Methods and apparatus of cluster based RRM measurement prediction for wireless communication systems
Cluster-based RRM measurement prediction using AI/ML models addresses the challenge of generalizing cell-specific models in 3GPP 5G NR networks by reducing network load and latency through efficient model transfer and prediction across cell clusters, thereby improving mobility performance.
Patent Information
- Application Number
- PCT/CN2024/105946
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2024-07-17
- Publication Date
- 2026-01-22
AI Technical Summary
Existing AI/ML-based RRM measurement solutions in 3GPP 5G NR networks face challenges in generalizing cell-specific models due to UE mobility, leading to increased network load and latency when switching models for new cells, which is not efficiently addressed by current mobility mechanisms.
Implementing cluster-based RRM measurement prediction using AI/ML models that allow UE to perform beam sweeping and prediction across clusters, reducing the need for frequent model switching by grouping cells into clusters based on geographical, beam, and frequency characteristics, and utilizing spatial, temporal, and frequency domain measurements.
This approach reduces network load and latency by enabling efficient model transfer and prediction across cell clusters, enhancing mobility performance and minimizing interruptions during handovers.
Smart Images

Figure CN2024105946_22012026_PF_FP_ABST
Abstract
Description
METHODS AND APPARATUS OF CLUSTER BASED RRM MEASUREMENT PREDICTION FOR WIRELESS COMMUNICATION SYSTEMSFIELD
[0001] The present disclosure relates generally to communication systems, and more particularly, the method of cluster based RRM measurement prediction for wireless communication systems.BACKGROUND
[0002] In the conventional network of the 3rd generation partnership project (3GPP) 5G new radio (NR) , considered UE mobility, UE keeps measures and reports radio resource signal environment quality to maintain service continuity and quality. Legacy HO design controlled by a series of L3 procedures including RRM measurement and RRC Reconfiguration, which involves amount of signaling and latency. Conditional handover is introduced to reduces signaling overhead by allowing the UE to make a handover decision based on predefined conditions, leading to a faster HO. Dual Active Protocol Stack (DAPS) aims to minimize interruption by maintaining two active protocol stacks, allowing the UE to communicate with both the source and target cells simultaneously during the handover process. To further reduce the latency, overhead, and interruption time during UE mobility, the mobility mechanism L1 / L2 based inter-cell mobility (LTM, L1L2-triggered Mobility) is enhanced to enable a serving cell to change via beam management with L1 / L2 signaling.
[0003] 3GPP proposed three study use cases in the AI / ML mobility topic to achieve the research goal of reducing measurement and signaling overhead and enhancing mobile network handover performance in release19, including AI / ML-based RRM measurement, AI / ML-based measurement event prediction, and AI / ML-based RLF / HOF prediction. Currently, most AI / ML solution are based on cell-specific model, but due to the mobility characteristic of terminals, cell-specific models is hard to generalize. When UE enter a new cell, new specific cell model needs to be switched / transferred, which means that a large number of models (parameters) need to be transmitted when UE moving, resulting in an increase in network load and a certain amount of latency.
[0004] In this invention, apparatus and mechanisms are sought to use cluster based RRM measurement prediction for mobility mechanisms of wireless communication systems to balance the generalization and complexity of AI / ML model.SUMMARY
[0005] The following presents a simplified summary of one or more aspects in order to provide a basic understanding of such aspects. This summary is not an extensive overview of all contemplated aspects, and is intended to neither identify key or critical elements of all aspects nor delineate the scope of any or all aspects. Its sole purpose is to present some concepts of one or more aspects in a simplified form as a prelude to the more detailed description that is presented later.
[0006] In an aspect of the disclosure, a method, a computer-readable medium, and an apparatus are provided. The apparatus may be a UE. The UE performs beam sweeping to measures on a first cluster of cells, then predicts the measurement results on a second cluster of cells. The measurement results and assistance information (UE position / speed) can be used to construct the model input. The radio resource of the model label and model input are defined by spatial, temporal, frequency domain and any combinations of the domains. The measurement of model input and model label can be beam level and cell level with L1 / L3 filtering. The AI / ML model is applied to derive the cell quality of the first cluster, the second cluster of cells or both of them, and also is applied to evaluating the reporting criteria to trigger the measurement report and sending the measurement report to the network.
[0007] To the accomplishment of the foregoing and related ends, the one or more aspects comprise the features hereinafter fully described and particularly pointed out in the claims. The following description and the annexed drawings set forth in detail certain illustrative features of the one or more aspects. These features are indicative, however, of but a few of the various ways in which the principles of various aspects may be employed, and this description is intended to include all such aspects and their equivalents.BRIEF DESCRIPTION OF THE DRAWINGS
[0008] Figure 1 illustrates a schematic system diagram illustrating an exemplary wireless network in accordance with embodiments of the current invention.
[0009] Figure 2 illustrates an exemplary diagram for the cell-based model update.
[0010] Figure 3 further illustrates the exemplary flow for the training stage and inference stage for cell-based model.
[0011] Figure 4 illustrates an exemplary diagram for the cluster-based model update.
[0012] Figure 5 illustrates an exemplary diagram for the measurement level of cluster-based model.
[0013] Figure 6 illustrates an exemplary diagram for the prediction domain of cluster-based model.
[0014] Figure 7 illustrate an exemplary overall flow for cluster based RRM prediction measurement procedure in accordance with embodiments of the current invention.DETAILED DESCRIPTION
[0015] The detailed description set forth below in connection with the appended drawings is intended as a description of various configurations and is not intended to represent the only configurations in which the concepts described herein may be practiced. The detailed description includes specific details for the purpose of providing a thorough understanding of various concepts. However, it will be apparent to those skilled in the art that these concepts may be practiced without these specific details. In some instances, well known structures and components are shown in block diagram form in order to avoid obscuring such concepts.
[0016] Several aspects of telecommunication systems will now be presented with reference to various apparatus and methods. These apparatus and methods will be described in the following detailed description and illustrated in the accompanying drawings by various blocks, components, circuits, processes, algorithms, etc. (collectively referred to as “elements” ) . These elements may be implemented using electronic hardware, computer software, or any combination thereof. Whether such elements are implemented as hardware or software depends upon the particular application and design constraints imposed on the overall system.
[0017] Aspects of the present disclosure provide methods, apparatus, processing systems, and computer readable mediums for NR (new radio access technology, or 5G technology) , 6G or other radio access technology. NR may support various wireless communication services. These services may havse different quality of service (QoS) requirements e.g. latency and reliability requirements.
[0018] Figure 1 illustrates a schematic system diagram illustrating an exemplary wireless network in accordance with embodiments of the current invention. Wireless system includes one or more fixed base infrastructure units forming a network distributed over a geographical region. The base unit may also be referred to as an access point, an access terminal, a base station, a Node-B, an eNode-B, a gNB, or by other terminology used in the art. As an example, base stations serve a number of mobile stations within a serving area, for example, a cell, or within a cell sector. In some systems, one or more base stations are coupled to a controller forming an access network that is coupled to one or more core networks. gNB1and gNB2 are base stations in NR, the serving area of which may or may not overlap with each other. As an example, UE1 or mobile station is only in the service area of gNB1 and connected with gNB1. UE1 is connected with gNB1 only, gNB1 is connected with gNB1 and 2 via Xn interface. gNB1 and gNB2 are clustered into cluster 1, gNB3, gNB4 and gNB5 are clustered into cluster 2, gNB6 and gNB7 are clustered into cluster 3. In one embodiment, the AI / ML model is trained at NW side and delivered from UE server to UE. In another embodiment, the AI / ML model is trained at UE side and delivered from NW server to UE.
[0019] Figure 1 further illustrates simplified interaction flow for UE1 and gNB3. The gNB provides measurement configuration to UE by RRC configuration signaling. The gNB can request UE to measure intra-frequency, inter-frequency measurements. UE performs measurements and based on the measurement evaluate the criteria for measurement report. The AI / ML model is used to predict the actual measurements results. In one embodiment, the AI / ML model is at UE side. UE performs measurement prediction and report the model output to gNB. gNB makes handover decision and sends handover command to UE.
[0020] According to some embodiments, UE has an antenna, which transmits and receives radio signals. A RF transceiver, coupled with the antenna, receives RF signals from antenna, converts them to baseband signal, and sends them to processor. In one embodiment, the RF transceiver may comprise two RF modules (not shown) . A first RF module is used for transmitting and receiving on one frequency band, and the other RF module is used for different frequency bands transmitting and receiving which is different from the first transmitting and receiving. RF transceiver also converts received baseband signals from processor, converts them to RF signals, and sends out to antenna. Processor processes the received baseband signals and invokes different functional modules to perform features in UE. Memory stores program instructions and data to control the operations of mobile station. UE also includes multiple function modules that carry out different tasks in accordance with embodiments of the current invention.
[0021] Figure 2 illustrates an exemplary diagram for the cell-based model update. In one embodiment (as shown in sub-figure (a) ) , the cell-based model is applicable for individual cell. In one embodiment, the UE performs model update when UE is moving out of certain applicable cell of model. In another embodiment (as shown in sub-figure (b) ) , the cell-based model is applicable for all cells in a cluster. In one embodiment, the UE no need to perform model update within all cells in cluster.
[0022] In one embodiment, for the cell-based model applicable for individual cell and all cells in cluster, the model input is the measurement of first specific cell and the model label / output is the measurement of second specific cell. In one embodiment, the measurement of model input and label / output is defined by spatial, temporal, frequency domain and any combinations of the domains. In one embodiment, the second cell is the intra-cell of the first cell. In another embodiment, the second cell is the inter-cell of the first cell.
[0023] Figure 3 further illustrates the exemplary flow for the training stage and inference stage for cell-based model. In one embodiment, for the cell-based model applicable for individual cell (as shown in sub-figure (a) ) , at training stage, the measurement of first specific cell as input and measurement of the second specific cell as label are combined to pass through training loop. In another embodiment, for the cell-based model applicable for all cells in cluster (as shown in sub-figure (b) ) , at training stage, all pairs of the measurement of first specific cell (as model input) and measurement of the second specific cell (as label) in cluster are combined to pass through training loop. At inference stage, in one embodiment, for the cell-based model applicable for individual cell and all cells in cluster, the trained AI / ML model using measurement of first cell as model input and measurement of the second cell as model outputs.
[0024] Figure 4 illustrates an exemplary diagram for the cluster-based model update. The cluster-based model is applicable for all cells in cluster. In one embodiment, the cluster is grouped using the gNB geographical coordinates, the beam configuration, operating frequency, bandwidth, transmission power, and antenna height, etc. In another embodiment, the cluster is grouped up to UE implementation. As shown in sub-figure (a) , the movement of the UE within the same cluster does not require the transfer / switching of new model, the transfer / switching of the model is required only when the UE moves to an area of a different cluster. Sub-figure (b) further illustrates the exemplary flow for the training stage and inference stage for cluster-based model. At training stage, the measurement of first cluster (as model input) and measurement of the second cluster (as label) are combined to pass through training loop. At inference stage, in one embodiment, the trained AI / ML model using measurement of first cluster as model input and measurement of the second cluster as model outputs. In one embodiment, the measurement of model input and label / output is defined by spatial, temporal, frequency domain and any combinations of the domains for the first cluster and the second cluster. In one embodiment, the first cluster is same with the second cluster of cells. In one embodiment, the first cluster is the subset of the second cluster of cells. In one embodiment, the first cluster is a partial intersection set with the second cluster of cells.
[0025] Figure 5 illustrates an exemplary diagram for the measurement level of cluster-based model. In one embodiment, the measurement of the first cluster cells (as model input) is L1 beam level measurement results without L1 filtering at point A. In one embodiment, the measurement of the second cluster cells is without L1 filtering at point A, with L1 filtering at point A1, L1 cell level results at point B, L3 beam level results at point E or L3 cell level results at point C. In another embodiment, the measurement of the first cluster cells (as model input) is L1 beam level measurement results with L1 filtering at point A1. In one embodiment, the measurement of the second cluster cells is measurement with L1 filtering at point A1, L1 cell level results at point B, L3 beam level results at point E or L3 cell level results at point C. In one embodiment, the measurement for the first cluster and the second cluster is applicable for spatial, temporal, frequency domain and any combinations of the domains.
[0026] In one embodiment, the measurement of the first cluster cells is L3 beam level measurement results at point E, the measurement of the second cluster cells is L3 beam level results at point E. In one embodiment, the measurement for the first cluster and the second cluster is applicable for spatial, temporal, frequency domain and any combinations of the domains.
[0027] In one embodiment, the measurement of the first cluster cells is L1 cell level measurement results at point B, the measurement of the second cluster cells can be L1 cell level results at point B or L3 cell level results at point B. In one embodiment, the measurement for the first cluster and the second cluster is applicable for temporal, frequency domain and any combinations of the domains.
[0028] In one embodiment, the measurement of the first cluster cells is L3 cell level measurement results at point C, the measurement of the second cluster cells can be L3 cell level results at point C. In one embodiment, the measurement for the first cluster and the second cluster is applicable for temporal, frequency domain and any combinations of the domains.
[0029] Figure 6 illustrates an exemplary diagram for the prediction domain of cluster-based model. As shown in sub-figure (a) , in one embodiment, the measurement radio resource of first cluster and the second cluster are same in frequency and spatial domain, and UE performs measurement prediction at temporal domain, using historical measurement results [t0-N, t0] as model input and future measurement results [t1, t1+M] as label. In one embodiment, the t0 equals to t1. In another embodiment, the t0 less than t1.
[0030] As shown in sub-figure (b) , in one embodiment, the measurement radio resource of first cluster and the second cluster are same in frequency and temporal domain, and UE performs measurement prediction at spatial domain, using measurement results of partial beams of first cluster as model input and full / the other part of beam results of the second cluster as label.
[0031] As shown in sub-figure (c) , in one embodiment, the measurement radio resource of first cluster and the second cluster are same in spatial and temporal domain, and UE performs measurement prediction at frequency domain, using measurement results of first cluster with frequency 1 as model input and the second cluster with frequency 2 as label.
[0032] The prediction domain of the first cluster and the second cluster is any combinations of the temporal, spatial and frequency domain domains. In one embodiment, the measurement radio resource of first cluster and the second cluster are same in spatial domain, and UE performs measurement prediction at temporal and frequency domain with combination of sub-figure (a) and sub-figure (c) . In one embodiment, the measurement radio resource of first cluster and the second cluster are same in temporal domain, and UE performs measurement prediction at spatial and frequency domain with combination of sub-figure (b) and sub-figure (c) . In one embodiment, the measurement radio resource of first cluster and the second cluster are same in frequency domain, and UE performs measurement prediction at temporal and spatial domain with combination of sub-figure (a) and sub-figure (b) . In another embodiment, the measurement radio resource of first cluster and the second cluster are same in temporal, spatial and frequency domain, and UE performs measurement prediction at temporal, spatial and frequency domain with combination of sub-figure (a) , sub-figure (b) and sub-figure (c) .
[0033] Figure 7 illustrate an exemplary overall flow for cluster based RRM prediction measurement procedure in accordance with embodiments of the current invention. In one embodiment, UE performs model update (transfer / switching) autonomously. In one embodiment, UE decides to perform model update based on cluster update. In another embodiment, UE performs model update (transfer / switching) based on RAN / network indication. In one embodiment, UE pre-downloads models applicable for cluster / cell and performs model update by model switching. In another embodiment, UE does not pre-downloads models applicable for cluster / cell and performs model update by model (parameters) transfer. In one embodiment, for the temporal domain beam-quality prediction, the UE performs full beams sweeping at observation time window and stop beam sweeping at prediction time window. In one embodiment, for the spatial domain beam-quality prediction, the UE performs partial beam sweeping. In one embodiment, for the temporal-spatial domain beam-quality prediction, the UE performs partial beams sweeping at observation time window. In one embodiment, the UE evaluates the reporting criteria considers the measurement results which are actually measured, the measurement results which are predicted, or both of them are used, and which approach to use is configured by the network. In one embodiment, the UE reports the measurement results which are actually measured, the measurement results which are predicted, or both of them, and which approach to use is configured by the network. In one embodiment, the one or multiple AI / ML models is cell specific, i.e., one AI / ML model corresponds to one cell. In one embodiment, the one or multiple AI / ML models is cluster specific, i.e., one AI / ML model corresponds to a cluster of cells. In one embodiment, the measured RS quality can be SINR / RSRP / RSRQ.
[0034] It is understood that the specific order or hierarchy of blocks in the processes / flowcharts disclosed is an illustration of exemplary approaches. Based upon design preferences, it is understood that the specific order or hierarchy of blocks in the processes / flowcharts may be rearranged. Further, some blocks may be combined or omitted. The accompanying method claims present elements of the various blocks in a sample order, and are not meant to be limited to the specific order or hierarchy presented.
[0035] The previous description is provided to enable any person skilled in the art to practice the various aspects described herein. Various modifications to these aspects will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other aspects. Thus, the claims are not intended to be limited to the aspects shown herein but is to be accorded the full scope consistent with the language claims, wherein reference to an element in the singular is not intended to mean “one and only one” unless specifically so stated, but rather “one or more. ” The word “exemplary” is used herein to mean “serving as an example, instance, or illustration. ” Any aspect described herein as “exemplary” is not necessarily to be construed as preferred or advantageous over other aspects. Unless specifically stated otherwise, the term “some” refers to one or more. Combinations such as “at least one of A, B, or C, ” “one or more of A, B, or C, ” “at least one of A, B, and C, ” “one or more of A, B, and C, ” and “A, B, C, or any combination thereof” include any combination of A, B, and / or C, and may include multiples of A, multiples of B, or multiples of C. Specifically, combinations such as “at least one of A, B, or C, ” “one or more of A, B, or C, ” “at least one of A, B, and C, ” “one or more of A, B, and C, ” and “A, B, C, or any combination thereof” may be A only, B only, C only, A and B, A and C, B and C, or A and B and C, where any such combinations may contain one or more member or members of A, B, or C. All structural and functional equivalents to the elements of the various aspects described throughout this disclosure that are known or later come to be known to those of ordinary skill in the art are expressly incorporated herein by reference and are intended to be encompassed by the claims. Moreover, nothing disclosed herein is intended to be dedicated to the public regardless of whether such disclosure is explicitly recited in the claims. The words “module, ” “mechanism, ” “element, ” “device, ” and the like may not be a substitute for the word “means. ” As such, no claim element is to be construed as a means plus function unless the element is expressly recited using the phrase “means for. ”
[0036] While aspects of the present disclosure have been described in conjunction with the specific embodiments thereof that are proposed as examples, alternatives, modifications, and variations to the examples may be made. Accordingly, embodiments as set forth herein are intended to be illustrative and not limiting. There are changes that may be made without departing from the scope of the claims set forth below.
Claims
1.A method for UE to perform cluster based RRM prediction for wireless communication system, comprising the steps of:Performing measurement on a first cluster including set of cells, wherein the radio resources of the first cluster are defined by spatial, temporal, frequency domain and any combinations of the domains and the first cluster of the cells can be the serving cells and the neighboring cells of intra-frequency or inter-frequency;Predicting the measurement results on a second cluster including set of cells, wherein radio resources of the second cluster are defined by spatial, temporal, frequency domain and any combinations of the domains and the second set of the cells can be the serving cells and the neighboring cells of intra-frequency or inter-frequency, which can be same or different from the first cluster of cells set;Deriving the cell quality of the first set, the second set of cells or both of them;Evaluating the reporting criteria to trigger the measurement report and sending the measurement report to the network.2.The method of claim 1, further comprising grouping the cluster based on specific characteristic, wherein the characteristic can be signal measurements, geographical information, RAN configuration, etc.3.The method of claim 2, wherein the first cluster is same with the second cluster of cells.4.The method of claim 2, wherein the first cluster is the subset of the second cluster of cells.5.The method of claim 2, wherein the first cluster is a partial intersection set with the second cluster of cells.6.The method of claim 2, wherein the number of cells in cluster can be one or multiple cells.7.The method of claim 1, further comprising UE to collect the measurement of first cluster cells as model input and second cluster cells as label at training stage with / without other assistance information, wherein the measurement can be beam level results or cell level results.8.The method of claim 7, wherein the measurement of the first cluster cells is L1 beam level measurement results (without / after L1 filtering) , the measurement of the second cluster cells can be L1 beam level measurement, L1 cell level results, L3 beam level results or L3 cell level results.9.The method of claim 7, wherein the measurement of the first cluster cells is L3 beam level measurement results, the measurement of the second cluster cells can be L3 beam level results or L3 cell level results.10.The method of claim 7, wherein the measurement of the first cluster cells is L1 cell level measurement results, the measurement of the second cluster cells can be L1 cell level results or L3 cell level results.11.The method of claim 7, wherein the measurement of the first cluster cells is L3 cell level measurement results, the measurement of the second cluster cells can be L3 cell level results.12.The method of claim 1, wherein the prediction from the first cluster to the second of cluster is applicable for spatial, temporal, frequency domain and any combinations of the domains.13.The method of claim 1, wherein evaluating the reporting criteria considers the measurement results which are actually measured, the measurement results which are predicted, or both of them are used, and which approach to use is configured by the network.14.The method of claim 1, wherein measurement reporting reports the measurement results which are actually measured, the measurement results which are predicted, or both of them, and which approach to use is configured by the network.15.The method of claim 1, wherein the data format of measurement for training stage and inference stage can including cell ID, beam ID, beam quantity or cell quantity.16.The method of claim 1, wherein the measured RS quality can be SINR / RSRP / RSRQ.
Citation Information
Patent Citations
Mobility enhancements for conditional switching
CN117917126A
Techniques for cross-band channel prediction and reporting
US20210409133A1
Ai / ML model functionality in handover scenarios
US20240172080A1
Mobility reporting for non-serving cells based on machine learning
WO2023137684A1