Method and apparatus for carrier aggregation optimization

Abstract

The present invention relates to a method for configuring carrier aggregation for a current user equipment (14) in a wireless communication network located in a coverage area of ​​a base station, wherein the base station is capable of transmitting multiple carrier components using multiple transmission beams for each carrier component, the method comprising: acquiring a quality metric beam from a database (16) including quality metrics associated with carrier components in the multiple carrier components and with user equipment in the multiple user equipment; using the quality metrics to determine one or more candidate carrier components to be configured or deconfigured as auxiliary carrier components for the current user equipment; and configuring or deconfiguring the one or more carrier components.

Description

Technical Field

[0001] Various example embodiments relate to methods and apparatus for carrier aggregation optimization, and in particular to methods and apparatus for configuring carrier aggregation for users in a mobile communication system based on multiple carrier components using multiple beams per carrier component. Background Art

[0002] This section introduces aspects that may help facilitate a better understanding of the present disclosure. Therefore, the statements in this section should be read in this light and should not be construed as an admission of what exists or does not exist in the prior art.

[0003] Carrier aggregation is extremely important in modern mobile communication systems, where very high bit rate communications can be achieved by aggregating multiple carrier components at different center frequencies and by transmitting the aggregated carrier components simultaneously in both downlink and uplink.

[0004] The process of adding or removing one or more secondary carrier components is called carrier aggregation configuration. The classic way to select these secondary carrier components for carrier aggregation configuration is either through blind configuration or through measurement reports, as mentioned in 3GPP TS38.331. Specifically, when the adjacent secondary carrier component deviates better than the current secondary carrier component of the user equipment, the A6 measurement report as described in 3GPP Release 10 is triggered. In this case, the user equipment performs intra-frequency or inter-frequency measurements on the adjacent secondary carrier component, and the base station releases the current secondary carrier component after receiving the A6 measurement report and starts the process for adding the adjacent secondary carrier component reported in the measurement report. These methods require measurements on the secondary carrier components and frequent overhead on the uplink. These methods consume unnecessary battery of the user equipment and increase network latency.

[0005] Therefore, there is a need for a method that can perform carrier aggregation configuration with reduced overhead and improved latency. Summary of the invention

[0006] In some example embodiments, the present disclosure provides a method for configuring carrier aggregation for a current user equipment in a wireless communication network located in a coverage area of ​​a base station, the base station being capable of transmitting multiple carrier components using multiple transmission beams per carrier component, the method comprising:

[0007] obtaining one or more quality metrics from a lookup table, the lookup table comprising a quality metric for each of a plurality of carrier components for each of a plurality of locations of a user equipment in a plurality of user equipments;

[0008] Estimate the current user device location, and

[0009] One or more candidate carrier components that meet a quality metric threshold are selected based on the location of the current user equipment and the lookup table.

[0010] In an embodiment, if the candidate component carrier meets a predefined criterion, then the candidate component carrier is to be configured, otherwise the candidate component carrier is to be deconfigured.

[0011] In some example embodiments, such a method may also include one or more of the following features.

[0012] In a first example embodiment, the database comprises a lookup table comprising a quality metric for each of a plurality of carrier components or a subset thereof for each of a plurality of locations of a user equipment in a plurality of user equipments. In this embodiment, the determination of the one or more candidate carrier components comprises:

[0013] Estimate the current user device location, and

[0014] One or more candidate carrier components that meet a quality metric threshold are selected based on the location of the current user equipment and the lookup table.

[0015] In an embodiment, the method comprises the step of determining said quality metric for a carrier component or each carrier component in a plurality of carrier components or a subset thereof. For example, the quality metric for a carrier component in a plurality of carrier components for a location of a user equipment in a plurality of user equipments is an arithmetic mean of radio measurements of a plurality of transmission beams at the location of the user equipment.

[0016] The look-up table may also include the average number of carrier components per user equipment for each location included in the database or a subset thereof.

[0017] In some example embodiments, the present disclosure provides a method for configuring carrier aggregation for a current user equipment in a wireless communication network located in a coverage area of ​​a base station, the base station being capable of transmitting multiple carrier components using multiple transmission beams per carrier component, the method comprising:

[0018] obtaining one or more feature vectors from a database comprising a plurality of feature vectors, each feature vector comprising a radio measurement of a transmission beam associated with a respective one of a plurality of carrier components,

[0019] collecting radio measurements of a transmission beam of a predefined primary carrier component of the current user equipment, and

[0020] generating a current feature vector for a current user equipment, the current feature vector comprising radio measurements of a transmission beam of a primary carrier component,

[0021] Determine one or more candidate carrier components to be configured or deconfigured as secondary carrier components for the current user equipment using one or more feature vectors obtained from the database;

[0022] One or more candidate component carriers are configured or deconfigured.

[0023] In an embodiment, if the candidate component carrier meets a predefined criterion, then the candidate component carrier is to be configured, otherwise the candidate component carrier is to be deconfigured.

[0024] In some example embodiments, such a method may also include one or more of the following features.

[0025] In an embodiment, the determination of one or more candidate carrier components may include selecting one or more closest feature vectors among the feature vectors obtained from the database using a distance criterion. Specifically, the distance between the current feature vector and each closest feature vector may be required to be lower than a predefined distance threshold. Such a distance may be a Euclidean distance.

[0026] Alternatively, a lookup table associating the average number of carrier components to each of the multiple positions of the user equipment in the multiple user equipments may be provided, and the average number of carrier components metric is determined based on a database. In this case, the determination of one or more candidate carrier components may also include:

[0027] Estimate the location of the user device,

[0028] The number of candidate carrier components is selected based on the position of the current user equipment and the lookup table. For example, the lookup table associates an average number of carrier components to each of a plurality of positions of the current user equipment, and the average number of carrier components is selected as the number of candidate carrier components. The average number may be determined based on the database.

[0029] In an embodiment, the determination of one or more candidate carrier components may include:

[0030] One or more candidate carrier components for the current user equipment are selected using the current feature vector and a predefined carrier aggregation model.

[0031] Preferably, the carrier aggregation model provides one or more candidate carrier components when the current feature vector is given. Specifically, the carrier aggregation model is a trained neural network, and the training of the neural network is performed based on a database.

[0032] In an embodiment, each feature vector of the database further comprises the location of the radio measurement of the transmission beam, and the current feature vector further comprises the location of the current user equipment.

[0033] In an embodiment, the quality metric is an average reference signal received power or an average reference signal received quality or a value of a cumulative density function.

[0034] In an embodiment, the database includes a number of radio measurements of transmission beams higher than a predefined number. Specifically, the predefined number is a percentage of the total number of radio measurements of the transmission beams to the multiple transmission beams for all multiple carrier components. In other words, the predefined number may define a reliability level that the data set of radio measurements must achieve in order to be used for carrier aggregation configuration.

[0035] In an example embodiment, the present disclosure also provides a computer program comprising executable code that, when executed, causes a computer to perform the steps of such a method.

[0036] In some example embodiments, the present disclosure further provides an apparatus for configuring carrier aggregation for a current user equipment in a wireless communication network located in a coverage area of ​​a base station, wherein the base station is capable of transmitting multiple carrier components using multiple transmission beams for each carrier component, the apparatus comprising a component for performing the following operations:

[0037] obtaining one or more feature vectors from a database (16) comprising a plurality of feature vectors, each feature vector comprising a radio measurement of a transmission beam associated with a respective one of a plurality of carrier components,

[0038] collecting radio measurements of a transmission beam of a predefined primary carrier component of the current user equipment, and

[0039] generating a current feature vector for a current user equipment, the current feature vector comprising radio measurements of a transmission beam of a primary carrier component,

[0040] Using one or more feature vectors obtained from a database (16), determining one or more candidate component carriers to be configured or deconfigured as secondary component carriers for a current user equipment;

[0041] The one or more candidate carrier components are configured or deconfigured.

[0042] In some example embodiments, the present disclosure further provides an apparatus for configuring carrier aggregation for a current user equipment in a wireless communication network located in a coverage area of ​​a base station, the base station being capable of transmitting multiple carrier components using multiple transmission beams per carrier component, the apparatus comprising a component for performing the following operations:

[0043] obtaining one or more quality metrics from a lookup table, the lookup table comprising a quality metric for each of a plurality of carrier components for each of a plurality of locations of a user equipment in a plurality of user equipments;

[0044] Estimate the current user device location, and

[0045] selecting one or more candidate carrier components that meet a quality metric threshold based on a current user equipment location and a lookup table,

[0046] The one or more carrier components are configured or deconfigured.

[0047] In an embodiment, if the candidate component carrier meets a predefined criterion, then the candidate component carrier is to be configured, otherwise the candidate component carrier is to be deconfigured.

[0048] In an embodiment, the apparatus comprises a storage medium for storing said database.

[0049] In some example embodiments, the present disclosure further provides an apparatus for configuring carrier aggregation for a current user equipment in a wireless communication network located in a coverage area of ​​a base station, wherein the base station is capable of transmitting multiple carrier components using multiple transmission beams of each carrier component, the apparatus comprising:

[0050] at least one processor; and

[0051] at least one memory including computer program code,

[0052] The at least one memory and the computer program code are configured to, with the at least one processor, cause the apparatus to at least perform:

[0053] obtaining a quality metric from a database stored in at least one memory comprising quality metrics associated with the or each carrier component in a plurality of carrier components and with the or each user equipment in a plurality of user equipment;

[0054] using the quality metric to determine one or more candidate component carriers to be configured or deconfigured as secondary component carriers for the current user equipment;

[0055] The one or more carrier components are configured or deconfigured. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] These and other aspects of the invention will be apparent from and elucidated with reference to the exemplary embodiments described hereinafter, by way of example, with reference to the drawings.

[0057] Figure 1 A mobile communication system in which a method and apparatus for configuring carrier aggregation using multiple beams per carrier component may be implemented is illustrated.

[0058] Figure 2 It is a functional representation of a device for configuring carrier aggregation for a current user equipment.

[0059] Figure 3 According to the first exemplary embodiment, Figure 2 An iterative process for configuring carrier aggregation performed by a device.

[0060] Figure 4 According to the second exemplary embodiment, Figure 2 An iterative process for configuring carrier aggregation performed by a device.

[0061] Figure 5 According to the third exemplary embodiment, Figure 2 An iterative process for configuring carrier aggregation performed by a device.

[0062] Figure 6 is a functional diagram of a programmed computer in which an example embodiment of the invention may be implemented. DETAILED DESCRIPTION

[0063] Embodiments of an apparatus and method for configuring carrier aggregation will now be described. Carrier aggregation configuration includes identifying a set of configured carrier components for each user equipment. Once the carrier components are configured, the network can decide which carrier components to activate. On the other hand, deconfiguration includes removing carrier components from an established list for configured carrier components. Conventionally, carrier component configuration / deconfiguration is based on radio measurements reported by user equipment on different carrier components or it is done blindly. However, radio measurements require signaling overhead in order to measure and report quality metrics of different carrier components for each user (knowing that the number of configured carrier components can be up to 16 for a given user equipment in a 5G-based network) as well as additional latency.

[0064] The proposed method and apparatus utilize a database comprising radio information reported by user devices using radio frequency fingerprinting (RF fingerprinting) to reduce overhead and latency, especially in 5G-based networks. RF fingerprinting uses properties of radio transmissions to identify the wireless device that transmits the radio transmissions.

[0065] An example of a communication system for configuring carrier aggregation is provided in Figure 1 In this example, base station 1 communicates with user equipment 2 via four carrier components pCC, sCC1, sCC2, and sCC3. One of the carrier components pCC is designated as a primary carrier component, while the other carrier components sCC1, sCC2, and sCC3 are designated as secondary carrier components. Base station 1 is a node based on a 5G communication network and is capable of transmitting multiple transmission beams for each carrier component.

[0066] Figure 2An apparatus 10 is shown for configuring carrier aggregation for a current user equipment 14 in a wireless communication network located in a coverage area of ​​a base station 1. The base station 1 is capable of transmitting multiple carrier components pCC, sCC1, sCC2, sCC3 using multiple transmission beams per carrier component using beamforming methods known in the art. The apparatus 10 includes a controller 12, which can receive radio measurements from the current user equipment 14. Specifically, the base station 1 receives radio measurements from the current user equipment 14 and sends the radio measurement transmission to the controller 12.

[0067] The device 10 also includes a database 16 in communication with the controller 12 .

[0068] In particular, the controller 12 is arranged to estimate the location of the current user equipment 14. The controller 12 may be arranged to receive the location of the current user equipment 14 from a location management function comprised in the wireless communication network.

[0069] The controller 12 performs carrier aggregation configuration using the received radio measurements and / or the estimated position of the current user equipment 14. For example, the controller 12 may use the database 16 and the received radio measurements and / or the estimated position of the current user equipment 14 to select one or more candidate carrier components to be configured or deconfigured as secondary carrier components for the current user equipment.

[0070] If the one or more candidate component carriers meet the quality metric threshold, then the one or more candidate component carriers are to be configured. Otherwise, the one or more candidate component carriers are to be deconfigured.

[0071] In an example embodiment, the database 16 includes radio measurements of a transmission beam associated with a carrier component in the plurality of carrier components and a user equipment in the plurality of user equipments. The radio measurements of the transmission beams may be related to a reference signal received power (RSRP) or a reference signal received quality (RSRQ) as reported by the user equipment for an identified coupling (CC, beam) of a carrier component in the plurality of carrier components and a transmission beam in the plurality of transmission beams.

[0072] In an example embodiment, the database 16 also stores the location of each of the plurality of user equipments. Specifically, the location of the user equipment is obtained upon request by a location management function of the network or by a trigger on a minimum drive test as introduced in 3GPP Release 10.

[0073] In an example embodiment, the database 16 also stores the average number of component carriers configured per user equipment at a given location.

[0074] The database 16 may be constructed by collecting radio measurements of the transmission beams in an online process. The construction of the database 16 may be performed by the base station 1 or any other entity of the communication network such as an xRAN controller. In particular, data elements of the database such as position and / or radio measurements are collected whenever the data elements are available for a user equipment of the plurality of user equipments.

[0075] The apparatus 10 is intended to run the method for carrier aggregation configuration / deconfiguration in real time.The database 16 and / or the controller 12 may be located at the base station level or close to the base station 1, at the edge cloud or at a wireless intelligent controller (RIC).

[0076] A method 100 for configuring carrier aggregation according to a first exemplary embodiment is depicted in FIG. Figure 3 The method 100 comprises the following steps:

[0077] Step 102: Estimate the position of the current user equipment 14 located in or entering the coverage area of ​​the base station 1,

[0078] Step 104: Selecting one or more candidate carrier components from a lookup table stored in the database 16 in response to determining that the or each candidate carrier component satisfies the quality metric threshold based on the estimated position.

[0079] Step 106: Configure or deconfigure one or more carrier components as auxiliary carrier components for the current user equipment 14. In step 102, the position of the current user equipment 14 can be estimated using conventional positioning methods, such as using observed time difference of arrival (OTDOA) or using a global navigation satellite system (GNSS). Alternatively, the position of the current user equipment 14 can be estimated based on radio measurements (such as RSRP) of the current user equipment 14 using a machine learning method. Such a method is described in "J. Yan, L. Zhao, J. Tang, Y. Chen, R. Chen and L. Chen's "Hybrid Kernel Based Machine Learning Using Received Signal Strength Measurements for Indoor Localization" (IEEE Transactions on Vehicular Technology, vol. 67, no. 3, pp. 2824-2829, March 2018)".

[0080] The lookup table includes a quality metric for each of the multiple carrier components for each of the multiple locations of the user equipment in the multiple user equipments. Specifically, the quality metric is calculated using the RSRP measurement for the transmission beam of the given carrier component at the given location included in the database 16. For example, such a quality metric can be determined using the following formula:

[0081]

[0082] in is the quality metric of carrier component i at position (x, y), RSRP j(x，y) is the RSRP measurement for transmit beam j of carrier component i at position (x,y), and J is the total number of transmit beams reported at position (x,y). Normalization is used to obtain a quality metric in the region between 0 and 1, and it is achieved using the minimum and maximum possible values ​​of the beam RSRP measurements on all carrier components.

[0083] In an alternative embodiment, the quality metric is a cumulative density function, such as 5% of all reporting beams on each carrier component.

[0084] The lookup table may also include the average number of carrier components per user equipment configured at each location.

[0085] In step 106, a carrier component will be a candidate to be configured if its quality metric is above a threshold. The same carrier component will become a candidate to be deconfigured / released if its quality metric is below a threshold. The average number of carrier components gives an indication of how many carrier components may have to be configured.

[0086] The method 100 may further comprise the step of updating the look-up table and the database 16 using the radio measurements of the current user equipment.

[0087] The method 100 provides the advantage of allowing carrier aggregation to be performed with a reduced number of radio measurements reported by current user equipment 14, thus reducing latency in the communication network.

[0088] A method 200 for configuring carrier aggregation according to a second exemplary embodiment is depicted in FIG. Figure 4 The method 200 comprises the following steps:

[0089] Step 202: collecting radio measurements of a transmission beam of a predefined primary carrier component of the current user equipment 14,

[0090] Step 204: Generate a current feature vector for the current user equipment, the current feature vector comprising radio measurements of the transmission beam of the primary carrier component,

[0091] Step 206: Select one or more closest feature vectors from the database 16,

[0092] Step 208: Select one or more candidate carrier components for the current user equipment 14 based on the closest feature vector,

[0093] Step 210: configure or deconfigure one or more carrier components as secondary carrier components.

[0094] Preferably, the database 16 comprises a plurality of feature vectors, wherein each feature vector comprises radio measurements of a transmission beam associated with a respective carrier component of the plurality of carrier components.

[0095] In step 202 , radio measurements such as RSRP are collected for each transmission beam on the primary carrier component of the current user equipment 14 .

[0096] Example current feature vectors are described in Table 1 below.

[0097] CC ID Location Beam 1 Beam 2 Beam 3 Beam 4 … N <![CDATA[x n ,and n ]]> -55 -46 -60 -49 …

[0098] As shown in Table 1, the current feature vector includes the identity of the primary carrier component (CC ID) and the RSRP for each transmission beam (beam 1, beam 2, beam 3, beam 4, etc.). The current feature vector may include the location (x n ,y n ).

[0099] In an embodiment, the Euclidean distance between the current feature vector and each remaining feature vector is calculated. When the distance is below a predefined distance threshold, the remaining feature vector is selected as the closest feature vector. Specifically, step 206 can be performed using a K nearest neighbor algorithm. In fact, in step 206, the distance between the current feature vector and each feature vector included in the database 16 is calculated.

[0100] In step 208, one or more closest candidate carrier components associated with the closest eigenvectors are selected. Step 208 also includes selecting one or more candidate carrier components to be configured from the closest candidate carrier components in response to determining that the or each candidate carrier component meets the quality metric threshold. The actual configuration is performed in step 210.

[0101] In an embodiment, the look-up table is provided based on the database 16 and comprises the positions of the current user equipments of a plurality of current users associated with the average number of carrier components per user equipment.

[0102] In step 208, if the location of the current user equipment 14 is available, the average number 'm' is retrieved from the look-up table. Then, 'm' carrier components are selected from the carrier components associated with the 'm' closest eigenvectors.

[0103] Step 210 may be similar to Figure 1 Step 106.

[0104] The method 200 provides the advantage of determining the secondary carrier component to be configured / deconfigured based only on radio measurements of the transmission beam on the primary carrier component. Therefore, no additional measurements are required. The method 200 allows the delay of the communication network to be reduced. In fact, an estimation of the position of the user equipment is not required every time, which leads to an optimized result taking into account the position of the user equipment (when it is available).

[0105] A method 300 for configuring carrier aggregation according to a third exemplary embodiment is depicted in FIG. Figure 5 The method 300 comprises the following steps:

[0106] Step 302: collecting radio measurements of a transmission beam of a predefined primary carrier component of the current user equipment 14,

[0107] Step 304: Generate a current feature vector for the current user equipment, the current feature vector comprising radio measurements of the transmission beam of the primary carrier component,

[0108] Step 306: Select one or more candidate carrier components for the current user equipment 14 based on the current feature vector and the predefined carrier aggregation model.

[0109] Step 308: configure or deconfigure one or more carrier components as secondary carrier components.

[0110] Step 302 and step 304 can be performed with Figure 4 Step 202 and step 204 are performed in a similar manner.

[0111] In an exemplary embodiment, the database 16 comprises a plurality of feature vectors, wherein each feature vector comprises radio measurements of a transmission beam associated with a respective one of the plurality of carrier components.

[0112] Preferably, the carrier aggregation model is a trained neural network that provides one or more candidate carrier components given the current feature vector. Specifically, the carrier aggregation model can be a classic feedforward network / multilayer perceptron neural network, such as a deep neural network (DNN) trained on the database 16. The training can be performed on radio measurements of the transmission beams collected in the database 16, which maps the input (i.e., feature vectors) to outputs (i.e., one or more candidate carrier components) defined by their identification to be configured or deconfigured.

[0113] The training of the neural network is performed using a known method (back-propagation) and aims to estimate the weights of the neural network so as to minimize the loss (eg root mean square) between the provided output and the predicted output of the neural network.

[0114] In an embodiment, the training is performed offline. It can be implemented on top of the radio access network, for example at the edge cloud.

[0115] Step 308 may be similar to Figure 1 Step 106.

[0116] In an example embodiment, the method 100, 200 or 300 includes the step of determining a confidence level for the database 16. For example, the confidence level is obtained as follows:

[0117]

[0118] where δ RFCAM is the confidence level, n f is the number of radio measurements included in the database 16, and n total is the total number of possible radio measurements for multiple carrier components and transmit beams.

[0119] If the confidence level is below a predefined threshold, the method 100 , 200 or 300 may include the step of selecting one or more candidate component carriers using conventional methods such as blind configuration or A6 measurement reporting as described in 3GPP Release 10.

[0120] Figure 6 A functional diagram of a programmed computer, server, circuit system or device 600 that can be used for the purpose of implementing the above described method is shown. The computer 600 has a core and several peripherals connected via a communication bus. The main components of the core are a microprocessor 601 (often referred to as a CPU), a random access memory (RAM) 602, and a read-only memory (ROM) 603. The peripherals include devices that allow information to be input to the system from a user, output to a user, and stored and retrieved (mass storage devices such as hard disks 604 and network interfaces 605).

[0121] The present invention is not limited to the described exemplary embodiments. The following claims should be interpreted to reflect all modifications and alternative constructions that may be made by one skilled in the art and that fairly fall within the basic teaching as set forth herein.

[0122] The use of the verb "comprise" or "include" and its conjugations does not exclude the presence of elements or steps other than those stated in the claims. In addition, the use of the word "a" or "an" preceding an element or step does not exclude the presence of a plurality of such elements or steps. Example embodiments may be implemented by means of hardware as well as software. The same item of hardware may represent several "components".

[0123] In the claims, any reference signs placed between parentheses shall not be construed as limiting the scope of the claims.

Claims

1. A method for configuring carrier aggregation for a current user equipment (14) in a wireless communication network located in a coverage area of ​​a base station (1), the base station being capable of transmitting multiple carrier components using multiple transmission beams per carrier component, the method comprising: obtaining one or more feature vectors from a database (16) comprising a plurality of feature vectors, each feature vector comprising a radio measurement of the transmission beam associated with a respective carrier component of the plurality of carrier components, collecting (202, 302) radio measurements of the transmission beam of a predefined primary carrier component of the current user equipment, and generating (204, 304) a current eigenvector for the current user equipment, the current eigenvector comprising radio measurements of the transmission beam of the primary carrier component, Determine one or more candidate carrier components to be configured or deconfigured as secondary carrier components for the current user equipment using the one or more feature vectors obtained from the database (16) and a current feature vector; configuring or deconfiguring (210, 308) the one or more candidate carrier components, If the candidate carrier component meets a predefined criterion, then the candidate carrier component is to be configured, otherwise the candidate carrier component is to be deconfigured.

2. The method of claim 1 , wherein the determining of one or more candidate carrier components comprises: One or more closest feature vectors are selected among the feature vectors retrieved from the database (16), wherein the distance between the current feature vector and each closest feature vector is below a predefined distance threshold.

3. The method of claim 2, wherein the determining of one or more candidate carrier components further comprises: One or more candidate carrier components associated with the or each closest eigenvector and satisfying a quality metric threshold are selected.

4. The method of claim 2, wherein the determining of one or more candidate carrier components further comprises: estimating a location of the user equipment, selecting a number of candidate carrier components based on the location of the current user equipment and a lookup table, The lookup table associates an average number of carrier components to each of a plurality of positions of the current user equipment, wherein the average number of carrier components is selected as the number of the candidate carrier components.

5. The method according to claim 4, wherein the average number of carrier components is determined based on the database (16).

6. The method of claim 1 , wherein the determining of one or more candidate component carriers comprises: One or more candidate component carriers for the current user equipment are selected (306) using the current eigenvector and a predefined carrier aggregation model, wherein the carrier aggregation model provides the one or more candidate component carriers as a function of the current eigenvector. 7 . The method of claim 6 , wherein the carrier aggregation model is a trained neural network, wherein the training of the neural network is performed based on the database.

8. The method according to any one of claims 1 to 7, wherein each feature vector of the database further comprises the location of the radio measurements of the transmission beam, and the current feature vector further comprises the location of the current user equipment.

9. The method according to any of claims 1 to 8, wherein the database comprises a number of radio measurements of transmission beams higher than a predefined number.

10. The method according to claim 3, wherein the quality metric is an average reference signal received power or an average reference signal received quality or a value of a cumulative density function.

11. An apparatus (10, 600) for configuring carrier aggregation for a current user equipment (14) in a wireless communication network located in a coverage area of ​​a base station, the base station being capable of transmitting multiple carrier components using multiple transmission beams per carrier component, the apparatus comprising means for performing the following operations: obtaining one or more feature vectors from a database (16) comprising a plurality of feature vectors, each feature vector comprising a radio measurement of the transmission beam associated with a respective carrier component of the plurality of carrier components, collecting radio measurements of the transmission beam of a predefined primary carrier component of the current user equipment, and generating a current feature vector for the current user equipment, the current feature vector comprising radio measurements of the transmission beam of the primary carrier component, Determine one or more candidate carrier components to be configured or deconfigured as secondary carrier components for the current user equipment using the one or more feature vectors obtained from the database (16) and a current feature vector; The one or more candidate carrier components are configured or deconfigured, wherein if the candidate carrier component meets a predefined criterion, the candidate carrier component is to be configured, otherwise the candidate carrier component is to be deconfigured.

Images