Communication method and apparatus, electronic device, and nonvolatile storage medium

Abstract

The application discloses a communication method and device, electronic equipment and nonvolatile storage medium. The method comprises: obtaining flight parameters of a UAV, wherein the flight parameters are used to represent the flight state of the UAV during take-off and flight; determining target beam parameters of a space base station in a low-altitude network according to the flight parameters, wherein the beam parameters comprise: a target number of synchronization signal block beams transmitted by the space base station, and the target number is the minimum number of beams that the space base station can use to realize directional tracking of the UAV in the coverage range of the base station; and controlling the space base station to transmit synchronization signal block beams according to the target beam parameters, so as to realize communication between the space base station and the UAV. The application solves the technical problem of the related art that the low-altitude network deployment scheme has prominent ground interference and high network power consumption.

Description

Technical Field

[0001] This application relates to the field of wireless communication technology, and more specifically, to a communication method, apparatus, electronic device, and non-volatile storage medium. Background Technology

[0002] With the rapid evolution of the low-altitude economy, emerging businesses such as drone inspections and smart logistics are driving a continuous increase in demand for high-speed, low-latency airspace networks. However, among related technologies, the low-altitude networks deployed by operators exhibit significant ground interference, greatly impacting ground users. Furthermore, although the current scale of drone operations is limited, their suddenness and high real-time requirements prevent base stations from implementing deep energy-saving strategies, resulting in high overall network power consumption, which contradicts the development direction of green energy conservation.

[0003] There is currently no effective solution to the above problems. Summary of the Invention

[0004] This application provides a communication method, apparatus, electronic device, and non-volatile storage medium to at least solve the technical problems of prominent ground interference and high overall network power consumption in low-altitude network deployment schemes in related technologies.

[0005] According to one aspect of the embodiments of this application, a communication method is provided, comprising: acquiring flight parameters of a drone, wherein the flight parameters are used to characterize the flight state of the drone during takeoff and flight; determining target beam parameters of an airspace base station in a low-altitude network based on the flight parameters, wherein the target beam parameters include: a target number of synchronization signal block beams transmitted by the airspace base station, the target number being the minimum number of beams that the airspace base station can use to achieve directional tracking of drones within the coverage area of ​​the base station; and controlling the airspace base station to transmit synchronization signal block beams according to the target beam parameters to realize communication between the airspace base station and the drone.

[0006] Optionally, determining the target beam parameters of the airspace base station in the low-altitude network based on flight parameters includes: when the UAV is controlled in a first mode, obtaining the preset flight path corresponding to the UAV, and determining the initial beam parameters of the airspace base station based on the preset flight path; and, during the actual flight of the UAV, adjusting the initial beam parameters based on the flight parameters of the UAV during the actual flight to obtain the target beam parameters, wherein, in the first mode, the UAV flies according to the preset flight path; and / or, when the UAV is controlled in a second mode, predicting the flight path of the UAV based on the flight parameters of the UAV, and determining the target beam parameters based on the predicted flight path, wherein, in the second mode, the UAV is controlled by a flight control platform or a remote control handle.

[0007] Optionally, the method further includes: when there is a drone within the coverage area of ​​the airspace base station, setting the operating state of the airspace base station to a first state, wherein in the first state, the airspace base station can transmit synchronization signal block beams according to the target beam parameters; when there is no drone within the coverage area of ​​the airspace base station, setting the operating state of the airspace base station to a second state, wherein in the second state, the airspace base station stops transmitting signals on at least some carrier frequencies or enters sleep mode, and the power consumption of the airspace base station in the second state is less than the power consumption of the airspace base station in the first state.

[0008] Optionally, when the deployment mode of the low-altitude network is the first mode, setting the working state of the airspace base station to the second state includes: controlling the airspace base station to go into hibernation when there are no drones in the base station coverage area within a preset time period in the future. In the first mode, the low-altitude network is a network that is different from the ground base station network and is only used to cover the airspace, and the mechanical downtilt angle of the active antenna unit in the low-altitude network is negative.

[0009] Optionally, the deployment mode of the low-altitude network also includes: a second mode, in which the low-altitude network is a network that reuses ground base stations and activates a second carrier. The mechanical downtilt angle of the active antenna elements in the low-altitude network is zero. Part of the synchronization signal block beams in the second carrier are used for ground coverage, and part of the synchronization signal block beams are used for air coverage. When the deployment mode of the low-altitude network is the second mode, setting the working state of the airspace base station to the second state includes: in areas where the activation ratio of the ground second carrier is lower than a preset ratio threshold, adjusting the synchronization signal block beams in the second carrier used for air coverage to ground coverage. The activation ratio of the ground second carrier is used to characterize the proportion of the number of base stations in the area that have activated and enabled the second carrier to the total number of base stations. In areas where the activation ratio of the ground second carrier is not lower than the preset ratio threshold, stopping the synchronization signal block beams in the second carrier used for air coverage, and / or shutting down the airspace 3.5G carrier frequency.

[0010] Optionally, after setting the working state of the airspace base station to the second state, the method further includes: using a wake-up time prediction model to analyze the flight parameters of the UAV and determine the wake-up time of the airspace base station in the second state, wherein the wake-up time prediction model is obtained by iteratively training decision trees using a tree-by-tree addition method; at the wake-up time, performing a wake-up operation on the airspace base station, wherein the wake-up operation is used to adjust the airspace base station from the second state to the first state.

[0011] Optionally, the training process of the wake-up time prediction model includes: determining the objective function of the training process, wherein the objective function includes: a core classification loss term, a time accuracy loss term, and an energy-saving regularization term. The core classification loss term is used to characterize the accuracy of the model in predicting the arrival time of the UAV, the time accuracy loss term is used to characterize the accuracy of the model in predicting the wake-up time, and the energy-saving regularization term is used to characterize the model's control over the wake-up duration of the base station to minimize the wake-up duration; initializing the tree structure, starting from the root node, and gradually building a decision tree with the goal of minimizing the objective function; adding the newly trained decision tree to the model until the preset number of trees is reached or the model converges, thus obtaining the wake-up time prediction model.

[0012] According to another aspect of the embodiments of this application, a communication device is also provided, comprising: a flight parameter acquisition module for acquiring flight parameters of a UAV, wherein the flight parameters are used to characterize the flight state of the UAV during takeoff and flight; a beam parameter determination module for determining target beam parameters of an airspace base station in a low-altitude network based on the flight parameters, wherein the target beam parameters include: a target number of synchronization signal block beams transmitted by the airspace base station, the target number being the minimum number of beams that the airspace base station can use to achieve directional tracking of a UAV within the coverage area of ​​the base station; and a variable beam tracking module for controlling the airspace base station to transmit synchronization signal block beams according to the target beam parameters, so as to realize communication between the airspace base station and the UAV.

[0013] According to another aspect of the embodiments of this application, an electronic device is also provided, including: a memory and a processor, the processor being configured to run a program stored in the memory, wherein the program executes a communication method during runtime.

[0014] According to another aspect of the embodiments of this application, a non-volatile storage medium is also provided, the non-volatile storage medium including a stored computer program, wherein the device where the non-volatile storage medium is located executes a communication method by running the computer program.

[0015] According to another aspect of the embodiments of this application, a computer program product is also provided, including a computer program, wherein the computer program, when executed by a processor, implements the steps of a communication method.

[0016] In this embodiment, the flight parameters of the UAV are acquired, which characterize the UAV's flight status during takeoff and flight. Based on the flight parameters, the target beam parameters of the airspace base station in the low-altitude network are determined. The target beam parameters include the target number of synchronization signal block beams sent by the airspace base station, which is the minimum number of beams that the airspace base station can use to achieve directional tracking of UAVs within its coverage area. The airspace base station is controlled to send synchronization signal block beams according to the target beam parameters to realize the communication method between the airspace base station and the UAV. By reshaping the current 5G network communication mechanism, a new mode of 5G low-altitude minimum variable beam directional tracking and an AI base station wake-up scheme are proposed. This achieves the goal of significantly reducing active ground interference of the low-altitude network and reducing the overall network power consumption while ensuring the UAV's service perception. This solves the technical problems of prominent ground interference and high overall network power consumption in related low-altitude network deployment schemes. Attached Figure Description

[0017] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments of this application and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:

[0018] Figure 1 This is a hardware structure block diagram of a computer terminal (or electronic device) for implementing a communication method according to an embodiment of this application;

[0019] Figure 2 This is a schematic diagram of a communication method flow according to an embodiment of this application;

[0020] Figure 3 This is a schematic diagram of bit error statistics provided according to an embodiment of this application;

[0021] Figure 4 This is a schematic diagram of the structure of a communication device provided according to an embodiment of this application. Detailed Implementation

[0022] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0023] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0024] To facilitate a better understanding of the embodiments of this application by those skilled in the art, some technical terms or nouns involved in the embodiments of this application are explained as follows:

[0025] In related technologies, operators mainly use two methods to deploy low-altitude networks:

[0026] 1) First mode, namely "independent module" mode (new private network): Deploy a low-altitude network specifically for airspace coverage, and set the AAU mechanical downtilt angle to -20° to meet airspace coverage requirements;

[0027] 2) Second mode, namely the traditional "4+3" mode (reusing the ground base station to open the second carrier): the mechanical downtilt angle of the AAU (Active Antenna Unit) is configured to 0°, and the electronic tilt angle of the four SSB (Synchronization Signal / PBCH Block) beams of the second carrier is set to 13° to cover the ground, and the electronic tilt angle of the other three SSB beams is set to -2° to cover the airspace.

[0028] While the traditional "4+3" model offers cost advantages, it still relies on a ground-based base station architecture. This makes it prone to over-coverage issues and increased ground interference, leading to significant data rate attenuation for ground users in urban areas with high activation rates of the second ground carrier. The "independent module" model reduces ground interference through physical isolation with a negative mechanical downtilt angle, but it still struggles to eliminate its impact on ground users in areas with dense deployments of the second ground carrier. Furthermore, although the current scale of drone operations is limited, their suddenness and high real-time requirements prevent base stations from implementing deep energy-saving strategies, resulting in high overall network power consumption, which contradicts the trend towards green and energy-efficient development.

[0029] In summary, given the core issues of significant ground interference and high power consumption in low-altitude network deployments, it is urgent to develop a practical and feasible technical solution to effectively suppress ground interference and precisely optimize overall network power consumption.

[0030] To address the aforementioned issues, this application provides relevant solutions, which are detailed below.

[0031] According to an embodiment of this application, a communication method embodiment is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0032] The methods and embodiments provided in this application can be executed on mobile terminals, computer terminals, or similar computing devices. Figure 1 A hardware structure block diagram of a computer terminal (or electronic device) for implementing a communication method is shown. Figure 1 As shown, the computer terminal 10 (or electronic device) may include one or more processors 102 (shown as 102a, 102b, ..., 102n in the figure) 102 (processor 102 may include, but is not limited to, a microprocessor MCU or a programmable logic device FPGA, etc.), a memory 104 for storing data, and a transmission device 106 for communication functions. In addition, it may also include: a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of a BUS bus), a network interface, a power supply, and / or a camera. Those skilled in the art will understand that... Figure 1 The structure shown is for illustrative purposes only and does not limit the structure of the aforementioned electronic device. For example, computer terminal 10 may also include... Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown.

[0033] It should be noted that the aforementioned one or more processors 102 and / or other data processing circuits are generally referred to herein as "data processing circuits". These data processing circuits may be embodied, in whole or in part, in software, hardware, firmware, or any other combination thereof. Furthermore, the data processing circuits may be a single, independent processing module, or may be integrated, in whole or in part, into any other element within the computer terminal 10 (or electronic device). As involved in the embodiments of this application, the data processing circuits serve as a processor control mechanism (e.g., selection of a variable resistor termination path connected to an interface).

[0034] The memory 104 can be used to store software programs and modules of application software, such as the program instructions / data storage device corresponding to the communication method in the embodiments of this application. The processor 102 executes various functional applications and data processing by running the software programs and modules stored in the memory 104, thereby realizing the above-mentioned communication method. The memory 104 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include memory remotely located relative to the processor 102, and these remote memories can be connected to the computer terminal 10 via a network. Examples of the above-mentioned networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0035] The transmission device 106 is used to receive or send data via a network. Specific examples of the network described above may include a wireless network provided by the communication provider of the computer terminal 10. In one example, the transmission device 106 includes a Network Interface Controller (NIC), which can connect to other network devices via a base station to communicate with the Internet. In another example, the transmission device 106 may be a Radio Frequency (RF) module, used for wireless communication with the Internet.

[0036] The display may be, for example, a touchscreen liquid crystal display (LCD) that allows the user to interact with the user interface of the computer terminal 10 (or electronic device).

[0037] Under the above operating environment, this application provides a communication method. Figure 2 This is a schematic diagram of a communication method flow provided according to an embodiment of this application, such as... Figure 2 As shown, the method includes the following steps:

[0038] Step S202: Obtain the flight parameters of the UAV, wherein the flight parameters are used to characterize the flight status of the UAV during takeoff and flight.

[0039] Step S204: Based on the flight parameters, determine the target beam parameters of the airspace base station in the low-altitude network. The target beam parameters include the target number of synchronization signal block beams sent by the airspace base station. The target number is the minimum number of beams that the airspace base station can use to achieve directional tracking of UAVs within the base station's coverage area.

[0040] Step S206: Control the airspace base station to send a synchronization signal block beam according to the target beam parameters to realize communication between the airspace base station and the UAV.

[0041] Through the above steps, by reshaping the current 5G network communication mechanism, a new mode of 5G low-altitude minimum variable beam directional tracking and AI base station wake-up scheme are proposed. This achieves the goal of significantly reducing active ground interference of low-altitude networks and reducing the overall network power consumption while ensuring the perception of drone services. This solves the technical problems of prominent ground interference and high overall network power consumption in related technologies.

[0042] The communication method in steps S202 to S206 of the embodiments of this application will be further described below.

[0043] To address the issues of high ground interference and high power consumption in low-altitude networks deployed in related technologies, this application proposes a variable-number beam automatic configuration tracking mechanism. This mechanism is compatible with most UAV flight control platforms and 5G-connected UAV onboard communication terminals on the market, and is applicable to low-altitude networks of all operators. The variable beam tracking mechanism is described in detail below.

[0044] In traditional 5G terrestrial networks, base stations cannot predict user access time and location, requiring real-time broadcasting of Service Segments (SSBs) to facilitate timely access and handover. Unlike terrestrial networks, low-altitude networks are differentiated networks, only needing to ensure service awareness for contracted drone users; uncontracted drone users can conduct basic communication through terrestrial base stations. Therefore, this application's embodiment reshapes the existing 5G communication mode of low-altitude networks, eliminating the SSB broadcast mechanism. By monitoring flight parameters such as drone flight path, location, fuselage status, and network quality information transmitted by the drone's onboard communication terminal, it uses a beam tracking method that minimizes the variable number of beams to directionally send SSB beam services to contracted drone users. That is, based on the flight parameters, it determines the minimum number of beams required for the airspace base station to achieve directional tracking of drones within its coverage area, and other target beam parameters.

[0045] In practical applications, drone flight encompasses various flight scenarios. Based on the drone's control method, it can be divided into two categories: route planning flight scenario (first method) and autonomous flight control flight scenario (second method). In route planning, the pilot uses a flight control platform or remote control handle to set the flight path. The route information is transmitted to the drone and the backend via the drone's onboard communication terminal, and the drone flies according to the route. In autonomous flight control, the pilot controls the drone's flight via a remote control handle without setting a flight path. During takeoff and flight, real-time information such as latitude and longitude, altitude, speed, pitch angle, roll angle, yaw angle, access base station number, cell number, RSRP (Reference Signal Received Power), transmission rate, and network latency can all be transmitted to the backend via the drone's onboard communication terminal. This means the backend can obtain real-time information on the drone's flight path, location, aircraft status, and network quality.

[0046] In this embodiment, different strategies for determining target beam parameters are provided for these two different flight scenarios (UAV control methods), as detailed below.

[0047] In some embodiments of this application, determining the target beam parameters of an airspace base station in a low-altitude network based on flight parameters includes the following steps: when the UAV is controlled in a first mode, obtaining a preset flight path corresponding to the UAV, and determining the initial beam parameters of the airspace base station based on the preset flight path; and, during the actual flight of the UAV, adjusting the initial beam parameters based on the flight parameters of the UAV during the actual flight to obtain the target beam parameters, wherein, in the first mode, the UAV flies according to a preset flight path; and / or, when the UAV is controlled in a second mode, predicting the flight path of the UAV based on the UAV's flight parameters, and determining the target beam parameters based on the predicted flight path, wherein, in the second mode, the UAV is controlled by a flight control platform or a remote control handle.

[0048] Specifically, when performing beam tracking with a minimum variable number of beams, this embodiment first adjusts the SSB beams of the airspace base station to a custom mode. Then, in a flight path planning scenario, i.e., when the UAV is controlled in the first mode, the backend monitors and acquires new flight paths in real time. It then performs static planning on the number of SSB beams sent by the relevant airspace base station, the parameters of each beam, and the adjustment time, based on information such as the number of UAVs, their trajectories, and flight speeds, thus determining the initial beam parameters of the airspace base station. After the UAV takes off, the backend can continuously monitor service quality and dynamically adjust the pre-planned SSB beams (initial beam parameters) based on the actual location of the UAV.

[0049] For example, when a single base station covers a single drone, single SSB beam tracking is used. When multiple drones are within the coverage area of ​​a single base station, the number of SSB beams transmitted by the base station and the parameters of each beam are adjusted based on the drone's trajectory and speed. If multiple drones can be covered by the same beam at a certain moment, single SSB beam tracking is used; otherwise, multi-beam tracking is used. When multiple drones are within the coverage area of ​​multiple base stations, the number of beams and the parameters of each beam at the airspace base station at the intersection of flight paths are automatically adjusted based on the drones' intersection time, trajectory, and speed, achieving minimized directional tracking of all drones using multiple SSB beams. When a drone is at the edge of base station coverage, adjacent base stations are pre-scheduled to adjust the SSB beam coverage handover zone to ensure normal handover for the drone.

[0050] In the autonomous flight control scenario, specifically when the drone is controlled in the second mode, after the drone is powered on, the backend obtains the ground base station information accessed by the drone through the drone's onboard terminal. Upon takeoff, it schedules nearby airspace base stations to relay coverage, completing the switch from the ground network to the low-altitude network. Since there is no preset flight path, the backend continuously uses a GNN (Graph Neural Network) to predict the flight trajectory (flight path) during drone flight, dynamically adjusting the predicted trajectory based on the actual trajectory, and simultaneously adjusting the SSB beam tracking of the airspace base stations.

[0051] When two flight scenarios exist simultaneously, the backend can dynamically adjust the number of base station tracking beams and the parameters of each beam by combining the preset flight path, the predicted trajectory, and the actual flight path trajectory.

[0052] Through the aforementioned automatic beam configuration and tracking mechanism, low-altitude networks can significantly reduce ground interference, which will be described in detail below.

[0053] When deploying the "independent module" (first mode) or the traditional "4+3" mode (second mode), the low-altitude network needs to be frequency-shifted to a dedicated 3.5 GHz frequency, staggered from the 3.5 GHz frequency of the terrestrial network. Interference from the low-altitude network to the ground is divided into active and passive interference. Active interference includes SSB interference and SIB1 (System Information Block 1) interference, while passive interference is user communication interference, i.e., interference caused to other terrestrial users when they access the low-altitude network. The degree of interference is related to the number of terrestrial users accessing the network and the service load. Since passive interference is difficult to quantify, this application mainly considers SSB interference and SIB1 interference. Because the transmission periods of SSB and SIB1 in the current network are both in the millisecond range, from a macroscopic perspective, the interference is continuous and directly affects the communication quality of the terrestrial network. Figure 3 Actual measurements show that when the low-altitude network transmits SIB1, the bit error rate at the corresponding time slot reception location is significantly increased for users accessing the 3.5G band of the terrestrial network.

[0054] The following section presents interference modeling for different deployment modes, starting with the definition of average interference power:

[0055]

[0056] in, , These are the instantaneous transmission interference powers of SSB and SIB1, respectively. , These are the transmission cycles for SSB and SIB1, respectively. Let... , These are the transmission powers for a single SSB and SIB1, respectively. Equivalent to the transmit power of PDSCH (Physical Downlink Shared Channel); , The durations for single SSB and SIB1, respectively; , The channel gain for ground users is calculated for air-to-air and ground-to-ground coverage beams, taking into account antenna gain and path loss. , These represent the number of beams covering the air and the ground, respectively.

[0057] The average ground interference of the "independent module" and the traditional "4+3" mode are as follows: , As shown:

[0058]

[0059]

[0060] Due to the current network configuration and same, and The same applies, therefore the formula below uses... replace , replace In "Independent Module" mode The value is 7, under the "4+3" model. 3. The value is 4. Substituting the parameter into the above equation, we get:

[0061]

[0062]

[0063] The following example illustrates the interference analysis of the solution in this application, using the scenario of a single / multiple UAVs within the coverage area of ​​an airspace base station that can be covered by a single SSB beam. In this scenario, the solution in this application... Set the gain ratio to 1. The ground interference when deploying the "independent module" and "4+3" modes using the scheme of this application is as follows:

[0064]

[0065]

[0066] Under both deployment modes, the interference ratio between the proposed solution and traditional solutions in related technologies is:

[0067]

[0068]

[0069]

[0070] As shown in the above formula, when a single / multiple UAVs can be covered by a single SSB beam, the active ground interference of the proposed solution in the "independent module" mode is that of the traditional solution. This reduces interference by 85.7%; under the traditional "4+3" model, the active ground interference in this application is significantly less than that of the traditional scheme. Reduced %.

[0071] This application's embodiments reshape the existing 5G communication mode of low-altitude networks, eliminating the SSB broadcast mechanism and, for the first time in the industry, proposing a method to directionally send SSB beam services to contracted drone users using a beam tracking method with a minimized variable number of beams. The solution is compatible with most drone flight control platforms and 5G-connected drone onboard communication terminals on the market, applicable to low-altitude networks of all operators, and all flight scenarios. Based on the 5G low-altitude communication mode proposed in this application's embodiments, active ground interference can be reduced by 85.7% and 42.86% respectively under different deployment modes. Actual measurements show that compared to the optimal performance of a locked low-altitude network, the ground user rate decreases by approximately 9% in the traditional "independent module" mode, while the ground user rate of this application's solution is unaffected; the ground user rate decreases by approximately 19% in the traditional "4+3" mode, while the optimal ground user rate of this application's solution is reduced by only approximately 11%, resulting in an approximately 8% increase in user rate.

[0072] On the other hand, in related technologies, to meet the demand for UAV services that are characterized by sudden changes and high network real-time requirements, even if the service scale is small, airspace base stations still need to operate around the clock, making it impossible to adopt the deep energy-saving strategies of terrestrial networks, resulting in low resource utilization. Therefore, this application also provides a base station energy-saving strategy, which will be described in detail below.

[0073] In some embodiments of this application, the method further includes the following steps: when there is a drone within the coverage area of ​​the airspace base station, the operating state of the airspace base station is set to a first state, wherein in the first state, the airspace base station can transmit a synchronization signal block beam according to the target beam parameters; when there is no drone within the coverage area of ​​the airspace base station, the operating state of the airspace base station is set to a second state, wherein in the second state, the airspace base station stops transmitting signals on at least some carrier frequencies or enters sleep mode, and the power consumption of the airspace base station in the second state is less than the power consumption of the airspace base station in the first state.

[0074] Specifically, in the embodiments of this application, various operating states of the airspace base station can be defined, including:

[0075] 1) Dynamic service (corresponding to the first state above): When there are contracted drones within the coverage area, the SSB beam service drone users are sent in a targeted manner according to the beam tracking method with the minimum variable number proposed in the embodiments of this application;

[0076] 2) Carrier frequency shutdown (corresponding to the second state above): Carrier frequency shutdown is performed when there are no contracted drones within the coverage area;

[0077] 3) Deep hibernation (corresponding to the second state above): Deep hibernation is initiated when there are no contracted drones within the coverage area.

[0078] Total power consumption of the base station at time t under different operating states Power consumption by state SSB power consumption and SIB1 power consumption The composition is as shown in the following formula:

[0079]

[0080] in, Let be the number of SSBs activated at time t. Specifically as follows:

[0081]

[0082] in Based on standby power consumption, To handle incremental power consumption for business processes, This refers to the power consumption during carrier frequency shutdown. Power consumption for deep sleep mode.

[0083] Compared to traditional solutions in related technologies, the energy-saving rate of the solution in this application embodiment is shown in the following formula:

[0084]

[0085] in, The power consumption of the base station in the traditional solution of the related technology is shown in the following formula:

[0086]

[0087] The energy-saving performance of base stations under different conditions is explained below.

[0088] In dynamic service scenarios, for traditional solutions in related technologies where the corresponding symbols of SSB and SIB1 should have been sent but were not at time t, intelligent symbol shutdown measures can be adopted to save power consumption as follows:

[0089]

[0090] When the carrier frequency is turned off, the base station saves power. Its shutdown time percentage Related, The total activation time for the base station is as follows:

[0091]

[0092]

[0093] Similarly, during deep sleep, the base station saves power. Its proportion of hibernation time The relevant formula is as follows:

[0094]

[0095]

[0096] The energy-saving strategies and effects of the "independent module" mode (first mode) and the traditional "4+3" mode (second mode) are introduced below.

[0097] In some embodiments of this application, when the deployment mode of the low-altitude network is the first mode, setting the working state of the airspace base station to the second state includes: controlling the airspace base station to go into hibernation when there are no drones in the base station coverage area within a preset time period in the future. In the first mode, the low-altitude network is a network that is different from the ground base station network and is only used to cover the airspace, and the mechanical downtilt angle of the active antenna unit in the low-altitude network is negative.

[0098] Specifically, in the "independent module" mode, the air-to-ground network characteristics determine that the solution implemented in this application allows for a deep energy-saving strategy for base stations throughout the day based on drone operations. When no drones are operating, the airspace base station enters deep sleep mode, reducing power consumption by approximately 60% during sleep time. When a drone is planning its flight path or the pilot is manually controlling it, the number of SSB beams, parameters, and adjustment time used by the relevant airspace base station can be calculated by comprehensively planning the flight path and predicting the trajectory. The base station is then woken up before the drone arrives to ensure normal drone communication, and intelligent symbol shutdown is used to reduce dynamic service power consumption, which can reduce power consumption by approximately 8% in medium-load scenarios. When a drone flies out of the base station's coverage area and there are no drones in the short term, it enters deep sleep mode again. Based on a single base station providing uninterrupted drone service for 3 hours per day (the sum of all service hours per day), power consumption can be reduced by 53.5% in medium-load scenarios.

[0099] In some embodiments of this application, the deployment mode of the low-altitude network further includes: a second mode, in which the low-altitude network is a network that reuses ground base stations and activates a second carrier, the mechanical downtilt angle of the active antenna elements in the low-altitude network is zero, a portion of the synchronization signal block beams in the second carrier are used for ground coverage, and a portion of the synchronization signal block beams are used for air coverage; when the deployment mode of the low-altitude network is the second mode, setting the working state of the airspace base station to the second state includes: in areas where the ground second carrier activation ratio is lower than a preset ratio threshold, adjusting the synchronization signal block beams in the second carrier used for air coverage to ground coverage, wherein the ground second carrier activation ratio is used to characterize the proportion of the number of base stations in the area that have activated and enabled the second carrier to the total number of base stations; in areas where the ground second carrier activation ratio is not lower than the preset ratio threshold, stopping the synchronization signal block beams in the second carrier used for air coverage, and / or shutting down the airspace 3.5G carrier frequency.

[0100] Specifically, based on the traditional "4+3" model, this application proposes a dynamic adjustment strategy for the second carrier when reusing ground base stations.

[0101] In areas with a low terrestrial second carrier activation rate (i.e., areas where the terrestrial second carrier activation rate is below a preset threshold), air coverage is stopped when there are no drones. The base station beam is adjusted to "7+0" (i.e., the synchronization signal block beam used for air coverage in the second carrier is adjusted to ground coverage), with all beams providing ground coverage to enhance ground user perception. When a drone is planning its flight path or the pilot is manually controlling it, the number, parameters, and adjustment time of SSB beams used by the relevant airspace base stations are calculated based on the planned flight path and predicted trajectory. Before the drone arrives, the base station beam is adjusted to "6+1", "5+2", or "4+3" as needed to ensure normal drone communication, and intelligent symbol shutdown is used to reduce dynamic service power consumption. When the drone flies out of the base station coverage area, air coverage is stopped again. During nighttime when there is less traffic, carrier frequency shutdown or deep sleep is performed based on the ground network coverage. Carrier frequency shutdown can reduce power consumption by about 40% during the shutdown period.

[0102] In areas with a high proportion of ground-based second carrier activation (i.e., areas where the proportion of ground-based second carrier activation is not lower than a preset threshold), low-altitude network interference to the ground is significant. Therefore, when there are no drones, interference reduction solutions include, but are not limited to: 1) Adjusting the base station beam to "4+0" (i.e., stopping the synchronization signal block beam used for air coverage in the second carrier), that is, canceling air coverage without increasing ground coverage, thus reducing ground interference; 2) Turning off the 3.5GHz carrier frequency in the airspace, eliminating ground interference. When the drone plans its flight path or the pilot manually controls the flight, the number, parameters, and adjustment time of the SSB beams used by the relevant airspace base stations are calculated based on the comprehensive planning of the flight path and the predicted trajectory. Before the drone arrives, the air-to-air beams are adjusted / carrier frequencies are turned on as needed to ensure normal communication for the drone, and intelligent symbol shutdown is used to reduce dynamic service power consumption. After the drone flies out of the base station coverage area, air coverage is canceled / carrier frequencies are turned off. Based on a single base station providing uninterrupted service to drones for 3 hours a day, solution two in the medium-load scenario can reduce power consumption by 36%. Unlike the traditional "4+3" mode, the two schemes proposed in this application can reduce ground interference by 42.86% and 85.7% respectively in areas where the proportion of the second ground carrier is high.

[0103] In this application, the embodiments propose corresponding energy-saving strategies for different deployment modes under 5G low-altitude communication mode. Under the "independent module" mode, based on the calculation of 3 hours of uninterrupted service for drones by a single base station per day (the sum of all service times within a day), the power consumption can be reduced by 53.5% in medium-load scenarios. Under the "4+3" mode, based on the calculation of 3 hours of uninterrupted service for drones by a single base station per day, the power consumption can be reduced by 36% in medium-load scenarios.

[0104] Furthermore, when performing deep sleep or carrier frequency shutdown in the above energy-saving strategy (i.e., after setting the working state of the airspace base station to the second state), it is necessary to choose a reasonable time to wake up the base station. Waking up too early will increase unnecessary power consumption, while waking up too late will affect the normal communication of the UAV. Therefore, this application embodiment also provides a scheme for predicting the wake-up time (time point) of the base station, as follows.

[0105] In some embodiments of this application, after setting the working state of the airspace base station to the second state, the method further includes: using a wake-up time prediction model to analyze the flight parameters of the UAV and determine the wake-up time of the airspace base station in the second state, wherein the wake-up time prediction model is obtained by iteratively training decision trees using a tree-by-tree addition method; at the wake-up time, performing a wake-up operation on the airspace base station, wherein the wake-up operation is used to adjust the airspace base station from the second state to the first state.

[0106] Specifically, in the embodiments of this application, the aforementioned wake-up time prediction model can employ the XGBoost (eXtremeGradient Boosting) model to predict the wake-up timing of the base station. XGBoost uses a tree-by-tree addition method to iteratively train decision trees, with each tree learning the negative gradient direction of the current model, thereby improving prediction accuracy through collective intelligence. By performing a second-order Taylor expansion on the loss function and adding a regularization term to the objective function, the model can more accurately approximate the true loss function and is less prone to overfitting.

[0107] The model construction and training process is described below.

[0108] In some embodiments of this application, the training process of the wake-up time prediction model includes: determining the objective function of the training process, wherein the objective function includes: a core classification loss term, a time accuracy loss term, and an energy-saving regularization term. The core classification loss term is used to characterize the accuracy of the model in predicting the arrival time of the UAV, the time accuracy loss term is used to characterize the accuracy of the model in predicting the wake-up time, and the energy-saving regularization term is used to characterize the model's control over the wake-up duration of the base station to minimize the wake-up duration; initializing the tree structure, starting from the root node, and gradually building a decision tree with the goal of minimizing the objective function; adding the newly trained decision tree to the model until a preset number of trees is reached or the model converges, thereby obtaining the wake-up time prediction model.

[0109] Specifically, the core of XGBoost is to progressively minimize the objective function that includes a regularization term, as shown in the following equation:

[0110]

[0111] in For loss function, The prediction results are for the first t-1 trees. Let t be the function to be learned for the t-th tree. Penalty for regularization:

[0112]

[0113] in, To control the splitting penalty coefficient of tree complexity, The number of leaf nodes in the tree. The weight of the current leaf node. The L2 regularization coefficient is... is the L1 regularization coefficient.

[0114] To improve efficiency, Approximate the objective function using a second-order Taylor expansion:

[0115]

[0116] in, , , which are the gradient and curvature of the current sample, respectively, reflecting the error direction and the steepness of the error.

[0117] In XGBoost, the splitting of tree nodes has a significant impact on the model. The splitting criterion is that the split point maximizes the reduction of the objective function, i.e., maximizes the information gain. If the sample set of a certain node is... Split into the left subtree and right subtree Its information gain is:

[0118]

[0119] After obtaining the tree structure according to the above formula, it is still necessary to determine the optimal weight of each leaf node, which minimizes the approximate objective function. Let the... The weight of each leaf is Then the sample set of this node is ,Will , and Substituting the above pairs After approximating the objective function using a second-order Taylor expansion, the formula for... Taking the derivative, we can obtain the first... Optimal weights for leaf nodes:

[0120]

[0121] This concludes the complete explanation of XGBoost's tree construction process.

[0122] In this embodiment, to balance energy saving and base station service, a cost-sensitive three-segment objective function is proposed, consisting of a core classification loss term. Time accuracy loss item and energy-saving regularization terms The components are as follows:

[0123]

[0124]

[0125]

[0126]

[0127] in, and For adjustment coefficients, For time decay weight, The labels are 0 / 1, which are true labels. To predict probabilities, For focusing on difficult samples, The penalty weight for false negatives when a drone arrives but the base station fails to wake up. Weighting the penalty for false positives where the base station wakes up but the drone fails to arrive. For the positive sample set, To predict the time difference from the actual time, To minimize the safety lead time, The exponential growth coefficient, Let be the wake-up probability at time t. To see if any drones will arrive, For continuous wake-up duration, This is the maximum allowed duration for a single wake-up. Specifically, The main weighted focus loss reduces the weight of easily separable samples and focuses on difficult negative samples, which is used to solve the problems of sample imbalance (few drone arrival events) and cost asymmetry. The main penalty is advance warning, ensuring the base station arrives before the drone. Wake up within a short time to ensure service continuity while reducing base station power consumption; The main penalty is wake-up time, minimizing unnecessary wake-up duration.

[0128] The following derivations are presented sequentially. , , First-order and second-order derivatives are used for The Taylor expansion of .

[0129] make For the model's logarithmic output with respect to sample i, The first derivative is as follows:

[0130]

[0131] Among them, positive samples ( =1), negative samples ( The first derivative of (=0) is:

[0132]

[0133]

[0134] for Assuming the prediction time difference is related to probability, i.e. Considering only positive samples, the first derivative is as follows:

[0135]

[0136] for Considering only positive samples, the first derivative is as follows:

[0137]

[0138] Similar to the first derivative, the following gives the results for positive and negative samples. Second derivative, positive sample and The second derivative. For The second derivative is as follows:

[0139]

[0140]

[0141] for Considering only positive samples, the second derivative is as follows:

[0142]

[0143] for Considering only positive samples, the second derivative is as follows:

[0144]

[0145] Thus, the three objective functions proposed in this application embodiment have been explained. Substituting these functions and their first and second derivatives into the formulas used in the XGBoost tree construction process yields the complete XGBoost model. The dataset used by the model includes time, historical, periodic, and environmental features. Some data includes: current time (year, month, day, hour, minute, second), drone arrival time prediction error within 1 day, base station wake-up time error within 1 day, drone arrival time prediction error within 3 days, base station wake-up time error within 3 days, number of arrivals in the past 10 minutes, number of arrivals in the past 1 hour, time difference from the last arrival, moving average of arrivals in 30 minutes, number of drone arrivals in the same period within 3 days, current weather conditions, and weather conditions in the same period within 3 days. Due to the large number of features in the dataset, the importance of different features needs to be calculated after model training. The importance of each tree is as follows, where K is the number of trees:

[0146]

[0147] Once the importance of each data feature is determined, the key features that the model should focus on can be identified, low-importance features can be removed, the quality of data collection and processing of high-importance data can be improved, and subsequent model tuning can be carried out.

[0148] This application's embodiments utilize the XGBoost algorithm to select the base station's sleep / wake-up timing under the low-altitude 5G communication mode. A cost-sensitive three-segment objective function based on the relationship between the UAV and base station services is proposed. By using a weighted focus loss, the weight of easily separable samples is reduced, while focusing on difficult negative samples, thus addressing the problems of sample imbalance (few UAV arrival events) and cost asymmetry. Furthermore, by penalizing lead time, it ensures that the base station arrives before the UAV. Wake-up within a short time frame ensures service continuity while reducing base station power consumption; by balancing wake-up timing, unnecessary wake-up duration is minimized to maximize energy saving.

[0149] To verify the ground interference reduction effect of the proposed solution, experimental networks were built at the same site using both "independent modules" and "4+3" modes. Road tests were conducted on actual daily road routes using the 3.4G and 3.5G frequencies of the terrestrial network, with a ground second carrier activation rate greater than 50% and an average station spacing of less than 4km. Specific test results are shown in the table below.

[0150]

[0151] This includes ground user performance when the low-altitude network is locked, the 3.4 GHz frequency band is locked, and the 3.5 GHz frequency band is locked. It can be seen that the low-altitude network uses a dedicated 3.5 GHz frequency band, which has virtually no impact on the 3.4 GHz terrestrial network; the main consideration is co-channel interference with the 3.5 GHz terrestrial network. Compared to the optimal performance of locking the low-altitude network, the traditional "independent module" mode results in a ground user rate decrease of approximately 9%, while the proposed solution shows no loss in ground user rate. The traditional "4+3" mode results in a ground user rate decrease of approximately 19%, while the proposed solution only reduces the optimal ground user rate by approximately 11%, resulting in an approximately 8% increase in user rate. The rate decrease is mainly caused by the limited physical isolation of the "4+3" mode.

[0152] According to an embodiment of this application, an embodiment of a communication device is also provided. Figure 4 This is a schematic diagram of a communication device according to an embodiment of this application. Figure 4 As shown, the device includes:

[0153] The flight parameter acquisition module 40 is used to acquire the flight parameters of the UAV, wherein the flight parameters are used to characterize the flight status of the UAV during takeoff and flight.

[0154] The beam parameter determination module 42 is used to determine the target beam parameters of the airspace base station in the low-altitude network based on the flight parameters. The target beam parameters include the target number of synchronization signal block beams sent by the airspace base station. The target number is the minimum number of beams that the airspace base station can use to achieve directional tracking of UAVs within the coverage area of ​​the base station.

[0155] The variable beam tracking module 44 is used to control the airspace base station to send synchronization signal block beams according to the target beam parameters, so as to realize communication between the airspace base station and the UAV.

[0156] Optionally, determining the target beam parameters of the airspace base station in the low-altitude network based on flight parameters includes: when the UAV is controlled in a first mode, obtaining the preset flight path corresponding to the UAV, and determining the initial beam parameters of the airspace base station based on the preset flight path; and, during the actual flight of the UAV, adjusting the initial beam parameters based on the flight parameters of the UAV during the actual flight to obtain the target beam parameters, wherein, in the first mode, the UAV flies according to the preset flight path; and / or, when the UAV is controlled in a second mode, predicting the flight path of the UAV based on the flight parameters of the UAV, and determining the target beam parameters based on the predicted flight path, wherein, in the second mode, the UAV is controlled by a flight control platform or a remote control handle.

[0157] Optionally, the communication device is further configured to: when a drone is present within the base station coverage area of ​​the airspace base station, set the operating state of the airspace base station to a first state, wherein in the first state, the airspace base station is able to transmit a synchronization signal block beam according to the target beam parameters; and when no drone is present within the base station coverage area of ​​the airspace base station, set the operating state of the airspace base station to a second state, wherein in the second state, the airspace base station stops transmitting signals on at least some carrier frequencies or enters sleep mode, and the power consumption of the airspace base station in the second state is less than the power consumption of the airspace base station in the first state.

[0158] Optionally, when the deployment mode of the low-altitude network is the first mode, setting the working state of the airspace base station to the second state includes: controlling the airspace base station to go into hibernation when there are no drones in the base station coverage area within a preset time period in the future. In the first mode, the low-altitude network is a network that is different from the ground base station network and is only used to cover the airspace, and the mechanical downtilt angle of the active antenna unit in the low-altitude network is negative.

[0159] Optionally, the deployment mode of the low-altitude network also includes: a second mode, in which the low-altitude network is a network that reuses ground base stations and activates a second carrier. The mechanical downtilt angle of the active antenna elements in the low-altitude network is zero. Part of the synchronization signal block beams in the second carrier are used for ground coverage, and part of the synchronization signal block beams are used for air coverage. When the deployment mode of the low-altitude network is the second mode, setting the working state of the airspace base station to the second state includes: in areas where the activation ratio of the ground second carrier is lower than a preset ratio threshold, adjusting the synchronization signal block beams in the second carrier used for air coverage to ground coverage. The activation ratio of the ground second carrier is used to characterize the proportion of the number of base stations in the area that have activated and enabled the second carrier to the total number of base stations. In areas where the activation ratio of the ground second carrier is not lower than the preset ratio threshold, stopping the synchronization signal block beams in the second carrier used for air coverage, and / or shutting down the airspace 3.5G carrier frequency.

[0160] Optionally, after setting the working state of the airspace base station to the second state, the method further includes: using a wake-up time prediction model to analyze the flight parameters of the UAV and determine the wake-up time of the airspace base station in the second state, wherein the wake-up time prediction model is obtained by iteratively training decision trees using a tree-by-tree addition method; at the wake-up time, performing a wake-up operation on the airspace base station, wherein the wake-up operation is used to adjust the airspace base station from the second state to the first state.

[0161] Optionally, the training process of the wake-up time prediction model includes: determining the objective function of the training process, wherein the objective function includes: a core classification loss term, a time accuracy loss term, and an energy-saving regularization term. The core classification loss term is used to characterize the accuracy of the model in predicting the arrival time of the UAV, the time accuracy loss term is used to characterize the accuracy of the model in predicting the wake-up time, and the energy-saving regularization term is used to characterize the model's control over the wake-up duration of the base station to minimize the wake-up duration; initializing the tree structure, starting from the root node, and gradually building a decision tree with the goal of minimizing the objective function; adding the newly trained decision tree to the model until the preset number of trees is reached or the model converges, thus obtaining the wake-up time prediction model.

[0162] It should be noted that each module in the above communication device can be a program module (for example, a set of program instructions to implement a certain function) or a hardware module. For the latter, it can be manifested in the following forms, but is not limited to them: each of the above modules is manifested as a processor, or the functions of each of the above modules are implemented by a processor.

[0163] It should be noted that the communication device provided in this embodiment can be used to perform... Figure 2 The communication method shown above is also applicable to the embodiments of this application, and will not be repeated here.

[0164] This application embodiment also provides a non-volatile storage medium, which includes a stored computer program. The device containing the non-volatile storage medium executes the following communication method by running the computer program: acquiring flight parameters of a UAV, wherein the flight parameters are used to characterize the flight state of the UAV during takeoff and flight; determining the target beam parameters of an airspace base station in a low-altitude network based on the flight parameters, wherein the target beam parameters include: the target number of synchronization signal block beams sent by the airspace base station, the target number being the minimum number of beams that the airspace base station can use to achieve directional tracking of UAVs within its coverage area; and controlling the airspace base station to send synchronization signal block beams according to the target beam parameters to achieve communication between the airspace base station and the UAV.

[0165] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the communication methods described in various embodiments of this application: acquiring flight parameters of a UAV, wherein the flight parameters are used to characterize the flight state of the UAV during takeoff and flight; determining the target beam parameters of an airspace base station in a low-altitude network based on the flight parameters, wherein the target beam parameters include: the target number of synchronization signal block beams sent by the airspace base station, the target number being the minimum number of beams that the airspace base station can use to achieve directional tracking of UAVs within its coverage area; and controlling the airspace base station to send synchronization signal block beams according to the target beam parameters to achieve communication between the airspace base station and the UAV.

[0166] The sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0167] In the above embodiments of this application, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0168] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units can be a logical functional division, and in actual implementation, there may be other division methods. For instance, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual coupling, direct coupling, or communication connection may be through some interfaces; the indirect coupling or communication connection between units or modules may be electrical or other forms.

[0169] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0170] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0171] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as a USB flash drive, read-only memory (ROM), random access memory (RAM), portable hard drive, magnetic disk, or optical disk.

[0172] The above description is only a preferred embodiment of this application. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of this application, and these improvements and modifications should also be considered within the scope of protection of this application.

Claims

1. A communication method, characterized in that, include: The flight parameters of the UAV are obtained, wherein the flight parameters are used to characterize the flight status of the UAV during takeoff and flight. Based on the flight parameters, the target beam parameters of the airspace base station in the low-altitude network are determined. The target beam parameters include the target number of synchronization signal block beams transmitted by the airspace base station. The target number is the minimum number of beams that the airspace base station can use to achieve directional tracking of UAVs within the base station's coverage area. The airspace base station is controlled to send a synchronization signal block beam according to the target beam parameters in order to realize communication between the airspace base station and the UAV; The method further includes: when the UAV is present within the base station coverage area of ​​the airspace base station, setting the operating state of the airspace base station to a first state, wherein in the first state, the airspace base station can transmit the synchronization signal block beam according to the target beam parameters; when the UAV is not present within the base station coverage area of ​​the airspace base station, setting the operating state of the airspace base station to a second state, wherein in the second state, the airspace base station stops transmitting signals on at least some carrier frequencies or enters sleep mode, and the power consumption of the airspace base station in the second state is less than the power consumption of the airspace base station in the first state.

2. The communication method according to claim 1, characterized in that, Based on the flight parameters, the target beam parameters for airspace base stations in low-altitude networks are determined as follows: When the control mode of the UAV is the first mode, the preset flight path corresponding to the UAV is obtained, and the initial beam parameters of the airspace base station are determined based on the preset flight path; and, during the actual flight of the UAV, the initial beam parameters are adjusted based on the flight parameters of the UAV during the actual flight to obtain the target beam parameters, wherein, in the first mode, the UAV flies according to the preset flight path. And / or, When the control mode of the UAV is the second mode, the flight path of the UAV is predicted based on the flight parameters of the UAV, and the target beam parameters are determined based on the predicted flight path. In the second mode, the UAV is controlled by a flight control platform or a remote control handle to fly.

3. The communication method according to claim 1, characterized in that, When the deployment mode of the low-altitude network is the first mode, setting the operating state of the airspace base station to the second state includes: If the drone is not present within the coverage area of ​​the base station for a predetermined period of time in the future, the airspace base station is controlled to enter hibernation. In the first mode, the low-altitude network is a network that is distinct from the ground base station network and is used only for airspace coverage. The mechanical downtilt angle of the active antenna unit in the low-altitude network is negative.

4. The communication method according to claim 1, characterized in that, The deployment mode of the low-altitude network further includes a second mode, in which the low-altitude network is a network that reuses ground base stations and activates a second carrier. The mechanical downtilt angle of the active antenna elements in the low-altitude network is zero, and part of the synchronization signal block beams in the second carrier are used for ground coverage, while part of the synchronization signal block beams are used for air coverage. When the deployment mode of the low-altitude network is the second mode, setting the operating state of the airspace base station to the second state includes: In areas where the activation ratio of the second ground carrier is lower than a preset threshold, the synchronization signal block beam in the second carrier used for air coverage is adjusted to cover the ground. The activation ratio of the second ground carrier is used to characterize the proportion of the number of base stations that have activated and enabled the second carrier in the area to the total number of base stations. In areas where the activation ratio of the second ground carrier is not lower than the preset threshold, the synchronization signal block beam used for air coverage in the second carrier is stopped, and / or the 3.5G airspace carrier frequency is turned off.

5. The communication method according to claim 1, characterized in that, After setting the working state of the airspace base station to the second state, the method further includes: A wake-up time prediction model is used to analyze the flight parameters of the UAV and determine the wake-up time of the airspace base station in the second state. The wake-up time prediction model is obtained by iteratively training decision trees using a tree-by-tree addition method. At the wake-up time point, a wake-up operation is performed on the airspace base station, wherein the wake-up operation is used to adjust the airspace base station from the second state to the first state.

6. The communication method according to claim 5, characterized in that, The training process of the wake-up time prediction model includes: The objective function of the training process is determined, wherein the objective function includes: a core classification loss term, a time accuracy loss term, and an energy-saving regularization term. The core classification loss term is used to characterize the accuracy of the model in predicting the arrival time of the UAV. The time accuracy loss term is used to characterize the accuracy of the model in predicting the wake-up time. The energy-saving regularization term is used to characterize the model's control over the wake-up duration of the base station in order to minimize the wake-up duration. Initialize the tree structure, starting from the root node, and gradually build the decision tree with the goal of minimizing the objective function; The newly trained decision tree is added to the model until the preset number of trees is reached or the model converges, thus obtaining the wake-up time prediction model.

7. A communication device, characterized in that, include: The flight parameter acquisition module is used to acquire the flight parameters of the UAV, wherein the flight parameters are used to characterize the flight status of the UAV during takeoff and flight. The beam parameter determination module is used to determine the target beam parameters of the airspace base station in the low-altitude network based on the flight parameters. The target beam parameters include the target number of synchronization signal block beams transmitted by the airspace base station. The target number is the minimum number of beams that the airspace base station can use to achieve directional tracking of UAVs within the base station's coverage area. A variable beam tracking module is used to control the airspace base station to send a synchronization signal block beam according to the target beam parameters, so as to realize communication between the airspace base station and the UAV. The variable beam tracking module is further configured to: when the UAV is present within the base station coverage area of ​​the airspace base station, set the operating state of the airspace base station to a first state, wherein in the first state, the airspace base station can transmit the synchronization signal block beam according to the target beam parameters; and when the UAV is not present within the base station coverage area of ​​the airspace base station, set the operating state of the airspace base station to a second state, wherein in the second state, the airspace base station stops transmitting signals on at least a portion of the carrier frequencies or enters sleep mode, and the power consumption of the airspace base station in the second state is less than the power consumption of the airspace base station in the first state.

8. An electronic device, characterized in that, include: A memory and a processor, the processor being configured to run a program stored in the memory, wherein the program, when executed, performs the communication method according to any one of claims 1 to 6.

9. A non-volatile storage medium, characterized in that, The non-volatile storage medium includes a stored computer program, wherein the device containing the non-volatile storage medium executes the communication method according to any one of claims 1 to 6 by running the computer program.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the communication method according to any one of claims 1 to 6.

Images