Adaptive modulation and coding method, network equipment, network element and storage medium

Abstract

An adaptive modulation coding method, a network device, a network element and a storage medium, the method comprising: the network device grouping base stations based on a similarity algorithm of base station feature information under the condition of determining that the base stations in a jurisdiction area satisfy a trigger condition of an intelligent AMC algorithm based on federated learning; determining federated learning model network elements corresponding to each group of base stations; the federated learning model network element is triggered to execute a life cycle process, the life cycle process is used for obtaining an intelligent AMC algorithm model, and all the base stations in the same group share one intelligent AMC algorithm model. According to the embodiment, rich data resources of different devices can be collected, and the accuracy, generalization and other performance of the model are improved; a plurality of base stations in the federated learning model network element perform model training at the same time, so that the time for constructing the model is saved; a base station grouping rule is utilized to obtain a federated training global model suitable for the base station group for reasoning prediction, so that the computing power is saved, and the performance gain brought by an intelligent algorithm is obtained.

Description

Technical Field

[0001] The present application relates to the field of mobile communication technology, and in particular to an adaptive modulation and coding method, network equipment, network element and storage medium. Background Art

[0002] In 4G Long Term Evolution (LTE) and 5G New Radio (NR) wireless communication systems, Adaptive Modulation and Coding (AMC) technology is usually used to cope with the time-varying characteristics of wireless channels to ensure the transmission quality of wireless links. AMC is a technology that adaptively adjusts the modulation mode and coding rate of wireless link transmission according to the changes in the wireless channel: when the channel quality is poor, a lower-order Modulation and Coding Scheme (MCS) is selected, and when the channel quality is good, a higher-order MCS is selected, thereby maximizing the transmission efficiency of the wireless link while ensuring the reliability of the wireless link transmission.

[0003] The traditional AMC solution cannot accurately predict the channel quality at the time of future uplink data transmission. When the channel environment fluctuates greatly, it will lead to problems such as high network bit error rate and reduced throughput performance. Therefore, it may not be possible to select a suitable MCS. Summary of the invention

[0004] At least one embodiment of the present application provides an adaptive modulation and coding method, a network device, a network element and a storage medium, which are used to solve the problem that the AMC scheme cannot select a suitable MCS.

[0005] In order to solve the above technical problems, this application is implemented as follows:

[0006] In a first aspect, an embodiment of the present application provides an adaptive modulation and coding method, applied to a network device, including:

[0007] When the network device determines that the base stations in the jurisdiction meet the triggering conditions of the intelligent adaptive modulation and coding AMC algorithm based on federated learning, the network device groups the base stations based on the similarity algorithm of the base station feature information;

[0008] Determine the federated learning model network element corresponding to each group of base stations;

[0009] The federated learning model network element is triggered to execute a life cycle process, where the life cycle process is used to obtain an intelligent AMC algorithm model, and all base stations in the same group share one intelligent AMC algorithm model.

[0010] Optionally, the method further includes:

[0011] Receiving performance information of the intelligent AMC algorithm model sent by the base station;

[0012] Performing a performance evaluation on the intelligent AMC algorithm model according to the performance information;

[0013] The similarity threshold in the similarity algorithm is adjusted according to the performance evaluation result.

[0014] Optionally, the determining that the base stations within the jurisdiction meet the triggering condition of the intelligent adaptive modulation and coding AMC algorithm based on federated learning includes the following:

[0015] Receiving first indication information sent by a base station within a jurisdiction, where the first indication information is used to indicate that the base station meets a trigger condition of an intelligent AMC algorithm based on federated learning;

[0016] Receive network performance indicators and / or second indication information sent by base stations within the jurisdiction; determine whether the base station meets the triggering conditions of the intelligent AMC algorithm based on federated learning based on the network performance indicators and / or the second indication information; the second indication information is used to indicate that the base station meets the first condition.

[0017] Optionally, the trigger condition includes at least one of the following:

[0018] The network performance indicators of base stations within the jurisdiction do not meet the user's quality of service (QoS) requirements;

[0019] The base stations within the jurisdiction meet the first condition;

[0020] The first condition includes at least one of the following:

[0021] The computing power of base stations cannot support artificial intelligence (AI) model training;

[0022] Base station power consumption cannot support AI model training;

[0023] The prediction accuracy of the base station AI model training is lower than the first threshold;

[0024] The training convergence time of the base station AI model does not meet the user QoS requirements;

[0025] Using federated learning has performance gains over non-federated learning.

[0026] Optionally, grouping the base stations by using a similarity algorithm based on base station feature information includes:

[0027] According to the characteristic information of each base station, the similarity of characteristic information between different base stations is calculated;

[0028] The base stations are grouped according to the feature information similarity and a preset similarity threshold.

[0029] Optionally, the feature information includes at least one of the following:

[0030] Base station hardware information;

[0031] Configuration information of the base station;

[0032] Base station user information;

[0033] Wireless channel environment information of the base station;

[0034] Input features of the base station’s intelligent algorithm;

[0035] Output characteristics of the base station’s intelligent algorithm;

[0036] Model expression of the intelligent algorithm of the base station.

[0037] Optionally, determining the federated learning model network element corresponding to each group of base stations includes at least one of the following:

[0038] For a group of base stations, determining a local model training node of the group of base stations according to computing resources of the base stations in the group and / or similarity of feature information between the base stations;

[0039] For a group of base stations, a global model aggregation node of the group of base stations is determined based on the computing power resources of the base stations in the group and / or the connection resources between the base stations in the group and the local model training nodes. The global model aggregation node is a base station in the group of base stations, or a network device.

[0040] Optionally, the local model training node satisfies a second condition, and the second condition includes at least one of the following:

[0041] Computing resources can meet the needs of AI intelligent algorithms;

[0042] The characteristic information of the base station is a second threshold value of all data information of the group of base stations.

[0043] Optionally, the global model aggregation node satisfies a third condition, and the third condition includes at least one of the following:

[0044] The computing resources can meet the demand for computing resources when aggregating and / or updating model parameter information;

[0045] The connection resources can meet the latency requirements for aggregating and / or sending model parameter information;

[0046] Meet the synchronization requirements of sending different model parameter information to the base station.

[0047] Optionally, the triggering of the federated learning model network element to execute a lifecycle process includes:

[0048] Send third indication information to the federated learning model network element, where the third indication information is used to instruct the federated learning model network element to execute a life cycle process.

[0049] Optionally, performing performance evaluation on the intelligent AMC algorithm model according to the performance information includes:

[0050] Evaluate the AI ​​model performance indicators of the intelligent AMC algorithm model according to the performance information;

[0051] The AI ​​model performance indicator includes at least one of the following:

[0052] The accuracy of model training;

[0053] Data distribution coverage;

[0054] Convergence time of model training;

[0055] Generalizability;

[0056] robustness;

[0057] Energy consumption.

[0058] Optionally, performing performance evaluation on the intelligent AMC algorithm model according to the performance information includes:

[0059] Evaluate the AMC algorithm performance index of the intelligent AMC algorithm model according to the performance information;

[0060] The AMC algorithm performance index includes at least one of the following:

[0061] Throughput;

[0062] Communication reliability;

[0063] Delay;

[0064] Initial Block Error Rate (IBLER).

[0065] In a second aspect, an embodiment of the present application provides an adaptive modulation and coding method, which is applied to a federated learning model network element, including:

[0066] The federated learning model network element executes the lifecycle process to obtain the intelligent AMC algorithm model;

[0067] The intelligent AMC algorithm model is sent to a group of base stations corresponding to the federated learning model network element.

[0068] Optionally, the federated learning model network element includes: a local model training node and a global model aggregation node;

[0069] The execution life cycle process to obtain the intelligent AMC algorithm model includes:

[0070] The local model training node downloads the initial model file from the global model aggregation node;

[0071] The local model training node performs local model training according to local data and the initial model file to obtain updated model information;

[0072] The local model training node sends the updated model information to the global model aggregation node;

[0073] The global model aggregation node integrates the updated model information sent by all local model training nodes to obtain the intelligent AMC algorithm model.

[0074] Optionally, the method further includes:

[0075] Receive third indication information sent by the network device, where the third indication information is used to instruct the federated learning model network element to execute a life cycle process.

[0076] In a third aspect, an embodiment of the present application provides a network device, including a transceiver and a processor, wherein:

[0077] The processor is configured to group the base stations based on a similarity algorithm of base station feature information when it is determined that the base stations within the jurisdiction meet the triggering conditions of the intelligent adaptive modulation and coding AMC algorithm based on federated learning;

[0078] Determine the federated learning model network element corresponding to each group of base stations;

[0079] The federated learning model network element is triggered to execute a life cycle process, where the life cycle process is used to obtain an intelligent AMC algorithm model, and all base stations in the same group share one intelligent AMC algorithm model.

[0080] Optionally, the transceiver is used to: receive performance information of the intelligent AMC algorithm model sent by the base station;

[0081] The processor is further configured to: perform a performance evaluation on the intelligent AMC algorithm model according to the performance information; and adjust a similarity threshold in the similarity algorithm according to the performance evaluation result.

[0082] Optionally, the processor determines that the base station within the jurisdiction meets the triggering condition of the intelligent adaptive modulation and coding AMC algorithm based on federated learning, including the following:

[0083] Receiving first indication information sent by a base station within a jurisdiction, where the first indication information is used to indicate that the base station meets a trigger condition of an intelligent AMC algorithm based on federated learning;

[0084] Receive network performance indicators and / or second indication information sent by base stations within the jurisdiction; determine whether the base station meets the triggering conditions of the intelligent AMC algorithm based on federated learning based on the network performance indicators and / or the second indication information; the second indication information is used to indicate that the base station meets the first condition.

[0085] Optionally, the trigger condition includes at least one of the following:

[0086] The network performance indicators of base stations within the jurisdiction do not meet the user QoS requirements;

[0087] The base stations within the jurisdiction meet the first condition;

[0088] The first condition includes at least one of the following:

[0089] The computing power of the base station cannot support AI model training;

[0090] Base station power consumption cannot support AI model training;

[0091] The prediction accuracy of the base station AI model training is lower than the first threshold;

[0092] The training convergence time of the base station AI model does not meet the user QoS requirements;

[0093] Using federated learning has performance gains over non-federated learning.

[0094] Optionally, the processor groups the base stations based on a similarity algorithm of base station feature information, including:

[0095] According to the characteristic information of each base station, the similarity of characteristic information between different base stations is calculated;

[0096] The base stations are grouped according to the feature information similarity and a preset similarity threshold.

[0097] Optionally, the feature information includes at least one of the following:

[0098] Base station hardware information;

[0099] Configuration information of the base station;

[0100] Base station user information;

[0101] Wireless channel environment information of the base station;

[0102] Input features of the base station’s intelligent algorithm;

[0103] Output characteristics of the base station’s intelligent algorithm;

[0104] Model expression of the intelligent algorithm of the base station.

[0105] Optionally, the processor determines the federated learning model network element corresponding to each group of base stations, including at least one of the following:

[0106] For a group of base stations, determining a local model training node of the group of base stations according to computing resources of the base stations in the group and / or similarity of feature information between the base stations;

[0107] For a group of base stations, a global model aggregation node of the group of base stations is determined based on the computing power resources of the base stations in the group and / or the connection resources between the base stations in the group and the local model training nodes. The global model aggregation node is a base station in the group of base stations, or a network device.

[0108] Optionally, the local model training node satisfies a second condition, and the second condition includes at least one of the following:

[0109] Computing resources can meet the needs of AI intelligent algorithms;

[0110] The characteristic information of the base station is a second threshold value of all data information of the group of base stations.

[0111] Optionally, the global model aggregation node satisfies a third condition, and the third condition includes at least one of the following:

[0112] The computing resources can meet the demand for computing resources when aggregating and / or updating model parameter information;

[0113] The connection resources can meet the latency requirements for aggregating and / or sending model parameter information;

[0114] Meet the synchronization requirements of sending different model parameter information to the base station.

[0115] Optionally, the processor triggers the federated learning model network element to execute a lifecycle process, including:

[0116] Send third indication information to the federated learning model network element, where the third indication information is used to instruct the federated learning model network element to execute a life cycle process.

[0117] Optionally, the processor performs performance evaluation on the intelligent AMC algorithm model according to the performance information, including:

[0118] Evaluate the AI ​​model performance indicators of the intelligent AMC algorithm model according to the performance information;

[0119] The AI ​​model performance indicator includes at least one of the following:

[0120] The accuracy of model training;

[0121] Data distribution coverage;

[0122] Convergence time of model training;

[0123] Generalizability;

[0124] robustness;

[0125] Energy consumption.

[0126] Optionally, the processor performs performance evaluation on the intelligent AMC algorithm model according to the performance information, including:

[0127] Evaluate the AMC algorithm performance index of the intelligent AMC algorithm model according to the performance information;

[0128] The AMC algorithm performance index includes at least one of the following:

[0129] Throughput;

[0130] Communication reliability;

[0131] Delay;

[0132] IBLER.

[0133] In a fourth aspect, an embodiment of the present application provides a federated learning model network element, including a transceiver and a processor, wherein:

[0134] The processor is used to: execute the life cycle process and obtain the intelligent AMC algorithm model;

[0135] The transceiver is used to send the intelligent AMC algorithm model to a group of base stations corresponding to the federated learning model network element.

[0136] Optionally, the federated learning model network element includes: a local model training node and a global model aggregation node;

[0137] The processor executes the life cycle process to obtain an intelligent AMC algorithm model, including:

[0138] The local model training node downloads the initial model file from the global model aggregation node;

[0139] The local model training node performs local model training according to local data and the initial model file to obtain updated model information;

[0140] The local model training node sends the updated model information to the global model aggregation node;

[0141] The global model aggregation node integrates the updated model information sent by all local model training nodes to obtain the intelligent AMC algorithm model.

[0142] Optionally, the transceiver is also used to: receive third indication information sent by a network device, and the third indication information is used to instruct the federated learning model network element to execute a life cycle process.

[0143] In a fifth aspect, an embodiment of the present application provides an adaptive modulation and coding device, including:

[0144] A grouping module, configured to group the base stations based on a similarity algorithm of base station feature information when it is determined that the base stations within the jurisdiction meet the triggering conditions of the intelligent adaptive modulation and coding AMC algorithm based on federated learning;

[0145] A first determination module is used to determine the federated learning model network element corresponding to each group of base stations;

[0146] The first processing module is used to trigger the federated learning model network element to execute a life cycle process, where the life cycle process is used to obtain an intelligent AMC algorithm model, and all base stations in the same group share one intelligent AMC algorithm model.

[0147] In a sixth aspect, an embodiment of the present application provides an adaptive modulation and coding device, including:

[0148] The second processing module is used to execute the life cycle process and obtain the intelligent AMC algorithm model;

[0149] The first sending module is used to send the intelligent AMC algorithm model to a group of base stations corresponding to the federated learning model network element.

[0150] In the seventh aspect, an embodiment of the present application provides a network device, comprising: a processor, a memory, and a program stored in the memory and executable on the processor, wherein the program implements the steps of the above-mentioned adaptive modulation and coding method when executed by the processor.

[0151] In the eighth aspect, an embodiment of the present application provides a federated learning model network element, characterized in that it includes: a processor, a memory, and a program stored in the memory and executable on the processor, wherein the program implements the steps of the above-mentioned adaptive modulation and coding method when executed by the processor.

[0152] In a ninth aspect, an embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the above-mentioned adaptive modulation and coding method are implemented.

[0153] In the embodiment of the present application, when the network device determines that the base station meets the triggering conditions of the intelligent AMC algorithm, the base station is grouped based on the similarity algorithm of the base station feature information; the federated learning model network element corresponding to each group of base stations is determined, and the federated learning model network element is triggered to execute the life cycle process, and finally the intelligent AMC algorithm model is obtained, and a group of base stations share the intelligent AMC algorithm model. This embodiment can collect rich data resources from different devices and improve the performance of the model such as accuracy and generalization; multiple base stations in the federated learning model network element perform model training at the same time, which greatly saves the time of building the model; the base station grouping rules are used to find the base station group, so as to obtain the global model of federated training applicable to the base station group for reasoning and prediction, save computing power and obtain the performance gain brought by the intelligent algorithm. BRIEF DESCRIPTION OF THE DRAWINGS

[0154] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present application. Also, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings:

[0155] Figure 1 This is a flowchart of an adaptive modulation and coding method according to an embodiment of the present application;

[0156] Figure 2 This is a second flow chart of the adaptive modulation and coding method according to an embodiment of the present application;

[0157] Figure 3 This is a third flow chart of the adaptive modulation and coding method according to an embodiment of the present application;

[0158] Figure 4 This is one of the structural schematic diagrams of the adaptive modulation and coding device in an embodiment of the present application;

[0159] Figure 5 This is a second structural diagram of the adaptive modulation and coding device according to an embodiment of the present application;

[0160] Figure 6 This is one of the structural diagrams of the network device according to the embodiment of the present application;

[0161] Figure 7 This is one of the structural diagrams of the federated learning model network element of the embodiment of the present application;

[0162] Figure 8 This is a second structural diagram of a network device according to an embodiment of the present application;

[0163] Fig. 9 This is the second structural diagram of the federated learning model network element of the embodiment of the present application. DETAILED DESCRIPTION

[0164] The exemplary embodiments of the present application will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present application are shown in the accompanying drawings, it should be understood that the present application can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided in order to enable a more thorough understanding of the present application and to fully convey the scope of the present application to those skilled in the art.

[0165] The terms "first", "second", etc. in the specification and claims of the present application are used to distinguish similar objects, and need not be used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchangeable in appropriate circumstances, so that the embodiments of the present application described herein can be implemented in a sequence other than those illustrated or described herein, for example. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, the process, method, system, product or equipment comprising a series of steps or units need not be limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or equipment. "And / or" in the specification and claims represents at least one of the connected objects.

[0166] The technology described herein is not limited to NR systems and Long Time Evolution (LTE) / LTE-Advanced (LTE-A) systems, and can also be used for various wireless communication systems, such as Code Division Multiple Access (CDMA), Time Division Multiple Access (TDMA), Frequency Division Multiple Access (FDMA), Orthogonal Frequency Division Multiple Access (OFDMA), Single-carrier Frequency Division Multiple Access (SC-FDMA) and other systems. The terms "system" and "network" are often used interchangeably. A CDMA system can implement radio technologies such as CDMA2000, Universal Terrestrial Radio Access (UTRA). UTRA includes Wideband Code Division Multiple Access (WCDMA) and other CDMA variants. A TDMA system can implement radio technologies such as Global System for Mobile Communication (GSM). OFDMA systems can implement radio technologies such as Ultra Mobile Broadband (UMB), Evolution-UTRA (E-UTRA), IEEE 802.21 (Wi-Fi), IEEE 802.16 (WiMAX), IEEE 802.20, Flash-OFDM, etc. UTRA and E-UTRA are parts of Universal Mobile Telecommunications System (UMTS). LTE and more advanced LTE (such as LTE-A) are new UMTS versions that use E-UTRA. UTRA, E-UTRA, UMTS, LTE, LTE-A, and GSM are described in documents from an organization named "3rd Generation Partnership Project" (3GPP). CDMA2000 and UMB are described in documents from an organization named "3rd Generation Partnership Project 2" (3GPP2).The techniques described herein may be used for the systems and radio technologies mentioned above as well as for other systems and radio technologies. However, the following description describes an NR system for example purposes and uses NR terminology in much of the following description, although the techniques may also be applicable to applications other than NR system applications.

[0167] The following description provides examples and does not limit the scope, applicability, or configuration set forth in the claims. Changes may be made to the functions and arrangements of the elements discussed without departing from the spirit and scope of the present disclosure. Various examples may appropriately omit, replace, or add various procedures or components. For example, the described methods may be performed in an order different from that described, and various steps may be added, omitted, or combined. In addition, features described with reference to certain examples may be combined in other examples.

[0168] As described in the background technology, in the prior art, based on the traditional AMC solution, it is not possible to timely and accurately predict the channel quality at the time of future uplink data transmission. When the channel environment fluctuates greatly, it will lead to problems such as high network bit error rate and reduced throughput performance, so it may not be possible to select a suitable MCS. In order to solve at least one of the above problems, an embodiment of the present application provides an adaptive modulation and coding method, which can reduce or avoid the occurrence of the above situation, make the predicted channel quality at the time of future uplink data transmission more accurate, and thus help the AMC module select a suitable MCS value.

[0169] Please refer to Figure 1 , an adaptive modulation and coding method provided in an embodiment of the present application is applied to a network device, including:

[0170] Step 101: When the network device determines that the base stations within the jurisdiction meet the triggering conditions of the intelligent adaptive modulation and coding AMC algorithm based on federated learning, the network device groups the base stations based on the similarity algorithm of the base station feature information.

[0171] In this embodiment, the network device may be a base station or an upper-layer network device, such as: management and maintenance equipment (Operation, Administration and Maintenance, OAM), a near real-time radio access network intelligent controller (Near Real Time RAN Intelligent Controller, Near-RT RIC) defined in the open radio access network (Open RAN, referred to as O-RAN) architecture, a non-real time radio access network intelligent controller (Non-real time RAN Intelligent Controller, Non-RT RIC), etc.

[0172] Intelligent solutions based on AI / machine learning (ML) algorithms, such as intelligent AMC solutions, require model training on base stations, and the computing cost is much higher than traditional algorithms that are not based on AI / ML algorithms. Intelligent algorithms are not required in all situations. Network equipment can determine whether the triggering conditions of the intelligent AMC algorithm based on federated learning are met based on conditions such as the network performance indicators of the base station. When the triggering conditions are met, the intelligent algorithm solution based on federated learning is triggered.

[0173] Step 102: Determine the federated learning model network element corresponding to each group of base stations;

[0174] The network device can use a similarity algorithm of the characteristic information of the base stations in the jurisdiction area to group all or part of the base stations in the jurisdiction area, and optionally, for example, group the base stations that meet the trigger conditions. Each group of base stations obtained shares an intelligent AMC algorithm model, so the network device can determine the federated learning model network element for each group of base stations. The federated learning model network element includes: one or more local model training nodes and a global model aggregation node.

[0175] Step 103: trigger the federated learning model network element to execute a life cycle process, where the life cycle process is used to obtain an intelligent AMC algorithm model. All base stations in the same group share one intelligent AMC algorithm model.

[0176] In this embodiment, the network device triggers the federated learning model network element to perform model training, executes the life cycle process and finally obtains the intelligent AMC algorithm model. Specifically, the global model aggregation node in the federated learning model network element aggregates the model information reported by each local model training node to obtain the intelligent AMC algorithm model. The intelligent AMC algorithm model is an intelligent AMC algorithm model shared by multiple base stations in a group of base stations. Adaptive modulation and coding can be implemented based on the intelligent AMC algorithm model.

[0177] In the embodiment of the present application, when the network device determines that the base station meets the triggering conditions of the intelligent AMC algorithm, the base station is grouped based on the similarity algorithm of the base station feature information; the federated learning model network element corresponding to each group of base stations is determined, and the federated learning model network element is triggered to execute the life cycle process, and finally the intelligent AMC algorithm model is obtained, and a group of base stations share the intelligent AMC algorithm model. This embodiment can collect rich data resources from different devices and improve the performance of the model such as accuracy and generalization; multiple base stations in the federated learning model network element perform model training at the same time, which greatly saves the time of building the model; the base station grouping rules are used to find the base station group, so as to obtain the global model of federated training applicable to the base station group for reasoning and prediction, save computing power and obtain the performance gain brought by the intelligent algorithm.

[0178] As an optional embodiment, the determining that the base stations within the jurisdiction meet the triggering condition of the intelligent adaptive modulation and coding AMC algorithm based on federated learning includes the following:

[0179] (1) receiving first indication information sent by a base station within a jurisdiction, where the first indication information is used to indicate that the base station meets a trigger condition of an intelligent AMC algorithm based on federated learning;

[0180] (2) receiving network performance indicators and / or second indication information sent by a base station within a jurisdiction; determining, based on the network performance indicators and / or the second indication information, whether the base station meets the triggering condition of the intelligent AMC algorithm based on federated learning; the second indication information is used to indicate that the base station meets the first condition.

[0181] In this embodiment, the network device can determine whether the base station meets the triggering conditions of the intelligent AMC algorithm based on federated learning based on the indication information reported by the base station, that is, the base station itself can determine whether the triggering conditions of the intelligent AMC algorithm based on federated learning are met based on network performance indicators, its own capabilities, etc., and report it to the network device. The base station may also only report the network performance indicators and / or the second indication information to the network device. The second indication information may indicate its own capabilities and indicate whether its own capabilities meet the first condition. The network device can determine whether the base station meets the triggering conditions of the intelligent AMC algorithm based on federated learning based on the network performance indicators and / or the second indication information of the base station. Optionally, the network device can also monitor the network performance indicators of the base station to determine whether the base station meets the triggering conditions of the intelligent AMC algorithm based on federated learning.

[0182] As an optional embodiment, the trigger condition includes at least one of the following:

[0183] (1) A network performance indicator of a base station within the jurisdiction does not meet a user QoS requirement; optionally, not meeting the user QoS requirement may be that the network performance indicator is greater than or less than a threshold set for the network performance indicator.

[0184] Optionally, the network performance indicator includes at least one of the following:

[0185] 1) IBLER;

[0186] 2) Throughput;

[0187] 3) Delay;

[0188] 4) Communication reliability (comprehensive evaluation of network performance indicators).

[0189] (2) The base stations within the jurisdiction meet the first condition; wherein the first condition includes at least one of the following:

[0190] a) The base station computing power conditions cannot support AI model training; for example: the base station computing power does not support AI model training, and the base station computing power-related parameter values ​​do not meet the relevant thresholds for AI model training.

[0191] b) The power consumption of the base station cannot support the training of the AI ​​model; for example, the power consumption of the base station is limited and cannot support the training of the AI ​​model, and the power consumption parameter value of the base station does not meet the relevant threshold of the AI ​​model training.

[0192] c) The prediction accuracy of the base station AI model training is lower than the first threshold;

[0193] d) The training convergence time of the base station AI model does not meet the user's QoS requirements. For example, when the training convergence time of the base station AI model is long, the network performance will be degraded and will not meet the user's QoS requirements.

[0194] e) There is a performance gain when using federated learning over non-federated learning, such as when there is a performance gain when using federated learning over non-federated learning solutions.

[0195] In this embodiment, the intelligent algorithm solution based on federated learning is trained on multiple base stations. Not all situations require intelligent solutions and federated learning model frameworks. It is necessary to design how to trigger the intelligent solution and federated learning model framework. When a base station meets certain conditions, the intelligent algorithm based on federated learning is triggered.

[0196] As an optional embodiment, grouping the base stations by a similarity algorithm based on base station feature information includes:

[0197] According to the characteristic information of each base station, the similarity of characteristic information between different base stations is calculated;

[0198] The base stations are grouped according to the feature information similarity and a preset similarity threshold.

[0199] Optionally, the feature information includes at least one of the following:

[0200] 1) Base station hardware information; base station type, base station antenna information

[0201] 2) Base station configuration information; base station time-frequency resource scheduling configuration parameters, user multiple-input multiple-output (MIMO) related configuration parameters

[0202] 3) Base station user information; user QoS requirements, user distribution, user mobility speed, terminal capabilities, user service types

[0203] 4) Base station wireless channel environment information; interference information, wireless channel information

[0204] 5) Input features of the intelligent algorithm of the base station; for example, the intelligent AMC algorithm includes but is not limited to the following aspects:

[0205] a: AMC algorithm related configuration parameters: such as target IBLER, outer loop control positive acknowledgment (ACK) step size, outer loop control negative acknowledgment (NACK) step size, initial MCS, etc.;

[0206] b: AMC algorithm related time-frequency resource scheduling information: such as channel quality indicator (CQI), MCS, resource block (RB) resource allocation, etc.;

[0207] c: Intelligent algorithm models: such as Long Short Term Memory networks (LSTM), Convolutional Neural Networks (CNN) and model hyperparameters.

[0208] 6) Output characteristics of the base station’s intelligent algorithm;

[0209] 7) Model expression of the intelligent algorithm of the base station.

[0210] In this embodiment, the network device can classify the base stations according to the hardware and configuration information of the base stations, the user information of the base stations, the wireless channel environment, the input / output characteristics of the intelligent algorithm, the algorithm model expression, etc., so that the base stations in the same group can jointly train an intelligent algorithm model based on the federated learning framework. Specifically, the base station feature information related to the base station grouping includes but is not limited to the above aspects.

[0211] The network equipment implements base station grouping based on the characteristic information of the base stations. For example, if the intelligent algorithm-related characteristics and intelligent algorithm models of different base stations are the same, the base stations can be further grouped based on the similarity of the relevant characteristic data between different base stations, and the same algorithm model parameters can be jointly trained using federated learning in the same group of base stations.

[0212] Since the characteristic attributes of each base station are similar and the data samples of each base station exist independently, a horizontal federated learning framework is adopted. Optionally, the similarity algorithm for calculating the similarity of feature information can use the cosine similarity algorithm. For example, the time series of a feature of base station 1 is taken as x, and the time series of a feature of base station 2 is taken as y, and the formula is as follows:

[0213]

[0214] The larger the similarity value calculated by the above formula is, the more similar a certain feature of base station 1 and base station 2 is, and the more likely they are to be classified into the same group of base stations.

[0215] Optionally, base stations whose similarity values ​​meet a preset threshold value may be grouped into one group. Optionally, the principle of grouping base stations includes at least one of the following:

[0216] 1) The more similar the data information of related features of different base stations is, the higher the prediction accuracy after aggregation is, but the performance on unknown data sets is poor, that is, the generalization is poor.

[0217] 2) The higher the difference in data information of relevant features of different base stations, the lower the prediction accuracy and the stronger the generalization.

[0218] Multiple thresholds can be set according to the prediction accuracy of the AI / ML model in the intelligent algorithm. When the prediction accuracy exceeds threshold 1, the number of base station categories can be reduced; when the prediction accuracy is lower than threshold 2, the number of base station categories is increased.

[0219] As an optional embodiment, determining the federated learning model network element corresponding to each group of base stations includes at least one of the following:

[0220] (1) For a group of base stations, local model training nodes of the group of base stations are determined according to the computing resources of the base stations in the group and / or the similarity of feature information between the base stations.

[0221] Optionally, the local model training node satisfies a second condition, and the second condition includes at least one of the following:

[0222] Computing resources can meet the needs of AI intelligent algorithms;

[0223] The characteristic information of the base station is a second threshold value of all data information of the group of base stations.

[0224] In this embodiment, based on the result of the base station grouping, some base station nodes can be selected for local training of federated learning for the base stations in each group. The selection principle can be: the computing power resources of the base station nodes in the group are sufficient to meet the computing power requirements of the AI ​​intelligent algorithm; and / or, among the nodes that meet the computing power resources, at least several nodes are selected, and according to the data similarity of the input features, their data information can represent a certain proportion threshold of all data information in the group.

[0225] (2) For a group of base stations, a global model aggregation node of the group of base stations is determined based on the computing resources of the base stations in the group and / or the connection resources between the base stations in the group and the local model training nodes. The global model aggregation node is a base station in the group of base stations, or a network device.

[0226] Optionally, the global model aggregation node satisfies a third condition, and the third condition includes at least one of the following:

[0227] The computing resources can meet the demand for computing resources when aggregating and / or updating model parameter information;

[0228] The connection resources can meet the latency requirements for aggregating and / or sending model parameter information;

[0229] Meet the synchronization requirements of sending different model parameter information to the base station.

[0230] In this embodiment, for each group of base stations, a base station node or other intelligent network device can be selected as the aggregation node of the group federated learning to complete the aggregation and update of model parameters. That is, the global model aggregation node can be a base station or an intelligent network device.

[0231] The principles for selecting the aggregation node may include at least one of the following:

[0232] The computing resources are sufficient to meet the computing power requirements for aggregating and updating AI models.

[0233] The connection resources are sufficient to meet the latency requirements for aggregating and sending AI model parameters to each local model training node.

[0234] Two AI / ML models are required to implement intelligent algorithms for the same base station, but the two models are located in different base station groups. It is necessary to consider the synchronization of different AI / ML model parameters arriving at the base station at different aggregation nodes.

[0235] After the base stations are grouped, the model training nodes, and the global model aggregation nodes are selected, an initial template for the federated learning AI algorithm model is developed.

[0236] Optionally, the triggering of the federated learning model network element to execute a lifecycle process includes:

[0237] Send third indication information to the federated learning model network element, where the third indication information is used to instruct the federated learning model network element to execute a life cycle process.

[0238] In this embodiment, the network device may instruct the federated learning model network element to execute the life cycle process. Optionally, the life cycle process of the federated learning model includes but is not limited to the following steps:

[0239] 1) The local model training node downloads the initial model file from the global model aggregation node or other network devices;

[0240] 1) Local model training: The local model training node improves the model by learning from local data;

[0241] 3) Model summarization (autonomy): The local model training node summarizes the improvements to the model into a relatively small update;

[0242] 4) Local model upload (autonomous): The local model training node encrypts the model update and sends it to the global model aggregation node;

[0243] 5) Model integration (union): The global model aggregation node integrates the updated information of multiple local models to obtain a shared model, namely the intelligent AMC algorithm model.

[0244] 6) Model distribution: The global model aggregation node distributes the shared model to all base stations in the group.

[0245] As an optional embodiment, the method further includes:

[0246] Receiving performance information of the intelligent AMC algorithm model sent by the base station;

[0247] Performing a performance evaluation on the intelligent AMC algorithm model according to the performance information;

[0248] The similarity threshold in the similarity algorithm is adjusted according to the performance evaluation result.

[0249] In this embodiment, the network device can evaluate and optimize the obtained intelligent AMC algorithm model. The base station reports the performance information of the intelligent AMC algorithm model to the network device, and the network device evaluates the intelligent AMC algorithm model based on the information. The similarity threshold in the similarity algorithm can be adjusted according to the evaluation node, thereby optimizing the intelligent AMC algorithm model.

[0250] Optionally, the performing performance evaluation on the intelligent AMC algorithm model according to the performance information includes: evaluating an AI model performance indicator of the intelligent AMC algorithm model according to the performance information;

[0251] The AI ​​model performance indicator includes at least one of the following:

[0252] The accuracy of model training;

[0253] Data distribution coverage;

[0254] Convergence time of model training;

[0255] Generalizability;

[0256] robustness;

[0257] Energy consumption.

[0258] Optionally, the performing performance evaluation on the intelligent AMC algorithm model according to the performance information includes: evaluating an AMC algorithm performance indicator of the intelligent AMC algorithm model according to the performance information;

[0259] The AMC algorithm performance index includes at least one of the following:

[0260] Throughput;

[0261] Communication reliability;

[0262] Delay;

[0263] IBLER.

[0264] Optionally, the network device can dynamically adjust the similarity threshold based on the performance indicators of the training model. For example, when the training model is overfitting, indicating that the data set is not rich enough, the similarity threshold can be lowered to allow more base stations to form a federated learning group. When the training model is underfitting, indicating that the model complexity is not sufficient to express the data set information, the similarity threshold can be increased to reduce the number of base stations and the diversity of the data.

[0265] The implementation method of the adaptive modulation coding is described below through a specific embodiment.

[0266] like Figure 2 As shown, including:

[0267] Step 21: The intelligent network device triggers the intelligent AMC algorithm solution based on federated learning.

[0268] Specifically, step 211: monitoring performance indicators related to the intelligent AMC algorithm.

[0269] When the network performance indicators of the base station node, such as IBERL, throughput, and latency, fail to meet the threshold, the intelligent AMC algorithm solution can be triggered.

[0270] Optionally, the network device may send a subscription request to the base station to subscribe to the network performance indicator of the base station. For example, the base station triggers reporting when its network performance indicator is lower than or higher than a threshold.

[0271] Step 212: Triggering the intelligent AMC algorithm solution based on federated learning.

[0272] Optionally, for base stations whose network performance indicators cannot meet the threshold, if their computing power conditions are insufficient to support AI model training, or energy-saving conditions cannot support AI model training, or their accuracy after training cannot reach the threshold at which the model can be deployed; or the training convergence time of the AI ​​model of this base station does not meet the user's QoS requirements, then an intelligent AMC algorithm solution based on federated learning can be triggered.

[0273] The base station or upper-layer network device, as an intelligent network device, initiates a federated learning request, applies to jointly train the intelligent AMC model with other base stations, and receives the model parameters trained to achieve the model deployment accuracy, triggering the intelligent AMC algorithm solution mechanism based on federated learning.

[0274] Step 22: Federated learning model network element collaborative orchestration management.

[0275] Step 221: Implement base station grouping and cluster the base stations based on a similarity algorithm or the like.

[0276] This embodiment needs to further aggregate and classify the base stations according to the input and output feature dimensions and model expressions of the intelligent algorithm, so that the intelligent AMC algorithm model can be shared among the base stations in the same group.

[0277] In the intelligent AMC algorithm designed in this embodiment, the models that need to be trained are the uplink interference time series prediction model and the channel matrix time series prediction model, using, for example, the LSTM algorithm.

[0278] The input of the uplink interference time series prediction model 1 is the uplink interference prediction value RIP, and the output is the uplink interference prediction value RIP(n+Δ) at the future Δ time. The input and output logical relationship is universal among different base stations. The base station grouping can be realized based on the similarity algorithm, and multiple base station devices can cooperate to train a time series prediction model.

[0279] Channel matrix time series prediction model Model 2 has the channel matrix H(k,r,p) as input and the channel matrix H(k,r,p) at the future Δ time as output n+Δ (k, r, p), the input and output logical relationship is universal among different base stations. Base station grouping can be implemented based on the similarity algorithm, and multiple base station devices can cooperate to train a time series prediction model.

[0280] The time series of the uplink interference prediction value RIP input to the uplink interference time series prediction model 1 has different time fluctuation periods, trends, and amplitudes in different base stations. Through the similarity algorithm, a group of base stations whose uplink interference prediction value RIP sequence similarity in a historical period is higher than a threshold 1 can be divided into a group to jointly train an intelligent AMC algorithm model.

[0281] Channel Matrix Time Series Prediction Model Model 2 Input Channel Matrix H n+Δ The time series of (k, r, p) has different time fluctuation periods, trends, and amplitudes in different base stations. Through the similarity algorithm, a group of base stations with uplink interference prediction values ​​(such as received interference power (RIP)) with a sequence similarity higher than a threshold 2 in a historical period are grouped together to train a model together.

[0282] The processes of grouping base stations in the federated learning framework for uplink interference time series prediction model 1 and channel matrix time series prediction model 2 are independent of each other, that is, they can be divided in different forms.

[0283] Optionally, the base station grouping principle is as follows:

[0284] 1) The more similar the data information of related features of different base stations is, the higher the prediction accuracy after aggregation, and the poorer the generalization;

[0285] 2) The higher the difference in data information of relevant features of different base stations, the lower the prediction accuracy and the stronger the generalization.

[0286] Step 222: Select a local model training node based on the data similarity between base stations in the group and the computing resource perception of each base station.

[0287] According to the base station grouping results, for each group of base stations, some base station nodes are selected as local model training nodes for local training of federated learning. The selection principle is not elaborated here.

[0288] Step 223: Select a global model aggregation node based on the connection resources and computing power resources between the local training node. The selection principle is not described here.

[0289] Step 23: Trigger the lifecycle process of the federated learning model.

[0290] Step 24: The intelligent network device subscribes to the performance information of the intelligent AMC algorithm model from the base station, and performs AI model performance indicators and intelligent AMC algorithm performance evaluation based on the performance information of the intelligent AMC algorithm model.

[0291] The intelligent AMC solution of this embodiment predicts uplink interference and channel matrix, and uses the following formula (3) to obtain the uplink channel noise ratio UL_SINR at the time of future physical uplink shared channel (PUSCH) data service transmission, thereby improving the accuracy of base station selection of MCS and meeting the requirements of high reliability and low latency of wireless network.

[0292]

[0293]

[0294]

[0295] Among them, S n+Δ(k,r) is the useful signal strength of each subcarrier received by the base station; S(n+Δ) is the average useful signal strength per RB / resource block group (RBG) for scheduled user i in a certain frequency domain. UL_SINR(n+Δ) is the uplink channel noise ratio at time (n+Δ). Specifically, the channel matrix prediction value at time tti(n+Δ) obtained by channel prediction is Formula (1) is used to further calculate the useful signal strength S of each subcarrier received by the base station: n+Δ (k,r).X n+Δ (k,p) is the reference signal sent by the user at time tti(n+Δ), which is known to the base station according to the configuration of the base station on the transmitter and the uplink power control function. K is the total number of subcarriers in a certain frequency domain for scheduled user i, R is the number of receiving antennas of the base station, P is the total number of antennas at the transmitter, N_sc is the number of subcarriers contained in each RB / RBG, and the average useful signal strength S(n+Δ) per RB / RBG for scheduled user i in a certain frequency domain can be calculated by formula (2). Finally, UL_SINR(n+Δ) is obtained using formula (3).

[0296] The data characteristics of the uplink interference prediction input in formula (3) are the uplink interference value RIP received by each RB / RBG in the working frequency band of the serving cell, including the interference value of historical data and the current statistical period, that is, the time series of the uplink interference value of each RB / RBG. The output is the uplink interference prediction value RIP(n+Δ) at the future Δ time.

[0297] The data features of the channel prediction input in formula (3) are the channel data of the user requesting scheduling, which is a K*R*P dimensional matrix H(k,r,p), where K is the number of subcarriers in the frequency domain of the scheduled user, R is the number of antennas at the receiving end, and P is the number of antennas at the transmitting end. It includes historical data and channel data of the current statistical period, that is, the R*P dimensional matrix time series of each subcarrier. The output is the channel matrix H at the future time Δ n+Δ (k,r,p).

[0298] Uplink interference prediction and channel prediction are both time series predictions, which can be implemented using LSTM models, RNN, STL+GRU models, etc. The output is the uplink channel data at the future k time points.

[0299] According to the uplink interference prediction value and channel data at the future time Δ, the uplink channel noise ratio UL_SINR at the future time Δ is obtained.

[0300] In the intelligent AMC algorithm, the models that need to be trained are the uplink interference time series prediction model and the channel matrix time series prediction model, such as the LSTM model. The input and output feature dimensions of the model, as well as the input and output logical relationships, are universal among different base stations, so multiple base station devices in the federated learning framework can be used to collaboratively train a time series prediction model.

[0301] The embodiments of the present application provide an application scenario of an intelligent AMC algorithm solution that can utilize a federated learning framework. The input and output feature dimensions and model expressions of the intelligent AMC algorithm are universal among different base station devices and are suitable for utilizing a networked learning framework. The embodiments of the present application design trigger conditions for an intelligent AMC solution based on federated learning, which are used to trigger the solution to save computing power when there is sufficient demand. The embodiment of the present application designs a method that can classify base stations that can use a universal intelligent AMC algorithm model into one category based on the similarity of data distribution, and adopts federated learning among base stations of the same type. Base station nodes are selected based on data differences and remaining computing power to train local model parameters. Base stations or other network devices with low transmission costs and sufficient computing power are selected as nodes for global model aggregation to establish a shared machine learning model.

[0302] In this application, the network device can dynamically adjust the similarity threshold based on the performance indicators of the training model. When the training model is overfitting, it means that the data set is not rich enough, and the similarity threshold can be lowered to allow more base stations to form a federated learning group; when the training model is underfitting, it means that the model complexity is not enough to express the data set information, and the similarity threshold can be increased to reduce the number of base stations and the diversity of the data.

[0303] The adaptive modulation and coding of the embodiment of the present application is based on the uplink interference and channel matrix prediction values ​​to obtain the channel quality at the future uplink data service transmission time, which can improve the accuracy of the base station's selection of MCS. The method first uses uplink interference data and channel matrix data to predict the uplink interference prediction value and channel matrix prediction value at the future uplink data transmission time. The base station converts the prediction value into the uplink interference value and channel matrix value for each RB / RBG of the scheduled user i in a certain frequency domain through appropriate processing, and provides the signal to interference plus noise ratio (SINR) of the channel quality to the AMC module of the base station, thereby helping the AMC module to select a suitable MCS value.

[0304] The embodiments of the present application can collect data from different devices to enrich data resources and improve model performance such as accuracy and generalization; multiple base stations can perform model training simultaneously, which greatly saves the time of building models; for base station nodes with insufficient computing power, inference and prediction can be performed through the global model of federal training, saving computing power.

[0305] like Figure 3 As shown, the embodiment of the present application also provides an adaptive modulation and coding method, which is applied to a federated learning model network element, including:

[0306] Step 301: The federated learning model network element executes the lifecycle process to obtain an intelligent AMC algorithm model;

[0307] Step 302: Send the intelligent AMC algorithm model to a group of base stations corresponding to the federated learning model network element.

[0308] In this embodiment, after grouping the base stations, the network device can determine the federated learning model network element corresponding to each group of base stations, and trigger the federated learning model network element to execute the life cycle process. The federated learning model network element can obtain the intelligent AMC algorithm model by executing the life cycle process. For the same base station group, all base stations in the group share one intelligent AMC algorithm model. The federated learning model network element can send the intelligent AMC algorithm model to the private base stations in the group.

[0309] Optionally, the federated learning model network element includes: a local model training node and a global model aggregation node;

[0310] The execution life cycle process to obtain the intelligent AMC algorithm model includes:

[0311] The local model training node downloads the initial model file from the global model aggregation node;

[0312] The local model training node performs local model training according to local data and the initial model file to obtain updated model information;

[0313] The local model training node sends the updated model information to the global model aggregation node;

[0314] The global model aggregation node integrates the updated model information sent by all local model training nodes to obtain the intelligent AMC algorithm model.

[0315] Optionally, the method further includes:

[0316] Receive third indication information sent by the network device, where the third indication information is used to instruct the federated learning model network element to execute a life cycle process.

[0317] In this embodiment, the network device can instruct the federated learning model network element to execute the life cycle process through the third indication information.

[0318] In the embodiments of the present application, multiple base stations perform model training simultaneously, which greatly saves the time of building the model. For base station nodes with insufficient computing power, inference prediction can be performed through the global model of federal training, saving computing power.

[0319] The above describes various methods of the embodiments of the present application. The following further provides devices for implementing the above methods.

[0320] Please refer to Figure 4 The embodiment of the present application further provides an adaptive modulation and coding device 400, which is applied to a network device, including:

[0321] A grouping module 410 is used to group the base stations based on a similarity algorithm of base station feature information when it is determined that the base stations within the jurisdiction meet the triggering conditions of the intelligent adaptive modulation and coding AMC algorithm based on federated learning;

[0322] A first determination module 420 is used to determine the federated learning model network element corresponding to each group of base stations;

[0323] The first processing module 430 is used to trigger the federated learning model network element to execute a life cycle process, where the life cycle process is used to obtain an intelligent AMC algorithm model. All base stations in the same group share one intelligent AMC algorithm model.

[0324] Optionally, the device further comprises:

[0325] A first receiving module, used to receive the performance information of the intelligent AMC algorithm model sent by the base station;

[0326] An evaluation module, used to perform performance evaluation on the intelligent AMC algorithm model according to the performance information;

[0327] The optimization module is used to adjust the similarity threshold in the similarity algorithm according to the performance evaluation result.

[0328] Optionally, the device further includes: a second determining module, configured to perform one of the following:

[0329] Receiving first indication information sent by a base station within a jurisdiction, where the first indication information is used to indicate that the base station meets a trigger condition of an intelligent AMC algorithm based on federated learning;

[0330] Receive network performance indicators and / or second indication information sent by base stations within the jurisdiction; determine whether the base station meets the triggering conditions of the intelligent AMC algorithm based on federated learning based on the network performance indicators and / or the second indication information; the second indication information is used to indicate that the base station meets the first condition.

[0331] Optionally, the trigger condition includes at least one of the following:

[0332] The network performance indicators of base stations within the jurisdiction do not meet the user QoS requirements;

[0333] The base stations within the jurisdiction meet the first condition;

[0334] The first condition includes at least one of the following:

[0335] The computing power of the base station cannot support AI model training;

[0336] Base station power consumption cannot support AI model training;

[0337] The prediction accuracy of the base station AI model training is lower than the first threshold;

[0338] The training convergence time of the base station AI model does not meet the user QoS requirements;

[0339] Using federated learning has performance gains over non-federated learning.

[0340] Optionally, the grouping module is specifically used for:

[0341] According to the characteristic information of each base station, the similarity of characteristic information between different base stations is calculated;

[0342] The base stations are grouped according to the feature information similarity and a preset similarity threshold.

[0343] Optionally, the feature information includes at least one of the following:

[0344] Base station hardware information;

[0345] Configuration information of the base station;

[0346] Base station user information;

[0347] Wireless channel environment information of the base station;

[0348] Input features of the base station’s intelligent algorithm;

[0349] Output characteristics of the base station’s intelligent algorithm;

[0350] Model expression of the intelligent algorithm of the base station.

[0351] Optionally, the first determining module is specifically configured to perform at least one of the following:

[0352] For a group of base stations, determining a local model training node of the group of base stations according to computing resources of the base stations in the group and / or similarity of feature information between the base stations;

[0353] For a group of base stations, a global model aggregation node of the group of base stations is determined based on the computing power resources of the base stations in the group and / or the connection resources between the base stations in the group and the local model training nodes. The global model aggregation node is a base station in the group of base stations, or a network device.

[0354] Optionally, the local model training node satisfies a second condition, and the second condition includes at least one of the following:

[0355] Computing resources can meet the needs of AI intelligent algorithms;

[0356] The characteristic information of the base station is a second threshold value of all data information of the group of base stations.

[0357] Optionally, the global model aggregation node satisfies a third condition, and the third condition includes at least one of the following:

[0358] The computing resources can meet the demand for computing resources when aggregating and / or updating model parameter information;

[0359] The connection resources can meet the latency requirements for aggregating and / or sending model parameter information;

[0360] Meet the synchronization requirements of sending different model parameter information to the base station.

[0361] Optionally, the first processing module is specifically used to:

[0362] Send third indication information to the federated learning model network element, where the third indication information is used to instruct the federated learning model network element to execute a life cycle process.

[0363] Optionally, the evaluation module is specifically used for:

[0364] Evaluate the AI ​​model performance indicators of the intelligent AMC algorithm model according to the performance information;

[0365] The AI ​​model performance indicator includes at least one of the following:

[0366] The accuracy of model training;

[0367] Data distribution coverage;

[0368] Convergence time of model training;

[0369] Generalizability;

[0370] robustness;

[0371] Energy consumption.

[0372] Optionally, the evaluation module is specifically used for:

[0373] Evaluate the AMC algorithm performance index of the intelligent AMC algorithm model according to the performance information;

[0374] The AMC algorithm performance index includes at least one of the following:

[0375] Throughput;

[0376] Communication reliability;

[0377] Delay;

[0378] IBLER.

[0379] It should be noted that the device in this embodiment is a device corresponding to the method applied to the network device, and the implementation methods in the above embodiments are all applicable to the embodiments of the device, and can also achieve the same technical effects. The parts and beneficial effects of this embodiment that are the same as those of the method embodiment will not be described in detail here.

[0380] Please refer to Figure 5 The embodiment of the present application further provides an adaptive modulation and coding device 500, comprising:

[0381] The second processing module 510 is used to execute the life cycle process and obtain the intelligent AMC algorithm model;

[0382] The first sending module 520 is used to send the intelligent AMC algorithm model to a group of base stations corresponding to the federated learning model network element.

[0383] Optionally, the federated learning model network element includes: a local model training node and a global model aggregation node;

[0384] The second processing module 510 is specifically used for:

[0385] The local model training node downloads the initial model file from the global model aggregation node;

[0386] The local model training node performs local model training according to local data and the initial model file to obtain updated model information;

[0387] The local model training node sends the updated model information to the global model aggregation node;

[0388] The global model aggregation node integrates the updated model information sent by all local model training nodes to obtain the intelligent AMC algorithm model.

[0389] Optionally, the device further comprises:

[0390] The second receiving module receives third indication information sent by the network device, and the third indication information is used to instruct the federated learning model network element to execute a life cycle process.

[0391] It should be noted that the device in this embodiment is a device corresponding to the method applied to the federated learning model network element, and the implementation methods in the above embodiments are applicable to the embodiments of the device, and can also achieve the same technical effects. The parts and beneficial effects of this embodiment that are the same as those of the method embodiment will not be described in detail here.

[0392] Please refer to Figure 6 , the embodiment of the present application further provides a network device 600, including: a transceiver 601 and a processor 602;

[0393] The processor 602 is configured to group the base stations based on a similarity algorithm of base station feature information when determining that the base stations within the jurisdiction meet the triggering condition of the intelligent adaptive modulation and coding AMC algorithm based on federated learning;

[0394] Determine the federated learning model network element corresponding to each group of base stations;

[0395] The federated learning model network element is triggered to execute a life cycle process, where the life cycle process is used to obtain an intelligent AMC algorithm model, and all base stations in the same group share one intelligent AMC algorithm model.

[0396] Optionally, the transceiver is used to: receive performance information of the intelligent AMC algorithm model sent by the base station;

[0397] The processor is further configured to: perform a performance evaluation on the intelligent AMC algorithm model according to the performance information; and adjust a similarity threshold in the similarity algorithm according to the performance evaluation result.

[0398] Optionally, the processor determines that the base station within the jurisdiction meets the triggering condition of the intelligent adaptive modulation and coding AMC algorithm based on federated learning, including the following:

[0399] Receiving first indication information sent by a base station within a jurisdiction, where the first indication information is used to indicate that the base station meets a trigger condition of an intelligent AMC algorithm based on federated learning;

[0400] Receive network performance indicators and / or second indication information sent by base stations within the jurisdiction; determine whether the base station meets the triggering conditions of the intelligent AMC algorithm based on federated learning based on the network performance indicators and / or the second indication information; the second indication information is used to indicate that the base station meets the first condition.

[0401] Optionally, the trigger condition includes at least one of the following:

[0402] The network performance indicators of base stations within the jurisdiction do not meet the user QoS requirements;

[0403] The base stations within the jurisdiction meet the first condition;

[0404] The first condition includes at least one of the following:

[0405] The computing power of the base station cannot support AI model training;

[0406] Base station power consumption cannot support AI model training;

[0407] The prediction accuracy of the base station AI model training is lower than the first threshold;

[0408] The training convergence time of the base station AI model does not meet the user QoS requirements;

[0409] Using federated learning has performance gains over non-federated learning.

[0410] Optionally, the processor groups the base stations based on a similarity algorithm of base station feature information, including:

[0411] According to the characteristic information of each base station, the similarity of characteristic information between different base stations is calculated;

[0412] The base stations are grouped according to the feature information similarity and a preset similarity threshold.

[0413] Optionally, the feature information includes at least one of the following:

[0414] Base station hardware information;

[0415] Configuration information of the base station;

[0416] Base station user information;

[0417] Wireless channel environment information of the base station;

[0418] Input features of the base station’s intelligent algorithm;

[0419] Output characteristics of the base station’s intelligent algorithm;

[0420] Model expression of the intelligent algorithm of the base station.

[0421] Optionally, the processor determines the federated learning model network element corresponding to each group of base stations, including at least one of the following:

[0422] For a group of base stations, determining a local model training node of the group of base stations according to computing resources of the base stations in the group and / or similarity of feature information between the base stations;

[0423] For a group of base stations, a global model aggregation node of the group of base stations is determined based on the computing power resources of the base stations in the group and / or the connection resources between the base stations in the group and the local model training nodes. The global model aggregation node is a base station in the group of base stations, or a network device.

[0424] Optionally, the local model training node satisfies a second condition, and the second condition includes at least one of the following:

[0425] Computing resources can meet the needs of AI intelligent algorithms;

[0426] The characteristic information of the base station is a second threshold value of all data information of the group of base stations.

[0427] Optionally, the global model aggregation node satisfies a third condition, and the third condition includes at least one of the following:

[0428] The computing resources can meet the demand for computing resources when aggregating and / or updating model parameter information;

[0429] The connection resources can meet the latency requirements for aggregating and / or sending model parameter information;

[0430] Meet the synchronization requirements of sending different model parameter information to the base station.

[0431] Optionally, the processor triggers the federated learning model network element to execute a lifecycle process, including:

[0432] Send third indication information to the federated learning model network element, where the third indication information is used to instruct the federated learning model network element to execute a life cycle process.

[0433] Optionally, the processor performs performance evaluation on the intelligent AMC algorithm model according to the performance information, including:

[0434] Evaluate the AI ​​model performance indicators of the intelligent AMC algorithm model according to the performance information;

[0435] The AI ​​model performance indicator includes at least one of the following:

[0436] The accuracy of model training;

[0437] Data distribution coverage;

[0438] Convergence time of model training;

[0439] Generalizability;

[0440] robustness;

[0441] Energy consumption.

[0442] Optionally, the processor performs performance evaluation on the intelligent AMC algorithm model according to the performance information, including:

[0443] Evaluate the AMC algorithm performance index of the intelligent AMC algorithm model according to the performance information;

[0444] The AMC algorithm performance index includes at least one of the following:

[0445] Throughput;

[0446] Communication reliability;

[0447] Delay;

[0448] IBLER.

[0449] It should be noted that the device in this embodiment is a device corresponding to the method applied to the network device, and the implementation methods in the above embodiments are all applicable to the embodiments of the device, and can also achieve the same technical effects. The parts and beneficial effects of this embodiment that are the same as those of the method embodiment will not be described in detail here.

[0450] Please refer to Figure 7 , the embodiment of the present application also provides a federated learning model network element 700, including: a transceiver 701 and a processor 702;

[0451] The processor 702 is used to: execute the life cycle process to obtain an intelligent AMC algorithm model;

[0452] The transceiver 701 is used to send the intelligent AMC algorithm model to a group of base stations corresponding to the federated learning model network element.

[0453] Optionally, the federated learning model network element includes: a local model training node and a global model aggregation node;

[0454] The processor executes the life cycle process to obtain an intelligent AMC algorithm model, including:

[0455] The local model training node downloads the initial model file from the global model aggregation node;

[0456] The local model training node performs local model training according to local data and the initial model file to obtain updated model information;

[0457] The local model training node sends the updated model information to the global model aggregation node;

[0458] The global model aggregation node integrates the updated model information sent by all local model training nodes to obtain the intelligent AMC algorithm model.

[0459] Optionally, the transceiver is also used to: receive third indication information sent by a network device, and the third indication information is used to instruct the federated learning model network element to execute a life cycle process.

[0460] It should be noted that the device in this embodiment is a device corresponding to the method applied to the federated learning model network element, and the implementation methods in the above embodiments are applicable to the embodiments of the device, and can also achieve the same technical effects. The parts and beneficial effects of this embodiment that are the same as those of the method embodiment will not be described in detail here.

[0461] Please refer to Figure 8 An embodiment of the present application also provides a network device 800, including a transceiver 810, a processor 800, a memory 820, and a program or instruction stored on the memory 820 and executable on the processor 800; when the processor 800 executes the program or instruction, the steps of the adaptive modulation and coding method performed by the network device are implemented.

[0462] The transceiver 810 is used to receive and send data under the control of the processor 800 .

[0463] Among them, Figure 8 In the embodiment, the bus architecture may include any number of interconnected buses and bridges, specifically linking together various circuits of one or more processors represented by processor 800 and memory represented by memory 820. The bus architecture may also link together various other circuits such as peripherals, voltage regulators, and power management circuits, which are well known in the art and are therefore not further described herein. The bus interface provides an interface. The transceiver 810 may be a plurality of components, i.e., including a transmitter and a receiver, providing a unit for communicating with various other devices on a transmission medium. The processor 800 is responsible for managing the bus architecture and general processing, and the memory 820 may store data used by the processor 800 when performing operations.

[0464] Please refer to Fig. 9 An embodiment of the present application also provides a federated learning model network element 900, including a transceiver 910, a processor 900, a memory 920, and a program or instruction stored on the memory 920 and executable on the processor 900; when the processor 900 executes the program or instruction, the steps of the adaptive modulation and coding method performed by the federated learning model network element are implemented.

[0465] The transceiver 910 is used to receive and send data under the control of the processor 900.

[0466] Among them, Fig. 9In the embodiment, the bus architecture may include any number of interconnected buses and bridges, specifically linking together various circuits of one or more processors represented by processor 900 and memory represented by memory 920. The bus architecture may also link together various other circuits such as peripherals, voltage regulators, and power management circuits, which are well known in the art and are therefore not further described herein. The bus interface provides an interface. The transceiver 910 may be a plurality of components, i.e., including a transmitter and a receiver, providing a unit for communicating with various other devices on a transmission medium. The processor 900 is responsible for managing the bus architecture and general processing, and the memory 920 may store data used by the processor 900 when performing operations.

[0467] The embodiment of the present application also provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, each process of the above-mentioned adaptive modulation and coding method embodiment is implemented, and the same technical effect can be achieved. To avoid repetition, it is not repeated here. Among them, the computer-readable storage medium is such as a read-only memory (ROM), a random access memory (RAM), a disk or an optical disk, etc.

[0468] It should be noted that, in this article, the terms "include", "include" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "includes a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element.

[0469] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, a magnetic disk, or an optical disk), and includes a number of instructions for a terminal (which can be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to execute the methods described in each embodiment of the present application.

[0470] The embodiments of the present application are described above in conjunction with the accompanying drawings, but the present application is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of the present application, ordinary technicians in this field can also make many forms without departing from the purpose of the present application and the scope of protection of the claims, all of which are within the protection of the present application.

Claims

1. An adaptive modulation and coding method, applied to a network device, characterized in that: include: When the network device determines that the base stations in the jurisdiction meet the triggering conditions of the intelligent adaptive modulation and coding AMC algorithm based on federated learning, the network device groups the base stations based on the similarity algorithm of the base station feature information; Determine the federated learning model network element corresponding to each group of base stations; The federated learning model network element is triggered to execute a life cycle process, where the life cycle process is used to obtain an intelligent AMC algorithm model, and all base stations in the same group share one intelligent AMC algorithm model.

2. The method according to claim 1, characterized in that The method further comprises: Receiving performance information of the intelligent AMC algorithm model sent by the base station; Performing a performance evaluation on the intelligent AMC algorithm model according to the performance information; The similarity threshold in the similarity algorithm is adjusted according to the performance evaluation result.

3. The method according to claim 1, characterized in that The determining that the base stations within the jurisdiction meet the triggering condition of the intelligent adaptive modulation and coding AMC algorithm based on federated learning includes the following: Receiving first indication information sent by a base station within a jurisdiction, where the first indication information is used to indicate that the base station meets a trigger condition of an intelligent AMC algorithm based on federated learning; Receiving a network performance indicator and / or a second indication information sent by a base station within a jurisdiction; determining, according to the network performance indicator and / or the second indication information, that the base station meets a trigger condition of an intelligent AMC algorithm based on federated learning; The second indication information is used to indicate that the base station meets the first condition.

4. The method according to claim 1 or 3, characterized in that: The trigger condition includes at least one of the following: The network performance indicators of base stations within the jurisdiction do not meet the user QoS requirements; The base stations within the jurisdiction meet the first condition; The first condition includes at least one of the following: The computing power of base stations cannot support the training of artificial intelligence (AI) models; Base station power consumption cannot support AI model training; The prediction accuracy of the base station AI model training is lower than the first threshold; The training convergence time of the base station AI model does not meet the user's QoS requirements; Using federated learning has performance gains over non-federated learning.

5. The method according to claim 1, characterized in that: The grouping of the base stations based on a similarity algorithm of base station feature information includes: According to the characteristic information of each base station, the similarity of characteristic information between different base stations is calculated; The base stations are grouped according to the feature information similarity and a preset similarity threshold.

6. The method according to claim 5, characterized in that The characteristic information includes at least one of the following: Base station hardware information; Configuration information of the base station; Base station user information; Wireless channel environment information of the base station; Input features of the base station’s intelligent algorithm; Output characteristics of the base station’s intelligent algorithm; Model expression of the intelligent algorithm of the base station.

7. The method according to claim 1, characterized in that The determining of the federated learning model network element corresponding to each group of base stations includes at least one of the following: For a group of base stations, determining a local model training node of the group of base stations according to computing resources of the base stations in the group and / or similarity of feature information between the base stations; For a group of base stations, a global model aggregation node of the group of base stations is determined based on the computing power resources of the base stations in the group and / or the connection resources between the base stations in the group and the local model training nodes. The global model aggregation node is a base station in the group of base stations, or a network device.

8. The method according to claim 7, characterized in that The local model training node satisfies a second condition, wherein the second condition includes at least one of the following: Computing resources can meet the needs of AI intelligent algorithms; The characteristic information of the base station is a second threshold value of all data information of the group of base stations.

9. The method according to claim 7, characterized in that: The global model aggregation node satisfies a third condition, wherein the third condition includes at least one of the following: The computing resources can meet the demand for computing resources when aggregating and / or updating model parameter information; The connection resources can meet the latency requirements for aggregating and / or sending model parameter information; Meet the synchronization requirements of sending different model parameter information to the base station.

10. The method according to claim 1, characterized in that The triggering of the federated learning model network element to execute the life cycle process includes: Send third indication information to the federated learning model network element, where the third indication information is used to instruct the federated learning model network element to execute a life cycle process.

11. The method according to claim 2, characterized in that The performing performance evaluation on the intelligent AMC algorithm model according to the performance information includes: Evaluate the AI ​​model performance indicators of the intelligent AMC algorithm model according to the performance information; The AI ​​model performance indicator includes at least one of the following: The accuracy of model training; Data distribution coverage; Convergence time of model training; Generalizability; robustness; Energy consumption.

12. The method according to claim 2, characterized in that: The performing performance evaluation on the intelligent AMC algorithm model according to the performance information includes: Evaluate the AMC algorithm performance index of the intelligent AMC algorithm model according to the performance information; The AMC algorithm performance index includes at least one of the following: Throughput; Communication reliability; Delay; Initial transmission block error rate IBLER.

13. An adaptive modulation and coding method, applied to a federated learning model network element, characterized in that: include: The federated learning model network element executes the lifecycle process to obtain the intelligent AMC algorithm model; The intelligent AMC algorithm model is sent to a group of base stations corresponding to the federated learning model network element.

14. The method according to claim 13, characterized in that The federated learning model network element includes: a local model training node and a global model aggregation node; The execution life cycle process to obtain the intelligent AMC algorithm model includes: The local model training node downloads the initial model file from the global model aggregation node; The local model training node performs local model training according to local data and the initial model file to obtain updated model information; The local model training node sends the updated model information to the global model aggregation node; The global model aggregation node integrates the updated model information sent by all local model training nodes to obtain the intelligent AMC algorithm model.

15. The method according to claim 13, characterized in that The method further comprises: Receive third indication information sent by the network device, where the third indication information is used to instruct the federated learning model network element to execute a life cycle process.

16. A network device, characterized in that: comprising a transceiver and a processor, wherein: The processor is used to group the base stations based on a similarity algorithm of base station feature information when it is determined that the base stations within the jurisdiction meet the triggering conditions of the intelligent adaptive modulation and coding AMC algorithm based on federated learning; Determine the federated learning model network element corresponding to each group of base stations; The federated learning model network element is triggered to execute a life cycle process, where the life cycle process is used to obtain an intelligent AMC algorithm model, and all base stations in the same group share one intelligent AMC algorithm model.

17. A federated learning model network element, characterized in that: comprising a transceiver and a processor, wherein: The processor is used to: execute the life cycle process and obtain the intelligent AMC algorithm model; The transceiver is used to send the intelligent AMC algorithm model to a group of base stations corresponding to the federated learning model network element.

18. An adaptive modulation and coding device, characterized in that: include: A grouping module, configured to group the base stations based on a similarity algorithm of base station feature information when it is determined that the base stations within the jurisdiction meet the triggering conditions of the intelligent adaptive modulation and coding AMC algorithm based on federated learning; A first determination module is used to determine the federated learning model network element corresponding to each group of base stations; The first processing module is used to trigger the federated learning model network element to execute a life cycle process, where the life cycle process is used to obtain an intelligent AMC algorithm model, and all base stations in the same group share one intelligent AMC algorithm model.

19. An adaptive modulation and coding device, characterized in that: include: The second processing module is used to execute the life cycle process and obtain the intelligent AMC algorithm model; The first sending module is used to send the intelligent AMC algorithm model to a group of base stations corresponding to the federated learning model network element.

20. A network device, characterized in that: include: A processor, a memory, and a program stored in the memory and executable on the processor, wherein when the program is executed by the processor, the steps of the method according to any one of claims 1 to 12 are implemented.

21. A federated learning model network element, characterized in that: include: A processor, a memory, and a program stored in the memory and executable on the processor, wherein when the program is executed by the processor, the steps of the method according to any one of claims 13 to 15 are implemented.

22. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 12 are implemented, or the steps of the method according to any one of claims 13 to 15 are implemented.

Images