Dual-connection configuration method, device, equipment, medium and product

Abstract

The invention discloses a dual-connection configuration method and device, equipment, a medium and a product. The method comprises the following steps: acquiring network energy consumption information and / or network system performance information and / or terminal performance information; and determining the configuration of the dual connectivity according to the acquired information. The scheme of the application can realize flexible adjustment of the dual-connection decision, reduce the energy consumption of the UE or the network, and improve the performance of the terminal and the network.

Description

Technical Field

[0001] This invention relates to the field of mobile communication technology, and more specifically, to a dual-connectivity configuration method, apparatus, device, medium, and product. Background Technology

[0002] For mobility optimization scenarios, 5G NR first introduces the prediction of the terminal's movement trajectory within the range of the next-hop base station in the NR single-connection scenario, and makes connection decisions based on the predicted trajectory.

[0003] Building upon single-connectivity mobility optimization, 5G NR plans to optimize terminal mobility in dual-connectivity scenarios under NR-DC. Dual-connectivity mobility optimization primarily considers combining predictions of terminal movement trajectories or location information with predictions of the amount of data transmitted by the terminal. The problem with this approach is that, although it leverages the predictive capabilities of AI technology, the criteria for determining whether a terminal needs to establish dual connectivity are relatively fixed and cannot be flexibly adjusted based on the actual situation of the terminal or network. This may not only affect terminal power consumption but also lead to wasted network energy or impact network system performance. Summary of the Invention

[0004] To address the aforementioned issues, this invention proposes a dual-connectivity configuration method, apparatus, device, medium, and product that enables flexible adjustment of dual-connectivity decisions, reduces UE or network power consumption, and improves terminal and network performance.

[0005] This invention provides a dual-connectivity configuration method, which is applied to a cell node and includes:

[0006] To obtain network energy consumption information and / or network system performance information and / or terminal performance information;

[0007] Determine the dual-connection configuration based on the information obtained.

[0008] Preferably, acquiring network energy consumption information and / or network system performance information and / or terminal performance information includes:

[0009] Based on the network energy consumption information and / or the network system performance information and / or the terminal performance information obtained by measurement or recording.

[0010] As a preferred option, obtaining network energy consumption information and / or network system performance information and / or terminal performance information includes:

[0011] The network energy consumption information and / or the network system performance information and / or the terminal performance information are generated by using a preset prediction model based on the information obtained from measurement or recording.

[0012] The network energy consumption information and / or the network system performance information and / or the terminal performance information are obtained by other nodes based on measurement or recording.

[0013] As a preferred option, obtaining network energy consumption information and / or network system performance information and / or terminal performance information includes:

[0014] Receive network energy consumption information and / or network system performance information and / or terminal performance information sent by other nodes.

[0015] As a preferred embodiment, the method further includes:

[0016] Send request information to other nodes.

[0017] As a preferred embodiment, the method further includes: receiving request information sent by other nodes, and feeding back network energy consumption information and / or network system performance information and / or terminal performance information to other nodes.

[0018] Furthermore, the request information includes first information and / or second information;

[0019] The first information is used to indicate the relevant information that other nodes need to report back to the master node;

[0020] The second piece of information is used to provide prediction-related information to other nodes.

[0021] Furthermore, the second information includes at least one of the following:

[0022] The amount of data the terminal needs to transmit;

[0023] Transmission demand time;

[0024] PSCell filtering rules, wherein the PSCell filtering rules include network load threshold and / or available resource threshold;

[0025] The first information includes at least one of the following:

[0026] First indication information used to indicate predictive information about network energy consumption;

[0027] Second indication information used to indicate network energy consumption;

[0028] Third indication information used to indicate network load prediction information;

[0029] Fourth indication information used to indicate network load;

[0030] The fifth indication information used to indicate the recommended list of cells under the target node.

[0031] As a preferred embodiment, the network energy consumption information includes energy efficiency;

[0032] The network system performance information includes system throughput and network load;

[0033] The terminal performance information includes the terminal's downlink throughput, uplink throughput, data packet latency, and packet loss rate.

[0034] As a preferred embodiment, the method further includes:

[0035] Receive network energy consumption information and / or network system performance information and / or terminal performance information sent by other nodes;

[0036] The configuration may be adjusted for performance based on the received information, or the AI / ML model that generated the configuration may be corrected based on feedback.

[0037] As a preferred embodiment, determining the dual-connection configuration based on the acquired information includes:

[0038] When there are two or more candidate SNs that meet the candidate performance requirements for a certain target terminal, the predicted network energy consumption / predicted network load of the candidate SNs are compared, and the candidate SN with the lower predicted network energy consumption / network load is selected as the target SN for dual connectivity.

[0039] As a preferred embodiment, determining the dual-connection configuration based on the acquired information includes:

[0040] When the network energy consumption of a node is measured to be no less than a preset first threshold, or the network load of a node is no less than a preset second threshold, a message to reduce the data transmission configuration of the node is sent to the terminal that has established a dual connection with the node, and / or a message to reduce the priority of the node is sent to the terminal that has established a dual connection with the node and has two or more candidate SNs.

[0041] As a preferred embodiment, determining the dual-connection configuration based on the acquired information includes:

[0042] When the predicted network energy consumption of a certain node is not less than the preset third threshold, the amount of data that the detection terminal needs to transmit is determined.

[0043] When the amount of data that the terminal needs to transmit is not less than the preset fourth threshold, the node is used as the target SN and an add / change operation is performed.

[0044] As a preferred embodiment, determining the dual-connection configuration based on the acquired information includes:

[0045] When the predicted network energy consumption of a node is not less than the preset fifth threshold, the amount of data that the terminal needs to transmit and the predicted network load are detected.

[0046] When the amount of data that the terminal needs to transmit is not less than the preset sixth threshold and the predicted network load is not greater than the preset seventh threshold, the node is used as the target SN and an add / change operation is performed.

[0047] As a preferred embodiment, determining the dual-connection configuration based on the acquired information includes:

[0048] When the measured uplink or downlink throughput of the terminal is not greater than the preset eighth threshold, the network load information and / or radio resource status information fed back by the pre-confirmed target SN will be used as the input data for training the preset AI / ML model.

[0049] This invention also provides a dual-connection configuration device, the device comprising:

[0050] The data acquisition module is used to acquire network energy consumption information and / or network system performance information and / or terminal performance information;

[0051] The configuration module is used to determine the configuration of the dual connections based on the acquired information.

[0052] Preferably, the data acquisition module is specifically used for:

[0053] Based on the network energy consumption information and / or the network system performance information and / or the terminal performance information obtained by measurement or recording.

[0054] Preferably, the data acquisition module is specifically used for:

[0055] The network energy consumption information and / or the network system performance information and / or the terminal performance information are generated by using a preset prediction model based on the information obtained from measurement or recording.

[0056] The network energy consumption information and / or the network system performance information and / or the terminal performance information are obtained by other nodes based on measurement or recording.

[0057] Preferably, the data acquisition module is specifically used for:

[0058] Receive network energy consumption information and / or network system performance information and / or terminal performance information sent by other nodes.

[0059] Preferably, the device further includes a data interaction module for:

[0060] Send request information to other nodes.

[0061] Preferably, the device further includes a data interaction module for:

[0062] It receives request information sent by other nodes and sends back network energy consumption information and / or network system performance information and / or terminal performance information to other nodes.

[0063] Preferably, the request information includes first information and / or second information;

[0064] The first information is used to indicate the relevant information that other nodes need to report back to the master node;

[0065] The second piece of information is used to provide prediction-related information to other nodes.

[0066] Furthermore,

[0067] The amount of data the terminal needs to transmit;

[0068] Transmission demand time;

[0069] PSCell filtering rules, wherein the PSCell filtering rules include network load threshold and / or available resource threshold;

[0070] The first information includes at least one of the following:

[0071] First indication information used to indicate predictive information about network energy consumption;

[0072] Second indication information used to indicate network energy consumption;

[0073] Third indication information used to indicate network load prediction information;

[0074] Fourth indication information used to indicate network load;

[0075] The fifth indication information is used to indicate the recommended list of cells under the target node.

[0076] Preferably, the network energy consumption information includes energy efficiency;

[0077] The network system performance information includes system throughput and network load;

[0078] The terminal performance information includes the terminal's downlink throughput, uplink throughput, data packet latency, and packet loss rate.

[0079] Preferably, the device further includes a calibration module for:

[0080] Receive network energy consumption information and / or network system performance information and / or terminal performance information sent by other nodes;

[0081] The configuration may be adjusted for performance based on the received information, or the AI / ML model that generated the configuration may be corrected based on feedback.

[0082] Preferably, the configuration module is specifically used for:

[0083] When there are two or more candidate SNs that meet the candidate performance requirements for a certain target terminal, the predicted network energy consumption / predicted network load of the candidate SNs are compared, and the candidate SN with the lower predicted network energy consumption / network load is selected as the target SN for dual connectivity.

[0084] Preferably, the configuration module is specifically used for:

[0085] When the network energy consumption of a node is measured to be no less than a preset first threshold, or the network load of a node is no less than a preset second threshold, a message to reduce the data transmission configuration of the node is sent to the terminal that has established a dual connection with the node, and / or a message to reduce the priority of the node is sent to the terminal that has established a dual connection with the node and has two or more candidate SNs.

[0086] Preferably, the configuration module is specifically used for:

[0087] When the predicted network energy consumption of a certain node is not less than the preset third threshold, the amount of data that the detection terminal needs to transmit is determined.

[0088] When the amount of data that the terminal needs to transmit is not less than the preset fourth threshold, the node is used as the target SN and an add / change operation is performed.

[0089] Preferably, the configuration module is specifically used for:

[0090] When the predicted network energy consumption of a node is not less than the preset fifth threshold, the amount of data that the terminal needs to transmit and the predicted network load are detected.

[0091] When the amount of data that the terminal needs to transmit is not less than the preset sixth threshold and the predicted network load is not greater than the preset seventh threshold, the node is used as the target SN and an add / change operation is performed.

[0092] Preferably, the configuration module is specifically used for:

[0093] When the measured uplink or downlink throughput of the terminal is not greater than the preset eighth threshold, the network load information and / or radio resource status information fed back by the pre-confirmed target SN will be used as the input data for training the preset AI / ML model.

[0094] This invention also provides a communication device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor executes the computer program to implement the dual-connection configuration method as described in any of the above embodiments.

[0095] This invention also provides a computer-readable storage medium, which includes a stored computer program, wherein the computer program, when running, controls the device where the computer-readable storage medium is located to execute the dual-connection configuration method as described in any of the above embodiments.

[0096] This invention also provides a computer program product, including a computer program / instructions that, when executed by a processor, implement the steps of any of the methods described above.

[0097] This invention provides a dual-connectivity configuration method, apparatus, device, medium, and product. The method is applied to a cell node and involves acquiring network energy consumption information and / or network system performance information and / or terminal performance information; based on the acquired information, a dual-connectivity configuration is determined. This solution enables flexible adjustment of dual-connectivity decisions, reduces UE or network energy consumption, and improves terminal and network performance. Attached Figure Description

[0098] Figure 1 This is a flowchart illustrating the dual-connection configuration method provided in an embodiment of the present invention;

[0099] Figure 2 This is a schematic diagram of the AI / ML model calculation configuration provided in an embodiment of the present invention;

[0100] Figure 3 This is a schematic diagram of the structure of a dual-connection configuration device provided in an embodiment of the present invention;

[0101] Figure 4 This is a schematic diagram of the structure of a communication device provided in an embodiment of the present invention. Detailed Implementation

[0102] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0103] 5G networks require continuous optimization of key performance indicators (KPIs), such as latency, reliability, connection density, user experience, and energy efficiency. AI / ML (Artificial Intelligence (AI) / Machine Learning (ML) extracts features from massive amounts of data in complex scenarios and trains and derives models to enable prediction and corresponding decisions regarding measurements, important events, and network resource status. This helps operators improve network performance and optimize user experience.

[0104] For mobility optimization scenarios, 5G NR first introduces UE movement trajectory prediction within the next-hop base station range in NR single-connectivity scenarios. Specifically, a source node with AI / ML capabilities uses an AI / ML model to predict the movement trajectory of a specific UE. The source node then sends the predicted trajectory to the target node, which can directly use this prediction information to reserve transmission resources in advance. On the other hand, to continuously iterate and update the AI / ML model, the source node also needs to obtain real terminal movement trajectories from the target node as feedback. These real trajectory trajectories can be used to monitor the performance of the AI / ML model output, allowing for timely optimization and continuous improvement of the AI / ML model's prediction and decision-making performance.

[0105] The 5G NR plan includes UE mobility optimization in NR-DC scenarios with dual connectivity. Currently, network decisions on whether to establish dual connectivity for a particular terminal primarily consider the amount of data the terminal needs to transmit. AI-based dual connectivity mobility optimization, on the other hand, mainly considers the prediction of the terminal's movement trajectory or location information, as well as the predicted amount of data the terminal needs to transmit, to determine whether dual connectivity is necessary. When predicting the combination of PCell and PSCell, it mainly relies on whether network resources and scheduling can meet the terminal's data transmission requirements. The problem with this approach is that although it utilizes the predictive capabilities of AI technology, the criteria for determining whether a terminal needs to establish dual connectivity are relatively fixed and cannot be flexibly adjusted based on the actual situation of the terminal and the network. This may not only affect terminal power consumption but also lead to wasted network energy or impact network system performance.

[0106] To address the aforementioned technical issues, this paper provides a dual-connectivity configuration method, which is applied to a cell node. (See [link to relevant documentation]). Figure 1 This is a flowchart illustrating a dual-connection configuration method provided in an embodiment of the present invention. The method includes:

[0107] Step S1: Obtain network energy consumption information and / or network system performance information and / or terminal performance information;

[0108] Step S2: Determine the dual-connection configuration based on the obtained information.

[0109] In this specific implementation, the master node MN obtains network energy consumption information and / or network system performance information and / or terminal performance-related information. This information can be used to assist the MN in making relevant decisions in dual-connectivity scenarios (such as NR-DC).

[0110] It should be noted that this invention is applied to cell nodes, which can be primary or secondary nodes. In specific implementations, it can be applied to the original primary node, the original secondary node, or the target primary or secondary node during handover. In this embodiment, the specific implementation process of the scheme is illustrated using the primary node MN; in other embodiments, the scheme can be applied to other cell nodes.

[0111] It should be noted that this decision-making process can be based on inference from traditional non-AI methods, or it can be based on prediction / decision information output by AI / ML model inference.

[0112] When making decisions related to dual-connectivity scenarios, AI / ML models can be used for decision calculation.

[0113] See Figure 2 This is a flowchart illustrating the AI / ML model computation configuration provided in an embodiment of the present invention. The specific process is as follows:

[0114] AI / ML models include the following functional units:

[0115] The data collection unit provides input data for the model training unit and the model inference unit.

[0116] Input data includes measurement data from user terminals and different network elements, feedback data from the Actor module, and output data from AI / ML models. It only provides the raw data and does not need to perform different data preparations (data cleaning, data formatting, data transformation, etc.) for different AI / ML algorithms.

[0117] The Model Training unit is responsible for training, testing, and validating AI / ML models, and generating performance metrics for the models. Its specific functions include:

[0118] Data preparation involves organizing the training data provided by the Data Collection unit, including data cleaning, data formatting, and data transformation.

[0119] Model Deployment / Update: Deploys trained, tested, and validated AI / ML models to the model inference unit.

[0120] The Model Inference unit provides the inference output of the AI / ML model, i.e., to make predictions or decisions, and can also provide performance feedback results to the model training unit to verify the performance of the AI / ML model.

[0121] The model inference unit also has a data preparation function: it organizes the inference data provided by the data acquisition unit, including data cleaning, data formatting, and data conversion.

[0122] The execution unit receives the inference output, i.e., prediction or decision, from the model inference unit and initiates the corresponding action.

[0123] The results fed back to the data acquisition unit can be used for AI / ML model training, inference, or performance testing.

[0124] Mobility optimization is one of the typical scenarios combining 5G and AI technologies. It uses data collection and AI technology to predict the UE's movement trajectory (i.e., target node / cell) and mobility management-related measurements over a future period of time, thereby assisting the network in making cell handover decisions and reserving resources in advance.

[0125] It should be noted that when calculating specific dual-connection configurations, AI / ML models can be pre-trained based on different types of data. That is, the model can be trained based on a combination of network energy consumption information and / or network system performance information and / or terminal performance information, and one or more of these can be selected as model input parameters to determine the model output results.

[0126] When performing inferences in a non-AI manner, the steps to be executed under different performance parameter conditions can be pre-planned based on a pre-established performance parameter and decision matching database. The operation instructions can be matched based on real-time information to determine the configuration and perform dual-connection control.

[0127] This application establishes a judgment mechanism for UE dual connectivity or SN change operations by combining factors such as network energy consumption, system performance, or terminal performance. This mechanism ensures the robustness of UE movement in MR-DC scenarios and allows for more flexible and reasonable selection of the target secondary node SN or primary / secondary cell PSCell for the UE. It enables AI technology to better assist the network in making dual connectivity-related decisions and effectively avoids energy and resource waste of nodes.

[0128] In another embodiment of the present invention, the process of obtaining network energy consumption information and / or network system performance information and / or terminal performance information specifically includes:

[0129] Data obtained through measurement or recording, namely network energy consumption information, network system performance information, and terminal performance information, can be current and historical information obtained through measurement.

[0130] It should be noted that historical and current data indicate different detection intervals. When the detection interval is short, the measurement data used each time configuration is performed may be historical data, which has a certain time interval from the current time. When the detection cycle is short, real-time detection data can be directly used as measurement data, and the current data has strong real-time characteristics.

[0131] Furthermore, the choice between real-time and historical data depends on the data volume requirements. Historical data can utilize a large amount of data over a past period, and the average value of the data can be used to reduce errors, but it cannot reflect real-time changes in network performance. Real-time data, on the other hand, only uses currently detected data, with a smaller data volume, but the data has high real-time accuracy and can reflect the real-time network performance.

[0132] Different data acquisition schemes can be selected based on different needs, thereby expanding the scope of application of the schemes.

[0133] In another embodiment of the present invention, the process of obtaining network energy consumption information and / or network system performance information and / or terminal performance information specifically includes:

[0134] Information obtained through measurement or recording is used to predict a future period / moment.

[0135] That is, the network energy consumption information and / or the network system performance information and / or the terminal performance information are generated by using a preset prediction model.

[0136] When predicting information for a future period based on a predictive model, a model building and training process is required beforehand. During model building and training, historical data is collected and used to determine the correspondence between the predicted data and the historical data. This allows for the generation of network energy consumption information and / or network system performance information and / or terminal performance information based on historical information.

[0137] It should be noted that, when making predictions, different types of performance information are predicted separately, so that the required network energy consumption information and / or network system performance information and / or terminal performance information can be determined based on historical information.

[0138] In another embodiment of the present invention, the process of obtaining network energy consumption information and / or network system performance information and / or terminal performance information specifically includes:

[0139] Receive information from other nodes, such as neighboring nodes, potential target SNs, target SNs, etc., predicted for a future time period / moment, and / or current and historical information obtained through measurement.

[0140] Specifically, the network energy consumption information and / or the network system performance information and / or the terminal performance information sent by other nodes can be actively sent by other nodes to the master node MM, or they can be sent by other nodes to the master node MN based on a request from the master node MN.

[0141] In another embodiment provided by the present invention, the method further includes:

[0142] Sending request information to other nodes means that the master node MN actively sends a request to other nodes to receive information, so that the other nodes can send back the corresponding information to the master node MN based on the request.

[0143] Furthermore, the method also includes the master node sending back information to other nodes based on requests from other nodes, specifically:

[0144] Receive request information sent by other nodes, and send back the requested network energy consumption information and / or network system performance information and / or terminal performance information to other nodes.

[0145] In another embodiment of the present invention, the master node MN requests and receives information related to network energy consumption, network system performance and terminal performance from other nodes. The request information includes first information and / or second information.

[0146] The first information is used to indicate the relevant information that other nodes need to report to the master node MN; the second information is used to provide other nodes with information related to the prediction, and other nodes can use the second information as input information for AI prediction.

[0147] It should be noted that there is no requirement for the order of sending the first and second messages, and the two messages can be sent in the same message (e.g., different IEs in the same message) or in different messages.

[0148] In another embodiment provided by the present invention, the first information may include one or more of the following:

[0149] The first indication information is used to indicate the predicted network energy consumption;

[0150] The second indication information is used to indicate the measured / actual network energy consumption;

[0151] The third indication information is used to indicate the predicted network load.

[0152] The fourth indication information is used to indicate the measured / actual network load; the fifth indication information is used to indicate the recommended list of cells under the target node.

[0153] It should be noted that the recommended cell list indicated in the fifth instruction may include only one cell, or it may include a list of multiple different cells. Based on this instruction, other nodes can provide feedback on one or more cells that are preferred as PScells.

[0154] The required forecast information, combined with the required forecast time, can indicate the relevant forecast information at a certain point in the future.

[0155] The second information includes one or more of the following:

[0156] The data volume / UE traffic that the terminal needs to transmit can be represented as the total amount of data that the UE is expected to transmit (i.e., the amount of data transmitted together by MN and SN), or it can be represented as the amount of data that is expected to be transmitted by SN.

[0157] The moment when the UE is expected to have a large data transmission requirement is the moment when the conditions for establishing dual connections are met.

[0158] PSCell filtering rules, which include network load thresholds and / or available resource thresholds.

[0159] PSCells are filtered according to the indicated rules, using at least one of the network load threshold or available resource threshold values ​​as the filtering rules.

[0160] In another embodiment of the present invention, the obtained network energy consumption information includes energy efficiency.

[0161] Energy efficiency refers to the energy consumption required to transmit a unit of data; it can also be characterized by energy-related indicators, representing the mapping relationship with specific energy consumption values.

[0162] Network system performance information may include, but is not limited to, system throughput and network load.

[0163] Terminal performance information includes, but is not limited to, UE downlink throughput, UE uplink throughput, data packet latency, and packet loss rate.

[0164] By accurately reflecting the network status of the network and terminals through energy efficiency, throughput, network load, latency, and packet loss rate, the dual-connectivity decision / judgment method is adjusted in combination with the actual situation of the terminals and the network. While ensuring the data transmission needs and mobility robustness of the terminals, it also takes into account the network energy consumption and network load and other related network indicator requirements.

[0165] In another embodiment provided by the present invention, the method further includes:

[0166] After generating prediction information and / or measuring / collecting the true values ​​of relevant information, other nodes send corresponding feedback information to the master node MN; the process by which other nodes measure / collect the true values ​​of relevant information is as follows:

[0167] This occurs before the master node MN forms a dual-connection decision, i.e., the relevant feedback information serves as input information for the master node MN decision or the AI / ML module; and / or:

[0168] After the UE establishes a dual connection with other nodes (at this time, the target SN), the measured / collected real values ​​are used as a reference for the configuration adjustment of the master node MN, or as input information for the performance verification of the AI / ML module, to perform feedback correction on the AI / ML model.

[0169] Before and after configuration generation, information uploaded by other nodes is received to ensure real-time updates and verification of the configuration, thereby improving the accuracy of configuration generation.

[0170] In another embodiment of the present invention, after the master node MN obtains information related to network energy consumption, network system performance, and terminal performance, it uses this information to make judgments / decision-making regarding dual-connection related operations, specifically including:

[0171] When there are two or more candidate SNs that meet the candidate performance requirements for a certain target terminal, the predicted network energy consumption / predicted network load of the candidate SNs are compared, and the candidate SN with the lower predicted network energy consumption / network load is selected as the target SN for dual connectivity.

[0172] Specifically: If there are two or more candidate SNs for a certain terminal, the master node MN can further compare the predicted network energy consumption of each candidate target SN, or the MN can further compare the predicted network load of each candidate target SN.

[0173] The node with the lower predicted network energy consumption or the node with the lower predicted network load is selected as the target SN to establish dual connections for the terminal.

[0174] In another embodiment provided by the present invention, when determining the dual-connection configuration in step S2, the following steps are specifically performed:

[0175] When the network energy consumption of a node is measured to be no less than the preset first threshold, or the network load of a node is no less than the preset second threshold, the master node MN can trigger operations such as SN change for certain terminals that have established dual connections (e.g., there are other candidate target SNs) that meet the conditions, thereby reducing the number of users connected to the node and the data transmission.

[0176] When the network energy consumption of a node is measured to be no less than the preset first threshold, or the network load of a node is no less than the preset second threshold, the master node MN can prioritize certain terminals with two or more candidate target SNs as target SNs.

[0177] It should be noted that the threshold value can be set according to the actual situation, either pre-configured by the network or directly defined by the protocol.

[0178] In another embodiment provided by the present invention, when determining the dual-connection configuration in step S2, the following steps are specifically performed:

[0179] When the predicted network energy consumption of a node is not less than the preset third threshold, it indicates that the network energy consumption of that node is already high.

[0180] At this point, the amount of data the terminal needs to transmit is detected. If the amount of data the terminal needs to transmit is not less than the preset fourth threshold, it indicates that the UE needs to transmit a large amount of data through dual connections. The master node MN sets this node as the target SN and performs operations such as SNaddition (MN-initiated), MN-initiated / SN-initiated SN change, etc.

[0181] Otherwise, when the amount of data that the terminal needs to transmit is less than the fourth threshold value, the master node MN will not configure the target SN for the UE.

[0182] It should be noted that the threshold value can be set according to the actual situation, either pre-configured by the network or directly defined by the protocol.

[0183] In another embodiment provided by the present invention, when determining the dual-connection configuration in step S2, the following steps are specifically performed:

[0184] When the predicted network energy consumption of a node is not less than the preset fifth threshold, the amount of data that the terminal needs to transmit and the predicted network load are detected. The master node MN only adds or changes the target SN when the amount of data that the terminal needs to transmit is large and the predicted network load is low.

[0185] When the amount of data that the terminal needs to transmit is not less than the preset sixth threshold and the predicted network load is not greater than the preset seventh threshold, the node is taken as the target SN and operations such as SN addition (MN-initiated), MN-initiated / SN-initiated SN change are performed.

[0186] Otherwise, when the amount of data that the terminal needs to transmit is less than the fourth threshold value, the master node MN will not configure the target SN for the UE.

[0187] It should be noted that the threshold value can be set according to the actual situation, either pre-configured by the network or directly defined by the protocol.

[0188] In another embodiment provided by the present invention, when determining the dual-connection configuration in step S2, the following steps are specifically performed:

[0189] When the measured uplink or downlink throughput of the terminal is not greater than the preset eighth threshold, that is, the uplink / downlink throughput of the UE after dual-connectivity transmission does not reach the predicted effect, it indicates that the available resources or scheduling of the target SN cannot complete the data transmission of the UE in a short time. Then, the measured / real network load and / or radio resource status information fed back by the target SN is further combined as input data for AI / ML model retraining. The purpose is to reduce the priority of the node with the network load and / or radio resource status as the target SN in the subsequent dual-connectivity decision / prediction.

[0190] This case fully considers factors such as network energy consumption, system performance, and terminal performance. While ensuring the data transmission needs and mobility robustness of the terminal, it also considers the network indicator requirements such as network energy consumption and network load. The judgment mechanism for UE dual connectivity or SN change operations, which combines factors such as network energy consumption, system performance, and terminal performance, allows for more flexible and reasonable selection of the target secondary node SN or primary and secondary cell PSCell for the UE in order to ensure the robustness of UE mobility in MR-DC scenarios. This enables AI technology to better assist the network in making dual connectivity-related decisions and effectively avoids energy and resource waste of nodes.

[0191] See Figure 3 This is another structural schematic diagram of a dual-connection configuration device provided in an embodiment of the present invention, the device comprising:

[0192] The data acquisition module is used to acquire network energy consumption information and / or network system performance information and / or terminal performance information;

[0193] The configuration module is used to determine the dual-connection configuration based on the acquired information.

[0194] The dual-connection configuration device provided in this embodiment can execute all the steps and functions of the dual-connection configuration method provided in any of the above embodiments. The specific functions of the device will not be described in detail here.

[0195] See Figure 4 This is a schematic diagram of a communication device provided in an embodiment of the present invention. The communication device includes a processor, a memory, and a computer program stored in the memory and executable on the processor, such as a dual-connection configuration program. When the processor executes the computer program, it implements the steps in each of the above-described dual-connection configuration method embodiments, for example... Figure 1 The steps S1 to S2 are shown. Alternatively, when the processor executes the computer program, it implements the functions of each module in the above-described device embodiments.

[0196] For example, the computer program can be divided into one or more modules, which are stored in the memory and executed by the processor to complete the present invention. The one or more modules can be a series of computer program instruction segments capable of performing specific functions, which describe the execution process of the computer program in the dual-connection configuration device. For example, the computer program can be divided into several modules, the specific functions of which have been described in detail in the dual-connection configuration method provided in any of the above embodiments; therefore, the specific functions of the device will not be repeated here.

[0197] The communication device described can be a desktop computer, laptop, handheld computer, or cloud server, etc. The communication device may include, but is not limited to, a processor and memory. Those skilled in the art will understand that the schematic diagram is merely an example of a communication device and does not constitute a limitation on a dual-connection configuration device. It may include more or fewer components than illustrated, or combine certain components, or use different components. For example, the communication device may also include input / output devices, network access devices, buses, etc.

[0198] The processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor. The processor is the control center of the dual-connectivity configuration device, connecting all parts of the dual-connectivity configuration device via various interfaces and lines.

[0199] The memory can be used to store the computer programs and / or modules. The processor implements various functions of the dual-connection configuration device by running or executing the computer programs and / or modules stored in the memory and by calling data stored in the memory. The memory may mainly include a program storage area and a data storage area. The program storage area may store the operating system, at least one application program required for a function (such as sound playback function, image playback function, etc.), etc.; the data storage area may store data created according to the use of the mobile phone (such as audio data, phonebook, etc.). In addition, the memory may include high-speed random access memory, and may also include non-volatile memory, such as hard disk, memory, plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, at least one disk storage device, flash memory device, or other volatile solid-state storage device.

[0200] If the module integrated in the dual-connection configuration device is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the above embodiments of the present invention can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium, etc.

[0201] This invention also provides a computer program product, including a computer program / instruction, which, when executed by a processor, implements the steps of the functional network element implementing the method described in the above embodiments.

[0202] The computer program product provided in this embodiment can execute all the steps and functions of the dual-connection configuration method provided in any of the above embodiments. The specific functions of the product will not be described in detail here.

[0203] It should be noted that those skilled in the art can make various improvements and modifications without departing from the principles of this invention, and these improvements and modifications are also considered to be within the scope of protection of this invention.

Claims

1. A dual-connection configuration method, characterized in that, The method is applied to a cell node, and the method includes: To obtain network energy consumption information and / or network system performance information and / or terminal performance information; Determine the dual-connection configuration based on the information obtained.

2. The dual-connection configuration method according to claim 1, characterized in that, Obtain network energy consumption information and / or network system performance information and / or terminal performance information, including: Based on the network energy consumption information and / or the network system performance information and / or the terminal performance information obtained by measurement or recording.

3. The dual-connection configuration method according to claim 1, characterized in that, Obtain network energy consumption information and / or network system performance information and / or terminal performance information, including: The network energy consumption information and / or the network system performance information and / or the terminal performance information are generated by using a preset prediction model based on the information obtained from measurement or recording.

4. The dual-connection configuration method according to claim 1, characterized in that, Obtain network energy consumption information and / or network system performance information and / or terminal performance information, including: Receive network energy consumption information and / or network system performance information and / or terminal performance information sent by other nodes; The network energy consumption information and / or the network system performance information and / or the terminal performance information are obtained by other nodes based on measurement or recording.

5. The dual-connection configuration method according to claim 1, characterized in that, The method further includes: Send request information to other nodes; The request information includes first information and / or second information; The first information is used to indicate the relevant information that other nodes need to report back to the master node; The second piece of information is used to provide prediction-related information to other nodes.

6. The dual-connection configuration method according to claim 1, characterized in that, The method further includes: receiving request information sent by other nodes, and feeding back network energy consumption information and / or network system performance information and / or terminal performance information to other nodes.

7. The dual-connection configuration method according to claim 5, characterized in that, The second information includes at least one of the following: The amount of data the terminal needs to transmit; Transmission demand time; PSCell filtering rules, wherein the PSCell filtering rules include network load threshold and / or available resource threshold; The first information includes at least one of the following: First indication information used to indicate predictive information about network energy consumption; Second indication information used to indicate network energy consumption; Third indication information used to indicate network load prediction information; Fourth indication information used to indicate network load; The fifth indication information is used to indicate the recommended list of cells under the target node.

8. The dual-connection configuration method according to claim 1, characterized in that, The network energy consumption information includes energy efficiency; The network system performance information includes system throughput and network load; The terminal performance information includes the terminal's downlink throughput, uplink throughput, data packet latency, and packet loss rate.

9. The dual-connection configuration method according to claim 1, characterized in that, The method further includes: Receive network energy consumption information and / or network system performance information and / or terminal performance information sent by other nodes; The configuration may be adjusted for performance based on the received information, or the AI / ML model that generated the configuration may be corrected based on feedback.

10. The dual-connection configuration method according to claim 1, characterized in that, Determining the dual-connection configuration based on the acquired information includes: When there are two or more candidate SNs that meet the candidate performance requirements for a certain target terminal, the predicted network energy consumption / predicted network load of the candidate SNs are compared, and the candidate SN with the lower predicted network energy consumption / network load is selected as the target SN for dual connectivity.

11. The dual-connection configuration method according to claim 1, characterized in that, Determining the dual-connection configuration based on the acquired information includes: When the network energy consumption of a node is measured to be no less than a preset first threshold, or the network load of a node is no less than a preset second threshold, a message to reduce the data transmission configuration of the node is sent to the terminal that has established a dual connection with the node, and / or a message to reduce the priority of the node is sent to the terminal that has established a dual connection with the node and has two or more candidate SNs.

12. The dual-connection configuration method according to claim 1, characterized in that, Determining the dual-connection configuration based on the acquired information includes: When the predicted network energy consumption of a certain node is not less than the preset third threshold, the amount of data that the detection terminal needs to transmit is determined. When the amount of data that the terminal needs to transmit is not less than the preset fourth threshold, the node is used as the target SN and an add / change operation is performed.

13. The dual-connection configuration method according to claim 1, characterized in that, Determining the dual-connection configuration based on the acquired information includes: When the predicted network energy consumption of a node is not less than the preset fifth threshold, the amount of data that the terminal needs to transmit and the predicted network load are detected. When the amount of data that the terminal needs to transmit is not less than the preset sixth threshold and the predicted network load is not greater than the preset seventh threshold, the node is used as the target SN and an add / change operation is performed.

14. The dual-connection configuration method according to claim 1, characterized in that, Determining the dual-connection configuration based on the acquired information includes: When the measured uplink or downlink throughput of the terminal is not greater than the preset eighth threshold, the network load information and / or radio resource status information fed back by the pre-confirmed target SN will be used as the input data for training the preset AI / ML model.

15. A dual-connection configuration device, characterized in that, The device includes: The data acquisition module is used to acquire network energy consumption information and / or network system performance information and / or terminal performance information; The configuration module is used to determine the configuration of the dual connections based on the acquired information.

16. A communication device, characterized in that, It includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor, when executing the computer program, implements the dual-connection configuration method as described in any one of claims 1 to 14.

17. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored computer program, wherein, when the computer program is executed, it controls the device on which the computer-readable storage medium resides to perform the dual-connection configuration method as described in any one of claims 1 to 14.

18. A computer program product comprising a computer program / instructions, characterized in that, When the computer program / instructions are executed by the processor, they implement the steps of the method described in any one of claims 1 to 14.

Images