Network-side node, user equipment ADN methods performed by the same and storage medium

Abstract

The embodiments of the present disclosure provide a network-side node, a user equipment and methods performed by the same and a storage medium, which involves the field of artificial intelligence. The method includes: receiving a sub-band sounding reference signal (SRS) from a first UE, wherein the sub-band SRS is an SRS transmitted by the first UE using a sub-band in a full-band; obtaining a full-band frequency selective fading (FSF) trend corresponding to the first UE; determining a full-band SRS channel of the first UE based on the full-band FSF trend and the sub-band SRS; performing uplink / downlink multi-antenna system scheduling based on the full-band SRS channel. Alternatively, the above method executed by electronic apparatus may be executed by using artificial intelligence models.

Description

NETWORK-SIDE NODE, USER EQUIPMENT ADN METHODS PERFORMED BY THE SAME AND STORAGE MEDIUM

[0001] The present disclosure relates to a communication field, and specifically to a method performed by a network-side node, a network-side node, a method performed by a user equipment (UE), a UE, a computer-readable storage medium and a computer program product.

[0002] In a wireless communication field, uplink / downlink multi-antenna system scheduling is particularly important for improving throughput and system performance of a UE. For example, the uplink / downlink multi-antenna system scheduling may be performed based on a sounding reference signal (SRS). But, SRS resources are limited, and as the number of UEs increases, only a portion of UEs may be allocated SRS resources, and other UEs that are not allocated SRS resources must adopt other uplink / downlink multi-antenna system scheduling methods. However, the use of other scheduling methods may lead to decrease in UE throughput and system performance may decrease as the number of UEs increases. In view of this, there is a need for techniques that can better improve the UE throughput and, in turn, the system performance.

[0003] According to a first aspect of embodiments of the present disclosure, there is provided a method performed by a method performed by a network-side node, the method includes: receiving a sub-band SRS from a first UE, wherein the sub-band SRS is an SRS transmitted by the first UE using a sub-band in a full-band; obtaining a full-band frequency selective fading (FSF) trend corresponding to the first UE; determining a full-band SRS channel of the first UE based on the full-band FSF trend and the sub-band SRS; performing uplink / downlink multi-antenna system scheduling based on the full-band SRS channel.

[0004] Alternatively, the full-band FSF trend is obtained based on demodulation reference signal (DMRS) information of a plurality of UEs in a zone to which the first UE belongs, wherein a distance among the plurality of UEs in the zone is less than a first threshold value.

[0005] Alternatively, the obtaining of the full-band FSF trend corresponding to the first UE includes: receiving, from another network-side node, the full-band FSF trend obtained by the other network-side node based on the DMRS information; or obtaining the full-band FSF trend based on the DMRS information.

[0006] Alternatively, the obtaining of the full-band FSF trend based on the DMRS information includes: obtaining FSF for each DMRS of the plurality of UEs in the zone to which the first UE belongs; obtaining the full-band FSF trend based on the obtained FSF.

[0007] Alternatively, the obtaining of the FSF for each DMRS of the plurality of UEs in the zone to which the first UE belongs includes: obtaining resource block (RB)-level FSF for each DMRS, wherein the RB-level FSF is FSF on respective RBs occupied by each DMRS in the frequency domain, wherein the obtaining of the full-band FSF trend based on the obtained FSF includes: obtaining the full-band FSF trend by combining the RB-level FSF for each DMRS in the zone to which the first UE belongs.

[0008] Alternatively, the obtaining of the RB-level FSF for each DMRS includes: obtaining resource element (RE)-level FSF among different RBs, wherein the RE-level FSF includes magnitude difference and phase difference of each DMRS over corresponding REs of different RBs; obtaining the RB-level FSF based on the RE-level FSF, wherein the RB-level FSF includes magnitude difference and phase difference of each DMRS over different RBs.

[0009] Alternatively, the obtaining of the full-band FSF trend by combining the RB-level FSF for each DMRS in the zone to which the first UE belongs includes; selecting the RB-level FSF of a DMRS in the zone to which the first UE belongs that satisfies a predetermined condition as an initial full-band FSF trend; updating the full-band FSF trend by combining the initial full-band FSF trend with the RB-level FSF of DMRSs in the zone other than the selected DMRS until a predetermined update end condition is satisfied.

[0010] Alternatively, the determining of the full-band SRS channel of the first UE based on the full-band FSF trend and the sub-band SRS includes: predicting a full-band FSF fluctuation of the first UE based on the full-band FSF trend and the sub-band SRS; determining the full-band SRS channel of the first UE based on the full-band FSF fluctuation and the full-band FSF trend.

[0011] Alternatively, the predicting of the full-band FSF fluctuation of the first UE based on the full-band FSF trend and the sub-band SRS includes: extracting a feature of FSF of the sub-band SRS and a feature of the full-band FSF trend using a first artificial intelligence (AI) network; predicting the full-band FSF fluctuation using a second AI network based on the extracted features.

[0012] Alternatively, the extracting of the feature of the FSF of the sub-band SRS and the feature of the full-band FSF trend using the first AI network includes: determining the FSF of the sub-band SRS and extracting the feature of the FSF of the sub-band SRS based on the FSF of the sub-band SRS using a first sub-network in the first AI network; extracting the feature of the full-band FSF trend using a second sub-network in the first AI network.

[0013] Alternatively, the predicting of the full-band FSF fluctuation using the second AI network based on the extracted features includes: obtaining a sub-band FSF fluctuation feature based on the extracted features; obtaining a first full-band FSF fluctuation and a second full-band FSF fluctuation based on the sub-band FSF fluctuation feature using a first prediction network and a second prediction network in the second AI network, respectively, wherein the first prediction network is used for predicting a frequency fluctuation in a first direction and the second prediction network is used for predicting a frequency fluctuation in a second direction; obtaining the full-band FSF fluctuation based on the first full-band FSF fluctuation and the second full-band FSF fluctuation.

[0014] Alternatively, the determining of the full-band SRS channel of the first UE based on the full-band FSF fluctuation and the full-band FSF trend includes: determining similarity between the full-band FSF fluctuation and the full-band FSF trend based on a feature of FSF of the sub-band SRS and a feature of the full-band FSF trend using a third AI network; obtaining the full-band SRS channel by fusing, based on the similarity, the full-band FSF fluctuation and the full-band FSF trend using a fourth AI network.

[0015] Alternatively, the method further includes: dividing UEs under the samethe same cell into zones based on information reported by the UEs under the same cell, wherein a distance among UEs in the same zone is less than the first threshold value; determining the zone to which the first UE belongs.

[0016] Alternatively, the dividing of the UEs under the same cell into the zones based on the information reported by the UEs under the same cell includes: calculating a regional similarity between the respective UEs under the same cell based on the information, wherein the regional similarity indicates a positional relationship between the UEs; dividing the respective UEs under the same cell into corresponding zones based on the regional similarity, wherein the information includes information related to at least one of: a UE position, a reference signal received power (RSRP), a signal to interference plus noise ratio (SINR) and a precoding matrix indication (PMI).

[0017] Alternatively, the uplink / downlink multi-antenna system scheduling includes: at least one of beamforming, cooperative multipoint transmission, and multi-user pairing for downlink; and / or at least one of beamforming, cooperative multipoint transmission, multi-user pairing, power control, localization, and resource allocation for uplink.

[0018] Alternatively, the method further includes: transmitting SRS configuration information to the first UE, wherein the SRS configuration information is used to configure the first UE to transmit the sub-band SRS to the network-side node using a set single sub-band in the full-band during each SRS period of a plurality of SRS periods, wherein the receiving of the sub-band SRS from the first UE includes: receiving, from the first UE, the sub-band SRS transmitted based on the SRS configuration information.

[0019] Alternatively, the method further includes: obtaining a time selective fading (TSF) trend corresponding to the first UE; predicting a real-time SRS channel of the first UE based on the TSF trend and historical SRS information of the first UE, wherein the historical SRS information includes information about the sub-band SRS; wherein the performing of the uplink / downlink multi-antenna system scheduling based on the full-band SRS channel includes: performing the uplink / downlink multi-antenna system scheduling based on the full-band SRS channel and the real-time SRS channel.

[0020] Alternatively, the TSF trend is obtained based on DMRS information of a plurality of UEs within a cluster to which the first UE belongs in a zone to which the first UE belongs, wherein a distance among the plurality of UEs within the cluster is less than the first threshold value, and difference among moving speeds of the plurality of UEs is less than a second threshold value and / or difference among moving directions of the plurality of the UEs is less than a third threshold value.

[0021] Alternatively, the obtaining of the TSF trend corresponding to the first UE includes: receiving, from another network-side node, the TSF trend obtained by the other network-side node based on the DMRS information; or obtaining the TSF trend based on the DMRS information.

[0022] Alternatively, the method further includes: collecting DMRS information of the plurality of UEs within the cluster to which the first UE belongs, wherein each UE in the plurality of UEs within the cluster to which the first UE belongs has at least two DMRSs at the same RB position during at least two consecutive SRS periods, wherein, the obtaining of the TSF trend based on the DMRS information includes: calculating, for each UE in the cluster, a DMRS difference at the same RB position in different slots of the SRS periods based on magnitudes and phases of the DMRSs at the same RB position in the different slots; obtaining the TSF trend based on the DMRS difference.

[0023] Alternatively, the predicting of the real-time SRS channel based on the TSF trend and the historical SRS information of the first UE includes: predicting a channel fluctuation due to a change in a moving speed and / or a moving direction of the first UE based on the TSF trend and the historical SRS information; predicting the real-time SRS channel based on the predicted channel fluctuation and the TSF trend.

[0024] Alternatively, the predicting of the channel fluctuation due to the moving trajectory of the first UE based on the TSF trend and the historical SRS information includes: extracting SRS features based on the historical SRS information using a fifth AI network and obtaining SRS features with different weights by a self-attention network; extracting a TSF feature based on the TSF trend using a sixth AI network; predicting, based on the SRS features with different weights and the TSF feature, the channel fluctuation using a seventh AI network, wherein the predicting the real-time SRS channel based on the predicted channel fluctuation and the TSF trend includes: predicting the real-time SRS channel using an eighth AI network based on the channel fluctuation and the TSF feature.

[0025] Alternatively, the method further includes: determining a zone to which the first UE belongs; determining a moving speed and / or a moving direction of the first UE based on information related to at least one of RSRP and PMI reported by the first UE; determining a cluster to which the first UE belongs in the zone to which the first UE belongs, based on the moving speed and / or the moving direction.

[0026] According to a second aspect of embodiments of the present disclosure, there is provided a method performed by a network-side node, the method includes: receiving a sub-band SRS from a first UE, wherein the sub-band SRS is an SRS transmitted by the first UE using a sub-band in a full-band; obtaining a TSF trend corresponding to the first UE; predicting a real-time SRS channel for the first UE based on the TSF trend and historical SRS information of the first UE, wherein the historical SRS information includes information about the sub-band SRS; performing uplink / downlink multi-antenna system scheduling based on the predicted real-time SRS channel.

[0027] Alternatively, the TSF trend is obtained based on DMRS information of a plurality of UEs within a cluster to which the first UE belongs in a zone to which the first UE belongs, wherein a distance among the plurality of UEs within the cluster is less than the first threshold value, and difference among moving speeds of the plurality of UEs is less than a second threshold value and / or difference among moving directions of the plurality of the UEs is less than a third threshold value.

[0028] Alternatively, the obtaining of the TSF trend corresponding to the first UE includes: receiving, from another network-side node, the TSF trend obtained by the other network-side node based on the DMRS information; or obtaining the TSF trend based on the DMRS information.

[0029] Alternatively, the method further includes: collecting DMRS information of the plurality of UEs within the cluster to which the first UE belongs, wherein each UE in the plurality of UEs within the cluster to which the first UE belongs has at least two DMRSs at the same RB position during at least two consecutive SRS periods, wherein, the obtaining of the TSF trend based on the DMRS information includes: calculating, for each UE in the cluster, a DMRS difference at the same RB position in different slots of the SRS periods based on magnitudes and phases of the DMRSs at the same RB position in the different slots; obtaining the TSF trend based on the DMRS difference.

[0030] Alternatively, the predicting of the real-time SRS channel based on the TSF trend and the historical SRS information of the first UE includes: predicting a channel fluctuation due to a change in a moving trajectory of the first UE based on the TSF trend and the historical SRS information; predicting the real-time SRS channel based on the predicted channel fluctuation and the TSF trend.

[0031] Alternatively, the predicting of the channel fluctuation due to the change in the moving speed and / or the moving direction of the first UE based on the TSF trend and the historical SRS information includes: extracting SRS features based on the historical SRS information using a fifth AI network and obtaining SRS features with different weights by a self-attention network; extracting a TSF feature based on the TSF trend using a sixth AI network; predicting, based on the SRS features with different weights and the TSF feature, the channel fluctuation using a seventh AI network, wherein the predicting the real-time SRS channel based on the predicted channel fluctuation and the TSF trend includes: predicting the real-time SRS channel using an eighth AI network based on the channel fluctuation and the TSF feature.

[0032] Alternatively, the method further includes: determining a zone to which the first UE belongs; determining a moving speed and / or a moving direction of the first UE based on information related to at least one of RSRP and PMI reported by the first UE; determining a cluster to which the first UE belongs in the zone to which the first UE belongs, based on the moving speed and / or the moving direction.

[0033] Alternatively, the uplink / downlink multi-antenna system scheduling includes: at least one of beamforming, cooperative multipoint transmission, and multi-user pairing for downlink; and / or at least one of beamforming, cooperative multipoint transmission, multi-user pairing, power control, localization, and resource allocation for uplink.

[0034] Alternatively, the method further includes: transmitting SRS configuration information to the first UE, wherein the SRS configuration information is used to configure the first UE to transmit the sub-band SRS to the network-side node using a set single sub-band in the full-band during each SRS period of a plurality of SRS periods, wherein the receiving of the sub-band SRS from the first UE includes: receiving, from the first UE, the sub-band SRS transmitted based on the SRS configuration information.

[0035] According to a third aspect of embodiments of the present disclosure, there is provided a method performed by a network-side node, the method includes: transmitting SRS configuration information to a first UE, wherein the SRS configuration information is used to configure the first UE to transmit a sub-band SRS to the network-side node using a set single sub-band in a full-band during each SRS period of a plurality of SRS periods; receiving, from the first UE, the sub-band SRS transmitted based on the SRS configuration information, wherein the sub-band SRS is used to perform uplink / downlink multi-antenna system scheduling.

[0036] According to a fourth aspect of embodiments of the present disclosure, there is provided a method performed by a network-side node, the method includes: obtaining a full-band FSF trend corresponding to a first UE based on DMRS information of a plurality of UEs in a zone to which the first UE belongs, wherein a distance among the plurality of UEs in the zone is less than a first threshold value; transmitting the full-band FSF trend to another network-side node, wherein the full-band FSF trend is used to determine a full-band SRS channel of the first UE, the full-band SRS channel being used to perform uplink / downlink multi-antenna system scheduling.

[0037] Alternatively, the method further includes: dividing UEs under the same cell into zones based on information reported by the UEs under the same cell, wherein a distance among UEs in the same zone is less than the first threshold value; determining the zone to which the first UE belongs.

[0038] Alternatively, the dividing of the UEs under the same cell into the zones based on the information reported by the UEs under the same cell includes: calculating a regional similarity between the respective UEs under the same cell based on the information; dividing the respective UEs under the same cell into corresponding zones based on the regional similarity, wherein the information includes information related to at least one of: a UE position, a RSRP, a signal to SINR and a PMI.

[0039] Alternatively, the method further includes: obtaining a time selective fading (TSF) trend corresponding to the first UE based on DMRS information of a plurality of UEs within a cluster to which the first UE belongs in a zone to which the first UE belongs, wherein a distance among the plurality of UEs within the cluster is less than the first threshold value, and difference among moving speeds of the plurality of UEs is less than a second threshold value and / or difference among moving directions of the plurality of the UEs is less than a third threshold value; transmitting the TSF trend to another network-side node.

[0040] Alternatively, the method further includes: determining a moving speed and / or a moving direction of the first UE based on information related to at least one of RSRP and PMI reported by the first UE; determining a cluster to which the first UE belongs in the zone to which the first UE belongs, based on the moving speed and / or the moving direction.

[0041] According to a fifth aspect of embodiments of the present disclosure, there is provided a method performed by a network-side node, the method includes: obtaining a time selective fading (TSF) trend corresponding to a first UE based on DMRS information of a plurality of UEs within a cluster to which the first UE belongs in a zone to which the first UE belongs, wherein a distance among the plurality of UEs within the cluster is less than a first threshold value and difference among moving speeds of the plurality of UEs is less than a second threshold value and / or difference among moving directions of the plurality of UEs is less than a third threshold value; transmitting the TSF trend to another network-side node, wherein the TSF trend is used to predict a real-time (SRS) channel of the first UE, the real-time SRS channel being used to perform uplink / downlink multi-antenna system scheduling.

[0042] According to a sixth aspect of embodiments of the present disclosure, there is provided a method performed by a UE, the method includes: receiving SRS configuration information from a network-side node, wherein the SRS configuration information is used to configure the first UE to transmit a sub-band SRS to the network-side node using a set single sub-band in a full-band during each SRS period of a plurality of SRS periods; transmitting the sub-band SRS to the network-side node based on the SRS configuration information, wherein the sub-band SRS is used to perform uplink / downlink multi-antenna system scheduling.

[0043] According to a seventh aspect of embodiments of the present disclosure, there is provided a network-side node, the network-side node includes: a transceiver; a processor coupled to the transceiver and configured to perform the method performed by a network-side node as described above.

[0044] According to an eighth aspect of embodiments of the present disclosure, there is provided a UE, the UE includes: a transceiver; a processor coupled to the transceiver and configured to perform the method performed by a UE as described above.

[0045] According to a ninth aspect of embodiments of the present disclosure, there is provided an electronic apparatus, the electronic apparatus includes: at least one processor; at least one transceiver and / or at least one memory coupled to the at least one processor, wherein the at least one processor is configured to perform any of the methods as described above.

[0046] According to a tenth aspect of embodiments of the present disclosure, there is provided a computer-readable storage medium storing　computer programs or instructions that, when executed by at least one processor, cause the at least one processor to perform any of the methods as described above.

[0047] According to an eleventh aspect of embodiments of the present disclosure, there is provided a computer program product including computer programs, the computer programs, when being executed by a processor, implement any of the methods as described above.

[0048] According to the technical solution provided in embodiments of the present disclosure, by obtaining the full-band FSF trend corresponding to the first UE and determining the full-band SRS channel of the first UE based on the full-band FSF trend and the sub-band SRS, the network-side node is enabled to determine the full-band SRS channel even if the first UE transmits an SRS using a sub-band, thus facilitating better performing the up / downlink multi-antenna system scheduling based on the full-band SRS channel, which improves the accuracy of the uplink / downlink multi-antenna system scheduling, thereby improving the throughput of the first UE, and, in turn, improving the system performance.

[0049] According to the technical solution provided in embodiments of the present disclosure, by obtaining the TSF trend corresponding to the first UE and predicting the real-time SRS channel of the first UE based on the TSF trend and the historical SRS information of the first UE, it is possible to predict the real-time SRS channel of the first UE in the above method even if the first UE transmits an SRS using a sub-band, thus facilitating better performing the uplink / downlink multi-antenna system scheduling based on the predicted real-time SRS channel, which improves the accuracy of the uplink / downlink multi-antenna system scheduling, thereby improving the throughput of the UE, and, in turn, improving the system performance.

[0050] According to the technical solution provided in embodiments of the present disclosure, the network-side node transmits, to the first UE, the SRS configuration information for configuring the first UE to transmit the sub-band SRS to the network-side node using the set single sub-band in the full-band during each of the plurality of SRS periods, such that the first UE transmits the sub-band SRS based on the SRS configuration information, which may realize the single sub-band long-period SRS configuration, so that it is possible to support more UEs to obtain SRS resources with limited SRS resources, thus, uplink / downlink multi-antenna system scheduling may be performed more based on the SRS, which minimizes having to use other scheduling methods when SRS resources are insufficient, thereby contributing to improving the throughput of the UE and the system performance.

[0051] According to the technical solution provided in embodiments of the present disclosure, the network-side node obtains the full-band FSF trend corresponding to the first UE based on the DMRS information of the plurality of UEs in the zone to which the first UE belongs and transmits the full-band FSF trend to another network-side node, which may reduce the computational burden of the other network-side node, and enable the other network-side node to determine, based on the received full-band FSF trend, the full-band SRS channel of the first UE to perform the uplink / downlink multi-antenna system scheduling based on the full-band SRS channel, thereby improving the accuracy of the uplink / downlink multi-antenna system scheduling, and thus improving the throughput of the UE and improving the system performance.

[0052] According to the technical solution provided in embodiments of the present disclosure, the network-side node obtains the TSF trend based on the DMRS information of the plurality of UEs in the cluster to which the first UE belongs in the zone to which the first UE belongs and transmits the TSF trend to another network-side node, which may reduce the computational burden of the other network-side node, and enable the other network-side node to predict a real-time SRS channel based on the received TSF trend to perform the uplink / downlink multi-antenna system scheduling based on the predicted real-time SRS channel, thereby improving the accuracy of the uplink / downlink multi-antenna system scheduling, and thus improving the throughput of the UE and improving the system performance.

[0053] According to the technical solution provided in embodiments of the present disclosure, the UE receives, from the network-side node, the SRS configuration information for configuring the first UE to transmit the sub-band SRS to the network-side node using the set single sub-band in the full-band in each of the plurality of SRS periods and transmits the sub-band SRS to the network-side node based on the SRS configuration information, which makes it possible to support, with limited SRS resources, more UEs obtaining SRS resources, thereby allowing uplink / downlink multi-antenna system scheduling to be performed more based on the SRS, minimizing having to performing uplink / downlink multi-antenna system scheduling by using other scheduling methods when SRS resources are insufficient, and thus contributing to the improvement of the throughput of the UE and the system performance.

[0054] It should be understood that the above general description and the detailed descriptions that follow are merely exemplary and explanatory and do not limit the present disclosure.

[0055] The accompanying drawings herein are incorporated into and form part of the specification, illustrate embodiments consistent with the disclosure, which are used in conjunction with the specification to explain the principles of the disclosure and do not constitute an undue limitation of the disclosure.

[0056] FIG. 1 illustrates a schematic diagram of a beamforming method.

[0057] FIG. 2 is a schematic diagram illustrating SRS resource management.

[0058] FIG. 3 is a flowchart illustrating a method performed by a network-side node according to a first embodiment of the present disclosure.

[0059] FIG. 4 illustrates a schematic diagram of an SRS configuration method according to embodiments of the present disclosure.

[0060] FIG. 5 is a flowchart illustrating a method performed by a network-side node according to a second embodiment of the present disclosure.

[0061] FIG. 6 is a schematic diagram illustrating a DMRS and a SRS with similar FSF trends.

[0062] FIG. 7 is a schematic diagram illustrating obtaining a full-band DMRS by combining DMRSs of multiple UEs.

[0063] FIG. 8 is a schematic diagram illustrating a trend of FSF through a set of UEs.

[0064] FIG. 9 is a schematic diagram illustrating an existence of different fluctuations in FSF for different UEs.

[0065] FIG. 10 illustrates a schematic diagram of a zone division according to embodiments of the present disclosure.

[0066] FIG. 11 is a schematic diagram illustrating calculation of a RE-level FSF according to embodiments of the present disclosure.

[0067] FIGS. 12 to 15 are schematic diagrams illustrating calculation of a full-band FSF trend.

[0068] FIG. 16 illustrates a schematic diagram of determining a full-band SRS channel using an AI model.

[0069] FIG. 17 is a flowchart illustrating a method performed by a network-side node according to a third embodiment of the present disclosure.

[0070] FIG. 18 illustrates a schematic diagram of TSF changes with different moving speeds.

[0071] FIG. 19 is a schematic diagram illustrating a division of clusters.

[0072] FIG. 20 is a schematic diagram illustrating DMRS positions of different UEs within a cluster during different SRS periods.

[0073] FIG. 21 illustrates a schematic diagram for calculating a DMRS difference at the same RB position in different slots of an SRS period.

[0074] FIG. 22 is a schematic diagram illustrating a TSF trend.

[0075] FIG. 23 illustrates a schematic diagram for predicting a real-time SRS channel using an AI model.

[0076] FIG. 24 is a flowchart illustrating a method performed by a network-side node according to a fourth embodiment of the present disclosure.

[0077] FIG. 25 is a flowchart illustrating a method performed by a network-side node according to a fifth embodiment of the present disclosure.

[0078] FIG. 26 is a flowchart illustrating a method performed by a UE according to a sixth embodiment of the present disclosure.

[0079] FIG. 27 is a schematic diagram illustrating an exemplary timing of operations according to embodiments of the present disclosure.

[0080] FIG. 28 is a diagram illustrating an exemplary deployment architecture according to embodiments of the present disclosure.

[0081] FIG. 29 is a block diagram illustrating a network-side node according to embodiments of the present disclosure.

[0082] FIG. 30 is a block diagram illustrating a UE according to embodiments of the present disclosure.

[0083] FIG. 31 illustrates a schematic diagram of a structure of an electronic apparatus according to embodiments of the present disclosure.

[0084] The following description with reference to the accompanying drawings is provided to aid in a thorough understanding of various embodiments of the present disclosure as defined by claims and equivalents thereof. This description includes various specific details to aid in understanding but should only be considered exemplary. Accordingly, those ordinary skills in the art will recognize that various changes and modifications may be made to the various embodiments described herein without departing from the scope and spirit of the present disclosure. In addition, descriptions of well-known features and structures may be omitted for the sake of clarity and brevity.

[0085] The terms and phrases used in the claims and the following description are not limited to dictionary meaning thereof, but are used only by the inventor to enable a clear and consistent understanding of the present disclosure. Accordingly, it should be apparent to those skilled in the art that, the following description of the various embodiments of the present disclosure is provided for an illustrative purpose only and is not intended to a purpose of limiting the present disclosure as defined by the appended claims and equivalents thereof.

[0086] It should be understood that, "a", "an" and "the" in a singular form may also include a plural reference, unless the context clearly indicates otherwise. Thus, for example, a reference to a "part surface" includes a reference to one or more such surfaces. When it refers to one element as being "connected" or "coupled" to another element, the one element may be directly connected or coupled to the other element, or it may refer to a connection relationship between the one element and the other element established through an intermediate element. In addition, "connected" or "coupled" as used herein may include wirelessly connected or wirelessly coupled.

[0087] The term "include" or "may include" refers to the presence of a function, operation, or component of the corresponding disclosure that may be used in the various embodiments of the present disclosure, and does not limit the presence of one or more additional functions, operations, or features. In addition, the terms "include" or "have" may be interpreted to denote certain features, figures, steps, operations, constituent elements, components, or combinations thereof, but should not be interpreted to exclude the possibility of the presence of one or more other features, figures, steps, operations, constituent elements, components, or combinations thereof.

[0088] The term "or" as used in the various embodiments of the present disclosure includes any of the listed terms and all combinations thereof. For example, "A or B" may include A, may include B, or may include both A and B. When describing a plurality of (two or more) items, the plurality of items may refer to one, more, or all of the plurality of items if a relationship among the plurality of items is not explicitly defined. For example, for the description "a parameter A comprises A1, A2, A3", it may be implemented as parameter A comprising A1, A2 or A3, or as parameter A comprising at least two of the three items of the parameter A1, A2, A3.

[0089] All terms (including technical or scientific terms) used in the present disclosure have the same meaning as understood by those skilled in the art to which the present disclosure belongs, unless defined differently. Common terms as defined in dictionaries are interpreted to have a meaning consistent with the context in the relevant technology art and should not be interpreted in an idealized or overly formalistic manner, unless expressly so defined in the present disclosure.

[0090] At least part of the functions in a device or electronic apparatus provided in the embodiments of the present disclosure may be implemented through an AI model, such as, at least one of a plurality of modules of the device or electronic apparatus may be implemented through the AI model. A function associated with AI may be performed through the non-volatile memory, the volatile memory, and the processor.

[0091] The processor may include one or more processors. At this time, the one or more processors may be a general purpose processor, such as a central processing unit (CPU), an application processor (AP), or the like, or may be a graphics-only processing unit such as a graphics processing unit (GPU), a visual processing unit (VPU), and / or an AI-dedicated processor such as a neural processing unit (NPU).

[0092] The one or more processors control processing of input data in accordance with a predefined operating rule or artificial intelligence (AI) model stored in the non-volatile memory and the volatile memory. The predefined operating rule or artificial intelligence model is provided through training or learning.

[0093] Here, being provided through learning means that, by applying a learning algorithm to a plurality of learning data, a predefined operating rule or an AI model of a desired characteristic is made. The learning may be performed in a device or electronic apparatus itself in which AI according to embodiments is performed, and / or may be implemented through a separate server / system.

[0094] The AI model may consist of a plurality of neural network layers. Each layer has a plurality of weight values, and performs a neural network calculation by calculating between the input data of this layer (such as, a calculation result of the previous layer and / or the input data of the AI model) and the plurality of weight values of the current layer. Examples of neural networks include, but are not limited to, a convolutional neural network (CNN), a deep neural network (DNN), a recurrent neural network (RNN), a restricted Boltzmann Machine (RBM), a deep belief network (DBN), a bidirectional recurrent deep neural network (BRDNN), a generative adversarial networks (GAN), and a deep Q-network.

[0095] The learning algorithm is a method for training a predetermined target device (for example, a robot) using a plurality of learning data to cause, allow, or control the target device to make a determination or prediction. Examples of the learning algorithm include, but are not limited to, supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning.

[0096] According to the present disclosure, at least one step of a method performed in an electronic apparatus may be implemented using an artificial intelligence model. A processor of the electronic apparatus may perform pre-processing operations on data to convert it into a form suitable for use as an input to the artificial intelligence model. The artificial intelligence model may be obtained by training. Here, "obtained by training" means that a predefined operation rule or artificial intelligence model configured to perform a desired feature (or purpose) is obtained by training a basic artificial intelligence model with multiple pieces of training data by a training algorithm.

[0097] Below, the technical solutions of the embodiments of the disclosure and the technical effects produced by the technical solutions of the disclosure will be explained by describing several optional embodiments. It should be noted that, the following embodiments may be referred to, imitated or combined with each other, and the same term, similar features and similar implementation steps in different embodiments will not be described repeatedly.

[0098] As described in the background art, the uplink / downlink multi-antenna system scheduling may be performed based on the SRS. However, SRS resources are limited, and as the number of UEs increases, only a portion of UEs may be allocated SRS resources, and other UEs that are not allocated SRS resources must use other scheduling methods, which leads to decrease in UE throughput and, in turn, degradation in system performance. For example, the uplink / downlink multi-antenna system scheduling may include at least one of beamforming, cooperative multipoint transmission, and multi-user pairing for downlink; and / or, at least one of beamforming, cooperative multipoint transmission, multi-user pairing, power control, localization, and resource allocation for uplink. Below, for descriptive convenience, this problem is illustrated by taking the uplink / downlink multi-antenna system scheduling being the beamforming as an example to, however, the various embodiments that will be described herein are not limited to being used only for the beamforming, but may be used for all uplink / downlink multi-antenna system scheduling.

[0099] For example, beamforming may be realized in two ways. FIG. 1 illustrates a schematic diagram of the beamforming. As shown in FIG. 1, one beamforming approach is an SRS-based beamforming approach, in which the UE transmits an SRS to a network-side node and the network-side node performs the beamforming based on the received SRS. Another approach is a PMI-based beamforming approach, in which the UE transmits a PMI to the network-side node and the network-side node performs the beamforming based on the received PMI. Typically, the PMI-based beamforming is applicable to a few UEs, e.g., high-speed mobile UEs, while the SRS-based beamforming is applicable to most UEs, e.g., low and medium-speed UEs, and low-speed MU-MIMO UEs. However, the SRS resources are limited, and SRS resource management is required. FIG. 2 is a schematic diagram illustrating the SRS resource management. As shown in FIG. 2, a judgment of SRS resources is first performed before performing the beamforming, and if the SRS resources are sufficient, the SRS-based beamforming is prioritized to be performed, otherwise the PMI-based beamforming is performed. As the number of UEs increases, only a part of UEs may be assigned SRS resources, and other UEs that are not assigned SRS resources have to adopt the PMI-based beamforming. However, the adoption of the PMI-based beamforming leads to the loss of accuracy of beamforming weights, which results in decrease in UE throughput and decrease in cell throughput, and thus the system performance may decrease as the number of UEs increases. For example, the decrease of the UE throughput will affect the user's experience of high throughput demand services, such as AR / VR, HD video, V2X, etc., especially at the cell edge. For example, without sufficient SRS resources, the number of UEs based on SRS resources is limited, so that the probability for SRS-based MU- MIMO is low, so average cell throughput will be significantly reduced. The decrease in the UE throughput or the decrease in the cell throughput ultimately leads to the degradation of the system performance. Therefore, techniques for increasing the UE throughput to improve the system performance are needed.

[0100] However, a basic scheme of current SRS configuration is full-band configuration. Due to the limited number of SRS resources, only a small number of UEs may be supported using this scheme, which causes that other UEs cannot obtain SRS resources, resulting in the following problems:

[0101] Problem 1: With limited SRS resources, the number of supported UEs is insufficient, resulting in lower performance. For example, for UEs without SRS resources under Single-user Multiple-Input Multiple-Output (SU-MIMO), only the PMI-based beamforming may be used, and the throughput and performance of the PMI-based beamforming will significantly decrease compared to the SRS-based beamforming. For MU-MIMO, the probability of SRS-based MU-MIMO is small, and thus the average cell throughput will be significantly reduced.

[0102] Problem 2: Beamforming (e.g., calculation of the beamforming weight) depends on partial information of the channel, resulting in low system performance. For example, when sparse sub-band hopping is used, the channel information of the whole band cannot be obtained, and the beamforming weight is calculated based on only the partial information of the channel to perform beamforming, which leads to performance degradation.

[0103] Problem 3: Beamforming cannot match channel changing, resulting in performance degradation. Since there are N sub-band hopping, the real period for full-band SRS is N×P(P is the SRS period). Beamforming (e.g., the beamforming weight) based on so long period SRS channel cannot match the change of the channel, leading to a significant degradation in the system performance.

[0104] It should be noted that although problems 1, 2, and 3 are described above by taking the beamforming as an example, the above problems also exist in other uplink / downlink multi-antenna system scheduling. In this regard, the present disclosure proposes various technical solutions to ultimately solve the problem of degradation in the system performance by solving one of the above problems.

[0105] FIG. 3 is a flowchart illustrating a method performed by a network-side node according to a first embodiment of the present disclosure.

[0106] As shown in FIG. 3, at step S310, SRS configuration information is transmitted to a first UE, wherein the SRS configuration information is used to configure the first UE to transmit a sub-band SRS to the network-side node using a set single sub-band in a full-band during each SRS period of a plurality of SRS periods. The transmitting of the sub-band SRS to the network-side node using the set single sub-band in the full-band during each SRS period of the plurality of SRS periods may be transmitting the sub-band SRS to the network-side node using the same single sub-band during each SRS period, i.e., the sub-band used for transmitting the SRS in each SRS period is the same. At step S320, the sub-band SRS transmitted based on the SRS configuration information is received from the first UE, wherein the sub-band SRS may be used to perform uplink / downlink multi-antenna system scheduling.

[0107] FIG. 4 illustrates a schematic diagram of an SRS configuration method according to embodiments of the present disclosure.

[0108] As shown in FIG. 4, in order to support more UEs with limited SRS resources, the present disclosure proposes a single sub-band long-period SRS configuration method. As shown in FIG. 4, in the single sub-band long-period SRS configuration method, the UE may be configured by SRS configuration information to transmit a sub-band SRS to a network-side node using a set single sub-band in a full-band during each of a plurality of SRS periods.

[0109] According to a first embodiment of the present disclosure, the network-side node transmits, to the first UE, the SRS configuration information for configuring the first UE to transmit the sub-band SRS to the network-side node using the set single sub-band in the full-band during each of the plurality of SRS periods, such that the first UE transmits the sub-band SRS based on the SRS configuration information, which may realize the single sub-band long-period SRS configuration, so that it is possible to support more UEs to obtain SRS resources with limited SRS resources, thus, uplink / downlink multi-antenna system scheduling (e.g., beamforming) may be performed more based on the SRS, which minimizes having to use other scheduling methods (e.g., having to use the PMI-based beamforming) when SRS resources are insufficient, and thus solves the above mentioned problem 1, thereby contributing to improve the system performance.

[0110] However, although the SRS configuration proposed in the present disclosure may support more UEs to obtain SRS resources, which reduces the degradation of the system performance, it may also still be challenged with problems 2 and 3 mentioned above.

[0111] FIG. 5 is a flowchart illustrating a method performed by a network-side node according to a second embodiment of the present disclosure.

[0112] Referring to FIG. 5, at step S510, a sub-band SRS is received from a first UE, wherein the sub-band SRS is an SRS transmitted by the first UE using a sub-band in a full-band. According to embodiments, the sub-band SRS may be either an SRS transmitted by the first UE based on the SRS configuration method proposed in the present disclosure using a set single sub-band ( the same single sub-band) in the full-band, or an SRS transmitted by the first UE based on a different sub-band in the full-band, for example, an SRS transmitted using a sparse hopping sub-band based on SRS configuration mode of scheme 2.

[0113] At step S520, a full-band FSF trend corresponding to the first UE is obtained. According to embodiments, the full-band FSF trend is obtained based on DMRS information of a plurality of UEs in a zone to which the first UE belongs, wherein a distance among the plurality of UEs in the zone is less than a first threshold value. The distance among the plurality of UEs being less than the first threshold value indicates that the plurality of UEs are in close proximity to each other.

[0114] Since what the network-side node received is the sub-band SRS transmitted by the first UE using the sub-band, however, performing the beamforming based only on the sub-band SRS channel may result in the degradation of the system performance, with respect to this, the present disclosure proposes to obtain the full-band FSF trend based on the DMRS information, and then determine a full-band SRS channel based on the full-band FSF trend and the sub-band SRS. The FSF is a signal difference between different frequencies caused by multipath transmission.

[0115] For a UE, the DMRS is another uplink reference signal in addition to the SRS, and since the DMRS has similar multipath transmission as the SRS, the characteristic of the DMRS FSF is similar to that of the SRS FSF. As shown in FIG. 6, the FSF trends of the DMRS and the SRS are similar, therefore, the full-band FSF trend may be obtained based on the DMRS information, and then the full-band SRS channel may be determined based on the full-band FSF trend and the sub-band SRS. However, the frequency of the DMRS is determined by scheduling, and it cannot be guaranteed that a UE has a full-band DMRS, and the full-band DMRS may be obtained if DMRSs of a set of UEs are combined. For example, as shown in FIG. 7, the full-band DMRS may be obtained by combining DMRSs of a plurality of UEs. When these UEs are in close proximity to each other, they have similar multipath transmissions, and their FSFs are similar, and therefore, as shown in FIG. 8, the full-band FSF trend may be obtained based on DMRSs of a set of UEs. For example, according to embodiments of the present disclosure, the full-band FSF trend may be obtained based on DMRS information of a plurality of UEs in a zone to which the first UE belongs, wherein the distance among the plurality of UEs in the zone is less than the first threshold value.

[0116] After the full-band FSF trend is obtained, the FSFs of different UEs may also fluctuate differently due to minor differences in positions in the set of UEs, as shown in FIG. 9, and the sub-band SRS may provide fluctuation information, thus, at step S530, a full-band SRS channel of the first UE is determined based on the full-band FSF trend and the sub-band SRS. The full-band SRS channel is used for uplink / downlink multi-antenna system scheduling, e.g., for uplink / downlink beamforming, e.g., for calculation of beamforming weights. For example, if the determined full-band SRS channel is accurate, the beam may be more accurately directed to the UE when performing the beamforming, so that the throughput of the UE is maximized. The full-band SRS channel is dependent on the FSF caused by the multipath scenario. The FSF includes a trend and a fluctuation. The trend of the FSF is a common feature and may be determined from all DMRSs of a set of UEs that are in close proximity. The fluctuation of the FSF is a particular feature of each UE and may be determined from the sub-band SRS and the full-band FSF trend of the UE. By determining the full-band SRS channel of the first UE based on the full-band FSF trend and the sub-band SRS, both the FSF trend and the possible FSF fluctuations of different UEs are taken into account, thereby making it possible to determine a more accurate full-band SRS channel.

[0117] After determining the full-band SRS channel, at step S540, uplink / downlink multi-antenna system scheduling may be performed based on the full-band SRS channel. Since a more accurate full-band SRS channel may be determined by the above steps S520 and S530 of the present disclosure, performing the uplink / downlink multi-antenna system scheduling based on such band SRS channel may improve the throughput of the UE, and thus improve the system performance.

[0118] In the following, step S520 and step S530 are described in detail, respectively.

[0119] In the above description of step S520, it is mentioned that the full-band FSF trend is obtained based on the DMRS information of the plurality of UEs in the zone to which the first UE belongs. In the following, a manner of determining the zone to which the first UE belongs is first described. Optionally, according to embodiments, the method shown in FIG. 5 may further include: dividing UEs under the same cell into zones based on information reported by the UEs under the same cell, wherein a distance among UEs in the same zone is less than a first threshold value; and determining the zone to which the first UE belongs.

[0120] According to embodiments, a regional similarity between the respective UEs under the same cell may be calculated based on the information reported by the UEs under the same cell, wherein the regional similarity indicates a positional relationship among the UEs; and based on the regional similarity, the respective UEs under the same cell are divided into corresponding zones. As an example, the information reported by the UEs may include information related to at least one of the following items: a UE position, an RSRP, an SINR, and a PMI.

[0121] According to the embodiment, the position, the moving speed and the moving direction of the UE change over time, and FSFs of UEs with large regional similarity are similar. Performance data such as the position, the RSRP, the SINR, the PMI, etc., of the UEs within a cell may be collected. Based on the position, RSRP, SINR, PMI, the regional similarity between different UEs is calculated, and UEs with high regional similarity are divided into the same zone. For example, if the UE position is accessible, the regional similarity calculation formula may be:

[0122]

[0123] Where S is the regional similarity and x, y are geographic positions of the UEs, such as a latitude and a longitude.

[0124] If the UE position is not accessible, the regional similarity calculation formula may be:

[0125]

[0126]

[0127] If the regional similarity of UEs is higher than a certain threshold value, the UEs are divided into the same zone. An average of the positions, RSRPs, SINRs, PMIs of all UEs in the same zone may be calculated, and this average is used to represent this zone. FIG. 10 illustrates a schematic diagram of a zone division according to embodiments of the present disclosure. As shown in FIG. 10, for example, a cell may be divided into three zones based on the regional similarity, each zone includes a plurality of UEs, and the plurality of UEs in each zone have similar position information, e.g., a distance among the plurality of UEs is less than the first threshold value. According to embodiments, the zone division may be performed periodically, and after the zone division, when a new UE appears, a zone to which the new UE belongs may be determined based on information reported by the UE (e.g., information related to at least one of a position, an RSRP, an SINR, and a PMI of the UE). For example, a regional similarity between the UE and the pre-divided each zone may be calculated in the manner of calculating the regional similarity mentioned above, and the UE is divided into the zone with the highest zone similarity. For example, the zone to which the first UE belongs may be determined based on the information reported by the first UE. For example, in the case where the UE position cannot be obtained, a zone to which a UE corresponding to each DMRS belongs may be determined based on the RSRP, the SINR, or the PMI reported by the UE corresponding to each DMRS in the following manner:

[0128] For example, a zone with the closest distance may be selected as the zone to which the UE corresponding to each DMRS belongs. For each DMRS sample, the Euclidean distance between the UE corresponding to the sample and each zone is calculated:

[0129]

[0130] Wherein x_si is an RSRP, SINR, PMI of the UE corresponding to each sample; and x_zi is a representative RSRP, SINR, PMI of the zone. A zone with the smallest Euclidean distance is selected as the zone to which the UE corresponding to the sample belongs.

[0131] According to embodiments, step S520 may include: receiving, from another network-side node, the full-band FSF trend obtained by the other network-side node based on the DMRS information; or, obtaining the full-band FSF trend based on the DMRS information. That is, the network-side node may either obtain the full-band FSF trend based on the DMRS information by itself or receive, from another network-side node, the full-band FSF trend obtained by the other network-side node based on the DMRS information, which depends on whether or not the network-side node has sufficient computational resources. If the computational resources are sufficient, the network-side node may obtain the full-band FSF trend based on the DMRS information by itself. Otherwise, another network node may obtain the full-band FSF trend based on the DMRS information and then transmit the full-band FSF trend to the network-side node. As an example, the network-side node may be a base station, and the other network-side node may be an RAN Intelligent Controller (RIC), but is not limited to this.

[0132] Hereinafter, a way of obtaining the full-band FSF trend corresponding to the first UE based on the DMRS information is described in connection with examples.

[0133] According to embodiments, the obtaining of the full-band FSF trend corresponding to the first UE based on the DMRS information may include: obtaining FSF for each DMRS of the plurality of UEs in the zone to which the first UE belongs; and obtaining the full-band FSF trend based on the obtained FSF.

[0134] For example, after determining each DMRS of the plurality of UEs in the zone to which the first UE belongs in the manner described above, FSF of each DMRS of the plurality of UEs in the zone to which the first UE belongs may be obtained. The FSF may, for example, be magnitude difference and phase difference at different frequencies. For example, in 4G / 5G systems, a Resource Block (RB) represents a frequency resource, and thus the FSF may be calculated from the magnitude difference and the phase difference on different RBs. According to embodiments, the obtaining of the FSF of each DMRS of the plurality of UEs in the zone to which the first UE belongs may include: obtaining RB-level FSF of each DMRS. According to embodiments, the RB-level FSF is FSF on respective RBs occupied by each DMRS in the frequency domain. As an example, the obtaining of the RB-level FSF of each DMRS may include: obtaining Resource Element (RE)-level FSF between different RBs, wherein the RE-level FSF includes magnitude difference and phase difference of each DMRS over corresponding REs of different RBs; obtaining the RB-level FSF based on the RE-level FSF, wherein the RB-level FSF includes magnitude difference and phase difference of each DMRS over different RBs.

[0135] For example, it is assumed that there are 12 REs at each RB, the magnitude difference and the phase difFference of every 12 REs may be calculated according to the following formula:

[0136]

[0137]

[0138] where n is an RE position of a DMRS on a certain RB.

[0139] FIG. 11 is a schematic diagram illustrating calculation of a RE-level FSF. As shown in FIG. 11, for an RB(m) and an RB(m+1), RE-level FSF between the RB(m) and the RB(m+1) may be obtained by obtaining the magnitude difference and the phase difference of the DMRS on the corresponding REs of the RB(m) and the RB(m+1).

[0140] After obtaining the RE-level FSFs, RB-level FSF may be obtained based on the RE-level FSFs. For example, the RE-level FSFs on one RB may be averaged to obtain the RB-level FSF, but is not limited thereto.

[0141] According to embodiments, after obtaining the RB-level FSF for each DMRS, a full-band FSF trend may be obtained by combining the RB-level FSF for each DMRS in the zone to which the first UE belongs. According to embodiments, the obtaining of the full-band FSF trend by combining the RB-level FSF of each DMRS in the zone to which the first UE belongs includes: selecting the RB-level FSF of a DMRS in the region to which the first UE belongs that satisfies a predetermined condition as an initial full-band FSF trend; updating the full-band FSF trend by combining the initial full-band FSF trend with the RB-level FSF of DMRSs in the region other than the DMRS that has the most RBs, until a predetermined update end condition is satisfied. For example, the RB-level FSF for a DMRS that has the most RBs in the zone to which the first UE belongs may be selected.

[0142] FIGS. 12 to 15 are schematic diagrams illustrating calculation of a full-band FSF trend.

[0143] As shown in FIG. 12, it is assumed that RB-level FSFs of four DMRSs are obtained, wherein a certain DMRS has 5 RBs and is a DMRS with the most RBs among the four DMRSs, for example, the RB-level FSF of the DMRS with 5 RBs may first be selected as an initial full-band FSF trend, i.e., a current full-band FSF trend. Subsequently, the full-band FSF trend may be updated by continuously combining the current full-band FSF trend with the RB-level FSF of the other DMRSs until the update end condition is satisfied.

[0144] ·For a complete overlap case, overlap parts may be combined by filtering, and the specific combining process is shown in FIG. 13.

[0145] For example, a combined scale is first calculated based on the overlap parts:

[0146] combined scale = Full-band FSF[first overlap RB] / RB-level FSF[first overlap RB]

[0147] where "Full-band FSF[first overlap RB]" is RB-level FSF of the first overlap RB in the current full-band FSF trend, and "RB-level FSF[first overlap RB]" is RB-level FSF of the first overlap RB in DMRS FSF to be combined.

[0148] Subsequently, the combined full-band FSF trend is calculated by filtering:

[0149] Full-band FSF [overlap RB] = coef * full-band FSF [overlap RB] + (1-coef) * RB-level FSF * combined scale

[0150] where "Full-band FSF [overlap RB]" is the full-band FSF trend after the overlap parts are combined, "coef" is a filter coefficient, ranging from 0 to 1, with a default value of 0.5, "full-band FSF [overlap RB]" is RB-level FSF of the overlap RB in the current full-band FSF trend, and "RB-level FSF" is RB-level FSF of the overlap RB in the DMRS FSF to be combined.

[0151] ·For a partial overlap case, overlap parts may be combined by filtering and non-overlap parts may be padded. FIG. 14 illustrates a schematic diagram for obtaining a full-band FSF trend in a partial overlap case.

[0152] ◆ Firstly, a combined scale is calculated based on the overlap parts:

[0153] combined scale = Full-band FSF[first overlap RB] / RB-level FSF[first overlap RB] .

[0154] where "Full-band FSF[first overlap RB]" is RB-level FSF of the first overlap RB in the current full-band FSF trend, and "RB-level FSF[first overlap RB]" is RB-level FSF of the first overlap RB in the DMRS FSF to be combined.

[0155] ◆ Secondly, the full-band FSF trend after the overlap parts are combined is calculated by filtering as shown in FIG. 14:

[0156] Full-band FSF [overlap RB] = coef * full-band FSF [overlap RB] + (1-coef) * RB-level FSF [overlap RB] * combined scale

[0157] where "Full-band FSF [overlap RB]" is the full-band FSF trend after combining the overlap parts, "coef" is a filter coefficient, ranging from 0 to 1, with a default value of 0.5, "full-band FSF [overlap RB]" is RB-level FSF of the overlap RB in the current full-band FSF trend, and "RB-level FSF" is RB-level FSF of the overlap RB in the DMRS FSF to be combined.

[0158] ◆ Finally, the full-band FSF trend after the non-overlapp parts are combined is calculated by padding as shown in FIG. 14:

[0159] Full-band FSF[non-overlap RB] = RB-level FSF[non-overlap RB] * combined scale

[0160] where "Full-band FSF[non-overlap RB]" is the full-band FSF trend after the non-overlap parts are combined, and "RB-level FSF[non-overlap RB]" is RB-level FSF of the non-overlap RB in the DMRS FSF to be combined.

[0161] · For a non-overlap case, non-overlap parts are padded by interpolation, and FIG. 15 illustrates a schematic diagram for obtaining a full-band FSF trend in a non-overlap case.

[0162] ◆ As shown in FIG. 15, firstly, the current full-band FSF trend is interpolated until the first overlap RB: Full-band FSF interp[first overlap RB] = interpolate(Full-band FSF), where "interpolate()" is an interpolation function, "Full-band FSF interp[first overlap RB]" is RB-level FSF of a first overlap RB in the full-band FSF trend after interpolation. For example, any interpolation method may be used to interpolate the current full-band FSF trend until the first overlap RB, and the present disclosure does not limit the interpolation method.

[0163] ◆ Secondly, a combined scale is calculated based on the overlap parts: combined scale = Full-band FSF interp[first overlap RB] / RB-level FSF[first overlap RB], which is calculated in the same manner as the manner of calculating the combined scale described above.

[0164] ◆ Finally, the full-band FSF trend after the non-overlap parts are combined is calculated by padding: Full-band FSF[non-overlap RB] = RB-level FSF[non-overlap RB] * combined scale, where "Full-band FSF[non-overlap RB]" is the full-band FSF trend after the non-overlap parts are combined, and "RB-level FSF[non-overlap RB]" is RB-level FSF of the non-overlap RB in the DMRS FSF to be combined.

[0165] In the above manner, the full-band FSF trend may be continuously updated until a predetermined update end condition is satisfied. For example, when the FSF trend is the full-band and the change between the current FSF trend and the last FSF trend is less than a certain threshold value, the full-band FSF trend update is completed; when the FSF trend is non-full-band and the DMRSs are depleted in a zone (i.e., there is no DMRS available in a zone), the full-band FSF trend update is completed after the FSF trend is interpolated to the full-band.

[0166] it has been described above, in conjunction with the accompanying figures and examples, how to obtain a full-band FSF trend based on DMRS information. After the full-band FSF trend is obtained, as described above, at step S530, the full-band SRS channel of the first UE is determined based on the full-band FSF trend and the sub-band SRS. Hereinafter, a manner of determining the full-band SRS channel of the first UE based on the full-band FSF trend and the sub-band SRS is described in connection with the accompanying drawings and examples.

[0167] According to embodiments, step S530 may include: predicting a full-band FSF fluctuation of the first UE based on the full-band FSF trend and the sub-band SRS; and determining the full-band SRS channel of the first UE based on the full-band FSF fluctuation and the full-band FSF trend. According to embodiments, an artificial intelligence (AI) model may be utilized to determine the full-band SRS channel of the first UE. FIG. 16 illustrates a schematic diagram of determining a full-band SRS channel using an AI model. The determination process will be described below in connection with FIG. 16.

[0168] For example, the predicting of the full-band FSF fluctuation of the first UE based on the full-band FSF trend and the sub-band SRS may include: extracting a feature of FSF of the sub-band SRS and a feature of the full-band FSF trend using a first artificial intelligence (AI) network; predicting the full-band FSF fluctuation using a second AI network based on the extracted features. As an example, the extracting of the feature of the FSF of the sub-band SRS and the feature of the full-band FSF trend using the first AI network includes: determining the FSF of the sub-band SRS and extracting the feature of the FSF of the sub-band SRS based on the FSF of the sub-band SRS using a first sub-network in the first AI network; extracting the feature of the full-band FSF trend using a second sub-network in the first AI network. As shown in FIG. 16, for example, the feature of the FSF of the sub-band SRS and the feature of the full-band FSF trend may be extracted using the first AI network (labeled as a“FSF-CNN” in FIG. 20). The “FSF-CNN”may include a first sub-network“sub-band CNN” and a second sub-network “full-band CNN”. For example, the determining of the FSF of the sub-band SRS may include determining RB-level FSF of the sub-band SRS, the“sub-band CNN” may extract the feature of the FSF of the sub-band SRS based on the RB-level FSF of the sub-band SRS, and the“full-band CNN”may extract the feature of the full-band FSF trend. The feature of the FSF of the sub-band SRS may also be referred to as“sub-band FSF feature / characteristic”, for example, the“sub-band FSF feature”may include sub-band FSF change feature(s) / characteristic(s) in the frequency domain, including a variance, a gradient, a mean value, an extreme value, and the like. The feature of the full-band FSF trend may also be referred to as “full-band FSF trend feature / characteristic”, for example, the“full-band FSF trend feature”may include full-band FSF change feature(s) / characteristic(s) in the frequency domain, including a variance, a gradient, a mean value, an extreme value, and the like. These FSF change features may reflect multipath information in different scenarios.

[0169] After extracting the feature of the FSF of the sub-band SRS and the feature of the full-band FSF trend, next, the full-band FSF fluctuation may be predicted using the second AI network based on the extracted features. According to embodiments, the predicting of the full-band FSF fluctuation using the second AI network based on the extracted features may include: obtaining a sub-band FSF fluctuation feature based on the extracted features; obtaining a first full-band FSF fluctuation and a second full-band FSF fluctuation based on the sub-band FSF fluctuation feature using a first prediction network and a second prediction network in the second AI network, respectively, wherein the first prediction network is used for predicting a frequency fluctuation in a first direction and the second prediction network is used for predicting a frequency fluctuation in a second direction; obtaining the full-band FSF fluctuation based on the first full-band FSF fluctuation and the second full-band FSF fluctuation.

[0170] As an example, the second AI network may be a Temporal Convolutional Network (TCN) based network, which may include a first prediction network and a second prediction network. The first prediction network may be a forward TCN for predicting a frequency fluctuation in a first direction, and the second prediction network may be a backward TCN for predicting a frequency fluctuation in a second direction. The frequency fluctuation in the first direction may be a fluctuation in a high-frequency direction, which is also referred to as a“high-frequency FSF fluctuation”. The frequency fluctuation in the second direction may be a fluctuation in a low-frequency direction, also referred to as a “low-frequency FSF fluctuation”. The input to the forward TCN may be sub-band FSF fluctuation features to be arranged in a positive order. The input to the backward TCN may be sub-band FSF fluctuation features arranged in a reverse order (i.e., an inverted order). A first full-band FSF fluctuation, i.e., a full-band FSF fluctuation based on a forward prediction (prediction in the high-frequency direction), may be obtained using the forward TCN. A second full-band FSF fluctuation, i.e., a full-band FSF fluctuation based on a backward prediction (prediction in the low-frequency direction), may be obtained using the backward TCN. Next, a final full-band FSF fluctuation may be obtained by mapping both the first full-band FSF fluctuation and the second full-band FSF fluctuation to the full-band.

[0171] After obtaining the full-band FSF fluctuation, the full-band SRS channel of the first UE may be determined based on the full-band FSF fluctuation and the full-band FSF trend. Considering that relative positions of different UEs in the same zone are different, and the larger the relative distance is, the larger the fluctuation is, thus the similarity of the full-band FSF trend and the full-band FSF fluctuation of different UEs may be used as a reference for the relative positions. According to embodiments, the determining of the full-band SRS channel of the first UE based on the full-band FSF fluctuation and the full-band FSF trend includes: determining similarity between the full-band FSF fluctuation and the full-band FSF trend based on a feature of FSF of the sub-band SRS and a feature of the full-band FSF trend using a third AI network; obtaining the full-band SRS channel by fusing, based on the similarity, the full-band FSF fluctuation and the full-band FSF trend using a fourth AI network.

[0172] As shown in FIG. 16, the third AI network (referred to as a"similarity CNN"in FIG. 16) may determine the similarity between the full-band FSF fluctuation and the full-band FSF trend based on the based on the feature of FSF of the sub-band SRS and the feature of the full-band FSF trend. Subsequently, the determined similarity, the full-band FSF fluctuation and the full-band FSF trend may be input into the fourth AI network to predict the full-band SRS channel. The fourth network may, for example, be a Fully Convolutional Network (FCN), but is not limited thereto.

[0173] After obtaining the full-band SRS channel, returning to refer to FIG. 5, at step S540, uplink / downlink multi-antenna system scheduling may be performed based on the full-band SRS channel. For example, step S540 may include: performing the uplink / downlink multi-antenna system scheduling based on the full-band SRS channel. As mentioned above, the uplink / downlink multi-antenna system scheduling may include: at least one of beamforming, cooperative multipoint transmission, and multi-user pairing for downlink; and / or, at least one of beamforming, cooperative multipoint transmission, multi-user pairing, power control, positioning, and resource allocation for uplink. For example, at step S540, beamforming weights may be calculated based on the full-band SRS channel and the beamforming may be performed based on the beamforming weights.

[0174] According to the method shown in FIG. 5, the full-band FSF trend obtained based on the DMRS information of the plurality of UEs in the zone to which the first UE belongs is acquired, and the full-band SRS channel of the first UE is determined based on the full-band FSF trend and the sub-band SRS, so that the network-side node may determine the full-band SRS channel even if the first UE transmits an SRS using a sub-band, which solves the above problem 2, thereby facilitating better execution of uplink / downlink multi-antenna system scheduling based on the full-band SRS channel, improving the accuracy of the uplink / downlink multi-antenna system scheduling, and thus improving the throughput of the first UE and improving the system performance. For example, the beamforming weights may be more accurately calculated based on the determined full-band SRS channel, so that the beam is more accurately directed to the first UE, which in turn improves the throughput of the first UE and ultimately improves the system performance.

[0175] As mentioned above, the present disclosure also proposes an SRS configuration method which is also applicable to the method shown in FIG. 5. That is, the sub-band SRS received at step S910 may be an SRS transmitted by the first UE using a set single sub-band in the full-band based on the SRS configuration method proposed in the present disclosure. Thus, optionally, the method shown in FIG. 5 further includes: transmitting SRS configuration information to the first UE, wherein the SRS configuration information is used to configure the first UE to transmit the sub-band SRS to the network-side node using a set single sub-band in the full-band during each SRS period of a plurality of SRS periods. In this case, receiving the sub-band SRS from the first UE at step S510 includes: receiving, from the first UE, a sub-band SRS transmitted based on the SRS configuration information. As mentioned above in the description with respect to FIG. 3, the SRS configuration information is transmitted to the first UE, in order that the first UE transmits the sub-band SRS based on that SRS configuration information, which can support more UEs to obtain SRS resources with limited SRS resources, so that uplink / downlink multi-antenna system scheduling may be performed more based on the SRS, which minimizes having to use other scheduling methods (e.g., having to use the PMI-based beamforming) when SRS resources are insufficient, and thus solves the above mentioned problem 1, thereby contributing to improve the system performance.

[0176] Optionally, on the basis of solving the problem 2 and / or the problem 1 mentioned above, the present disclosure also proposes a solution to solve the problem 3 mentioned above. It should be noted that the present disclosure may solve the problem 1, problem 2 and problem 3 individually to realize the improvement of system performance, or, optionally, may solve any combination of the problem 1, the problem 2 and the problem 3 mentioned above simultaneously to realize the improvement of the system performance. In the following, a method performed by a network-side node according to a third embodiment of the present disclosure is described by taking solving the problem 3 alone as an example.

[0177] FIG. 17 is a flowchart illustrating a method performed by a network-side node according to a third embodiment of the present disclosure.

[0178] To address the problem 3 that uplink / downlink multi-antenna system scheduling (e.g., the beamforming) does not match channel changes, a real-time SRS channel may be predicted, e.g., channel prediction is performed between 2 SRS periods. The present disclosure proposes to predict the real-time SRS channel based on a Time Selective Fading (TSF) trend. The TSF may be a signal difference between different times caused by a moving trajectory (including a moving speed and / or a moving direction) of the UE. If the moving speed and / or the moving direction are different, the moving trajectory of the UE is different and the TSF is different. For example, as shown in FIG. 18, the moving speed is different, so the TSF is different, e.g., the signal power is different.

[0179] For a UE, features of TSF for the DMRS and the SRS are similar. However, the DMRS is determined by scheduling, thus, there is no guarantee that a UE has a full-band DMRS, which may be obtained if DMRSs of a set of UEs are combined. When these UEs are close to each other and have similar trajectories, the TSF is similar. Therefore, the TSF trend may be obtained with such a set of UEs. However, due to minor positional and trajectory differences among UEs in a group, there are different fluctuations in the TSF of different UEs, and for this reason, the real-time SRS channel may be predicted based on historical SRS information and the TSF trend.

[0180] The method performed by a network-side node according to a third embodiment of the present disclosure is described in detail below with reference to FIG. 17.

[0181] As shown in FIG. 17, at step S1710, a sub-band SRS is received from the first UE. According to embodiments, the sub-band SRS may be an SRS transmitted by the first UE using a sub-band in the full-band. According to embodiments, the sub-band SRS may be either an SRS transmitted by the first UE based on the SRS configuration method proposed in the present disclosure using a set single sub-band (the same single sub-band) in the full-band, or an SRS transmitted by the first UE based on a different sub-band in the full-band, for example, an SRS transmitted using a hopping sub-band based on a SRS configuration mode of scheme 1 or an SRS transmitted using a sparse hopping sub-band a SRS configuration mode of scheme 2. Optionally, for example, the method illustrated in FIG. 17 may further include: transmitting SRS configuration information to the first UE, wherein the SRS configuration information is used to configure the first UE to transmit the sub-band SRS to the network-side node using a set single sub-band in the full-ban during each SRS period of a plurality of SRS periods. In this case, receiving the sub-band SRS from the first UE at step S1710 may include: receiving, from the first UE, a sub-band SRS that is transmitted based on the SRS configuration information. By means of the above SRS configuration method, the above problem 1 may be solved, which in turn facilitates supporting more UEs with limited SRS resources, thereby improving the system performance.

[0182] At step S1720, a TSF trend corresponding to the first UE is obtained. According to embodiments, the TSF trend is obtained based on DMRS information of a plurality of UEs within a cluster to which the first UE belongs in a zone to which the first UE belongs, wherein a distance among the plurality of UEs within the cluster is less than a first threshold value and difference among moving speeds of the plurality of UEs is less than a second threshold value and / or difference among moving directions of the plurality of UEs is less than a third threshold value.

[0183] It is mentioned in the description of step S1720 that the TSF trend is obtained based on the DMRS information of the plurality of UEs within the cluster to which the first UE belongs in the zone to which the first UE belongs. Hereinafter, a manner of determining a cluster to which the first UE belongs is first described. According to embodiments, optionally, although not shown, the method shown in FIG. 17 may further include: determining a zone to which the first UE belongs; determining a moving speed and / or a moving direction of the first UE based on information related to at least one of RSRP and PMI reported by the first UE; determining a cluster to which the first UE belongs in the zone to which the first UE belongs, based on the moving speed and / or the moving direction. In the description above in relation to FIG. 5, a manner of determining the zone to which the first UE belongs has been described. For example, a regional similarity between the first UE and each pre-divided zone may be calculated in accordance with the regional similarity calculation method mentioned above, and the first UE may be divided into a zone with the highest regional similarity. After determining the zone to which the first UE belongs, a moving speed and / or a moving direction of the first UE may be determined, e.g., based on information related to at least one of an RSRP and a PMI. For example, the moving speed and / or the moving direction of the first UE may be determined based on a RSRP change and a PMI change. Then, a cluster to which the first UE belongs may be determined based on the moving speed and / or the moving direction. A zone may include at least one cluster, where a distance among UEs in the same zone is less than a first threshold value, and where the UEs in the same cluster not only have distances between each other that are less than the first threshold value, but also have differences between the moving speeds that are less than a second threshold value and / or differences between the moving directions that are less than a third threshold value.

[0184] FIG. 19 is a schematic diagram illustrating a division of clusters. As shown in FIG. 19, by collecting information reported by UEs under the same cell, the UEs may be divided into three zones. Further, the zone may be divided into at least one cluster based on a moving trajectory of each UE in the zone, e.g., a zone 3 is divided into four clusters.

[0185] For each UE in the zone, the following judgment may be made:

[0186] With the change of time,

[0187]

[0188]

[0189]

[0190]

[0191]

[0192]

[0193] ·If the change value of the RSRP is in a range of (TH3, ∞), the UE speed is a high speed and this UE is not divided into any cluster.

[0194] Wherein, TH1, TH2, TH3, TH4 are threshold values for the change value of the RSRP and TH4 is a threshold value for the change value of the PMI.

[0195] According to embodiments, step S1720 may include: receiving, from another network-side node, the TSF trend obtained by the other network-side node based on the DMRS information; or, obtaining the TSF trend based on the DMRS information. That is, the network-side node may either obtain the TSF trend based on the DMRS information by itself or receive, from another network-side node, the TSF trend obtained by the other network-side node based on the DMRS information, depending on whether or not the network-side node has sufficient computational resources, and if the computational resources are sufficient, the network-side node may obtain the TSF trend based on the DMRS information by itself, otherwise, another network node may obtain the TSF trend based on the DMRS information and then transmit the TSF trend to the network-side node. As an example, the network-side node may be a base station and the other network-side node may be a RIC, without limitation.

[0196] Since multipath effects within a cluster are similar, the SRS TSF trend and the DMRS TSF trend are also similar, and thus the TSF trend may be obtained based on DMRS information of a plurality of UEs within the cluster to which the first UE belongs. Optionally, the method shown in FIG. 17 may further include: collecting DMRS information of a plurality of UEs within the cluster to which the first UE belongs, wherein each UE of the plurality of UEs within the cluster to which the first UE belongs has at least two DMRSs at the same RB position during at least two consecutive SRS periods. That is, if the UE has two or more DMRS information at the same RB position during at least two consecutive SRS periods, then the DMRS information is collected for that UE. FIG. 20 is a schematic diagram illustrating DMRS positions of different UEs within a cluster during different SRS periods. FIG. 20 illustrates that there are three UEs within the cluster and shows two SRS periods T1 and T2, with one SRS period including N slots. For example, a UE2 has three DMRSs at a 3rd RB position within two consecutive SRS periods, and information about these DMRSs of the UE2 is collected. For another example, a UE3 has three DMRSs at a 4th RB position within two consecutive SRS periods, information about these DMRSs for the UE3 is collect. After collecting the DMRS information of the plurality of UEs in the cluster where the first UE is located, the TSF trend may be obtained based on the DMRS information. According to embodiments, the obtaining of the TSF trend based on the DMRS information includes: calculating, for each UE in the cluster, a DMRS difference at the same RB position in different slots of the SRS periods based on magnitudes and phases of the DMRSs at the same RB position in the different slots; obtaining the TSF trend based on the DMRS difference.

[0197] FIG. 21 illustrates a schematic diagram for calculating a DMRS difference at the same RB positions in different slots of an SRS period.

[0198]

[0199]

[0200]

[0201]

[0202] For the UE2, according to the similar calculation method as the UE1, the following DMRS differences may be calculated:

[0203]

[0204] For the UE3, according to the similar calculation as the UE1, the following DMRS differences may be calculated:

[0205]

[0206]

[0207]

[0208]

[0209] After determining the DMRS differences of different time intervals within the cluster, the TSF trend of the cluster may be obtained based on the DMRS differences of different time intervals. For example, DMRS amplitude differences and DMRS phase differences of different time intervals within the cluster are determined as a TSF trend of the cluster, based on the DMRS differences of different time intervals within the cluster. FIG. 22 is a schematic diagram illustrating a TSF trend. As shown in FIG. 22, the TSF trend includes magnitude differences and phase differences of different time intervals. The TSF trend of a cluster is the TSF trend of UEs in the cluster, and thus, in the case where the cluster to which the first UE belongs is determined, the TSF trend of the cluster to which the first UE belongs may be used as the TSF trend of the first UE. The way of determining the cluster to which the first UE belongs has been described above and will not be repeated here.

[0210] Returning to refer to FIG. 17, after the TSF trend is obtained at step S1720, next, at step S1730, a real-time SRS channel of the first UE is predicted based on the TSF trend and historical SRS information of the first UE, wherein the historical SRS information includes information about the sub-band SRS. As mentioned above, although a TSF trend may be obtained based on the DMRS information of UEs within a cluster, there are different fluctuations in the TSF of different UEs due to minor positional and trajectory differences among UEs in a cluster, and for this reason, the real-time SRS channel may be predicted based on the historical SRS information and the TSF trend to accurately predict the real-time SRS channels of different UEs.

[0211] According to embodiments, step S1730 may include: predicting a channel fluctuation due to a change in a moving speed and / or a moving direction of the first UE based on the TSF trend and the historical SRS information; predicting the real-time SRS channel based on the predicted channel fluctuation and the TSF trend. The fluctuation of the SRS channel changes over time due to the difference in the moving speed and / or moving direction of the UE, and therefore, the channel fluctuation due to the change in the moving speed and / or moving direction of the first UE is first predicted based on the TSF trend and the historical SRS information, and then, the real-time SRS channel is predicted based on the predicted channel fluctuation and the TSF trend. According to embodiments, the prediction of the real-time SRS channel may be realized using an AI model. For example, the predicting of the channel fluctuation due to the change in the moving trajectory of the first UE based on the TSF trend and the historical SRS information includes: extracting SRS features based on the historical SRS information using a fifth AI network and obtaining SRS features with different weights by a self-attention network; extracting a TSF feature based on the TSF trend using a sixth AI network; predicting, based on the SRS features with different weights and the TSF feature, the channel fluctuation using a seventh AI network. For example, the predicting the real-time SRS channel based on the predicted channel fluctuation and the TSF trend includes: predicting the real-time SRS channel using an eighth AI network based on the channel fluctuation and the TSF feature.

[0212] FIG. 23 illustrates a schematic diagram for predicting a real-time SRS channel using an AI model. As shown in FIG. 23, the AI model for predicting the real-time SRS channel includes a feature extraction module, a fluctuation extraction module, and an FCN module. For example, the feature extraction module includes a fifth AI network (e.g., may be a first CNN), a self-attention network, and a sixth AI network (e.g., may be a second CNN). The feature extraction module extracts SRS features in the time domain via the first CNN based on historical SRS information, and obtains SRS features with different weights via the self-attention network, the different weights reflecting different importance of the SRS features. In addition, the feature extraction module extracts a TSF feature based on the TSF trend via the second CNN. Subsequently, the SRS features with different weights and the TSF feature are input to a seventh AI network (e.g., may be a third CNN) to predict a channel fluctuation. For example, the channel fluctuation may include fluctuations in the phase and amplitude of the signal. Finally, the channel fluctuation and the TSF feature are input to an eighth AI network (e.g., may be a FCN) to predict the real-time SRS channel. The predicted real-time SRS channel includes amplitude and phase changes of the SRS over time.

[0213] Referring back to FIG. 17, after the real-time SRS channel is predicted, at step S1740, uplink / downlink multi-antenna system scheduling, e.g., beamforming, may be performed based on the predicted real-time SRS channel. For example, step S1740 may include: calculating beamforming weights based on the real-time SRS channel, and performing the beamforming based on the beamforming weights.

[0214] According to the method shown in FIG. 17, by obtaining the TSF trend corresponding to the first UE and predicting the real-time SRS channel of the first UE based on the TSF trend and the historical SRS information of the first UE, the real-time SRS channel of the first UE may be predicted in the above manner even if the first UE transmits an SRS using a sub-band, which solves the problem 3 above and thus facilitates better performing uplink / downlink multi-antenna system scheduling based on the predicted real-time SRS channel, so that s the accuracy of the uplink / downlink multi-antenna system scheduling is improved, thereby improving the throughput of the UE and improving the system performance. For example, the beamforming weights may be calculated more accurately based on the predicted real-time SRS channel, which improves the accuracy of the beamforming, thereby improving the throughput of the UE and improving the system performance.

[0215] As illustrated above, the present disclosure may solve the problem 1, the problem 2, and the problem 3 individually to achieve improved system performance, or, optionally, solve any combination of the problem 1, the problem 2, and the problem 3 described above simultaneously to achieve improved system performance. That is, the first embodiment, the second embodiment, and the third embodiment according to the present disclosure may be combined with each other.

[0216] For example, the method shown in FIG. 5 may further include: obtaining a TSF trend corresponding to the first UE; predicting a real-time SRS channel of the first UE based on the TSF trend and historical SRS information of the first UE, wherein the historical SRS information includes information about the sub-band SRS. According to embodiments, the TSF trend is obtained based on DMRS information of a plurality of UEs within a cluster to which the first UE belongs in a zone to which the first UE belongs, wherein a distance among the plurality of UEs within the cluster is less than a first threshold value and difference among moving speeds of the plurality of UEs is less than a second threshold value and / or difference among moving directions of the plurality of UEs is less than a third threshold value. In the case of including the above steps, step S540 in FIG. 5 may include: performing uplink / downlink multi-antenna system scheduling based on the full-band SRS channel and the real-time SRS channel. For example, beamforming weights are calculated based on the full-band SRS channel and the real-time SRS channel, and the beamforming is performed based on the beamforming weights. Performing the uplink / downlink multi-antenna system scheduling based on the full-band SRS channel and the real-time SRS channel not only solves the problem 2 but also solves the problem 3, which makes it possible to perform the uplink / downlink multi-antenna system scheduling more accurately compared to applying FIG. 5 and FIG. 17 individually, thereby further improving the throughput of the UEs and improving the system performance. The details related to obtaining the TSF trend and predicting the real-time SRS channel of the first UE based on the TSF trend and the historical SRS information of the first UE have been described above and will not be repeated herein. Optionally, the method shown in FIG. 5 may further include: determining a moving speed and / or a moving direction of the first UE based on information related to at least one of RSRP and PMI reported by the first UE; determining a cluster to which the first UE belongs in the zone to which the first UE belongs, based on the moving speed and / or the moving direction. The manner of determining the zone and the cluster has also been described above, and will not be repeated herein.

[0217] As mentioned in the above description of the steps of FIG. 5, the network-side node may receive, from another network-side node, the full-band FSF trend obtained by the other network node based on the DMRS information, depending on whether or not the network-side node has sufficient computational resources. If the computational resources are sufficient, the network-side node may obtain the full-band FSF trend based on the DMRS information by itself, otherwise another network node may obtain the full-band FSF trend based on the DMRS information, and then transmit the full-band FSF trend to the network-side node. Thus, according to a fourth embodiment of the present disclosure, a method performed by another network-side node as described above may also be provided.

[0218] FIG. 24 is a flowchart illustrating a method performed by a network-side node according to a fourth embodiment of the present disclosure. Referring to FIG. 24, at step S2410, a full-band FSF trend corresponding to the first UE is obtained based on DMRS information of a plurality of UEs in a zone to which the first UE belongs, wherein a distance among the plurality of UEs in the zone is less than a first threshold value. At step S2420, the full-band FSF trend is transmitted to another network-side node, wherein the full-band FSF trend is used to determine a full-band SRS channel of the first UE, the full-band SRS channel being used to perform uplink / downlink multi-antenna system scheduling. As an example, the network-side node in the method shown in FIG. 24 may be a RIC, and the other network-side node may be a gNB. In the above, the aspects related to obtaining the full-band FSF trend based on the DMRS information have been described and will not be repeated here.

[0219] According to the method shown in FIG. 24, the network-side node obtains the full-band FSF trend of the first UE based on the DMRS information of the plurality of UEs in the zone to which the first UE belongs and transmits the full-band FSF trend to another network-side node, which may reduce the computational burden of the other network-side node, and enable the other network-side node to determine, based on the received full-band FSF trend, the full-band SRS channel of the first UE to perform uplink / downlink multi-antenna system scheduling based on the full-band SRS channel, thereby improving the accuracy of the uplink / downlink multi-antenna system scheduling, and thus improving the throughput of the UE and improving the system performance.

[0220] Optionally, the method shown in FIG. 24 may further include: dividing UEs under the same cell into zones based on information reported by the UEs under the same cell, wherein a distance among UEs in the same zone is less than the first threshold value; determining the zone to which the first UE belongs. The content related to the zone division has been described above and will not be repeated here.

[0221] Optionally, the method shown in FIG. 24 may further include: obtaining a TSF trend corresponding to the first UE based on DMRS information of a plurality of UEs within a cluster to which the first UE belongs in the zone to which the first UE belongs, wherein a distance among the plurality of UEs within the cluster is less than the first threshold value, and difference among moving speeds of the plurality of UEs is less than a second threshold value and / or difference among moving directions of the plurality of the UEs is less than a third threshold value; transmitting the TSF trend to another network-side node. In the above, relevant contents of obtaining the TSF trend based on the DMRS information have been described and will not be repeated herein. Optionally, the method shown in FIG. 24 may further include: determining a moving speed and / or a moving direction of the first UE based on information related to at least one of RSRP and PMI reported by the first UE; determining a cluster to which the first UE belongs in the zone to which the first UE belongs, based on the moving speed and / or the moving direction. The content related to the cluster division　has been described above, and it will not be repeated here.

[0222] As mentioned in the above description of the steps of FIG. 17, the network-side node may either acquire the TSF trend based on the DMRS information by itself or receive, from another network-side node, the TSF trend acquired by the other network node based on the DMRS information, depending on whether or not the network-side node has sufficient computational resources, and if the computational resources are sufficient, the network-side node may acquire the TSF trend based on the DMRS information by itself, otherwise, another network node may obtain the TSF trend based on the DMRS information and then transmit the TSF trend to the network-side node. Thus, according to a fifth embodiment of the present disclosure, a method performed by another network-side node as described above may also be provided.

[0223] FIG. 25 is a flowchart illustrating a method performed by a network-side node according to a fourth embodiment of the present disclosure. Referring to FIG. 25, at step S2510, a TSF trend corresponding to the first UE is obtained based on DMRS information of a plurality of UEs within a cluster to which the first UE belongs in a zone to which the first UE belongs, wherein a distance among the plurality of UEs within the cluster is less than a first threshold value, and difference among moving speeds of the plurality of UEs is less than a second threshold value and / or difference among moving directions of the plurality of UEs is less than a third threshold value. At step S2520, the TSF trend is transmitted to another network-side node, wherein the TSF trend is used to predict a real-time SRS channel of the first UE, the real-time SRS channel being used to perform uplink / downlink multi-antenna system scheduling. In the above, the relevant contents of obtaining the TSF trend based on the DMRS information have been described and will not be repeated here.

[0224] According to the method shown in FIG. 25, the network-side node obtains the TSF trend based on the DMRS information of the plurality of UEs in the cluster to which the first UE belongs in the zone to which the first UE belongs and transmits the TSF trend to another network-side node, which may reduce the computational burden of the other network-side node, and enable the other network-side node to predict a real-time SRS channel based on the received TSF trend to perform uplink / downlink multi-antenna system scheduling based on the predicted real-time SRS channel, thereby improving the accuracy of the uplink / downlink multi-antenna system scheduling, and in turn, improving the throughput of the UE and improving the system performance.

[0225] Optionally, the method shown in FIG. 25 may further include steps related to determining the zone to which the first UE belongs and determining the cluster to which the first UE belongs, which are also not described herein.

[0226] FIG. 26 is a flowchart illustrating a method performed by a UE according to a sixth embodiment of the present disclosure.

[0227] Referring to FIG. 26, at step S2610, SRS configuration information is received from a network-side node, wherein the SRS configuration information is used to configure the first UE to transmit a sub-band SRS to the network-side node using a set single sub-band in a full-band during each SRS period of a plurality of SRS periods. At step S2620, based on the SRS configuration information, the sub-band SRS is transmitted to the network-side node, wherein the sub-band SRS is used to perform uplink / downlink multiple antenna system scheduling. In the above description related to FIG. 3, contents related to the SRS configuration information have been described and will not be repeated herein.

[0228] 1. According to the method shown in FIG. 26, the UE receives, from the network-side node, the SRS configuration information for configuring the first UE to transmit the sub-band SRS to the network-side node using the set single sub-band in the full-band in each of the plurality of SRS periods and transmits the sub-band SRS to the network-side node based on the SRS configuration information, which makes it possible to support, with limited SRS resources, more UEs obtaining SRS resources, thereby allowing uplink / downlink multi-antenna system scheduling to be performed more based on the SRS, minimizing having to performing uplink / downlink multi-antenna system scheduling by using other scheduling methods when SRS resources are insufficient, and thus contributing to the improvement of the system performance.

[0229] Above, the methods according to various embodiments of the present disclosure have been described, and for a clearer understanding of the idea of the present disclosure, an exemplary timing of operations according to embodiments of the present disclosure is further described below in conjunction with FIG. 27. However, it is clear to those skilled in the art that the timing of operations according to the present disclosure is not limited to the specific example shown in FIG. 27.

[0230] In the example shown in FIG. 27, the UE measures and reports performance parameter information (e.g., including at least one of an RSRP, an SINR, a PMI, and a position) of a cell to the gNB in real-time, the gNB may perform statistical calculations on the information and then transmit the obtained data to the RIC. The RIC may, based on the data, perform UE hierarchical grouping, i.e., perform zone and cluster dividing to determine a zone to which the UE belongs and a cluster to which it belongs. For example, based on the information measured and reported by the UE in real-time, a regional similarity among UEs under the same cell and moving trajectories of the UEs are calculated, and the UEs under the same cell are finally divided into different zones and clusters.

[0231] The gNB may perform uplink scheduling so that the UE transmits an uplink DMRS to it, and then, the gNB may transmit the uplink DMRS to the RIC. The RIC may obtain a full-band FSF trend based on DMRS information within the zone to which the UE belongs, and the RIC may obtain a TSF trend based on DMRS information within the cluster to which the UE belongs. Subsequently, the RIC may transmit the band FSF trend and the TSF trend to the gNB.

[0232] The gNB may perform an SRS configuration setup, e.g., perform a single sub-band long-period SRS configuration as proposed in the present disclosure, and transmit the SRS configuration information to the UE. After receiving the SRS configuration information, the UE may transmit a sub-band SRS to the gNB based on the SRS configuration information. Subsequently, the gNB may determine a full-band SRS channel based on the full-band FSF trend and the sub-band SRS, e.g., may determine the full-band SRS channel based on the full-band FSF trend and the sub-band SRS using an AI model. In addition, the gNB may predict a real-time SRS channel based on the TSF trend and historical SRS information, for example, the real-time SRS channel may be predicted based on the TSF trend and the historical SRS information utilizing an AI model. Finally, the gNB may perform uplink / downlink multi-antenna system scheduling based on the determined full-band SRS channel and the predicted real-time SRS channel. For example, the gNB performs beamforming based on the determined full-band SRS channel and the predicted real-time SRS channel. For example, beamforming weights are calculated based on the determined full-band SRS channel and the predicted real-time SRS channel, and the beamforming is performed based on the calculated beamforming weights.

[0233] FIG. 28 is a diagram illustrating an exemplary deployment architecture according to embodiments of the present disclosure.

[0234] As shown in FIG. 28, the training of the AI model for full-band SRS channel determination and the AI model for real-time SRS channel prediction mentioned above may be implemented in the RIC. For example, model training, hierarchical grouping of UEs, and obtaining the FSF trend and the TSF trend may be performed in an application module of the RIC.

[0235] The RIC may transmit the AI model to a media access control (MAC) in a distributed unit (DU) of the gNB after completing the model training. In addition, the RIC transmits the FSF trend and the TSF trend obtained by the application module to the MAC. The gNB may perform the determination of the full-band SRS channel and the prediction of the real-time SRS channel in the MAC, and then perform uplink / downlink multi-antenna system scheduling based on the determined full-band SRS channel and the real-time SRS channel, e.g., calculate beamforming weights and transmit the calculated beamforming weights to a control physical layer (C-PHY). The C-PHY performs beamforming based on the beamforming weights. In addition, the C-PHY periodically transmits the measurement data reported by the UE to the MAC for channel determination and prediction. In addition, the MAC periodically collects the data reported by the UE and reports it to the RIC for model training and FSF / TSF trend acquisition. As is clear to those skilled in the art, the deployment architecture according to the present disclosure is not limited to the specific example shown in FIG. 28, but may be appropriately adapted based on computing resources. For example, if the computing resources of the gNB are sufficient, all the operations performed in the RIC may be performed in the gNB.

[0236] Above, the methods and their effects according to various embodiments of the present disclosure have been described in connection with the accompanying drawings. In the following, apparatuses according to embodiments of the present disclosure are briefly described.

[0237] FIG. 29 is a block diagram illustrating a network-side node according to embodiments of the present disclosure. Referring to FIG. 29, a network-side node 2900 may include a transceiver 2910, and a processor 2920, wherein the processor 2920 is coupled to the transceiver 2910 and configured to perform any of the methods described above that are performed by the network-side node.

[0238] FIG. 30 is a block diagram illustrating a UE according to embodiments of the present disclosure. Referring to FIG. 30, a UE 3000 may include a transceiver 3010 and a processor 3020, wherein the processor 3020 is coupled to the transceiver 3010 and configured to perform the method performed by a UE as described above.

[0239] In embodiments of the present disclosure, there is also provided an electronic apparatus that includes at least one processor, and alternatively, further includes at least one transceiver and / or at least one memory coupled to the at least one processor, wherein the at least one processor is configured to perform the steps of the method provided in any alternative embodiment of the present disclosure.

[0240] FIG. 31 illustrates a schematic diagram of a structure of an electronic apparatus applicable to an exemplary embodiment of the present application. As shown in FIG. 31, the electronic apparatus 4000 shown in FIG. 31 includes: a processor 4001 and a memory 4003. Wherein the processor 4001 and the memory 4003 are coupled, e.g., through a bus 4002. Alternatively, the electronic apparatus 4000 may further include a transceiver 4004 which may be used for data interaction between the electronic apparatus and other electronic apparatuses, such as transmitting of data and / or receiving of data. It should be noted that, each of the processor 4001, the memory 4003, and the transceiver 4004 is not limited to one in a practice application, and the structure of the electronic apparatus 4000 does not constitute a limitation of the embodiments of the present disclosure. Alternatively, the electronic apparatus may be the first network node, the second network node, or the third network node.

[0241] The processor 4001 may be a Central Processing Unit (CPU), general purpose processor, Digital Signal Processor (DSP), Application Specific Integrated Circuit (ASIC), Field Programmable Gate Array (FPGA) or other programmable logic device, transistor logic device, hardware part, or any combination thereof. It may implement or perform various exemplary logic boxes, modules, and circuits described in conjunction with the disclosed contents of the present disclosure. The processor 4001 may also be a combination that implements computing functions, such as a combination containing one or more microprocessors, a combination of a DSP and a microprocessor, and the like.

[0242] The bus 4002 may include a pathway to transfer information between the above components. The bus 4002 may be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, and the like. The bus 4002 may be classed as an address bus, a data bus, a control bus, and the like. For ease of representation, only one bold line is shown in FIG. 31, but it does not mean that there is only one bus or one type of bus.

[0243] The memory 4003 may be a Read Only Memory (ROM) or other types of static storage apparatuses that can store static information and instructions, a Random Access Memory (RAM) or other types of dynamic storage apparatuses that can store information and instructions, may be an Electrically Erasable Programmable Read Only Memory (EEPROM), Compact Disc Read Only Memory (CD-ROM) or other optical disc storages, an optical disc storage (including a compressed disc, laser disc, optical disc, digital universal disc, Blu-ray disc, etc.), a disk storage medium, other magnetic storage apparatuses, or any other medium that may be used to carry or store computer programs and may be read by a computer, it is not limited herein.

[0244] The memory 4003 is used to store computer programs or executable instructions for performing the embodiments of the present disclosure, and is controlled for execution by the processor 4001. The processor 4001 is used to execute the computer programs or executable instructions stored in the memory 4003 to implement the steps shown in the preceding method of the embodiments.

[0245] An embodiment of the present disclosure provides a computer readable storage medium storing computer programs or instructions, the computer programs or instructions, when being executed by at least one processor may perform or implement the steps in the preceding method of the embodiments and corresponding contents.

[0246] An embodiment of the present disclosure provides a computer program product including computer programs, the computer programs, when being executed by a processor, may implement the steps shown in the preceding method of the embodiments and corresponding contents.

[0247] The terms "first", "second", "third", "fourth", "1", "2" and the like (if exists) in the specification and claims of the present disclosure and the above drawings are used to distinguish similar objects, and need not be used to describe a specific order or sequence. It should be understood that, data used as such may be interchanged in appropriate situations, so that the embodiments of the present disclosure described here may be implemented in an order other than the illustration or text description.

[0248] It should be understood that, although each operation step is indicated by an arrow in the flowcharts of the embodiments of the present disclosure, an implementation order of these steps is not limited to an order indicated by the arrows. Unless explicitly stated herein, in some implementation scenarios of the embodiments of the present disclosure, the implementation steps in the flowcharts may be executed in other orders according to requirements. In addition, some or all of the steps in each flowchart may include a plurality of sub steps or stages, based on an actual implementation scenario. Some or all of these sub steps or stages may be executed at the same time, and each sub step or stage in these sub steps or stages may also be executed at different times. In scenarios with different execution times, an execution order of these sub steps or stages may be flexibly configured according to a requirement, which is not limited by the embodiment of the present disclosure.

[0249] The above text and accompanying drawings are provided as examples only to assist readers in understanding the present disclosure. They are not intended and should not be interpreted as limiting the scope of the present disclosure in any way. Although certain embodiments and examples have been provided, based on the content disclosed herein, it is apparent to those skilled in the art that, changes may be made to the illustrated embodiments and examples without departing from the scope of the present disclosure, and other similar implementation methods based on the technical concepts of the present disclosure also belongs to a protection scope of the embodiments of the present disclosure.

Claims

1.A method performed by a network-side node comprising:receiving a sub-band sounding reference signal (SRS) from a first UE, wherein the sub-band SRS is an SRS transmitted by the first UE using a sub-band in a full-band;obtaining a full-band frequency selective fading (FSF) trend corresponding to the first UE;determining a full-band SRS channel of the first UE based on the full-band FSF trend and the sub-band SRS;performing uplink / downlink multi-antenna system scheduling based on the full-band SRS channel.2.The method according to claim 1, wherein the full-band FSF trend is obtained based on demodulation reference signal (DMRS) information of a plurality of UEs in a zone to which the first UE belongs, wherein a distance among the plurality of UEs in the zone is less than a first threshold value.3.The method according to claim 2, wherein the obtaining of the full-band FSF trend corresponding to the first UE comprises:receiving, from another network-side node, the full-band FSF trend obtained by the other network-side node based on the DMRS information; orobtaining the full-band FSF trend based on the DMRS information.4.The method according to claim 3, wherein the obtaining of the full-band FSF trend based on the DMRS information comprises:obtaining FSF for each DMRS of the plurality of UEs in the zone to which the first UE belongs;obtaining the full-band FSF trend based on the obtained FSF.5.The method according to claim 1, wherein the determining of the full-band SRS channel of the first UE based on the full-band FSF trend and the sub-band SRS comprises:predicting a full-band FSF fluctuation of the first UE based on the full-band FSF trend and the sub-band SRS;determining the full-band SRS channel of the first UE based on the full-band FSF fluctuation and the full-band FSF trend.6.The method according to claim 5, wherein the predicting of the full-band FSF fluctuation of the first UE based on the full-band FSF trend and the sub-band SRS comprises:extracting a feature of FSF of the sub-band SRS and a feature of the full-band FSF trend using a first artificial intelligence (AI) network;predicting the full-band FSF fluctuation using a second AI network based on the extracted features.7.The method according to claim 5, wherein the determining of the full-band SRS channel of the first UE based on the full-band FSF fluctuation and the full-band FSF trend comprises:determining similarity between the full-band FSF fluctuation and the full-band FSF trend based on a feature of FSF of the sub-band SRS and a feature of the full-band FSF trend using a third AI network;obtaining the full-band SRS channel by fusing, based on the similarity, the full-band FSF fluctuation and the full-band FSF trend using a fourth AI network.8.The method according to claim 2, further comprising:dividing UEs under the same cell into zones based on information reported by the UEs under the same cell, wherein a distance between UEs in the same zone is less than the first threshold value;determining the zone to which the first UE belongs.9.The method according to any one of claims 1 to 8, further comprising:transmitting SRS configuration information to the first UE, wherein the SRS configuration information is used to configure the first UE to transmit the sub-band SRS to the network-side node using a set single sub-band in the full-band during each SRS period of a plurality of SRS periods,wherein the receiving of the sub-band SRS from the first UE comprises: receiving, from the first UE, the sub-band SRS transmitted based on the SRS configuration information.10.The method according to any one of claims 1 to 8, further comprising:obtaining a time selective fading (TSF) trend corresponding to the first UE;predicting a real-time SRS channel of the first UE based on the TSF trend and historical SRS information of the first UE, wherein the historical SRS information comprises information about the sub-band SRS;wherein the performing of the uplink / downlink multi-antenna system scheduling based on the full-band SRS channel comprises: performing the uplink / downlink multi-antenna system scheduling based on the full-band SRS channel and the real-time SRS channel.11.A network-side node comprising:at least one transceiver;memory, including one or more storage media, storing instructions; andat least one processor including processing circuitry, wherein the instructions, when executed by the at least one processor individually or collectively, cause the network-side node to:receive a sub-band sounding reference signal (SRS) from a first UE, wherein the sub-band SRS is an SRS transmitted by the first UE using a sub-band in a full-band;obtain a full-band frequency selective fading (FSF) trend corresponding to the first UE;determine a full-band SRS channel of the first UE based on the full-band FSF trend and the sub-band SRS;perform uplink / downlink multi-antenna system scheduling based on the full-band SRS channel.12.The network-side node of claim 11,wherein the full-band FSF trend is obtained based on demodulation reference signal (DMRS) information of a plurality of UEs in a zone to which the first UE belongs, wherein a distance among the plurality of UEs in the zone is less than a first threshold value.13.The network-side node of claim 12,wherein the instructions, when executed by the at least one processor individually or collectively, cause the network-side node to:receive, from another network-side node, the full-band FSF trend obtained by the other network-side node based on the DMRS information; orobtain the full-band FSF trend based on the DMRS information.14.The network-side node of claim 13,wherein the instructions, when executed by the at least one processor individually or collectively, cause the network-side node to:obtain FSF for each DMRS of the plurality of UEs in the zone to which the first UE belongs;obtain the full-band FSF trend based on the obtained FSF.15.The network-side node of claim 11,wherein the instructions, when executed by the at least one processor individually or collectively, cause the network-side node to:predict a full-band FSF fluctuation of the first UE based on the full-band FSF trend and the sub-band SRS;determine the full-band SRS channel of the first UE based on the full-band FSF fluctuation and the full-band FSF trend.

Images