Method, apparatus, device and medium for distributed beam management configuration

Abstract

The present disclosure provides a beam management configuration method, device, equipment and medium, relating to the technical field of wireless communication. The method comprises: a micro base station receives configuration signaling from a macro base station, the configuration signaling carrying initial beam configuration information, the initial beam configuration information including macro base station beam parameter configuration and micro base station beam parameter configuration; the micro base station takes the initial beam configuration information as the initial state of beam configuration intelligent decision, periodically senses the change of user equipment position distribution, adopts a deep reinforcement learning algorithm to maximize user throughput, and makes real-time beam configuration decision. According to the embodiment of the present disclosure, the direction of the beam can be adjusted in real time, and high-quality communication services are provided for users. In addition, the federal learning framework is adopted between the micro base station and the macro base station, and the privacy problem of user data is solved.

Description

Technical Field

[0001] This disclosure relates to the field of wireless communication technology, and in particular to a configuration method, apparatus, device and medium for distributed beam management. Background Technology

[0002] With the rapid increase in the number of network user devices, data traffic in the network has also experienced explosive growth. 5G enhanced mobile broadband (eMBB) has put forward requirements for ultra-high data transmission rates and mobility guarantees under wide coverage. The low-frequency microwave band used by 4G can obviously no longer meet the requirements, while the millimeter wave band can meet the high-speed data transmission needs of 5G.

[0003] To enhance coverage, millimeter-wave micro base stations can be deployed extensively in hotspot areas within the coverage range of existing low-frequency macro base stations, forming a high-low frequency heterogeneous network to provide high-speed communication services to users in these areas. However, traditional beam scanning requires a significant amount of time, which cannot meet the real-time requirements of beam configuration in high-low frequency heterogeneous network scenarios.

[0004] It should be noted that the information disclosed in the background section above is only used to enhance the understanding of the background of this disclosure, and therefore may include information that does not constitute prior art known to those skilled in the art. Summary of the Invention

[0005] This disclosure provides a configuration method, apparatus, device, and medium for distributed beam management, which at least to some extent overcomes the problem that traditional beam scanning in related technologies requires a lot of time and cannot meet the real-time requirements of beam configuration, as well as the problem of user privacy leakage when transmitting user data in multiple base stations.

[0006] Other features and advantages of this disclosure will become apparent from the following detailed description, or may be learned in part from practice of this disclosure.

[0007] According to one aspect of this disclosure, a configuration method suitable for distributed beam management of wireless intelligent air interfaces is provided. Multiple micro base stations are deployed in some hotspot areas within the service range of a macro base station. A federated learning framework is used between the macro base station and the micro base stations, deploying a global model at the macro base station and a local model at the micro base stations. The method is applied to the micro base stations and includes:

[0008] Receive configuration signaling from macro base station. The configuration signaling carries initial beam configuration information, including macro base station beam parameter configuration and micro base station beam parameter configuration.

[0009] The initial beam configuration information is used as the initial state for the micro base station to make beam configuration decisions, and the initial configuration for beam decision-making of the micro base station is performed.

[0010] Based on the initial beam configuration information, the micro base station collects local user location distribution data by interacting with the surrounding environment;

[0011] The collected local user location distribution data is input into a pre-trained local model to determine the beam configuration required to maximize the network's long-term throughput.

[0012] In one embodiment of this disclosure, the macro base station beam parameter configuration includes at least one of beamwidth and the upper limit number of serving micro base stations;

[0013] The micro base station beam configuration includes at least one of the following: the sector to which each beam points at the initial moment, the beam width, the number of sectors around a single micro base station, the available bandwidth of the macro base station occupied by all user equipment within a single micro base station, and the upper limit of the number of beams that a single micro base station can generate at a given moment.

[0014] In one embodiment of this disclosure, configuration signaling is transmitted via the Xn interface.

[0015] In one embodiment of this disclosure, the message type for configuration signaling is either an Xn setting request message or an Xn configuration update message.

[0016] In one embodiment of this disclosure, the initial beam configuration information is determined by the macro base station based on the cell network environment, channel conditions, geographical location of user equipment, and the number of access user equipment.

[0017] In one embodiment of this disclosure, the method further includes:

[0018] Collect user data through interaction with the environment;

[0019] Use user data to train the local model and update the parameters of the local model;

[0020] After the local model converges, the local model is uploaded to the macro base station so that the macro base station can aggregate the multiple local models received and update the global model parameters.

[0021] Download and update global model parameters from macro base stations;

[0022] Based on the global model parameters, the local model is updated to obtain the trained local model.

[0023] According to another aspect of this disclosure, a configuration method suitable for distributed beam management of wireless intelligent air interfaces is provided. Multiple micro base stations are deployed in some hotspot areas within the service range of a macro base station. A federated learning framework is used between the macro base station and the micro base stations, deploying a global model at the macro base station and a local model at the micro base stations. The method is applied to the macro base station and includes:

[0024] Configuration signaling is sent to the micro base station, carrying initial beam configuration information, including macro base station beam parameter configuration and micro base station beam parameter configuration, so that the micro base station uses the initial beam configuration information as the initial state for beam configuration decision-making. Each micro base station collects user location distribution data in the surrounding environment and inputs it into a pre-trained local model to obtain the beam configuration that maximizes the long-term throughput of the network and determines the beam configuration required to maximize the long-term throughput of the network.

[0025] According to another aspect of this disclosure, a configuration device suitable for distributed beam management of wireless intelligent air interfaces is provided. Multiple micro base stations are deployed in some hotspot areas within the service range of a macro base station. A federated learning framework is used between the macro base station and the micro base stations, with a global model deployed at the macro base station and a local model deployed at the micro base stations. The device is applied to the micro base stations and includes:

[0026] The signaling receiving module is used to receive configuration signaling from the macro base station. The configuration signaling carries initial beam configuration information, which includes macro base station beam parameter configuration and micro base station beam parameter configuration.

[0027] The initialization configuration module is used to initialize the micro base station's beam configuration decision by taking the initial beam configuration information as the initial state for beam configuration decision-making.

[0028] The data collection module is used by the micro base station to collect local user location distribution data by interacting with the surrounding environment based on the initial beam configuration information.

[0029] The beam configuration module is used to input the collected local user location distribution data into a pre-trained local model to determine the beam configuration required to maximize the long-term throughput of the network.

[0030] According to another aspect of this disclosure, a configuration device suitable for distributed beam management of wireless intelligent air interfaces is provided. Multiple micro base stations are deployed in some hotspot areas within the service range of a macro base station. A federated learning framework is used between the macro base station and the micro base stations, with a global model deployed at the macro base station and a local model deployed at the micro base stations. The device is applied to the macro base station and includes:

[0031] The signaling transmission module is used to send configuration signaling to the micro base station. The configuration signaling carries initial beam configuration information, which includes macro base station beam parameter configuration and micro base station beam parameter configuration. This allows the micro base station to use the initial beam configuration information as the initial state for intelligent beam configuration decision-making. Each micro base station collects local user location distribution data by interacting with the surrounding environment and inputs it into a pre-trained local model to obtain the beam configuration that maximizes the long-term throughput of the network and determines the beam configuration required to maximize the long-term throughput of the network.

[0032] According to another aspect of this disclosure, an electronic device is provided, comprising: a memory for storing instructions; and a processor for calling the instructions stored in the memory to implement the above-described configuration method for wireless intelligent air interface distributed beam management.

[0033] According to another aspect of this disclosure, a computer-readable storage medium is provided that stores computer instructions thereon, which, when executed by a processor, implement the above-described configuration method for distributed beam management of a wireless intelligent air interface.

[0034] According to another aspect of this disclosure, a computer program product is provided, which stores instructions that, when executed by a computer, cause the computer to implement the above-described configuration method for distributed beam management of a wireless intelligent air interface.

[0035] According to another aspect of this disclosure, a chip is provided, including at least one processor and an interface;

[0036] An interface is used to provide program instructions or data to at least one processor;

[0037] At least one processor is used to execute program instructions to implement the above-described configuration method for distributed beam management of wireless intelligent air interfaces.

[0038] The configuration method, apparatus, device, and medium for distributed beam management of wireless intelligent air interfaces provided in this disclosure deploy multiple micro base stations in some hotspot areas within the service range of a macro base station. A federated learning framework is used between the macro base station and the micro base stations, with a global model deployed at the macro base station and a local model deployed at the micro base stations. The macro base station performs initial beam configuration for multiple micro base stations through configuration signaling. The micro base stations input the collected local user location distribution data into the pre-trained local model to obtain the beam configuration that maximizes the long-term throughput of the network and determines the beam configuration required to maximize the long-term throughput of the network. The beam direction is adjusted in real time to provide users with high-quality communication services. This solves the problems of traditional beam scanning requiring a lot of time and failing to meet the real-time requirements of beam configuration, as well as the difficulties in beam management due to the dramatic increase in the number of beams.

[0039] Furthermore, this disclosure employs a federated learning framework between macro base stations and micro base stations, deploying a global model on macro base stations and a local model on micro base stations. During model training, only the models need to be exchanged instead of the raw data, effectively avoiding frequent signaling interactions between micro base stations, reducing system overhead and power consumption, and solving the privacy issue of raw data regarding user location. At the same time, it can improve network performance from a global perspective.

[0040] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0041] The accompanying drawings, which are incorporated in and form a part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure.

[0042] Obviously, the accompanying drawings described below are merely some embodiments of this disclosure. Those skilled in the art can obtain other drawings based on these drawings without any creative effort.

[0043] Figure 1 This diagram illustrates a smart beam management scenario according to an embodiment of the present disclosure.

[0044] Figure 2 A flowchart illustrating a configuration method for distributed beam management of a wireless intelligent air interface according to an embodiment of this disclosure is shown.

[0045] Figure 3 A schematic diagram illustrating the model training process in an embodiment of this disclosure is shown;

[0046] Figure 4 This diagram illustrates the process of a distributed federated learning model converging and distributing models in an embodiment of this disclosure.

[0047] Figure 5 A flowchart illustrating another configuration method applicable to distributed beam management of a wireless intelligent air interface is shown in an embodiment of this disclosure;

[0048] Figure 6 A flowchart illustrating another configuration method applicable to distributed beam management of a wireless intelligent air interface is shown in an embodiment of this disclosure;

[0049] Figure 7 This illustration shows a configuration device for distributed beam management of a wireless intelligent air interface according to an embodiment of the present disclosure.

[0050] Figure 8 This illustration shows a schematic diagram of another configuration device suitable for distributed beam management of a wireless intelligent air interface in an embodiment of this disclosure;

[0051] Figure 9 A structural block diagram of an electronic device according to an embodiment of the present disclosure is shown. Detailed Implementation

[0052] The exemplary implementation will now be described more fully with reference to the accompanying drawings.

[0053] It should be noted that the example implementation can be implemented in many forms and should not be construed as being limited to the examples set forth herein.

[0054] The inventors discovered that commonly used non-intelligent beam configuration methods include deterministic beam configuration and exhaustive beam configuration.

[0055] Deterministic beam configuration refers to base stations adjusting the beam direction according to a predefined sequence of directions. The drawback is that the beam configuration cannot be adjusted according to real-time changes in user distribution.

[0056] Exhaustive beam configuration involves the base station scanning all possible beam directions and selecting the optimal beam configuration. This decision-making process has a high latency and is not suitable for scenarios where user distribution changes rapidly.

[0057] Therefore, in the heterogeneous network technology described in the background, the following problems will be faced: 1) Traditional beam scanning requires a lot of time and cannot meet the real-time requirements of beam configuration; 2) User data is private, so how to avoid transmission in multiple base stations; 3) The number of beams in the network increases dramatically, making beam management more difficult.

[0058] Reinforcement learning has been widely applied in the field of communications and has achieved good results, validating its enormous potential. The dynamic beam configuration problem of dense millimeter-wave micro base stations is a continuous decision-making problem, and therefore, reinforcement learning can be applied to solve it.

[0059] Considering the distributed nature of networks and the privacy of user data, a method combining distributed federated learning and deep reinforcement learning can be used for intelligent decision-making on beam configuration.

[0060] The following detailed description of this exemplary implementation method is provided in conjunction with the accompanying drawings and embodiments.

[0061] In this embodiment, the intelligent decision-making for distributed beam configuration adopts a distributed federated learning framework, combined with a deep reinforcement learning-based beam optimization algorithm on the micro base station side, to find a real-time and efficient beam configuration strategy.

[0062] Figure 1 This illustrates a smart beam management scenario, such as... Figure 1 As shown, in a heterogeneous network with densely deployed micro base stations in hotspot areas, the low-frequency macro base station 101 (MBS) is responsible for global control plane signaling transmission and provides coverage services; the micro base station 102 (mSBS) is responsible for high-speed transmission of large amounts of service data in the data plane and provides high-quality communication services. The micro base stations can be millimeter-wave micro base stations. Both macro base station 101 and micro base station 102 can serve user equipment 103.

[0063] like Figure 1 As shown, the intelligent beam management scenario may also include obstacles 104 and reflectors 105.

[0064] Macro base station 101 can perform global static / semi-static / dynamic configuration of micro base stations 102 within its coverage area through control signaling based on the network environment, channel conditions, geographical location of user equipment 103, and number of access user equipment 103 in the cell, so as to support intelligent decision-making for distributed beam configuration.

[0065] In some embodiments, the macro base station 101 performs initial configuration for the micro base station through the Xn interface (which also serves as the transmission interface for subsequent model uploading and distribution), which is the initial state for the micro base station 102 to make intelligent beam configuration decisions.

[0066] In some embodiments, the micro base station 102 makes beam configuration decisions in real time based on the global model issued by the macro base station and the current changes in the location distribution of the user equipment 103.

[0067] Figure 2 This diagram illustrates a configuration method for distributed beam management of a wireless intelligent air interface according to an embodiment of the present disclosure. Figure 2 The configuration method shown is applicable to distributed beam management of wireless intelligent air interface. It can be applied to intelligent beam management scenarios. In intelligent beam management scenarios, multiple micro base stations are deployed in some hot spots within the service range of macro base stations. A federated learning framework is used between macro base stations and micro base stations. A global model is deployed on macro base stations and a local model is deployed on micro base stations.

[0068] like Figure 2 As shown, the configuration method for distributed beam management of wireless intelligent air interface provided in this embodiment includes steps S202-S208.

[0069] In S202, the macro base station sends configuration signaling to multiple micro base stations. The configuration signaling carries initial beam configuration information, which includes the macro base station beam parameter configuration and the micro base station beam parameter configuration.

[0070] In some embodiments, the macro base station beam parameter configuration may include beamwidth and the upper limit of the number of serving micro base stations; the micro base station beam configuration may include the sector to which each beam points at the initial moment, beamwidth, the number of sectors around a single micro base station, the available bandwidth of the macro base station occupied by all user equipment within a single micro base station, and the upper limit of the number of beams that a single micro base station can generate at a given moment.

[0071] In some embodiments, configuration signaling in S202 can be transmitted via the Xn interface.

[0072] In some embodiments, the message type of the configuration signaling can be an Xn SETUPREQUEST message or an Xn Configuration Update message, or it can be a custom type.

[0073] In addition, the message type for micro base stations to send information to macro base stations can be Xn SETUPREQUEST or Xn Configuration Update, or it can be a custom type.

[0074] In this embodiment of the disclosure, the initial configuration of intelligent beam management is uniformly configured by the macro base station. The macro base station sends configuration signaling to multiple micro base stations for the initial configuration of model parameters for intelligent beam configuration decision-making by millimeter-wave micro base stations under the distributed framework.

[0075] In S204, the initial beam configuration information is used as the initial state for the micro base station to make beam configuration decisions, and the initial configuration for beam decision-making of the micro base station is performed.

[0076] In S206, based on the initial beam configuration information, the micro base station collects local user location distribution data by interacting with the surrounding environment.

[0077] In S208, the collected local user location distribution data is input into a pre-trained local model to determine the beam configuration required to maximize the long-term throughput of the network.

[0078] In some embodiments, the local model runs on a micro base station, with the input being the local user location distribution data collected by the micro base station at time t, and the output being the maximum long-term throughput of the network. Then, based on the maximum long-term throughput of the network, the beam configuration required to satisfy the maximum long-term throughput of the network can be determined.

[0079] In this embodiment of the disclosure, the initial beam configuration information may be determined by the macro base station based on the network environment of the cell, channel conditions, geographical location of user equipment, and the number of access user equipment.

[0080] It should be noted that, in the embodiments of this disclosure, the user equipment may be a mobile phone, tablet computer, laptop, vehicle communication device, drone, remote-controlled aircraft, aircraft, small aircraft, vehicle, vehicle, vehicle communication device, and other wireless communication devices.

[0081] Beam configuration decision refers to the actions taken under the maximum throughput conditions, which is the direction of beam configuration.

[0082] This disclosure applies to distributed beam management of wireless intelligent air interfaces, addressing the issues of initial beam configuration and transmission of configuration parameters for millimeter-wave micro base stations in distributed networks. It provides a specific design scheme for initial beam parameter configuration and transmission, enabling real-time beam direction adjustment to provide users with high-quality communication services. This solves the problems of traditional beam scanning requiring significant time, failing to meet real-time beam configuration requirements, and the increasing difficulty in beam management due to the rapidly growing number of beams.

[0083] In some embodiments, this disclosure also includes a model training process. This disclosure uses a distributed federated learning framework running on a macro base station to complete the model aggregation and parameter distribution process, and uses a deep reinforcement learning algorithm running on a millimeter-wave micro base station to complete the model training and local beam configuration decision.

[0084] Figure 3 The process of model training in this disclosure is illustrated as follows: Figure 3 As shown, the model training process includes steps S302-S310.

[0085] In S302, user data is collected through interaction with the environment.

[0086] The collected user data is used as training samples for the local model. The training samples are only used locally at the micro base station and do not need to be transmitted to other base station equipment, thus avoiding information leakage caused by data transmission.

[0087] In S304, user data is used to train the local model and update the parameters of the local model.

[0088] The local model is trained on the micro base station until it converges.

[0089] In S306, after the local model converges, the local model is uploaded to the macro base station so that the macro base station can aggregate the multiple local models received and update the global model parameters.

[0090] In some embodiments, S306 can upload the local model to the macro base station via the Xn interface.

[0091] In some embodiments, the message type for a micro base station to upload a local model to a macro base station can be an Xn SETUP REQUEST message or an Xn Configuration Update message, or it can be a custom type.

[0092] During model training, micro base stations do not transmit user data to macro base stations, which reduces the risk of user data leakage.

[0093] In S308, global model parameters are downloaded and updated from the macro base station.

[0094] In S310, the local model is updated based on the global model parameters to obtain the trained local model.

[0095] After updating the local model based on the global model parameters, the micro base station can apply the updated local model to predict the maximum long-term throughput of the network in S204 above.

[0096] Figure 4 This diagram illustrates the process of accumulating and distributing the distributed federated learning model in this disclosure. The following section, in conjunction with the appendix, provides a detailed explanation. Figure 4 Explain the training process of the above model.

[0097] like Figure 4 As shown, the macro base station 401 stores two parameters: global model parameters and global control variables, while the micro base station 402 stores local model parameters and local control variables. This embodiment focuses on how the macro base station initializes and configures the parameters of the millimeter-wave micro base station and how it transmits the data.

[0098] The model training process in this embodiment may include the following steps:

[0099] Step a: At the start of training, the macro base station distributes the global model to initialize the local model of the millimeter-wave micro base station serving the service;

[0100] Step b: Initialize the parameters of the beam management model on the millimeter-wave micro base station side;

[0101] Step c: Each millimeter-wave micro base station collects user data by interacting with the environment, thereby training the model for the deep reinforcement learning algorithm and updating the local model parameters.

[0102] Step d, repeat step c, and proceed to step e after the local model converges;

[0103] Step e: All local models on the millimeter-wave micro base station side are uploaded to the macro base station via the Xn interface;

[0104] In step f, the macro base station will aggregate the received models, update the global model parameters, and distribute them through the Xn interface.

[0105] Step g: Each millimeter-wave micro base station downloads and updates the global model parameters from the macro base station to update the local model, and collects user data at the current time to make beam configuration decisions;

[0106] Step h, return to step a, and wait for the next round of beam configuration decision.

[0107] In this embodiment, the beam configuration problem is treated as a Markov Decision Process (MDP). The MDP consists of four tuples, M = (S, A, P, R), where S represents the state space, A represents the action space, P represents the state transition probability, and R represents the reward function. In some embodiments, the four tuples of the model can be defined as follows:

[0108] (1) State: The state of the network at time t is defined as S. t For micro base station b, its state is:

[0109]

[0110] Among them, U b For the set of users served by this base station at this moment, ∏ b (t) represents the beam configuration of the base station at this moment, that is, the specific sectors that each beam points to. U b The available bandwidth occupied by all users within the macro base station.

[0111] (2) Action: Specifies the node's action as configuring the beam direction. The action of the micro base station at time t is...

[0112] (3) Transition Probability: The transition probability is specified as P. t =P{S t+1 |S t a t}, that is, in state S t Next, use action a t The state becomes S. t+1 The probability of.

[0113] (4) Reward: Since the goal is to maximize the long-term throughput of the network, the reward function is defined as R. t =R(t), meaning the reward at the current moment is the system throughput.

[0114] This disclosure discloses a configuration method for distributed beam management of a wireless intelligent air interface, enabling beam configuration decisions based on distributed management. A federated learning framework is employed between macro base stations and micro base stations. Micro base stations upload their trained local models to the macro base stations for unified aggregation and then redistribution. This process only requires exchanging the learned models, not the raw data, effectively avoiding frequent signaling interactions between micro base stations, reducing system overhead and power consumption, and resolving the privacy issues related to raw user location data. Simultaneously, it improves network performance from a global perspective.

[0115] Subsequently, the micro base station updates its local model based on the global model parameters issued by the macro base station, and performs beam configuration strategies based on the current user location information. It can adjust the beam direction in real time to provide users with high-quality communication services. This solves the problems of traditional beam scanning requiring a lot of time and failing to meet the real-time requirements of beam configuration, as well as the problems of beam management difficulties caused by the dramatic increase in the number of beams.

[0116] Figure 5 This diagram illustrates a configuration method for distributed beam management of a wireless intelligent air interface according to an embodiment of the present disclosure. Figure 5 The configuration method shown is applicable to distributed beam management of wireless intelligent air interface. It can be applied to intelligent beam management scenarios. In intelligent beam management scenarios, multiple micro base stations are deployed in some hot spots within the service range of macro base stations. A federated learning framework is used between macro base stations and micro base stations. A global model is deployed on macro base stations and a local model is deployed on micro base stations.

[0117] Figure 5 The configuration method shown is applicable to distributed beam management of wireless intelligent air interface and is applied to micro base stations. The method includes steps S502-S506.

[0118] In S502, configuration signaling from a macro base station is received. The configuration signaling carries initial beam configuration information, which includes macro base station beam parameter configuration and micro base station beam parameter configuration.

[0119] In S504, the initial beam configuration information is used as the initial state for the micro base station to make beam configuration decisions, and the initial configuration for beam decision-making of the micro base station is performed.

[0120] In S506, based on the initial beam configuration information, the micro base station collects local user location distribution data by interacting with the surrounding environment;

[0121] In S508, the collected local user location distribution data is input into a pre-trained local model to determine the beam configuration required to maximize the network's long-term throughput.

[0122] In this embodiment of the disclosure, the micro base station can apply a local model to adjust the beam direction in real time, providing users with high-quality communication services. This solves the problems of traditional beam scanning requiring a lot of time and failing to meet the real-time requirements of beam configuration, as well as the problems of beam management difficulties caused by the dramatic increase in the number of beams.

[0123] Figure 6 This diagram illustrates a configuration method for distributed beam management of a wireless intelligent air interface according to an embodiment of the present disclosure. Figure 6The configuration method shown is applicable to distributed beam management of wireless intelligent air interface. It can be applied to intelligent beam management scenarios. In intelligent beam management scenarios, multiple micro base stations are deployed in some hot spots within the service range of macro base stations. A federated learning framework is used between macro base stations and micro base stations. A global model is deployed on macro base stations and a local model is deployed on micro base stations.

[0124] Figure 6 The configuration method shown is applicable to distributed beam management of wireless intelligent air interface and is applied to macro base stations. The method includes step S602.

[0125] In S602, configuration signaling is sent to the micro base station. The configuration signaling carries initial beam configuration information, including macro base station beam parameter configuration and micro base station beam parameter configuration, so that the micro base station uses the initial beam configuration information as the initial state for the micro base station to make beam configuration decisions. Each micro base station collects user location distribution data in the surrounding environment and inputs it into a pre-trained local model to obtain the beam configuration that maximizes the long-term throughput of the network and determines the beam configuration required to maximize the long-term throughput of the network.

[0126] In this embodiment of the disclosure, the macro base station uniformly configures the initialization configuration of intelligent beam management for multiple micro base stations, and the macro base station sends configuration signaling to multiple micro base stations for the model parameter initialization configuration of intelligent beam configuration decision-making of millimeter wave micro base stations under the distributed framework.

[0127] In embodiments of this disclosure, the terms "first," "second," and "third" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

[0128] In this disclosure, the term "and / or" is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this document generally indicates that the preceding and following related objects have an "or" relationship.

[0129] Furthermore, although the steps of the method in this disclosure are described in a specific order in the accompanying drawings, this does not require or imply that the steps must be performed in that specific order, or that all the steps shown must be performed to achieve the desired result.

[0130] In some embodiments, certain steps may be omitted, multiple steps may be combined into one step for execution, and / or one step may be broken down into multiple steps for execution.

[0131] Based on the same inventive concept, this disclosure also provides a configuration device suitable for distributed beam management of wireless intelligent air interfaces, as described in the following embodiments. Since the principle by which this device embodiment solves the problem is similar to that of the above-described method embodiments, the implementation of this device embodiment can refer to the implementation of the above-described method embodiments, and repeated details will not be elaborated further.

[0132] Figure 7 This embodiment illustrates a configuration device for distributed beam management of a wireless intelligent air interface. Multiple micro base stations are deployed in a partial hotspot area within the service range of a macro base station. A federated learning framework is used between the macro base station and the micro base stations, with a global model deployed at the macro base station and a local model deployed at the micro base stations. This configuration device for distributed beam management of a wireless intelligent air interface is applied to micro base stations, such as... Figure 7 As shown, the configuration device 700 for wireless intelligent air interface distributed beam management includes:

[0133] The signaling receiving module 702 is used to receive configuration signaling from the macro base station. The configuration signaling carries initial beam configuration information, which includes macro base station beam parameter configuration and micro base station beam parameter configuration.

[0134] The initialization configuration module 704 is used to initialize the micro base station by taking the initial beam configuration information as the initial state for beam configuration decision-making.

[0135] Data collection module 706 is used to collect local user location distribution data by interacting with the surrounding environment based on the initial beam configuration information;

[0136] The beam configuration module 708 is used to input the collected local user location distribution data into a pre-trained local model to determine the beam configuration required to maximize the long-term throughput of the network.

[0137] In some embodiments, the macro base station beam parameter configuration includes beamwidth and the upper limit of the number of serving micro base stations;

[0138] The micro base station beam configuration includes the sector to which each beam points at the initial moment, the beam width, the number of sectors around a single micro base station, the available bandwidth of the macro base station occupied by all user equipment within a single micro base station, and the upper limit of the number of beams that a single micro base station can generate at a given moment.

[0139] In some embodiments, configuration signaling is transmitted via the Xn interface.

[0140] In some embodiments, the message type of the configuration signaling is an Xn setting request message or an Xn configuration update message.

[0141] In some embodiments, the initial beam configuration information is determined by the macro base station based on the cell network environment, channel conditions, geographical location of user equipment, and number of access user equipment.

[0142] In some embodiments, the configuration device 700 for wireless intelligent air interface distributed beam management may further include a model training module, which performs the following steps:

[0143] Collect user data through interaction with the environment;

[0144] Use user data to train the local model and update the parameters of the local model;

[0145] After the local model converges, the local model is uploaded to the macro base station so that the macro base station can aggregate the multiple local models received and update the global model parameters.

[0146] Download and update global model parameters from macro base stations;

[0147] Based on the global model parameters, the local model is updated to obtain the trained local model.

[0148] Based on the same inventive concept, this disclosure also provides a configuration device suitable for distributed beam management of wireless intelligent air interfaces. Multiple micro base stations are deployed in some hotspot areas within the service range of a macro base station. A federated learning framework is used between the macro base station and the micro base stations, with a global model deployed at the macro base station and a local model deployed at the micro base stations. This configuration device for distributed beam management of wireless intelligent air interfaces is applied to macro base stations, such as... Figure 8 As shown, the configuration device 800 for wireless intelligent air interface distributed beam management includes:

[0149] The signaling sending module 802 is used to send configuration signaling to the micro base station. The configuration signaling carries initial beam configuration information, which includes macro base station beam parameter configuration and micro base station beam parameter configuration. This allows the micro base station to use the initial beam configuration information as the initial state for intelligent beam configuration decision-making. Each micro base station collects local user location distribution data by interacting with the surrounding environment and inputs it into a pre-trained local model to obtain the beam configuration that maximizes the long-term throughput of the network and determines the beam configuration required to maximize the long-term throughput of the network.

[0150] The concepts of "first" and "second" mentioned in this disclosure are used only to distinguish different devices, modules or units, and are not used to define the order of functions performed by these devices, modules or units or their interdependencies.

[0151] Regarding the configuration apparatus for wireless intelligent air interface distributed beam management in the above embodiments, the specific manner in which each module performs its operation has been described in detail in the embodiments of the configuration method for wireless intelligent air interface distributed beam management, and will not be elaborated here.

[0152] In summary, the configuration device for distributed beam management of wireless intelligent air interface provided in this application embodiment deploys multiple micro base stations in some hotspot areas within the service range of the macro base station. A federated learning framework is adopted between the macro base station and the micro base stations, with a global model deployed at the macro base station and a local model deployed at the micro base station. The macro base station performs initial beam configuration for multiple micro base stations through configuration signaling. The micro base stations input the initial beam configuration information into the pre-trained local model to obtain the maximum long-term throughput of the network. Then, based on the initial beam configuration information, the beam configuration required to maximize the long-term throughput of the network is determined, and the beam direction is adjusted in real time to provide users with high-quality communication services. This solves the problems of traditional beam scanning requiring a lot of time and failing to meet the real-time requirements of beam configuration, as well as the problems of beam management difficulties caused by the dramatic increase in the number of beams.

[0153] Furthermore, this disclosure employs a federated learning framework between macro base stations and micro base stations, deploying a global model on macro base stations and a local model on micro base stations. During model training, only the models need to be exchanged instead of the raw data, effectively avoiding frequent signaling interactions between micro base stations, reducing system overhead and power consumption, and solving the privacy issue of raw data regarding user location. At the same time, it can improve network performance from a global perspective.

[0154] It should be noted that although several modules or units of the device used for action execution are mentioned in the detailed description above, this division is not mandatory.

[0155] In fact, according to embodiments of this disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided and embodied by multiple modules or units.

[0156] Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities can be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor devices and / or microcontroller devices.

[0157] The following reference Figure 9 This describes the electronic device provided in the embodiments of this disclosure. Figure 9The electronic device 900 shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments disclosed herein.

[0158] Figure 9 This diagram illustrates the architecture of an electronic device 900 according to an embodiment of the present invention. Figure 9 As shown, the electronic device 900 includes, but is not limited to, at least one processor 910 and at least one memory 920.

[0159] Memory 920 is used to store instructions.

[0160] In some embodiments, memory 920 may include a readable medium in the form of volatile memory cells, such as random access memory (RAM) 9201 and / or cache memory 9202, and may further include read-only memory (ROM) 9203.

[0161] In some embodiments, the memory 920 may also include a program / utility 9204 having a set (at least one) program module 9205, such program module 9205 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each or some combination of these examples may include an implementation of a network environment.

[0162] In some embodiments, the memory 920 may store an operating system. This operating system may be a real-time operating system (RTX), such as Linux, UNIX, Windows, or OS X.

[0163] In some embodiments, the memory 920 may also store data.

[0164] As an example, processor 910 can read data stored in memory 920, which may be stored at the same memory address as the instruction, or the data may be stored at a different memory address than the instruction.

[0165] Processor 910 is configured to invoke instructions stored in memory 920 to implement the steps described in the "Exemplary Methods" section above, based on various exemplary embodiments of this disclosure. For example, processor 910 may execute the following steps of the above method embodiments:

[0166] Receive configuration signaling from macro base station. The configuration signaling carries initial beam configuration information, including macro base station beam parameter configuration and micro base station beam parameter configuration.

[0167] The initial beam configuration information is used as the initial state for the micro base station to make beam configuration decisions, and the initial configuration for beam decision-making of the micro base station is performed.

[0168] Based on the initial beam configuration information, the micro base station collects local user location distribution data by interacting with the surrounding environment;

[0169] The collected local user location distribution data is input into a pre-trained local model to determine the beam configuration required to maximize the network's long-term throughput.

[0170] Alternatively, perform the following steps in the above method embodiment:

[0171] Configuration signaling is sent to the micro base station, carrying initial beam configuration information, including macro base station beam parameter configuration and micro base station beam parameter configuration. This initial beam configuration information is used as the initial state for the micro base station to make intelligent beam configuration decisions. Each micro base station collects local user location distribution data by interacting with the surrounding environment and inputs it into a pre-trained local model to obtain the beam configuration that maximizes the long-term throughput of the network and determines the beam configuration required to maximize the long-term throughput of the network.

[0172] It should be noted that the processor 910 described above can be a general-purpose processor or a special-purpose processor. The processor 910 may include one or more processing cores, and the processor 910 executes various functional applications and data processing by running instructions.

[0173] In some embodiments, processor 910 may include a central processing unit (CPU) and / or a baseband processor.

[0174] In some embodiments, the processor 910 may determine an instruction based on the priority identifier and / or function category information carried in each control instruction.

[0175] In this disclosure, the processor 910 and the memory 920 can be configured separately or integrated together.

[0176] As an example, the processor 910 and memory 920 can be integrated on a single board or a system-on-a-chip (SOC).

[0177] like Figure 9 As shown, the electronic device 900 is presented in the form of a general-purpose computing device. The electronic device 900 may also include a bus 930.

[0178] Bus 930 can represent one or more of several types of bus structures, including a memory bus or memory controller, peripheral bus, graphics acceleration port, processor, or a local bus using any of the various bus structures.

[0179] Electronic device 900 can also communicate with one or more external devices 940 (e.g., keyboard, pointing device, Bluetooth device, etc.), and with one or more devices that enable a user to interact with electronic device 900, and / or with any device that enables electronic device 900 to communicate with one or more other computing devices (e.g., router, modem, etc.). Such communication can be performed through input / output (I / O) interface 950.

[0180] Furthermore, the electronic device 900 can also communicate with one or more networks (such as local area networks (LANs), wide area networks (WANs), and / or public networks, such as the Internet) via the network adapter 960.

[0181] like Figure 9 As shown, the network adapter 960 communicates with other modules of the electronic device 900 via the bus 930.

[0182] It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with electronic device 900, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0183] It is understood that the structure illustrated in the embodiments of this disclosure does not constitute a specific limitation on the electronic device 900. In other embodiments of this disclosure, the electronic device 900 may include... Figure 9 This may involve more or fewer components, or combining certain components, or splitting certain components, or different component arrangements. Figure 9 The components shown can be implemented in hardware, software, or a combination of both.

[0184] This disclosure also provides a computer-readable storage medium storing computer instructions thereon, which, when executed by a processor, implement the configuration method for distributed beam management of wireless intelligent air interfaces described in the above method embodiments.

[0185] In this embodiment of the disclosure, the computer-readable storage medium is a computer instruction that can be sent, propagated, or transmitted for use by or in conjunction with an instruction execution system, apparatus, or device.

[0186] As an example, a computer-readable storage medium is a non-volatile storage medium.

[0187] In some embodiments, more specific examples of computer-readable storage media in this disclosure may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, USB flash drives, portable hard drives, or any suitable combination of the foregoing.

[0188] In this embodiment of the disclosure, the computer-readable storage medium may include data signals propagated in baseband or as part of a carrier wave, wherein computer instructions (readable program code) are carried.

[0189] The transmitted data signal can take many forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof.

[0190] In some examples, computational instructions contained on a computer-readable storage medium may be transmitted using any suitable medium, including but not limited to wireless, wired, optical fiber, RF, etc., or any suitable combination thereof.

[0191] This disclosure also provides a computer program product that stores instructions that, when executed by a computer, cause the computer to implement the configuration method for wireless intelligent air interface distributed beam management described in the above method embodiments.

[0192] The aforementioned instructions can be program code. In practice, the program code can be written using any combination of one or more programming languages.

[0193] Programming languages ​​include object-oriented programming languages—such as Java and C++—as well as conventional procedural programming languages—such as the "C" language or similar programming languages.

[0194] The program code can be executed entirely on the user's computing device, partially on the user's computing device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0195] In cases involving remote computing devices, the remote computing devices can be connected to user computing devices via any type of network, including local area networks (LANs) or wide area networks (WANs), or they can be connected to external computing devices (e.g., via the Internet using an Internet service provider).

[0196] This disclosure also provides a chip, including at least one processor and an interface;

[0197] An interface is used to provide program instructions or data to at least one processor;

[0198] At least one processor is used to execute program instructions to implement the configuration method for wireless intelligent air interface distributed beam management described in the above method embodiments.

[0199] In some embodiments, the chip may further include a memory for storing program instructions and data, the memory being located within or outside the processor.

[0200] Those skilled in the art will understand that all or part of the steps of the above embodiments can be specifically implemented in the following forms: a completely hardware implementation, a completely software implementation (including firmware, microcode, etc.), or a combination of hardware and software implementations, which can be collectively referred to as "circuit", "module" or "system".

[0201] Other embodiments of this disclosure will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein.

[0202] This disclosure is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not disclosed herein. The description and examples are to be considered exemplary only, and the true scope and spirit of this disclosure are indicated by the appended claims.

Claims

1. A configuration method suitable for wireless intelligent air interface distributed beam management, characterized in that, A plurality of micro base stations are deployed in some hot spot areas within the service range of a macro base station, a federal learning framework is adopted between the macro base station and the micro base stations, a global model is deployed in the macro base station, and a local model is deployed in the micro base stations; The method is applied to a micro base station, and the method comprises: receiving configuration signaling from the macro base station, the configuration signaling carrying initial beam configuration information, the initial beam configuration information comprising macro base station beam parameter configuration and micro base station beam parameter configuration, the micro base station beam configuration comprising a sector pointed to by each beam at an initial time, a beam width, a number of sectors around a single micro base station, a bandwidth occupied by all user equipment in the single micro base station on a macro base station, and an upper limit number of beams generated by the single micro base station at a time; using the initial beam configuration information as an initial state for the micro base station to make a beam configuration decision, and initializing the micro base station for beam decision making; on the basis of the initial beam configuration information, collecting local user position distribution data by the micro base station through interaction with the surrounding environment; inputting the collected local user position distribution data into a pre-trained local model to determine a beam configuration that meets the need to maximize the long-term throughput of the network; wherein a state space of the local model used to determine the beam configuration of the micro base station comprises a user set served by the base station at the moment, a beam configuration of the base station at the moment, and a bandwidth occupied by all users in the user set on a macro base station; the beam configuration of the base station at the moment comprises a sector pointed to by each beam.

2. The method of claim 1, wherein, The macro base station beam parameter configuration comprises at least one of a beam width and an upper limit number of serving micro base stations.

3. The method of claim 2, wherein, The configuration signaling is transmitted through an Xn interface.

4. The method of claim 3, wherein, The message type of the configuration signaling is an Xn setup request message or an Xn configuration update message.

5. The method of claim 2, wherein, The initial beam configuration information is determined by the macro base station according to the network environment, channel conditions, geographic location of user equipment, and number of accessed user equipment in the cell.

6. The method according to any one of claims 1 to 5, characterized in that, The method further comprises: collecting user data through interaction with the environment; training the local model by applying the user data and updating parameters of the local model; after the local model converges, uploading the local model to the macro base station, so that the macro base station aggregates the received multiple local models to update global model parameters; downloading updated global model parameters from the macro base station; updating the local model based on the global model parameters to obtain a trained local model. 7.A configuration method suitable for wireless intelligent air interface distributed beam management, characterized in that, A plurality of micro base stations are deployed in some hot spot areas within the service range of a macro base station, a federal learning framework is adopted between the macro base station and the micro base stations, a global model is deployed in the macro base station, and a local model is deployed in the micro base stations; The method is applied to a macro base station, and the method comprises: The micro base station is sent configuration signaling, the configuration signaling carries initial beam configuration information, the initial beam configuration information includes macro base station beam parameter configuration and micro base station beam parameter configuration, so that the micro base station takes the initial beam configuration information as the initial state of the beam configuration decision of the micro base station, each micro base station collects local user position distribution data by interacting with the surrounding environment, inputs into the pre-trained local model, obtains the maximum network long-term throughput, and determines the beam configuration required to satisfy the maximum network long-term throughput; The micro base station beam configuration includes the sector to which each beam points at the initial time, the beam width, the number of sectors around a single micro base station, the available bandwidth of the macro base station occupied by all user equipment in a single micro base station, and the upper limit number of beams generated by a single micro base station at one time. The state space of the local model for determining the beam configuration of the micro base station includes the user set served by the base station at this moment, the beam configuration of the base station at this moment, and the available bandwidth of the macro base station occupied by all users in the user set; the beam configuration of the base station at this moment includes the sector to which each beam points. 8.A configuration device suitable for wireless intelligent air interface distributed beam management, characterized in that, Multiple micro base stations are deployed in part of the hot spot areas within the service range of the macro base station, a federal learning framework is used between the macro base station and the micro base station, a global model is deployed in the macro base station, and a local model is deployed in the micro base station. The device is applied to a micro base station, and the device includes: A signaling receiving module is configured to receive configuration signaling from the macro base station, the configuration signaling carries initial beam configuration information, the initial beam configuration information includes macro base station beam parameter configuration and micro base station beam parameter configuration, and the micro base station beam configuration includes the sector to which each beam points at the initial time, the beam width, the number of sectors around a single micro base station, the available bandwidth of the macro base station occupied by all user equipment in a single micro base station, and the upper limit number of beams generated by a single micro base station at one time. An initialization configuration module is configured to take the initial beam configuration information as the initial state of the beam configuration decision of the micro base station, and perform initialization configuration for the beam decision of the micro base station. A data collection module is configured to collect local user position distribution data by interacting with the surrounding environment on the basis of the initial beam configuration information. A beam configuration module is configured to input the collected local user position distribution data into a pre-trained local model to determine the beam configuration required to satisfy the maximum network long-term throughput. The state space of the local model for determining the beam configuration of the micro base station includes the user set served by the base station at this moment, the beam configuration of the base station at this moment, and the available bandwidth of the macro base station occupied by all users in the user set; the beam configuration of the base station at this moment includes the sector to which each beam points. 9.A configuration device suitable for wireless intelligent air interface distributed beam management, characterized in that, Multiple micro base stations are deployed in part of the hot spot areas within the service range of the macro base station, a federal learning framework is used between the macro base station and the micro base station, a global model is deployed in the macro base station, and a local model is deployed in the micro base station. The device is applied to a macro base station, and the device includes: The signaling sending module is configured to send configuration signaling to the micro base station, wherein the configuration signaling carries initial beam configuration information, and the initial beam configuration information comprises macro base station beam parameter configuration and micro base station beam parameter configuration, so that the micro base station takes the initial beam configuration information as an initial state for intelligent decision of beam configuration of the micro base station. Each micro base station collects local user position distribution data by interacting with the surrounding environment, inputs the data into a pre-trained local model, obtains maximum network long-term throughput, and determines beam configuration required to satisfy the maximum network long-term throughput. The micro base station beam configuration comprises a sector to which each beam points at an initial time, a beam width, a number of sectors around a single micro base station, available bandwidth of a macro base station occupied by all user equipment in the single micro base station, and an upper limit number of beams generated by the single micro base station at one time. A state space of the local model for determining the beam configuration of the micro base station comprises a user set served by the base station at this moment, a beam configuration of the base station at this moment, and available bandwidth of the macro base station occupied by all users in the user set; and the beam configuration of the base station at this moment comprises a sector to which each beam points.

10. An electronic device, comprising: The memory is configured to store instructions. The processor is configured to call the instructions stored in the memory, and implement the configuration method suitable for distributed beam management of a wireless intelligent air interface according to any one of claims 1 to 7. The computer instructions are executed by the processor to implement the configuration method suitable for distributed beam management of a wireless intelligent air interface according to any one of claims 1 to 7.

11. A computer readable storage medium having stored thereon computer instructions, wherein, ​

Images