COMP-based communication method, base station and readable storage medium
By analyzing the measurement report of the target UE in the serving cell and determining the cooperative cell using a machine learning model, directly conducting cooperative communication, the problem of untimely response of the cooperative cell is solved and the COMP collaboration performance is improved.
Patent Information
- Application Number
- CN202310739884.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2023-06-20
- Publication Date
- 2024-12-20
AI Technical Summary
In the field of communication, the cooperative cell responds to the measurement request of the serving cell in a timely manner, which affects the Coordinated Multiple Points (COMP) collaboration performance.
By sending measurement control information to the target UE in the serving cell, receiving and analyzing the measurement report to determine the fingerprint grid of the target UE, and determining the cooperative cell based on the trained machine learning model, collaborative communication is directly carried out, avoiding the cooperation to the cooperative cell Send a measurement request step.
It improves the COMP collaboration efficiency and performance, reduces the response time of the target UE, increases the proportion of collaborative RB and the number of collaboration times, and solves the problem of untimely response of collaborative cells.
Smart Images
Figure CN119172771A_ABST
Abstract
Description
Technical Field
[0001] The present application belongs to the field of communication technology, and specifically relates to a communication method, a base station and a readable storage medium based on coordinated multiple points (COMP). Background Art
[0002] In the field of communications, when the user equipment (UE) is located at the edge of the serving cell, the UE can not only receive signals from the serving cell, but also signals from other non-serving cells. In this way, the normal service performance of the UE will be interfered with. In addition, not only the serving cell receives the UE's uplink service, but the non-serving cell can also receive the UE's uplink service, which also interferes with the reception of the non-serving cell. The COMP communication technology can achieve the suppression or elimination of co-frequency networking and inter-cell interference by coordinating and processing interference in different cells, or avoiding interference, or converting interference into useful signals.
[0003] In the related technology, the process of the service cell using COMP technology to cooperate with the UE for communication generally includes: the service cell sends COMP measurement control information carrying COMP measurement conditions to the UE within the service range, and receives the measurement report reported by the cooperative UE that meets the COMP measurement conditions; the service cell determines the cooperative cell according to the pre-configured neighboring cell relationship; the service cell sends measurement requests for other reference signals such as SRS (Sounding Reference Signal) or CSI-RS (Channel Status Information Reference Signal) to the determined cooperative cell, and determines the appropriate cooperative cell based on the measurement results fed back by the cooperative cell (i.e., the measurement value of the reference signal); and communicates with the cooperative UE under the cooperation of the appropriate cooperative cell.
[0004] However, there is a problem in the related art that the collaborative cell does not respond to the measurement request of the serving cell in a timely manner, which affects the collaborative performance of COMP. For example, after receiving the measurement report reported by the collaborative UE that meets the COMP measurement conditions, the serving cell needs to initiate a reference signal measurement request to the collaborative cell. However, the collaborative cell responds to the measurement request of the serving cell only when its own resources are idle, resulting in poor real-time response of the collaborative cell, which results in the measurement results fed back by the collaborative cell not being able to reflect the current channel quality of the collaborative cell in a timely manner, affecting the collaborative performance of COMP. Summary of the invention
[0005] The embodiments of the present application provide a COMP collaborative communication method, a base station and a readable storage medium, which can solve the problem in the related art that the collaborative cell does not respond to the measurement request of the serving cell in a timely manner, thereby affecting the collaborative performance of COMP.
[0006] In a first aspect, an embodiment of the present application provides a COMP cooperative communication method, which is applied to a serving cell, including:
[0007] Sending COMP measurement control information to UEs within a service range, where the COMP measurement control information includes a COMP measurement condition;
[0008] Receiving a measurement report reported by a target UE that meets the COMP measurement condition;
[0009] Based on the measurement report, determining a fingerprint grid corresponding to the target UE; the fingerprint grid corresponds to at least one COMP feature model, and the COMP feature model is a trained machine learning model;
[0010] Determining a collaborative cell of the serving cell based on a COMP feature model corresponding to the fingerprint grid;
[0011] Communicate with the target UE in cooperation with the cooperative cell.
[0012] In a second aspect, an embodiment of the present application provides a base station, comprising: a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the steps of the method described in the first aspect are implemented.
[0013] In a third aspect, an embodiment of the present application provides a readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the method described in the first aspect are implemented.
[0014] In an embodiment of the present application, the serving cell sends COMP measurement control information to the UE within the service range, wherein the COMP measurement control information includes COMP measurement conditions; receives a measurement report reported by a target UE that meets the COMP measurement conditions; determines a fingerprint grid corresponding to the target UE based on the measurement report; the fingerprint grid corresponds to at least one COMP feature model, and the COMP feature model is a trained machine learning model; determines a cooperative cell of the serving cell based on the COMP feature model corresponding to the fingerprint grid; and communicates with the target UE in cooperation with the cooperative cell. In this way, in the process of cooperative communication between the serving cell and the target UE, the fingerprint grid corresponding to the target UE is determined based on the measurement report reported by the target UE, and the cooperative cell of the serving cell is determined based on the COMP feature model corresponding to the fingerprint grid, thereby eliminating the step of the serving cell sending a measurement request to the cooperative cell in the related technology, thereby solving the problem in the related technology that the cooperative cell does not respond to the measurement request of the serving cell in a timely manner, thereby affecting the cooperative performance of COMP. BRIEF DESCRIPTION OF THE DRAWINGS
[0015] Figure 1 A schematic flow chart of a communication method based on COMP provided in an embodiment of the present application;
[0016] Figure 2 A schematic flow chart of another communication method based on COMP provided in an embodiment of the present application;
[0017] Figure 3 A schematic flow chart of another communication method based on COMP provided in an embodiment of the present application;
[0018] Figure 4 A schematic flow chart of another communication method based on COMP provided in an embodiment of the present application;
[0019] Figure 5 A schematic diagram of a cooperative cell set of a serving cell provided in an embodiment of the present application;
[0020] Figure 6 A schematic flow chart of another communication method based on COMP provided in an embodiment of the present application;
[0021] Figure 7 A schematic flow chart of another communication method based on COMP provided in an embodiment of the present application;
[0022] Figure 8 A schematic structural diagram of a base station provided in an embodiment of the present application. DETAILED DESCRIPTION
[0023] The following will be combined with the drawings in the embodiments of the present application to clearly describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments in the present application belong to the scope of protection of this application.
[0024] The terms "first", "second", etc. in the specification and claims of the present application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable under appropriate circumstances, so that the embodiments of the present application can be implemented in an order other than those illustrated or described here, and the objects distinguished by "first", "second", etc. are generally of one type, and the number of objects is not limited. For example, the first object can be one or more. In addition, "and / or" in the specification and claims represents at least one of the connected objects, and the character " / " generally indicates that the objects associated with each other are in an "or" relationship.
[0025] As described in the background technology, there is a problem in the related technology that the collaborative cell does not respond to the measurement request of the serving cell in a timely manner, which affects the collaborative performance of COMP. In the related technology, the serving cell needs to initiate a measurement request of a reference signal to the collaborative cell. However, the collaborative cell responds to the measurement request of the serving cell only when its own resources are idle, resulting in poor real-time response of the collaborative cell, which results in the measurement result fed back by the collaborative cell not being able to reflect the current channel quality of the collaborative cell in a timely manner, affecting the collaborative performance of COMP.
[0026] Based on this, an embodiment of the present application provides a communication method based on COMP, which is applied to a serving cell. During the process of collaborative communication between the serving cell and the target UE, the fingerprint grid corresponding to the target UE is determined based on the measurement report reported by the target UE, and the collaborative cell of the serving cell is determined based on the COMP feature model corresponding to the fingerprint grid, thereby eliminating the step of the serving cell sending a measurement request to the collaborative cell in the related technology, thereby solving the problem in the related technology that the collaborative cell does not respond to the measurement request of the serving cell in a timely manner, thereby affecting the collaborative performance of COMP.
[0027] In practical applications, the COMP-based communication method provided in the embodiment of the present application can be applied to wireless networks that deploy COMP functions in 5G NR (New Radio), for example, SA (Standalone), NSA (Non-Standalone), TDD-NR or FDD-NR, etc. Of course, the COMP-based communication method provided in the embodiment of the present application can also be used in other wireless networks, and the present application does not limit this.
[0028] The following is a detailed description of the COMP-based communication method provided in the embodiment of the present application through specific embodiments and their application scenarios in conjunction with the accompanying drawings.
[0029] Figure 1 A flowchart of a communication method based on COMP is provided in an embodiment of the present application.
[0030] like Figure 1 As shown, a communication method based on COMP provided in an embodiment of the present application, applied to a serving cell, may include:
[0031] Step 110: Send COMP measurement control information to UEs within the service range, where the COMP measurement control information includes COMP measurement conditions.
[0032] In an embodiment of the present application, COMP communication technology may include but is not limited to at least one of the following: COMP JR (Joint Reception) technology, COMP JT (Joint Transmission) technology, COMPCS (Coordinated Scheduling) technology, and COMP CBF (Coordinated beamforming) technology.
[0033] The COMP measurement control information may include but is not limited to at least one of the following: measurement control information corresponding to COMP JR, measurement control information corresponding to COMP JT, measurement control information corresponding to COMP CS, and measurement control information corresponding to COMP CBF.
[0034] The COMP measurement control information may include COMP measurement conditions, and a UE that meets the COMP measurement conditions may perform COMP communication. The COMP measurement conditions may also include but are not limited to at least one of the following: measurement conditions corresponding to COMP JR, measurement conditions corresponding to COMP JT, measurement conditions corresponding to COMP CS, and measurement conditions corresponding to COMP CBF.
[0035] The serving cell may send the COMP measurement control information to the UE via an air interface reconfiguration message. For example, the serving cell may send the COMP measurement control information to the UE via an SSB (Synchronization Signal and PBCH block).
[0036] The serving cell may first configure the COMP function, and then send COMP measurement control information to the UE. Afterwards, the UE that meets the COMP measurement conditions may report a measurement report to the serving cell.
[0037] Step 120: Receive a measurement report reported by a target UE that meets the COMP measurement condition.
[0038] The measurement report may include various wireless signals related to the COMP function. For example, the measurement report may include the RSRP (Reference Signal Received Power) of the serving cell and the RSRP of the neighboring cells of the serving cell.
[0039] Of course, the measurement report may also include the SSB index of the serving cell, the SSB index of the adjacent cell, the uplink power of the serving cell, the uplink TA (Timing Advance) of the serving cell, the SINR (Signal to Interference plus Noise Ratio) of the reference signal of the serving cell, and other wireless signals related to the COMP function, which are not limited in this application.
[0040] Step 130: Based on the measurement report, determine a fingerprint grid corresponding to the target UE; the fingerprint grid corresponds to at least one COMP feature model, and the COMP feature model is a trained machine learning model.
[0041] Among them, the embodiment of the present application can pre-divide the service range of the service cell into multiple fingerprint grids according to the wireless signal related to the COMP function, and the range of the wireless signal related to the COMP function in each fingerprint grid of the multiple fingerprint grids is different. Furthermore, in step 130, the embodiment of the present application can determine that the target UE falls into one of the multiple fingerprint grids according to the wireless signal related to the COMP function in the measurement report reported by the target UE, and thus determine the fingerprint grid corresponding to the target UE.
[0042] Among them, for each fingerprint grid, the embodiment of the present application can pre-train at least one COMP feature model, the COMP feature model is a trained machine learning model, and the input of the COMP feature model can include the current time point, the load information of the collaborative cell, and at least one of the channel transmission delay difference information of the serving cell and the collaborative cell, and the present application does not impose specific restrictions on this. The output of the COMP feature model can be the COMP gain size of the collaborative cell to the target UE.
[0043] Step 140: Determine the cooperative cell of the serving cell based on the COMP feature model corresponding to the fingerprint grid.
[0044] The COMP feature model can be used to predict the COMP gain of each candidate coordinated cell of the serving cell to the target UE. Furthermore, the embodiment of the present application can determine the coordinated cell of the serving cell according to the COMP gain of each candidate coordinated cell to the target UE.
[0045] Step 150: Communicate with the target UE in cooperation with the cooperative cell.
[0046] The serving cell may perform COMP communication with the target UE in cooperation with the cooperative cell by using at least one COMP communication mode among COMP JR, COMP JT, COMP CS and COMP CBF according to the pre-configured COMP function. The specific communication process is a mature technology in the art and will not be described in detail here.
[0047] It can be understood that in the related technology, after receiving the measurement report reported by the UE that meets the COMP measurement conditions, the serving cell needs to determine the collaborative cell according to the pre-configured neighboring cell relationship; send measurement requests for other reference signals such as SRS or CSI-RS to the collaborative cell, and determine the appropriate collaborative cell based on the measurement results fed back by the collaborative cell; communicate with the UE in cooperation with the appropriate collaborative cell. It should be pointed out that when the serving cell sends measurement requests for other reference signals such as SRS or CSI-RS to the collaborative cell, it will conflict with the resources of the collaborative cell. For example, the collaborative cell will respond to the measurement request of the serving cell only when its own resources are idle, resulting in poor real-time performance of the SRS measurement, which in turn causes the measurement results fed back by the collaborative cell to fail to reflect the current channel quality of the collaborative cell in a timely manner, affecting the collaborative performance of COMP.
[0048] In the embodiment of the present application, through steps 130 and 140, the fingerprint grid corresponding to the target UE is determined based on the measurement report reported by the target UE, and the collaborative cell of the serving cell is determined based on the COMP feature model corresponding to the fingerprint grid, thereby eliminating the step of the serving cell sending a measurement request for other reference signals such as SRS or CSI-RS to the collaborative cell in the related technology, simplifying the COMP collaboration process, improving the COMP collaboration efficiency and performance, and solving the problem in the related technology that the collaborative cell does not respond to the measurement request of the serving cell in a timely manner, thereby affecting the collaborative performance of COMP.
[0049] Among them, the improvement of COMP collaboration efficiency and performance may include the reduction of the response time of the target UE, the increase of the collaborative RB (Resource Block) proportion of the target UE, the increase of the number of collaborative times of the target UE, etc., and this application does not make specific restrictions.
[0050] According to the COMP-based communication method provided in the embodiment of the present application, the serving cell sends COMP measurement control information to the UE within the service range, wherein the COMP measurement control information includes COMP measurement conditions; receives a measurement report reported by the target UE that meets the COMP measurement conditions; determines the fingerprint grid corresponding to the target UE based on the measurement report; the fingerprint grid corresponds to at least one COMP feature model, and the COMP feature model is a trained machine learning model; determines the cooperative cell of the serving cell based on the COMP feature model corresponding to the fingerprint grid; and communicates with the target UE under the cooperation of the cooperative cell. In this way, in the process of cooperative communication between the serving cell and the target UE, the fingerprint grid corresponding to the target UE is determined based on the measurement report reported by the target UE, and the cooperative cell of the serving cell is determined based on the COMP feature model corresponding to the fingerprint grid, thereby eliminating the step of the serving cell sending a measurement request to the cooperative cell in the related technology, thereby solving the problem in the related technology that the cooperative cell does not respond to the measurement request of the serving cell in a timely manner and affects the cooperative performance of COMP.
[0051] The above describes the use of the COMP feature model corresponding to the fingerprint grid to predict the COMP gain size of each candidate collaborative cell of the serving cell for the target UE, and then determine the collaborative cell of the serving cell. Before using the COMP feature model, the embodiment of the present application may also include a training process of the COMP feature model. By using the historical COMP collaborative data of the serving cell, the COMP feature model is trained so that the COMP feature model can predict the COMP gain size of the collaborative cell under different time periods, different loads, and different delays, thereby improving the accuracy of the COMP feature model. The following example illustrates this.
[0052] In a specific embodiment, the communication method based on COMP provided in the embodiment of the present application further includes a training process of the COMP feature model. For example, before the fingerprint grid corresponding to the target UE is determined in the above step 130, Figure 2 As shown, the communication method based on COMP provided in the embodiment of the present application may also include:
[0053] Step 210: Divide the service range of the service cell into a plurality of fingerprint grids;
[0054] Among them, the wireless signals related to the COMP function can be used to locate the position of the UE in the service cell. The embodiment of the present application can perform AI clustering analysis on the wireless signals related to the COMP function, and divide the service range of the service cell into multiple fingerprint grids. The range of the wireless signals related to the COMP function in each fingerprint grid in the multiple fingerprint grids is different.
[0055] For example, taking the example that the wireless signal related to the COMP function includes the RSRP of the service cell and the RSRP of the neighboring cells of the service cell, the embodiment of the present application can divide the service range of the service cell into multiple fingerprint grids according to the RSRP of the service cell and the RSRP of the neighboring cells of the service cell, and the range of the RSRP of the service cell and the RSRP of the neighboring cells of the service cell in each fingerprint grid of the multiple fingerprint grids is different.
[0056] Optionally, the wireless signal related to the COMP function may also include the SSB index of the serving cell, the SSB index of the adjacent cell, the uplink power of the serving cell, the uplink TA of the serving cell, or the SINR of the reference signal of the serving cell, and other wireless signals. Furthermore, in addition to the RSRP of the serving cell and the RSRP of the adjacent cells of the serving cell, the present application may also add at least one of these optional parameters to divide the service range of the serving cell in a more fine-grained manner. For example, an embodiment of the present application may divide the service range of the serving cell into multiple fingerprint grids according to the RSRP and SSB index of the serving cell and the RSRP and SSB index of the adjacent cells of the serving cell, and the ranges of the RSRP and SSB index of the serving cell and the RSRP and SSB index of the adjacent cells of the serving cell in each of the multiple fingerprint grids are different.
[0057] Of course, the embodiment of the present application can use different types of wireless signals related to the COMP function to divide the service range of the service cell into multiple fingerprint grids according to actual needs, and the embodiment of the present application does not limit the specific division method.
[0058] After the service range of the serving cell is divided into a plurality of fingerprint grids, for each of the plurality of fingerprint grids, at least one COMP feature model corresponding to the fingerprint grid is trained in the following manner (e.g., steps 220 to 230):
[0059] Step 220: Acquire training data for model training, wherein the training data includes historical COMP cooperation data of the serving cell, and the historical COMP cooperation data includes input sample information and COMP gain information of each cooperation cell of the serving cell to the cooperation UE within the range of the fingerprint grid;
[0060] Among them, one fingerprint grid corresponds to at least one coordinated cell, and one coordinated cell corresponds to one COMP feature model.
[0061] In an embodiment of the present application, when acquiring input sample information in historical COMP collaborative data, the serving cell may directly acquire the input sample information in the communication network.
[0062] The input sample information may include at least one of time dimension information, load information of the collaborative cell, and channel transmission delay difference information between the serving cell and the collaborative cell.
[0063] Among them, the granularity of the time dimension can be minutes, hours or days. The embodiments of the present application can be set according to actual needs, and the present application does not impose any restrictions on this.
[0064] The load information of the coordinated cell includes but is not limited to PRB (Physical RB) utilization, etc. RB utilization can characterize the load of the coordinated cell, and is calculated by dividing the sum of the number of PRBs used by the control channel and the traffic channel by the total number of available PRBs.
[0065] Among them, the channel between the service cell and the cooperative cell can be understood as a transmission channel established between the service cell and the cooperative cell to realize the COMP function, and the delay difference affects the performance of the COMP function.
[0066] In an embodiment of the present application, when obtaining the COMP gain information of each cooperative cell of the service cell in the historical COMP cooperation data for the cooperative UE within the range of the fingerprint grid, it is specifically possible to obtain the COMP gain information of each cooperative cell for the cooperative UE in the process of the service cell communicating with the UE using the existing cooperative communication process.
[0067] The COMP gain information may include a large amount of COMP gain information, for example, the COMP gain size of each coordinated cell under different time periods, different loads, and different delays.
[0068] Among them, the COMP gain information is a positive gain, and the COMP gain information includes but is not limited to the SINR gain after the service signal is combined, the flow gain, etc., and this application does not impose any restrictions on this.
[0069] Among them, the existing collaborative communication process may include: Step 1: The serving cell configures the COMP function, and then the serving cell sends COMP measurement control information to the UE, and receives the measurement report reported by the UE that meets the COMP measurement conditions, wherein the COMP measurement control information may include at least one of the following: COMP JR measurement (SSB), COMP JT measurement (SSB), COMP CS / CBF measurement (SSB); Step 2: Determine the collaborative cell, and the collaborative cell is determined according to the initial cell configuration. Usually, the selection is made according to the neighboring relationship of the cell configuration and the constraints such as the number of cells restricted by the network management; Step 3: For the UE that meets the COMP conditions, a measurement request for reference signals such as SRS / CSI-RS is sent to the collaborative cell determined in step 2, and a suitable collaborative cell is determined based on the measurement result fed back by the collaborative cell (i.e., the measurement value of the reference signal); Step 4: Communicate with the collaborative UE under the cooperation of a suitable collaborative cell.
[0070] Step 230: Train the initial COMP feature model using the training data to obtain a trained COMP feature model.
[0071] The initial COMP feature model is trained by the training data to obtain a trained COMP feature model, including:
[0072] For each cooperative cell under the fingerprint grid, perform the following steps:
[0073] Using the input sample information as input of an initial COMP feature model to obtain a predicted COMP gain;
[0074] The parameters of the initial COMP feature model are adjusted according to the predicted COMP gain and the acquired COMP gain information to obtain a trained COMP feature model.
[0075] Among them, the specific training process of the COMP feature model is a mature technology in this field and will not be repeated in this application.
[0076] In this way, the embodiment of the present application can use the COMP gains of each collaborative cell under different time periods, different loads, and different delays as training data, and train to obtain the COMP feature model of each collaborative cell under each fingerprint grid, so that the trained COMP feature model can more accurately predict the collaborative cell with better COMP performance, thereby improving the accuracy of the COMP feature model.
[0077] In another specific embodiment, in the above Figure 1Based on the embodiment shown: the measurement report reported by the target UE may include: the reference signal received power RSRP of the serving cell and the RSRP of the neighboring cells of the serving cell, and then, as Figure 3 As shown, in the above step 130, determining the fingerprint grid corresponding to the target UE based on the measurement report may include:
[0078] Step 1301: based on the RSRP of the serving cell and the RSRP of the neighboring cells of the serving cell in the measurement report reported by the target UE, locate the fingerprint grid where the target UE is located from the service range of the serving cell, wherein the service range of the serving cell includes multiple fingerprint grids.
[0079] Among them, the embodiment of the present application can perform AI clustering analysis on the RSRP of the serving cell and the RSRP of the adjacent cells of the serving cell in advance, and divide the service range of the serving cell into multiple fingerprint grids, and the range of the RSRP of the serving cell and the range of the RSRP of the adjacent cells of the serving cell in each fingerprint grid of the multiple fingerprint grids are different. Furthermore, the embodiment of the present application can locate the fingerprint grid where the target UE is located from the service range of the serving cell based on the RSRP of the serving cell and the RSRP of the adjacent cells of the serving cell in the measurement report reported by the target UE.
[0080] In this way, the embodiment of the present application can locate the fingerprint grid where the target UE is located through the measurement report, which is convenient for the subsequent acquisition of the COMP feature model corresponding to the fingerprint grid where the target UE is located, and the acquired COMP feature model can accurately predict the COMP gain of the cooperative cell of the fingerprint grid where the target UE is located to the target UE.
[0081] Of course, according to different ways of pre-dividing the fingerprint grid, the present application can also determine the fingerprint grid corresponding to the target UE in other ways, and the present application does not limit this. For example, an embodiment of the present application can pre-perform AI clustering analysis on the RSRP and SSB index of the serving cell and the RSRP and SSB index of the adjacent cells of the serving cell, and divide the service range of the serving cell into multiple fingerprint grids, and the RSRP and SSB index of the serving cell and the RSRP and SSB index of the adjacent cells of the serving cell in each fingerprint grid of the multiple fingerprint grids have different ranges. Furthermore, an embodiment of the present application can locate the fingerprint grid where the target UE is located from the service range of the serving cell based on the RSRP and SSB index of the serving cell and the RSRP and SSB index of the adjacent cells of the serving cell in the measurement report reported by the target UE.
[0082] In another specific embodiment, in order to determine the coordinated cell with better COMP performance, in the above Figure 1Based on the example shown: Figure 4 As shown, in the above step 140, determining the cooperative cell of the serving cell based on the COMP feature model corresponding to the fingerprint grid includes:
[0083] Step 1401: Obtain the collaborative cell set of the serving cell.
[0084] Among them, the embodiments of the present application can adopt various methods to obtain the cooperative cell set of the service cell according to actual needs, and the present application does not limit this.
[0085] The embodiment of the present application can pre-divide multiple time periods according to the granularity of the time dimension, and pre-configure the cooperative cell set corresponding to each time period. The granularity of the time dimension can be minutes, hours or days. The embodiment of the present application can be set according to actual needs, and the present application does not limit this. For example, Figure 5 As shown, the embodiment of the present application can be pre-divided into three time periods according to the granularity of the time dimension: time period 1, time period 2 and time period 3. The embodiment of the present application can pre-configure the collaborative cell set corresponding to time period 1, the collaborative cell set corresponding to time period 2, and the collaborative cell set corresponding to time period 3 based on historical COMP collaboration data, wherein the collaborative cell sets corresponding to the three time periods are different.
[0086] In step 1401, the present application can obtain the coordinated cell set corresponding to the target time period in which the current time point falls according to the target time period in which the current time point falls, and use it as the coordinated cell set of the serving cell. Figure 5 As shown, the present application can obtain the collaborative cell set corresponding to time period 1 according to the current time point falling into time period 1, as the collaborative cell set of the serving cell.
[0087] Alternatively, in step 1401, the embodiment of the present application may take the union of the candidate cooperative cells under each fingerprint grid of the serving cell in each time period, obtain all candidate cooperative cells of the serving cell, and sort all candidate cooperative cells according to the historical COMP gain, and take the M candidate cooperative cells with the largest gain as the cooperative cell set of the serving cell. For example, Figure 5 As shown, the embodiment of the present application can take the union of the collaborative cell set corresponding to time period 1, the collaborative cell set corresponding to time period 2, and the collaborative cell set corresponding to time period 3 to obtain all candidate collaborative cells of the service cell, and sort all candidate collaborative cells according to the historical COMP gain, and take the M cells with the largest gains as the collaborative cell set of the service cell.
[0088] For example, in practical applications, in the above step 1401, obtaining the coordinated cell set of the serving cell may include:
[0089] Acquire historical COMP cooperation data, where the historical COMP cooperation data includes multiple COMP gains of each cooperation cell in all cooperation cells of the serving cell for the cooperation UE;
[0090] Determine, based on historical COMP cooperation data, an average COMP gain of each cooperative cell in all cooperative cells of the serving cell for the cooperative UE;
[0091] According to the average COMP gain of each coordinated cell in all the coordinated cells for the coordinated UE, the coordinated cells in all the coordinated cells are sorted, and the first M coordinated cells with the largest COMP gain are selected as the coordinated cell set of the serving cell.
[0092] In this way, the embodiment of the present application determines the average COMP gain based on historical COMP collaboration data, and selects the top M collaborative cells with the largest average COMP gain as the collaborative cell set of the service cell, which can ensure that the cells in the collaborative cell set of the service cell are all collaborative cells with good COMP performance, which is equivalent to an initial screening of the collaborative cells of the service cell. In subsequent steps, the candidate collaborative cells corresponding to the fingerprint grid are selected from the collaborative cell set of the service cell, and the cells with larger COMP gain are selected from the candidate collaborative cells corresponding to the fingerprint grid. Through two selections, it can be ensured that the collaborative cells with better COMP performance are selected.
[0093] Step 1402: Determine at least one candidate cooperative cell corresponding to the fingerprint grid from the cooperative cell set of the serving cell.
[0094] The candidate coordinated cells corresponding to the fingerprint grid may be pre-configured according to historical COMP coordinated data, or the candidate coordinated cells corresponding to the fingerprint grid may be determined according to a measurement report reported by the target UE.
[0095] The cooperative cell set of the serving cell may include M cells, and the candidate cooperative cells corresponding to the fingerprint grid may include K cells. In the embodiment of the present application, the intersection of the cooperative cell set of the serving cell and the candidate cooperative cells corresponding to the fingerprint grid may be taken, and at least one (for example, L, L≤M, L≤K) candidate cooperative cell corresponding to the fingerprint grid is determined from the cooperative cell set of the serving cell. M, K, and L are all positive integers.
[0096] Step 1403: predicting the COMP gain of each candidate coordinated cell in the at least one candidate coordinated cell to the target UE by using the COMP feature model corresponding to the fingerprint grid.
[0097] The at least one candidate cooperative cell corresponding to the fingerprint grid may include L cells, and correspondingly, the COMP feature models corresponding to the fingerprint grid may also include L cells. Under one fingerprint grid, each candidate cooperative cell corresponds to one COMP feature model.
[0098] Among them, for each candidate collaborative cell under a fingerprint grid, the embodiment of the present application can input at least one of the current time point, the load information of the candidate collaborative cell, and the channel transmission delay difference information between the serving cell and the candidate collaborative cell into the corresponding COMP feature model to predict the COMP gain of the candidate collaborative cell for the target UE.
[0099] Furthermore, the present application predicts the COMP gain of each candidate coordinated cell in the L candidate coordinated cells to the target UE through the L COMP feature models corresponding to the fingerprint grid.
[0100] Step 1404: Sort the candidate coordinated cells according to the predicted COMP gains, and select the first N candidate coordinated cells with the largest COMP gains as coordinated cells of the serving cell; wherein N is a positive integer.
[0101] Among them, selecting the first N candidate coordinated cells with the largest COMP gains as coordinated cells of the serving cell can ensure that a coordinated cell with better COMP performance is selected.
[0102] In this way, the embodiment of the present application predicts the COMP gain of each candidate collaborative cell in at least one candidate collaborative cell for the target UE through the COMP feature model corresponding to the fingerprint grid, and selects the top N candidate collaborative cells with the largest COMP gain as the collaborative cells of the service cell, thereby ensuring that a collaborative cell with better COMP performance is selected.
[0103] It is understandable that if Figure 4 As shown, the embodiment of the present application can first obtain the collaborative cell set of the service cell, and then select L candidate collaborative cells corresponding to the fingerprint grid from the collaborative cell set of the service cell, and predict the COMP gain of each candidate collaborative cell in the L candidate collaborative cells to the target UE through the L COMP feature models corresponding to the fingerprint grid. Compared with directly predicting the COMP gain of the K candidate collaborative cells corresponding to the fingerprint grid through the K COMP feature models corresponding to the fingerprint grid, this method can reduce the workload of predicting the COMP gain of the candidate collaborative cells to the target UE in step 1403, and ensure timely and rapid determination of the collaborative cells of the service cell.
[0104] In practical applications, when there is no intersection between the cooperative cell set of the serving cell (including M cooperative cells) and the K candidate cooperative cells corresponding to the fingerprint grid, it is difficult to determine at least one candidate cooperative cell corresponding to the fingerprint grid from the cooperative cell set of the serving cell. In this case, the serving cell of the embodiment of the present application may not perform COMP communication with the target UE, but may perform normal communication with the target UE. Alternatively, in this case, the embodiment of the present application may also use other methods to determine the cooperative cell of the serving cell.
[0105] It should be pointed out that the embodiments of the present application can determine the cooperative cell of the service cell in different ways according to actual needs, and the present application does not limit the specific method of determining the cooperative cell of the service cell.
[0106] For example, in the above step 140, determining the cooperative cell of the serving cell based on the COMP feature model corresponding to the fingerprint grid may include:
[0107] Determine K candidate coordinated cells corresponding to the fingerprint grid;
[0108] Predicting the COMP gain of each candidate coordinated cell in the K candidate coordinated cells corresponding to the fingerprint grid to the target UE through the K COMP feature models corresponding to the fingerprint grid;
[0109] According to the predicted COMP gain, the candidate coordinated cells are sorted, and the first N candidate coordinated cells with the largest COMP gain are selected as coordinated cells of the serving cell; wherein N is a positive integer.
[0110] The K candidate collaborative cells corresponding to the fingerprint grid can be understood as all candidate collaborative cells corresponding to the fingerprint grid. In this way, the embodiment of the present application can predict the COMP gain of each candidate collaborative cell in all candidate collaborative cells corresponding to the fingerprint grid to the target UE, and can also ensure that a collaborative cell with better COMP performance is selected.
[0111] In addition, in practical applications, the embodiments of the present application may also pre-set a COMP fingerprint grid collection period, and collect COMP collaboration data during the COMP fingerprint grid collection period, so as to use more COMP collaboration data to update the COMP feature model and the collaborative cell set of the serving cell. Of course, the embodiments of the present application may also collect COMP collaboration data outside the COMP fingerprint grid collection period, so as to use more COMP collaboration data to update the COMP feature model and the collaborative cell set of the serving cell.
[0112] For example, in the above Figure 1 Based on the example shown: Figure 6As shown, in the above step 140, determining the cooperative cell of the serving cell based on the COMP feature model corresponding to the fingerprint grid includes:
[0113] Step 1405: determine whether the current time point falls within the COMP fingerprint grid collection period;
[0114] Among them, the service cell can pre-set the COMP fingerprint grid collection time period. Usually, the COMP fingerprint grid collection time period is set according to the collection of Y time granularity at every X time granularity, for example, collecting 5 minutes every 15 minutes; in step 1405, it can be determined whether the current time point falls into the COMP fingerprint grid collection time period. If so, execute step 1406, otherwise, the subsequent step 710 can be executed.
[0115] Step 1406: When the current time point does not fall into the COMP fingerprint grid collection period, determine the cooperative cell of the serving cell based on the COMP feature model corresponding to the fingerprint grid.
[0116] Among them, the specific content of determining the cooperative cell of the service cell can be referred to the above embodiment, which will not be repeated here.
[0117] Accordingly, after step 150, if Figure 6 As shown, the communication method based on COMP provided in the embodiment of the present application may also include:
[0118] Step 160: During the communication between the serving cell and the target UE, measure the COMP gain of the coordinated cell to the target UE;
[0119] Step 170: Update the parameters of the COMP characteristic model based on the measured COMP gain of the coordinated cell for the target UE, and update the coordinated cell set of the serving cell.
[0120] Among them, step 160 and step 170 can be performed after step 1406.
[0121] The present application measures the COMP gain of the cooperative cell for the target UE through step 160, and can obtain more training data to facilitate the subsequent continuous updating of the COMP feature model and the adaptive configuration of the cooperative cell set of the serving cell.
[0122] Alternatively, after step 1405, when the current time point falls into the COMP fingerprint grid collection period, as Figure 7 As shown, the communication method based on COMP provided in the embodiment of the present application may also include:
[0123] Step 710: Determine a candidate coordinated cell of the serving cell based on the measurement report;
[0124] Step 720: Send a reference signal measurement request to a candidate coordinated cell, receive a measurement result returned by the candidate coordinated cell, and determine a coordinated cell of the serving cell from the candidate coordinated cells based on the measurement result;
[0125] Among them, after step 720, the embodiment of the present application can also communicate with the target UE under the cooperation of the cooperative cell.
[0126] Step 730: During the communication between the serving cell and the target UE, measure the COMP gain of the coordinated cell to the target UE;
[0127] Step 740: Update the parameters of the COMP characteristic model based on the measured COMP gain of the cooperative cell for the target cooperative UE, and update the cooperative cell set of the serving cell.
[0128] Among them, the embodiment of the present application can use the existing COMP communication process (such as step 710-step 720) to collect training data, correct, improve, and update the COMP feature model and adaptively configure the collaborative cell set of the service cell during the COMP fingerprint grid collection period.
[0129] Among them, the difference between step 740 and step 170 is that the sources of the training data used to update the model are different. In the training data used to update the model in step 170, the cooperative cell is determined by the COMP feature model, and in the training data used to update the model in step 740, the cooperative cell is determined by the serving cell sending a reference signal measurement request to the cooperative cell. The specific methods of updating the COMP feature model in steps 740 and 170 are similar, and the specific content can be referred to Figure 2 The training process of the COMP feature model in the illustrated embodiment will not be described in detail here.
[0130] In this way, the embodiment of the present application can improve the accuracy of the COMP feature model and the collaborative cell set of the serving cell by continuously collecting COMP collaboration data and using more COMP collaboration data to update the COMP feature model and the collaborative cell set of the serving cell.
[0131] In addition, based on the same concept as the COMP-based communication method provided in the embodiment of the present application, the embodiment of the present application also provides a base station applied to a service cell.
[0132] like Figure 8As shown, an embodiment of the present application provides a base station 800, which may include: a memory 810 and a processor 820, wherein the memory 810 stores a computer program, and when the computer program is executed by the processor 820, the steps of the method provided in any of the above embodiments are implemented.
[0133] Among them, the base station provided in the embodiment of the present application can execute the steps of the method provided in any of the above embodiments and can achieve the same technical effects, which will not be repeated in this application.
[0134] In addition, an embodiment of the present application further provides a readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the method provided in any of the above embodiments are implemented.
[0135] Among them, the readable storage medium provided in the embodiment of the present application can execute the steps of the method provided in any of the above embodiments and can achieve the same technical effects, which will not be repeated in this application.
[0136] It should be noted that, in this article, the terms "comprise", "include" or any other variant thereof are intended to cover non-exclusive inclusion, so that the process, method, article or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise one..." do not exclude the presence of other identical elements in the process, method, article or device including the element. In addition, it should be pointed out that the scope of the methods and devices in the embodiments of the present application is not limited to performing functions in the order shown or discussed, and may also include performing functions in a substantially simultaneous manner or in reverse order according to the functions involved, for example, the described method may be performed in an order different from that described, and various steps may also be added, omitted, or combined. In addition, the features described with reference to certain examples may be combined in other examples.
[0137] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a computer software product, which is stored in a storage medium (such as ROM / RAM, a disk, or an optical disk), and includes a number of instructions for a terminal (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present application.
[0138] The embodiments of the present application are described above in conjunction with the accompanying drawings, but the present application is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of the present application, ordinary technicians in this field can also make many forms without departing from the purpose of the present application and the scope of protection of the claims, all of which are within the protection of the present application.
Claims
1. A communication method based on coordinated multi-point COMP, characterized in that: Applied to a serving cell, the method comprises: Sending COMP measurement control information to a user equipment UE within a service range, where the COMP measurement control information includes a COMP measurement condition; Receiving a measurement report reported by a target UE that meets the COMP measurement condition; Based on the measurement report, determining a fingerprint grid corresponding to the target UE; the fingerprint grid corresponds to at least one COMP feature model, and the COMP feature model is a trained machine learning model; Determining a collaborative cell of the serving cell based on a COMP feature model corresponding to the fingerprint grid; Communicate with the target UE in cooperation with the cooperative cell.
2. The method according to claim 1, characterized in that Before determining the fingerprint grid corresponding to the target UE based on the measurement report, the method further includes: Dividing the service range of the service cell into a plurality of fingerprint grids; For each fingerprint grid of the plurality of fingerprint grids, at least one COMP feature model corresponding to the fingerprint grid is trained in the following manner: Acquire training data for model training, the training data comprising historical COMP cooperation data of a serving cell, the historical COMP cooperation data comprising input sample information and COMP gain information of each cooperation cell of the serving cell for a cooperation UE within the range of the fingerprint grid; The initial COMP feature model is trained using the training data to obtain a trained COMP feature model.
3. The method according to claim 1, characterized in that The measurement report includes a reference signal received power RSRP of a serving cell and RSRPs of cells adjacent to the serving cell, and the determining, based on the measurement report, a fingerprint grid corresponding to the target UE includes: Based on the RSRP of the serving cell and the RSRP of the neighboring cells of the serving cell in the measurement report reported by the target UE, the fingerprint grid where the target UE is located is located from the service range of the serving cell, wherein the service range of the serving cell includes multiple fingerprint grids.
4. The method according to claim 1, characterized in that: The determining, based on the COMP feature model corresponding to the fingerprint grid, a coordinated cell of the serving cell includes: Acquire a collaborative cell set of the serving cell; Determining at least one candidate cooperative cell corresponding to the fingerprint grid from the cooperative cell set of the serving cell; Predicting the COMP gain of each candidate coordinated cell in the at least one candidate coordinated cell to the target UE by using the COMP feature model corresponding to the fingerprint grid; According to the predicted COMP gain, the candidate coordinated cells are sorted, and the first N candidate coordinated cells with the largest COMP gain are selected as coordinated cells of the serving cell; wherein N is a positive integer.
5. The method according to claim 4, characterized in that The acquiring of the coordinated cell set of the serving cell comprises: Acquire historical COMP cooperation data, where the historical COMP cooperation data includes multiple COMP gains of each cooperation cell in all cooperation cells of the serving cell for the cooperation UE; Determine, based on historical COMP cooperation data, an average COMP gain of each cooperative cell in all cooperative cells of the serving cell for the cooperative UE; According to the average COMP gain of each coordinated cell in all the coordinated cells for the coordinated UE, the coordinated cells in all the coordinated cells are sorted, and the first M coordinated cells with the largest COMP gain are selected as the coordinated cell set of the serving cell.
6. The method according to claim 1, characterized in that The determining, based on the COMP feature model corresponding to the fingerprint grid, a coordinated cell of the serving cell includes: Determine whether the current time point falls into the COMP fingerprint grid collection period; When the current time point does not fall within the COMP fingerprint grid collection period, the cooperative cell of the serving cell is determined based on the COMP feature model corresponding to the fingerprint grid.
7. The method according to claim 6, characterized in that After determining the cooperative cell of the serving cell based on the COMP feature model corresponding to the fingerprint grid, the method further includes: During the communication between the serving cell and the target UE, measuring the COMP gain of the coordinated cell to the target UE; The parameters of the COMP characteristic model are updated based on the measured COMP gain of the coordinated cell for the target UE, and the coordinated cell set of the serving cell is updated.
8. The method according to claim 6, characterized in that The method further comprises: When the current time point falls within the COMP fingerprint grid collection period, perform the following steps: Determining a candidate coordinated cell of the serving cell based on the measurement report; Sending a reference signal measurement request to a candidate coordinated cell, receiving a measurement result returned by the candidate coordinated cell, and determining a coordinated cell of the serving cell from the candidate coordinated cells based on the measurement result; During the communication between the serving cell and the target UE, measuring the COMP gain of the coordinated cell to the target UE; The parameters of the COMP characteristic model are updated based on the measured COMP gain of the cooperative cell to the target cooperative UE, and the cooperative cell set of the serving cell is updated.
9. A base station, characterized in that: The base station comprises: a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the steps of the method according to any one of claims 1 to 8 are implemented.
10. A readable storage medium, characterized in that: The readable storage medium stores a computer program, which implements the steps of the method according to any one of claims 1 to 8 when executed by a processor.