises at least one of: one or more first indications specifying whether the measurement results of the plurality of MOs can be obtained via AI predictions; one or more second indications for specifying types of the AI predictions; a third indication for specifying whether the terminal is allowed to determine a number of beams to derive cell quality; a first set of measurement threshold values to set conditions for the terminal to report measurement results of the beams, the cells, and / or the MOs to the base station; one or more second measurement threshold values below which the terminal is disallowed from reporting the measurement results of the beams, the cells, and / or the MOs to the base station; or one or more information elements to indicate MOs whose actual measurement results that can be used for predictions of other MOs.
[0023] In any one of the example implementations above, the configuration message comprises a list of information items for configuring the plurality of MOs; and at least one of the information items comprise a configuration data field for indicating whether a corresponding MO is to be predicted by AI.
[0024] In any one of the example implementations above, the configuration message comprises: a first list of information items for configuring the plurality of MOs; and a second list of information items separate from the first list of information items for specifying one or more prediction objects for the terminal to generate by AI prediction.
[0025] In any one of the example implementations above, the types of the AI predictions comprise at least spatial domain AI prediction type, temporal domain AI prediction type, and frequency domain AI prediction.
[0026] In any one of the example implementations above, the types of AI predictions are indicated in the configuration message on a per frequency, per MO, or per cell level.
[0027] In any one of the example implementations above, the first set of measurement threshold values and the one or more second measurement threshold values pertain to Reference Signal Receive Power (RSRP) , Reference Signal Received Quality (RSRQ) , or Signal to Interference Noise Ratio (SINR) value.
[0028] In any one of the example implementations above, the first set of measurement threshold values comprise a measurement report enablement threshold value and a measurement disablement threshold value; the measurement report enablement threshold value is lower than the measurement disablement threshold value; and the terminal is allowed to report the measurement results of the beams, the cells, and / or the MOs only after the measurement results drops below the measurement report enablement threshold value and before the measurement raises back above the measurement report disablement threshold value.
[0029] In any one of the example implementations above, the first set of measurement threshold values comprise a single measurement report threshold value; and the terminal is allowed to report the measurement results of the beams, the cells, and / or the MOs only when the measurement results drops below the single measurement report threshold value.
[0030] In any one of the example implementations above, when the measurement results of one of the MOs falls below a corresponding second measurement threshold value, a fourth indication therefor is included the measurement report.
[0031] In any one of the example implementations above, the method further include performing measurements and or prediction of the plurality of MOs according to the configuration message prior to preforming the handover procedure.
[0032] In any one of the example implementations above, the target base station is selected by the base station based on the measurement report, and the handover procedure comprises: receiving after a handover request from the base station to the target base station is successfully processed, a handover command from the base station for the terminal to complete the handover procedure with the target base station.
[0033] In any one of the example implementations above, the handover request comprises at least one of: data items comprising the measurement results and / or the AI predictions of the plurality of MOs; or one or more indications for indicating whether the data items are measured or AI predicted.
[0034] In any one of the example implementations above, data items comprising the measurement results and / or the AI predictions of the plurality of MOs are included in a first list and a second list in the handover request; the first list is identified as measured; and the second list is identified as AI predicted.
[0035] In any one of the example implementations above, the handover command comprises reference information indicating measured information as a reference for identifying and accessing the target base station.
[0036] In any one of the example implementations above, the handover command comprises at least one of: predicted measurement results for a target cell of the target base station; SSB indexes to indicate which SSBs the terminal is expected to perform a random access procedure on; a preamble path loss of a physical random access channel (PRACH) ; or a configured UL grant.
[0037] The terminal or base station of any one of the methods above is disclosed. The terminal or base station may include a processor and a memory, wherein the processor is configured to read computer code from the memory to cause the terminal or base station to perform the method of any one of the methods above.
[0038] A non-transitory computer-readable program medium with computer code stored thereupon is further disclosed. The computer code, when executed by a processor of the terminal or base station of any one of the methods above, is configured to cause the processor to implement any one of the methods above.
[0039] The above embodiments and other aspects and alternatives of their implementations are described in greater detail in the drawings, the descriptions, and the claims below.BRIEF DESCRIPTION OF THE DRAWINGS
[0040] FIG. 1 illustrates an example wireless communication network including a wireless access network, a core network, and data networks.
[0041] FIG. 2 illustrates an example wireless access network including a plurality of mobile stations / terminals or User Equipments (UEs) and a wireless access network node in communication with one another via an over-the-air radio communication interface.
[0042] FIG. 3 shows an example radio access network (RAN) architecture.
[0043] FIG. 4 shows an example communication protocol stack in a wireless access network node or wireless terminal device including various network layers.
[0044] FIG. 5 illustrates a general implementation of AI assisted mobility management based on either network side or terminal side AI models.
[0045] FIG. 6 shows an example implementation for configuration and performing a handover procedure assisted by network side AI.
[0046] FIG. 7 shows an example configuration for measurement objects in a mobility management configuration.
[0047] FIG. 8A shows an example threshold scheme for reporting measurements to the network by a terminal device.
[0048] FIG. 8B shows another example threshold scheme for reporting measurements to the network by a terminal device.
[0049] FIG. 9 shows an example configuration for measurement objects in a mobility management configuration.
[0050] FIG. 10 shows an example preparation information item of a handover request.
[0051] FIG. 11 shows another example preparation information item of a handover request.
[0052] FIG. 12 shows an example RRC reconfiguration message for a handover command.
[0053] FIG. 13. shows an example implementation for configuration and performing a handover procedure assisted by terminal side AI.
[0054] FIG. 14 shows an example configuration for measurement objects in a mobility management configuration.
[0055] FIG. 15 shows another example configuration for measurement objects in a mobility management configuration.DETAILED DESCRIPTION
[0056] The present disclosure will now be described in detail hereinafter with reference to the accompanied drawings, which form a part of the present disclosure, and which show, by way of illustration, specific examples of embodiments. The present disclosure may, however, be embodied in a variety of different forms and, therefore, the covered or claimed subject matter is intended to be construed as not being limited to any of the embodiments to be set forth below.
[0057] Throughout the specification and claims, terms may have nuanced meanings suggested or implied in context beyond an explicitly stated meaning. Likewise, the phrase “in one embodiment” or “in some embodiments” as used herein does not necessarily refer to the same embodiment and the phrase “in another embodiment” or “in other embodiments” as used herein does not necessarily refer to a different embodiment. The phrase “in one implementation” or “in some implementations” as used herein does not necessarily refer to the same implementation and the phrase “in another implementation” or “in other implementations” as used herein does not necessarily refer to a different implementation. It is intended, for example, that claimed subject matter includes combinations of exemplary embodiments or implementations in whole or in part.
[0058] In general, terminology may be understood at least in part from usage in context. For example, terms, such as “and” , “or” , or “and / or, ” as used herein may include a variety of meanings that may depend at least in part upon the context in which such terms are used. Typically, “or” if used to associate a list, such as A, B or C, is intended to mean A, B, and C, here used in the inclusive sense, as well as A, B or C, here used in the exclusive sense. In addition, the term “one or more” or “at least one” as used herein, depending at least in part upon context, may be used to describe any feature, structure, or characteristic in a singular sense or may be used to describe combinations of features, structures or characteristics in a plural sense. Similarly, terms, such as “a” , “an” , or “the” , again, may be understood to convey a singular usage or to convey a plural usage, depending at least in part upon context. In addition, the term “based on” or “determined by” may be understood as not necessarily intended to convey an exclusive set of factors and may, instead, allow for existence of additional factors not necessarily expressly described, again, depending at least in part on context.
[0059] This disclosure is directed generally to wireless communication networks and particularly to configuration and provisioning of mobility of wireless terminal devices assisted by Artificial Intelligence (AI) models residing either on the network side or the terminal side. For example, a configuration may be provided by the network to a terminal device with respect to such mobility management. Such a configuration may specify information related to actual measurements and reporting of measurement objects as well as generation and reporting of AI-predicted measurement results. The actual measurements and AI-predicted results may be identified and used to assist with mobility management, such as a handover, of the terminal device via adapted messaging in a mobility management procedure.
[0060] Wireless Network Overview
[0061] An example wireless communication network, shown as 100 in FIG. 1, may include wireless terminal devices or user equipment (UE) 110, 111, and 112, a carrier network 102, various service applications 140, and other data networks 150. The wireless terminal devices or UEs, may be alternatively referred to as wireless terminals. The carrier network 102, for example, may include access network nodes 120 and 121, and a core network 130. The carrier network 110 may be configured to transmit voice, data, and other information (collectively referred to as data traffic) among UEs 110, 111, and 112, between the UEs and the service applications 140, or between the UEs and the other data networks 150. The access network nodes 120 and 121 may be configured as various wireless access network nodes (WANNs, alternatively referred to as wireless base stations) to interact with the UEs on one side of a communication session and the core network 130 on the other. The term “access network” may be used more broadly to refer a combination of the wireless terminal devices 110, 111, and 112 and the access network nodes 120 and 121. A wireless access network may be alternatively referred to as Radio Access Network (RAN) . The core network 130 may include various network nodes configured to control communication sessions and perform network access management and traffic routing. The service applications 140 may be hosted by various application servers deployed outside of but connected to the core network 130. Likewise, the other data networks 150 may also be connected to the core network 130.
[0062] In the example wireless communication network of 100 of FIG. 1, the UEs may communicate with one another via the wireless access network. For example, UE 110 and 112 may be connected to and communicate via the same access network node 120. The UEs may communicate with one another via both the access networks and the core network. For example, UE 110 may be connected to the access network node 120 whereas UE 111 may be connected to the access network node 121, and as such, the UE 110 and UE 111 may communicate to one another via the access network nodes 120 and 121, and the core network 130. The UEs may further communicate with the service applications 140 and the data networks 150 via the core network 130. Further, the UEs may communicate to one another directly via side link communications, as shown by 113.
[0063] FIG. 2 further shows an example system diagram of the wireless access network 120 including a WANN 202 serving UEs 110 and 112 via the over-the-air interface 204. The wireless transmission resources for the over-the-air interface 204 include a combination of frequency, time, and / or spatial resource. Each of the UEs 110 and 112 may be a mobile or fixed terminal device installed with mobile access units such as SIM / USIM modules for accessing the wireless communication network 100. The UEs 110 and 112 may each be implemented as a terminal device including but not limited to a mobile phone, a smartphone, a tablet, a laptop computer, a vehicle on-board communication equipment, a roadside communication equipment, a sensor device, a smart appliance (such as a television, a refrigerator, and an oven) , or other devices that are capable of communicating wirelessly over a network. As shown in FIG. 2, each of the UEs such as UE 112 may include transceiver circuitry 206 coupled to one or more antennas 208 to effectuate wireless communication with the WANN 120 or with another UE such as UE 110. The transceiver circuitry 206 may also be coupled to a processor 210, which may also be coupled to a memory 212 or other storage devices. The memory 212 may be transitory or non-transitory and may store therein computer instructions or code which, when read and executed by the processor 210, cause the processor 210 to implement various ones of the methods described herein.
[0064] Similarly, the WANN 120 may include a wireless base station or other wireless network access point capable of communicating wirelessly via the over-the-air interface 204 with one or more UEs and communicating with the core network 130. For example, the WANN 120 may be implemented, without being limited, in the form of a 2G base station, a 3G nodeB, an LTE eNB, a 4G LTE base station, a 5G NR base station of a 5G gNB, a 5G central-unit base station, or a 5G distributed-unit base station. Each type of these WANNs may be configured to perform a corresponding set of wireless network functions. The WANN 202 may include transceiver circuitry 214 coupled to one or more antennas 216, which may include an antenna tower 218 in various forms, to effectuate wireless communications with the UEs 110 and 112. The transceiver circuitry 214 may be coupled to one or more processors 220, which may further be coupled to a memory 222 or other storage devices. The memory 222 may be transitory or non-transitory and may store therein instructions or code that, when read and executed by the one or more processors 220, cause the one or more processors 220 to implement various functions of the WANN 120 described herein.
[0065] Data packets in a wireless access network such as the example described in FIG. 2 may be transmitted as protocol data units (PDUs) . The data included therein may be packaged as PDUs at various network layers wrapped with nested and / or hierarchical protocol headers. The PDUs may be communicated between a transmitting device or transmitting end (these two terms are used interchangeably) and a receiving device or receiving end (these two terms are also used interchangeably) once a connection (e.g., a radio link control (RRC) connection) is established between the transmitting and receiving ends. Any of the transmitting device or receiving device may be either a wireless terminal device such as device 110 and 120 of FIG. 2 or a wireless access network node such as node 202 of FIG. 2. Each device may both be a transmitting device and receiving device for bi-directional communications.
[0066] The core network 130 of FIG. 1 may include various network nodes geographically distributed and interconnected to provide network coverage of a service region of the carrier network 102. These network nodes may be implemented as dedicated hardware network nodes. Alternatively, these network nodes may be virtualized and implemented as virtual machines or as software entities. These network nodes may each be configured with one or more types of network functions which collectively provide the provisioning and routing functionalities of the core network 130.
[0067] Returning to wireless radio access network (RAN) , FIG. 3 illustrates an example RAN 340 in communication with a core network 310 and wireless terminals UE1 to UE7. The RAN 340 may include one or more various types of wireless base station or WANNs 320 and 321 which may include but are not limited to gNB, eNodeB, NodeB, or other type of base stations. The RAN 340 may be backhauled to the core network 310. The WANNs 320, for example, may further include multiple separate access network nodes in the form of a Central Unit (CU) 322 and one or more Distributed Unit (DU) 324 and 326. The CU 322 is connected with DU1 324 and DU2 326 via various interfaces, for example, an F1 interface. The F1 interface, for example, may further include an F1-C interface and an F1-U interface, which may be used to carry control plane information and user plane data, respectively. In some embodiments, the CU may be a gNB Central Unit (gNB-CU) , and the DU may be a gNB Distributed Unit (gNB-DU) . While the various implementations described below are provided in the context of a 5G cellular wireless network, the underlying principles described herein are applicable to other types of radio access networks including but not limited to other generations of cellular network, as well as Wi-Fi, Bluetooth, ZigBee, and WiMax networks.
[0068] The UEs may be connected to the network via the WANNs 320 over an air interface. The UEs may be served by at least one cell. Each cell is associated with a coverage area. These cells may be alternatively referred to as serving cells. The coverage areas between cells may partially overlap. Each UE may be actively communicating with at least one cell while may be potentially connected or connectable to more than one cell. In the example of FIG. 1, UE1, UE2, and UE3 may be served by cell1 330 of the DU1, whereas UE4 and UE5 may be served by cell2 332 of the DU1, and UE6 and UE7 may be served by cell3 associated with DU2. In some implementations, a UE may be served simultaneously by two or more cells. Each of the UE may be mobile and the signal strength and quality from the various cells at the UE may depend on the UE location and mobility.
[0069] In some example implementations, the cells shown in FIG. 3 may be alternatively referred to as serving cells. The serving cells may be grouped into serving cell groups (CGs) . A serving cell group may be either a Master CG (MCG) or Secondary CG (SCG) . Within each type of cell groups, there may be one primary cell and one or more secondary cells. A primary cell in a MSG, for example, may be referred to as a PCell, whereas a primary cell in a SCG may be referred to as PScell. Secondary cells in either an MCG or an SCG may be all referred to as SCell. The primary cells including PCell and PScell may be collectively referred to as spCell (special Cell) . All these cells may be referred to as serving cells or cells. The term “cell” and “serving cell” may be used interchangeably in a general manner unless specifically differentiated. The term “serving cell” may refer to a cell that is serving, will serve, or may serve the UE. In other words, a “serving cell” may not be currently serving the UE. While the various embodiment described below may at times be referred to one of the types of serving cells above, the underlying principles apply to all types of serving cells in both types of serving cell groups.
[0070] FIG. 4 further illustrates a simplified view of the various network layers involved in transmitting user-plane PDUs from a transmitting device 402 to a receiving device 404 in the example wireless access network of FIGs. 1-3. FIG. 4 is not intended to be inclusive of all essential device components or network layers for handling the transmission of the PDUs. FIG. 4 illustrates that the data packaged by upper network layers 420 at the transmitting device 402 may be transmitted to corresponding upper layer 430 (such as radio resource control or RRC layer) at the receiving device 304 via Packet Data Convergence Protocol layer (PDCP layer, not shown in FIG. 4) and radio link control (RLC) layer 422 and of the transmitting device, the physical (PHY) layers of the transmitting and receiving devices and the radio interface, as shown as 406, and the media access control (MAC) layer 434 and RLC layer 432 of the receiving device. Various network entities in each of these layers may be configured to handle the transmission and retransmission of the PDUs.
[0071] In FIG. 4, the upper layers 420 may be referred as layer-3 or L3, whereas the intermediate layers such as the RLC layer and / or the MAC layer and / or the PDCP layer (not shown in FIG. 4) may be collectively referred to as layer-2, or L2, and the term layer-1 is used to refer to layers such as the physical layer and the radio interface-associated layers. In some instances, the term “low layer” may be used to refer to a collection of L1 and L2, whereas the term “high layer” may be used to refer to layer-3. In some situations, the term “lower layer” may be used to refer to a layer among L1, L2, and L3 that are lower than a current reference layer. Control signaling may be initiated and triggered at each of L1 through L3 and within the various network layers therein. These signaling messages may be encapsulated and cascaded into lower layer packages and transmitted via allocated control or data over-the-air radio resources and interfaces. The term “layer” generally includes various corresponding entities thereof. For example, a MAC layer encompasses corresponding MAC entities that may be created. The layer-1, for example, encompasses PHY entities. The layer-2, for another example encompasses MAC layers / entities, RLC layers / entities, service data adaptation protocol (SDAP) layers and / or PDCP layers / entities.
[0072] AI / ML Assisted Wireless Network Provisioning and Configuration
[0073] AI and Machine Learning (ML) (alternatively referred to AL generally) may facilitate more efficient configuration and provisioning in wireless networks. At the core of a general AI framework are various AI models. An AI model generally contains a large number of model parameters that are determined through a training process where correlations in a set of training data are learned and embedded in the trained model parameters. The trained model parameters may thus be used to generate inference or predictions from a set of input datasets. AI models are particularly suitable for situations where there is few trackable deterministic or analytical derivation paths between input data and output but correlations in historical data may be identified and may be embedded into the AI models via training processes.
[0074] AI models may be constructed and trained for various inference or predictive functionalities. Inferences or predictions generated by these AI models may facilitate various aspect of the configuration and provisioning of the over-the-air interface of a wireless network, including but not limited to resource management, resource allocation / selection (including spatial, radio frequency, and time resources) , mobility management, and radio link failure management.
[0075] AI assisted mobility management and radio link failure management may be particularly beneficial. Specifically, traditional beam, cell, and radio frequency provisioning involved in mobility and radio link failure management is inflexible and consumes much overhead. For example, traditional beam management typically relies on exhaustive beam sweeping / scanning and measurements. A UE may be configured to monitor and measure each reference signal and then report the measurement results to the NW for the NW to decide the best beam for the UE to switch to during mobility. This process is resource and power intensive and time consuming. Trained AI models that embed learned correlation between various network condition parameters can at least help reduce the number of measurements (or requiring fewer reference signals) via inference capability of these AI models. For example, in some implementations, AI models may help identify inferences of best candidate beams using other network conditions and / or reduced number of beam measurement, and then only sweep and measure a smaller number of candidate beams to select the beam for use in current communication.
[0076] The traditional non-AI approaches to mobility and / or radio failure management are further only reactive in that they do not take historical time correlations into consideration and thus can only react to current measurements in relation to predetermined or configured threshold values. Such traditional approaches thus cannot predict future network conditions and unable to provide proactive mobility and radio link failure management. As such, in situations where cell quality changes, e.g., degrades, rapidly (e.g., when UE mobility is high) , the network may not be able to know the degraded cell quality in time based on the traditional reactive approaches, leading to frequent handover failure or radio link failure during mobility. Therefore, it may be desirable in at least in such situations to implement a proactive rather than reactive scheme. A proactive approach may also be based on AI techniques described above. In an AI-based proactive scheme for mobility and / or radio link failure management, for example, the network can know the beam / cell quality change in advance (even before the change actually happens) via Artificial Intelligence / Machine Learning (AI / ML) algorithm. For example, the UE / NW may be able to predict whether the beams / cells will become worse in a future time instance via temporal-domain prediction.
[0077] In some example implementations of AI / ML assisted network provisioning including but not limited to mobility and radio link failure management, AI models may reside on the UE side. In some other implementations, AI model may instead reside on the network (NW) side. AI models may be provided as a service. AI models may be retrained and updated as needed. The UE or the NW may determine what models to retrieve or retain and how they are updated and configured for assisting in the various aspects of wireless communications.
[0078] In some example implementations including but not limited to AI-based proactive mobility and / or radio link failure management, inputs to the AI models on either the UE side or the NW side may be obtained from a set of measurements of one or more measurement objects (MOs) . A measurement object (MO) , for example, may be a spatial beam, a frequency channel, a cell, or the like. Each measurement object may be associated with a measurement identity. In some measurement mechanism, the UE may be configured by the NW to perform measurements on each measurement object associated with the measurement identity. For example, measurements may be triggered by one or more predefined or NW-configured conditions being met. For a particular cell, for example, the UE may measure one or more beams of the cell to derive beam quality and cell quality and then reports the results to the NW when some triggering criteria are met. The triggering criteria can be set in forms of either periodical measurement / reporting or a single event triggering or others.
[0079] In addition, the UE may be configured to perform AI-based inter-frequency predictions that may also benefit mobile management and radio link failure management. Without AI / ML assisted prediction, the UE would need to perform measurements on each frequency. However, with the assistance of one or more AI / ML algorithms, inter-frequency prediction may be achieved. As a result, there may be no need to actually measure each frequency and as such, the measurement burden can be reduced via predicting measurement results on some un-measured frequencies based on measured results on some other frequencies. For example, cell quality for inter-frequency neighbor cells may be predicted via AI / ML models based on measured cell quality of serving cell and / or intra-frequency neighbor cells. In this way, shorter measurement time gap during the communication sessions may be required or no time gap may be needed at all, and UE throughput may be improved. In addition, even for intra-frequency measurements, it is possible to predict the cell quality of intra-frequency neighbor cell (s) based on the cell quality of the serving cell, or based on the cell quality of the serving cell and other intra-frequency neighbor cells. Such predictions may be referred to as spatial-domain prediction or frequency-domain prediction.
[0080] AI portion of a general mobility management scheme is illustrated in FIG. 5. FIG. 5 shows that AI models residing on either the network side (e.g., at a base station) or terminal side may be used to provide, as an example, a spatial prediction of measurement results (e.g., for cell 4) . In this particular example shown, actual intra-frequency measurements of the current serving cell (cell 1) and its neighboring cells (cells 2 and 3) are processed by the AI model (s) to generate prediction of a current measurement result for cell 4 without actually measuring cell 4. The prediction result for cell 4 may further be made by the AI model for a future time, such that the prediction is both spatial and temporal. In some situations, a prediction by the AI model may be only temporal. The term “measurements” or “measurement results” , as referred to in this disclosure, may be actually measurements taken by the network or the terminal or may be predicted by the AI models. The actual measurements and / or the predicted measurements may be utilized for mobility management (e.g., for selection of target base station, target cell, and beams, and the like) .
[0081] This disclosure is directed generally to wireless communication networks and particularly to configuration and provisioning of mobility of wireless terminal devices assisted by Artificial Intelligence (AI) models residing either on the network side or the terminal side. For example, a configuration may be provided by the network to a terminal device with respect to such mobility management. Such a configuration may specify information related to actual measurements and reporting of measurement objects as well as generation and reporting of AI-predicted measurement results. The actual measurements and AI-predicted results may be identified and used to assist with mobility management, such as a handover, of the terminal device via adapted messaging in a mobility management procedure.
[0082] This disclosure specifically describes techniques that can be implemented for exchanging information between network and UE and / or between the network nodes, e.g. from gNB-DU to gNB-CU, from gNB-CU to gNB-DU, from source cell to target cell, from SN to MN, from MN to SN.
[0083] A network side node described below can be an eNB, an ng-eNB, or a gNB. The terminal or UE below can be configured with single carrier, carrier aggregation (CA) , dual connectivity (DC) . For DC, the MN can be an eNB, a ng-eNB, or a gNB; and the SN can be an eNB, a ng-eNB, or a gNB, but not only limited to 4G, 5G network equipment.
[0084] AI Based Mobility Management with Network Side AI Model
[0085] The example implementations below provide a handover management procedure involving a terminal device, a source base station, and a target base station. The handover management procedure may rely on at least one AI prediction. A mobility management configuration provided from the source base station to the terminal device may be adapted to include information items pertaining to the AI prediction aspect of the mobility management. In the example implementations below, the AI functions may reside on the network side, e.g., with the source base station.
[0086] An overall interaction flow or procedure among the terminal device or user equipment (UE) , the source base station, and the target base station for managing the AI-based mobility of the terminal device for such implementations is shown in FIG. 6, including the following example steps:
[0087] Step 1: The source base station may send a configuration message to the UE, the measurement configuration may concern actual measurements and AI-related information, as well as configuration for reporting of the measurements.
[0088] Step 2: UE may perform actual measurements based on the configuration.
[0089] Step 3: The UE may report the measurement results to the network (e.g., the source base station) based on the reporting configuration in the configuration message.
[0090] Step 4: The source base station may obtain predicted beam and / or cell level measurement results as inferred by network side AI models based on the measurement results reported from the UE.
[0091] Step 5: The source base station may decide whether to move the UE to another target cell based on the reported and / or predicted measurement results via a handover procedure. If handover is needed, the source base station may send a handover request to the target base station as selected.
[0092] Step 6: The target base station may perform admission control and send a handover request acknowledge message to the UE.
[0093] Step 7: The source base station may then send a handover command to the UE.
[0094] Step 8: Optionally, the UE may then perform a random access channel (RACH) procedure to gain access to the target cell.
[0095] Step 9: The UE may send a handover command complete message to the target base station after a successful completion of the handover procedure;
[0096] Step 10: Optionally, if needed, the UE may further perform and send actual measurement results corresponding to the predicted measurements of Step 4 for the target cell to the target base station, e.g., for purposes of evaluation of the performance of the AI model.
[0097] Further details are provided below for some of the steps of FIG. 6 above.
[0098] In Step 1, for example, in order to inform the UE which frequency point / cell / beam the UE shall perform measurement on, and when the UE is expected to report the measurement results to the network and how to report, the configuration message that the network (e.g., the source base station) sends to the UE may include or indicate one or more of the followings:
[0099] · A beam / cell list to indicate which beam (s) / cell (s) the UE is expected to measure and / or report.
[0100] · Information element (s) to indicate whether the network would predict measurement results for measurement objects (MOs) , which general includes cells, beams, and other objects. In some example implementations, the configuration message may include configurations for a list of MOs. An indication may be included for an MO among the list of MOs to specify whether that MO is to be predicted by the network. Alternatively, the configuration message may include two separate lists of MOs, where the first list may include MOs that actual measurements should be performed whereas the second list may include MOs that the measurements are to be AI-predicted by the network.
[0101] An example for the latter alternative (two-list configuration) is illustrated in FIG. 7, wherein the configuration message includes a “measObjectToAddModList” for configuring actually measured MOs and a “ai-measObjectToAddModList” for configuring MOs to be predicted by the network. The measurement results of the MOs in the second list would be obtained from AI prediction. According to the example configuration of FIG. 7, the network would predict the measurement results of ai-MO1, ai-MO2 and ai-MO3.
[0102] In some example implementation, indication information elements above can be provided in the configuration message on a per frequency point level or per cell level or per beam level. In some example implementations, if the information element is on a per cell level, a cell list may be included in the configuration message to indicate the cells whose measurement results would be predicted. In some other example implementations, if the information element is on a per beam level, a beam list may be included in the configuration message to indicate the beams whose measurement results would be predicted. In some example implementations, the two-list approach above be used for some cells, so that adoption of the two-list approach can be on a per cell level.
[0103] In some example implementations, if one MO / Cell / Beam’s measurement results would come from AI prediction, the UE would not perform actual measurement on this MO / Cell / Beam. In some other example implementations, the UE may still perform measurements on such MO / Cell / Beam for other purposes (e.g., evaluation purposes) , and may be based on AI-related radio resource management (RRM) requirements (e.g., such measurements may be performed over a longer measurement period compared with normal measurement) .
[0104] · One or more information elements to indicate types of the predictions performed by the network for the predicted MOs. For example, the prediction types may include spatial domain prediction type or temporal domain prediction type or frequency domain prediction type. In some example implementations, such information elements may be included on a per frequency point level or per MO level or per cell level or per beam level.
[0105] · A set of measurement thresholds to determine when the UE is required or configured to report AI related measurement results to the network. The term “AI-related measurement results” is used to refer to actual measurements that the UE takes either for direct usage in mobility management or for use by the network for obtain predicted measurement results. For example, the UE may be configured to report the AI-related measurement results to the network if the measured quality of the serving cell (e.g. cell results or beam results) satisfies certain criterion related to the set of measurement thresholds.
[0106] In some example implementations, the set of measurement thresholds may include a single measurement threshold for serving cell. The UE, for example, may be configured to report the AI-related measurement results of the MO or all MOs if the measured result of the serving cell is below the single measurement threshold, wherein the UE is configured to not report such result if it is below the single measurement threshold. An example of such single measurement threshold is illustrated in FIG. 8A. In FIG. 8A, the measurement is based on reference signal received power (RSRP) . The UE is configured to report AI-related measurement results to the network within [t1, t2] and [t3, t4] where the actual measurement of the corresponding MO is below the single measurement threshold.
[0107] In some other example implementations, two measurement thresholds may be implemented for threshold. Specifically, the AI-related measurement results reporting function may be enabled when the measurement results of serving cell is below a first threshold. After the AI-related reporting function is enabled, the AI-related measurement result reporting may be disabled if the measurement result of the serving cell rises above a second threshold. An example is illustrated in FIG. 8B, where the first threshold (in terms of, e.g., RSRP) is referred to as “threshold to enable AI reporting function” , whereas the second threshold is referred to as “threshold to disable AI reporting function. ” In the example of FIG. 8B, the first threshold may be lower than the second threshold, and the UE is configured to report AI-related measurement result of the MO or all MOs to the network within [t2, t3] . The two-level threshold scheme above may be advantageously implemented to reduce ping-pong effect in presence of rapid measurement fluctuations. In addition, the single threshold level scheme above may be viewed as a special case of the two-level scheme, where the two threshold levels coincide.
[0108] In the various implementations above, the measurements and the corresponding measurement thresholds may be specified in RSRP, and / or Reference Signal Received Quality (RSRQ) and / or Signal-to-Interference Noise Ratio (SINR) .
[0109] · A measurement threshold to determine whether a measurement result of an MO can be reported to the network. This threshold level may serve as a gateway reporting threshold for a recognition that measurement lower than certain level should not be reported because such measurement results may be inaccurate or may otherwise adversely affect the mobility decision or prediction by the network based on such measurement. The UE is configured to only potentially report the measurement above such a threshold. In some example implementations, when the measurement result is below such a threshold, the UE may (1) not report this measurement result to the network; and (2) report an indication / specific value to the network (e.g., the source base station) to indicate to or inform the network that this measurement result is below the threshold.
[0110] In some example implementations, the measurement threshold above may be configured for beam level measurement results or for cell level measurement results. The measurements and the threshold above may be specified in RSRP, RSRQ, and / or SINR) .
[0111] In some example implementations, the configuration message above may be carried in the an MeasConfig RRC information element and / or a separate RRC information element referred to as ai-MeasConfig included in an RRCReconfiguration message. An example is shown in FIG. 9. In the example configuration of FIG. 9, a MeasConfig information element is shown. The MeasConfig of FIG. 9 include a single MO list of configurations for MO1, MO2, and MO3. The MeasConfig of FIG. 9 also specifies two-level reporting thresholds for all MOs in RSRP, including “ai-ReportingEnable” threshold level of -110 dBm, and “ai-ReportingDisable” threshold level of -107 dBm. As such, when the RSRP measurement results of the serving cell are below -110 dBm, the measurement result reporting function is enabled. Thereafter, if the RSRP measurement results of the serving cell raises above the -107 dBm, the measurement result reporting function is disabled.
[0112] Further in the example of FIG. 9, for MO1, the UE is configured to perform actual measurement on the indicated beams (SSB 1, SSB 5, and SSB 9 in Cell 1 and SSB 1, SSB 3, and SSB 7 in Cell 2) . Further, the reporting of MO1 measurements (corresponding to the configured SSB indexes) can only be enabled when the measurement result is above -120 dBm (as specified by “thresholdForReporting” ) . For MO2 of FIG. 9, since its the prediction indication is set to ‘true’ , the network can predict the corresponding measurement results based on other MOs’ measurement results, the UE doesn’t need to perform actual measurement on this MO or the UE only needs to perform actual measurement based on the AI-related requirements for performance monitoring (e.g., using a different measurement and reporting timing) . For MO3 of FIG. 9, since the prediction indication is absent, the UE is required or configured to perform actual measurement on this MO.
[0113] In further detail for Step 5 of FIG. 6, the handover request transmitted from the source base station to the target base station (after the source base station select the target base station based on the measurement results reported from the UE and the measurements predicted by the network based on the actual measurements from the terminal) may contain or indicate one or more of the information elements:
[0114] · Applied AI / ML feature / function / model information.
[0115] · AI related additional information, which may include but is not limited to:
[0116] ○ UE speed;
[0117] ○ UE orientation;
[0118] ○ UE antenna array dimension;
[0119] ○ UE codebook; and the like.
[0120] · RSRP / RSRQ / SINR measurement results of MOs (including cells and beams) .
[0121] · Information to indicate whether the RSRP / RSRQ / SINR measurement results of MOs are from AI predication. In some example implementations, such indication can be provided on a per frequency point level or per cell level or per SSB level.
[0122] An example information element included in the handover request above is shown in FIG. 10. The example information element is referred as “HandoverPreparationInformation” , which contains a list of measurement results. In this example, the measurement results for cell with physical cell identifier PCI = 1 are from prediction as indicated by its resultsFromPrediction information element. The measurement results for cell with PCI=2 are from actual measurement, since the resultsFromPrediction indication is absent.
[0123] Another example “HandoverPreparationInformation” information item is shown in FIG. 11, wherein information related to AI predicted measurement results may be provided in a separate list, referred to as “ai-MeasResultsList2NR” , in addition to the list for actual measurement results, referred to as “measureResultist2NR” . Specifically, the information element of ai-MeasResultsList2NR may be used to send the measurement results from prediction to the target base station. In other words, the measurement results in the ai-MeasResultsList2NR are from prediction. The measurement results in the measResults2NR are from actual measurements instead.
[0124] In further detail for Step 7 of FIG. 6 with respect to the handover command transmitted to the UE, if the target cell’s measurement results are predicted by AI algorithm without real measurements on air interface, in order to accelerate the handover procedure, the handover command may include or indicate one or more the followings:
[0125] · Predicted measurement results of the target cell, including, for example, cell level measurement results and / or beam level result.
[0126] · Reference information to indicate which cell and which information the UE can take as reference in order to accelerate handover procedure. A reference cell as indicated can provide reference information for the UE to identify and access the target cell. Such reference information may include one or more of the followings:
[0127] ○ Uplink synchronization information (e.g. timing advance value) ;
[0128] ○ Downlink synchronization information (e.g. SFN, frame boundary, and the like) ;
[0129] ○ AGC (automatic gain control) source;
[0130] ○ SSB information, including one or more of: location of SSB; SSB quality information (e.g. which SSB has the best beam results) ; spatial relation information of the SSB; Quasi Co-Location (QCL) information of the SSB.
[0131] In some example implementations, the reference cell above can be serving cell, intra-frequency neighbor cell or inter-frequency neighbor cell.
[0132] In some example implementations, the reference cell above can be indicated by PCI or the cell index in a pre-defined cell list (e.g. cell list in the measObjectNR) .
[0133] · SSB index to indicate which SSB the UE is expected to perform RACH on. The UE may select the indicated SSB index to perform RACH procedure. In some implementations, network may indicate in the handover command more than one SSB to the UE, and UE may select one SSB among the indicated SSB list to perform RACH.
[0134] · Preamble path loss of PRACH. In some example implementations, the preamble path loss may be provided to the UE explicitly via absolute power value or implicitly via measurement results. In some example implementations, the granularity of preamble transmission power can be on a per SSB level or per cell level.
[0135] · Configured UL grant to help the UE send handover command complete message. In some example implementations, the configured ul grant is included in RRCReconfigurationWithSync.
[0136] An example RRCReconfiguration message serving as a handover command is shown in FIG. 12. In the example of FIG. 12, the UE may assume that the SFN and frame boundary align between target cell and cell 2. And the UE is expected to perform RACH on the SSB1. The UE uses the measurement results for SSB 1 (-100 dBm) to determine the preamble path loss.
[0137] In further detail for Step 10 of FIG. 6, in some example implementations, after the UE detaches the source cell upon successful handover, the UE may further perform actual measurement on the target cell and then reports the measurement results to the target cell. The reporting for the target cell’s results may be triggered upon one or more of the following conditions:
[0138] · The UE obtains available measurement results for the target cell.
[0139] · The network configures the UE to report measurement results for the target cell. In some example implementations, such configuration may be included in the handover command.
[0140] · When the difference between the actual measured value and predicted value (if indicated to the UE) exceeds a difference threshold. In some example implementations, such a difference threshold may be pre-defined or configured by the network via handover command.
[0141] The UE may report the measurement results to the network via one of the following mechanisms:
[0142] · The UE may report the measurement results via the handover command complete message; (e.g., as part of Step 9 above) .
[0143] · The UE may report the measurement results via the UEAssistanceInfomation message.
[0144] · The UE may report an indication to indicate that the measurement results for target cell is available. And then if the network requests the measurement results, the UE may send the measurement results to the network per the request.
[0145] AI Based Mobility Management with UE Side AI Model
[0146] The further example implementations below provide a handover management procedure involving a terminal device, a source base station, and a target base station. The handover management procedure may rely on at least one AI prediction. A mobility management configuration provided from the source base station to the terminal device may be adapted to include information items pertaining to the AI prediction aspect of the mobility management. In the example implementations below, the AI functions may reside on the UE side.
[0147] An overall interaction flow or procedure among the terminal device or user equipment (UE) , the source base station, and the target base station for managing the AI-based mobility of the terminal device for such implementations is shown in FIG. 13, including the following example steps:
[0148] Step 0: Optionally, the UE may first send its preferred configuration with respect to its mobility management to the network.
[0149] Step 1: The source gNB may send a measurement configuration message to the UE, the measurement configuration may concern actual measurements and AI-related information, as well as configuration for reporting of the actual measurements and / or predicted measurements.
[0150] Step 2: The UE may perform actual measurement and prediction of MOs to obtain beam and / or cell level measurement results or predictions. The predicted measurements may be obtained using UE side AI models based on actually measured results.
[0151] Step 3: If triggering criterion is met, the UE may send the measurement results including the actual measurement results and the prediction measurement results to the network (e.g., the source base station) .
[0152] Step 4: The source base station may decide whether to move the UE to another target cell based on the reported and / or predicted measurement results via a handover procedure. If handover is needed, the source base station may send a handover request to the target base station as selected.
[0153] Step 5: The target base station may perform admission control and send a handover request acknowledge message to the UE.
[0154] Step 6: The source base station may then send a handover command to the UE;
[0155] Step 7: Optionally, the UE may then perform a random access channel (RACH) procedure to gain access to the target cell;
[0156] Step 8: The UE may send a handover command complete message to the target base station after a successful completion of the handover procedure;
[0157] Step 9: Optionally, if needed, the UE may further perform and send actual measurement results corresponding to the predicted measurements of Step 4 for the target cell to the target base station, e.g., for purposes of evaluation of the performance of the AI model.
[0158] Further details are provided below for some of the steps of FIG. 13 above.
[0159] In Step 0 of FIG. 13, for example, the UE may send its preferred network configuration to the network. The network may consider the information included therein when determining network configuration for mobility management. Such preferred configuration may indicate or include one or more the followings:
[0160] · Number of beams to derive cell quality (e.g. nrofSS-BlocksToAverage) .
[0161] · Preferred threshold for the consolidation of the measurement results per SSB from L1 filter (e.g. absThreshSS-BlocksConsolidation) .
[0162] · Preferred AI input beam direction.
[0163] · Preferred beam pattern.
[0164] · Preferred codebook.
[0165] · Preferred configuration to determine layer 3 filtering (e.g., filterCoefficient) .
[0166] · Event related parameters (e.g., timeToTrigger, offset, and the like) .
[0167] · A parameter set indicating one or more information items above with an index in the pre-defined parameter set list.
[0168] In some example implementations, a reporting of the UE preferred network configuration above may be triggered upon:
[0169] · The network configures the UE to report the preferred measurement configuration.
[0170] · The network allows the UE to report the preferred network configuration, and the UE never reports the preferred network configuration before.
[0171] · The network allows the UE to report the preferred network configuration, and the UE preferred network configuration has changed.
[0172] · The UE need to report the AI mobility related UE capability.
[0173] In some example implementations, the UE preferred network configuration may be sent via UE capability (e.g. as UE capability included in the UECapabilityInformation) , or RRC signaling (e.g. the RRC signaling included in, for example, RRCReconfigurationComplete, UEAssistanceInformation or RRCResumeComplete) , and the like)
[0174] This step is optionally and may be used when needed, and need not be at a particular timing relation with the various other steps described above.
[0175] In Step 1 of FIG. 13, for example, in order to inform the UE which frequency point / cell / beam the UE shall perform measurement and / or prediction on, and when the UE is expected to report the measurement results and / or the prediction results to the network, and how to report, the configuration message that the network (e.g., the source base station) sends to the UE may include or indicate one or more of the following items:
[0176] · The information to indicate whether the measurement results of MOs (including beams and cells) can be obtained via prediction.
[0177] In some implementations, the configuration message may include configurations for a list of MOs. An indication may be included for an MO among the list of MOs to specify whether that MO is to be predicted by the network. Alternatively, the configuration message may include two separate lists of MOs, where the first list may include MOs that actual measurements should be performed whereas the second list may include MOs that the measurements are to be AI-predicted by the UE.
[0178] In some example implementation, indication information elements above can be provided in the configuration message on a per frequency point level or per cell level or per beam level. In some example implementations, if the information is on a per cell level, a cell list may be included in the configuration message to indicate the cells whose measurement results would be predicted. In some other example implementations, if the information is on a per beam level, a beam list may be included in the configuration message to indicate the beams whose measurement results would be predicted.
[0179] In some example implementations, if the measurement results of a MO can be obtained from prediction, the UE would perform prediction on this MO with UE side AI models. In some other example implementations, the UE may still perform measurements on such MOs for other purposes (e.g., evaluation purposes) , and may be based on AI-related radio resource management (RRM) requirements (e.g., such measurements may be performed over a longer measurement period compared with normal measurement) .
[0180] · One or more information elements to indicate MOs whose actual measurement results that can be used for predictions of other MOs. In other words, the one or more such information elements are used for specifying measured AI model input information for MOs to be predicted.
[0181] In some example implementations, such information elements may be a cell list (e.g. a list of PCI or a list of cell index) or a beam list (alist of beam index or bit map) .
[0182] In some example implementations, such information elements may be specified on a per UE level or per MO level or per Cell level.
[0183] · One or more information elements to indicate types of the predictions performed by the UE side AI models for the predicted MOs. For example, the prediction types may include spatial domain prediction type or temporal domain prediction type or frequency domain prediction type. In some example implementations, such information elements may be included on a per frequency point level or per MO level or per cell level or per beam level.
[0184] · One or more information elements to indicate that the UE is allowed determine the number of beams to derive cell quality. In some example implementations, if the UE determines the number of beams to derive cell quality, the UE may report the number to the network (e.g., the source base station) . In some example implementations, such reporting may be triggered (1) every time the UE sends the AI-related measurement results to the network; or (2) when the number of the beams has changed.
[0185] In some example implementations, the configuration message above may be carried in the an MeasConfig RRC information element and / or a separate RRC information element referred to as ai-MeasConfig included in an RRCReconfiguration message. An example is shown in FIG. 14. In the example of FIG. 14, a single MO list is provided. For MO1 (MO with ID=1) , the network would predict the measurement results of cell 4, cell 5 and cell 6 (as indicated by the “TopredictCelllist” under MO1) based on the measurement results of cell 1, cell 2 and cell 3 (as specified by the “predictionInput” ) . And only spatial domain prediction is allowed, i.e. temporal domain prediction is not allowed (as specified by the “PredictionType” element of MO1) . For MO2, the UE needs to perform actual measurement on this MO (as indicated by the “Prediction allowed” elopement being configured as “false” ) .
[0186] Another example is shown in FIG. 15, where separate lists of measurement MOs and prediction MOs are configured. According to this example, the measurement results of ai-MO1, ai-MO2 and ai-MO3 would be obtained from prediction, wherein MO1, MO2, and MO3 would be actually measured. Further according to this example, the UE would predict the measurement results of cell 1 based on the measurement results of SSB {1, 5, 9, 13} in cell 7 and SSB {0, 4, 8, 12} in cell 8, and predicts the measurement results of cell 3 based on the measurement results of SSB {0, 3, 7, 9} in cell 9 and SSB {1, 15, 19, 35} in cell 10.
[0187] In Step 4 of FIG. 13, the source base station may indicate to the target base station in the handover request one or more the following:
[0188] · RSRP / RSRQ / SINR measurement results of MOs (including cells and beams) .
[0189] · Information to indicate whether the RSRP / RSRQ / SINR measurement results of MOs are from AI predication. In some example implementations, such indication can be provided on a per frequency point level or per cell level or per SSB level.
[0190] In Step 6 of FIG. 13 with respect to the handover command transmitted to the UE, in order to accelerate the handover procedure, the handover command may include or indicate one or more the followings:
[0191] · Reference information to indicate which cell and which information the UE can take as reference in order to accelerate handover procedure. A reference cell as indicated can provide reference information for the UE to identify and access the target cell. Such reference information may include one or more of the followings:
[0192] ○ Uplink synchronization information (e.g. timing advance value) ;
[0193] ○ Downlink synchronization information (e.g. SFN, frame boundary, and the like) ;
[0194] ○ AGC (automatic gain control) source;
[0195] ○ SSB information, including one or more of: location of SSB; SSB quality information (e.g. which SSB has the best beam results) ; spatial relation information of the SSB; QCL information of the SSB.
[0196] · Configured UL grant to help the UE send handover command complete message. In some example implementations, the configured ul grant is included in RRCReconfigurationWithSync.
[0197] In some example implementations, the reference cell above can be serving cell, intra-frequency neighbor cell or inter-frequency neighbor cell.
[0198] In some example implementations, the reference cell above can be indicated by PCI or the cell index in a pre-defined cell list (e.g. cell list in the measObjectNR) .
[0199] In Step 9 of FIG. 13, in some example implementations, after the UE detaches the source cell upon successful handover, the UE may further perform actual measurement on the target cell and then reports the measurement results to the target cell. The reporting for the target cell’s results may be triggered upon one or more of the following conditions:
[0200] · The UE obtains available measurement results for the target cell.
[0201] · The network configures the UE to report measurement results for the target cell. In some example implementations, such configuration may be included in the handover command.
[0202] · When the difference between the actual measured value and predicted value (if indicated to the UE) exceeds a difference threshold. In some example implementations, such a difference threshold may be pre-defined or configured by the network via handover command.
[0203] The UE may report the measurement results to the network via one of the following mechanisms:
[0204] · The UE may report the measurement results via the handover command complete message; (e.g., as part of Step 8 above) .
[0205] · The UE may report the measurement results via the UEAssistanceInfomation message.
[0206] The UE may report an indication to indicate that the measurement results for target cell is available. And then if the network requests the measurement results, the UE may send the measurement results to the network per the request.
[0207] In the example procedure of FIG. 13 for UE side AI implementations, Steps 1, 3, 4, 5, 6, 7, 8, and 9 are analogous to Steps 1, 3, 5, 6, 7, 8, 9, and 10 of FIG. 6. As such, the detailed description of FIG. 6 with these steps applies to the corresponding steps of FIG. 13. In addition, description for Step 2 of FIG. 6 also applies to step 2 of FIG. 13 with respect to actual measurements of the MOs by the UE. Further, description of Step 4 of FIG. 6 also applies to Step 2 of FIG. 13 with respect to AI-predictions.
[0208] The description and accompanying drawings above provide specific example embodiments and implementations. The described subject matter may, however, be embodied in a variety of different forms and, therefore, covered or claimed subject matter is intended to be construed as not being limited to any example embodiments set forth herein. A reasonably broad scope for claimed or covered subject matter is intended. Among other things, for example, subject matter may be embodied as methods, devices, components, systems, or non-transitory computer-readable media for storing computer codes. Accordingly, embodiments may, for example, take the form of hardware, software, firmware, storage media or any combination thereof. For example, the method embodiments described above may be implemented by components, devices, or systems including memory and processors by executing computer codes stored in the memory.
[0209] Throughout the specification and claims, terms may have nuanced meanings suggested or implied in context beyond an explicitly stated meaning. Likewise, the phrase “in one embodiment / implementation” as used herein does not necessarily refer to the same embodiment and the phrase “in another embodiment / implementation” as used herein does not necessarily refer to a different embodiment. It is intended, for example, that claimed subject matter includes combinations of example embodiments in whole or in part.
[0210] Reference throughout this specification to features, advantages, or similar language does not imply that all of the features and advantages that may be realized with the present solution should be or are included in any single implementation thereof. Rather, language referring to the features and advantages is understood to mean that a specific feature, advantage, or characteristic described in connection with an embodiment is included in at least one embodiment of the present solution. Thus, discussions of the features and advantages, and similar language, throughout the specification may, but do not necessarily, refer to the same embodiment.
[0211] Furthermore, the described features, advantages and characteristics of the present solution may be combined in any suitable manner in one or more embodiments. One of ordinary skill in the relevant art will recognize, in light of the description herein, that the present solution can be practiced without one or more of the specific features or advantages of a particular embodiment. In other instances, additional features and advantages may be recognized in certain embodiments that may not be present in all embodiments of the present solution.
Claims
1.A method performed by a base station in radio communication with a terminal in a wireless access network, the method comprising:transmitting a configuration message to the terminal for mobility management of the terminal, the configuration message comprising at least one information item pertaining to artificial intelligence (AI) prediction of a measurement object (MO) among a plurality of MOs;receiving a measurement report from the terminal, the measurement report being generated by the terminal pertaining to the plurality of the MOs in accordance with the configuration message; andperforming a handover procedure for the terminal in collaboration with a target base station based on the measurement report.2.The method of claim 1, the configuration message comprises at least one of:a beam and / or cell list to indicate beams and / or cells that are expected to be measured and / or reported by the terminal;one or more first indications specifying whether the beams, the cells, and / or the plurality of MOs are predicted by AI predictions;one or more second indications for specifying types of the AI predictions;a first set of measurement threshold values to set conditions for the terminal to report measurement results of the beams, the cells, and / or the MOs to the base station;one or more second measurement threshold values below which the terminal is disallowed from reporting the measurement results of the beams, the cells, and / or the MOs to the base station; orone or more information elements to indicate MOs whose actual measurement results that can be used for predictions of other MOs.3.The method of claim 2, wherein:the configuration message comprises a list of information items for configuring the plurality of MOs; andat least one of the information items comprise a configuration data field for indicating whether a corresponding MO is to be predicted by AI.4.The method of claim 2, wherein the configuration message comprises:a first list of information items for configuring the plurality of MOs; anda second list of information items separate from the first list of information items for specifying one or more prediction objects for the terminal to generate by AI prediction.5.The method of claim 2, wherein the types of the AI predictions comprise at least spatial domain AI prediction type, temporal domain AI prediction type, and frequency domain AI prediction type.6.The method of claim 5, wherein the types of AI predictions are indicated in the configuration message on a per frequency, per MO, or per cell level.7.The method of claim 2, wherein the first set of measurement threshold values and the one or more second measurement threshold values pertain to Reference Signal Receive Power (RSRP) , Reference Signal Received Quality (RSRQ) , or Signal to Interference Noise Ratio (SINR) value.8.The method of claim 2, wherein:the first set of measurement threshold values comprise a measurement report enablement threshold value and a measurement disablement threshold value;the measurement report enablement threshold value is lower than the measurement disablement threshold value; andthe terminal is allowed to report the measurement results of the beams, the cells, and / or the MOs only after the measurement results drops below the measurement report enablement threshold value and before the measurement raises back above the measurement report disablement threshold value.9.The method of claim 2, wherein:the first set of measurement threshold values comprise a single measurement report threshold value; andthe terminal is allowed to report the measurement results of the beams, the cells, and / or the MOs only when the measurement results drops below the single measurement report threshold value.10.The method of claim 2, wherein when the measurement results of one of the beams, the cells, and the MOs falls below a corresponding second measurement threshold value, a third indication therefor is included the measurement report.11.The method of claim 2, wherein the handover procedure comprises:selecting, by the base station, the target base station based on the measurement report;sending a handover request to the target base station; andsending a handover command to the terminal for the terminal to complete the handover procedure with the target base station.12.The method of claim 11, wherein the handover request comprises at least one of:AI information associated with features / functions / models of the AI predictions;AI related additional information;data items comprising the measurement results and / or the AI predictions of the beams, the cells, and / or the MOs; orone or more third indications for indicating whether the data items are measured or AI predicted.13.The method of claim 12, wherein the data items are included in a list in the handover request and each data item comprises one of the one or more third indications.14.The method of claim 12, wherein the handover request comprises at least one of:AI information associated with features / functions / models of the AI predictions;AI related additional information; anddata items included in a first list and a second list, wherein the first list is identified as measured, and the second list is identified as AI predicted.15.The method of claim 11, wherein the handover command comprises at least one of:AI predicted target cell information;reference information indicating measured information as a reference for identifying and accessing the target base station;an SSB index over which the terminal is expected to perform a random access procedure;a preamble path loss for a physical random access channel (PRACH) associated with the random access procedure; ora configured uplink grant for the terminal to send a handover complete message.16.The method of claim 2, wherein the AI predictions are performed by the base station.17.The method of claim 2, wherein the AI predictions are performed by the terminal.18.A method performed by a terminal in radio communication with a base station in a wireless access network, the method comprising:receiving a configuration message from the base station for mobility management of the terminal, the configuration message comprising at least one information item pertaining to artificial intelligence (AI) prediction of a measurement object (MO) among a plurality of MOs;generating a measurement report comprising measurement results of the plurality of the MOs in accordance with the configuration message; andperforming a handover procedure from the base station to a target base station based on the measurement report.19.The method of claim 18, the configuration message comprises at least one of:one or more first indications specifying whether the measurement results of the plurality of MOs can be obtained via AI predictions;one or more second indications for specifying types of the AI predictions;a third indication for specifying whether the terminal is allowed to determine a number of beams to derive cell quality;a first set of measurement threshold values to set conditions for the terminal to report measurement results of the beams, the cells, and / or the MOs to the base station;one or more second measurement threshold values below which the terminal is disallowed from reporting the measurement results of the beams, the cells, and / or the MOs to the base station; orone or more information elements to indicate MOs whose actual measurement results that can be used for predictions of other MOs.20.The method of claim 19, wherein:the configuration message comprises a list of information items for configuring the plurality of MOs; andat least one of the information items comprise a configuration data field for indicating whether a corresponding MO is to be predicted by AI.21.The method of claim 19, wherein the configuration message comprises:a first list of information items for configuring the plurality of MOs; anda second list of information items separate from the first list of information items for specifying one or more prediction objects for the terminal to generate by AI prediction.22.The method of claim 19, wherein the types of the AI predictions comprise at least spatial domain AI prediction type, temporal domain AI prediction type, and frequency domain AI prediction.23.The method of claim 22, wherein the types of AI predictions are indicated in the configuration message on a per frequency, per MO, or per cell level.24.The method of claim 19, wherein the first set of measurement threshold values and the one or more second measurement threshold values pertain to Reference Signal Receive Power (RSRP) , Reference Signal Received Quality (RSRQ) , or Signal to Interference Noise Ratio (SINR) value.25.The method of claim 19, wherein:the first set of measurement threshold values comprise a measurement report enablement threshold value and a measurement disablement threshold value;the measurement report enablement threshold value is lower than the measurement disablement threshold value; andthe terminal is allowed to report the measurement results of the beams, the cells, and / or the MOs only after the measurement results drops below the measurement report enablement threshold value and before the measurement raises back above the measurement report disablement threshold value.26.The method of claim 19, wherein:the first set of measurement threshold values comprise a single measurement report threshold value; andthe terminal is allowed to report the measurement results of the beams, the cells, and / or the MOs only when the measurement results drops below the single measurement report threshold value.27.The method of claim 19, wherein when the measurement results of one of the MOs falls below a corresponding second measurement threshold value, a fourth indication therefor is included the measurement report.28.The method of claim 18, further comprising performing measurements and or prediction of the plurality of MOs according to the configuration message prior to preforming the handover procedure.29.The method of claim 18 wherein the target base station is selected by the base station based on the measurement report, and the handover procedure comprises:receiving after a handover request from the base station to the target base station is successfully processed, a handover command from the base station for the terminal to complete the handover procedure with the target base station.30.The method of claim 29, wherein the handover request comprises at least one of:data items comprising the measurement results and / or the AI predictions of the plurality of MOs; orone or more indications for indicating whether the data items are measured or AI predicted.31.The method of claim 29, wherein:data items comprising the measurement results and / or the AI predictions of the plurality of MOs are included in a first list and a second list in the handover request;the first list is identified as measured; andthe second list is identified as AI predicted.32.The method of claim 29, wherein the handover command comprises reference information indicating measured information as a reference for identifying and accessing the target base station.33.The method of claim 29, wherein the handover command comprises at least one of:predicted measurement results for a target cell of the target base station;SSB indexes to indicate which SSBs the terminal is expected to perform a random access procedure on;a preamble path loss of a physical random access channel (PRACH) ; ora configured UL grant.34.The base station or the terminal of any one of claims 1 to 33, the base station or the terminal comprising a processor and a memory, wherein the processor is configured to read computer code from the memory to cause the base station or the terminal to perform the method of any one of claims 1 to 33.35.A computer program product comprising a non-transitory computer-readable program medium with computer code stored thereupon, the computer code, when executed by a processor of the base station or the terminal of any one of claims 1 to 33, causing the processor to implement the method of any one of claims 1 to 33.
Citation Information
Patent Citations
Apparatus and method for performing handover in wireless communication system
CN114747256A
Ai / ML based mobility related prediction for handover
US20230413152A1
UE, network node and methods for handling mobility information in a communications network
US20240040461A1
Device and method for performing handover on basis of location in wireless communication system
WO2023058872A1