A wireless communication system and method for a drone fleet

Abstract

The present invention discloses a wireless communication system and method for a fleet of unmanned aerial vehicles, and relates to the field of wireless communication technology, including real-time collection of radio frequency signals, own positions and antenna direction data of a target area, and preprocessing; using a machine learning algorithm to construct a three-dimensional radio frequency environment model, inputting the preprocessed data into the three-dimensional radio frequency environment model, and predicting signal distribution, interference position and spectrum usage; using cross-layer optimization CLO to dynamically optimize the communication parameters of the unmanned aerial vehicles according to the prediction results; based on the optimized communication parameters, the unmanned aerial vehicles form a multi-hop transmission network; based on real-time data in the multi-hop transmission network, using a three-dimensional radio frequency environment model to predict the spectrum usage trend; dynamically allocating frequency band resources according to the predicted spectrum usage trend; the present invention realizes accurate perception of the dynamic radio frequency environment by collecting radio frequency signals, positions and antenna direction data of the target area, and using a sliding average method to smooth and normalize and integrate them into a data set.

Description

Technical Field

[0001] The present invention relates to the field of wireless communication technology, and in particular to a wireless communication system and method for a drone fleet. Background Art

[0002] Unmanned aerial vehicle (UAV) technology has achieved rapid development in recent years and has been applied in logistics, disaster relief, environmental monitoring and military fields. With the rise of UAV cluster applications, UAV swarm technology has gradually become a research hotspot. UAV swarms complete complex tasks through collaborative communication. Their communication systems need to have high reliability, strong anti-interference capabilities and efficient use of spectrum resources. However, the complex and changeable RF environment poses severe challenges to the communication system, such as signal attenuation, interference enhancement and limited spectrum resources. In addition, traditional communication systems lack real-time perception capabilities and intelligent optimization mechanisms for dynamic changes in the RF environment, making it difficult to meet the high demands of UAV swarm collaborative communication.

[0003] Existing drone communication systems have many shortcomings. First, traditional systems mostly use static frequency band allocation and fixed communication parameter configuration, lacking real-time perception of wireless signal strength, interference characteristics and spectrum utilization, resulting in reduced communication performance in dynamic environments. Second, existing RF environment modeling is mostly a two-dimensional method, which cannot accurately reflect the spatial position and three-dimensional environmental characteristics of the drone, and the model prediction accuracy is low. At the same time, communication parameter optimization is usually limited to a single-layer protocol stack, and it is difficult to coordinately adjust key parameters such as frequency band selection, transmission power and antenna direction through cross-layer optimization. In addition, existing technologies rely more on rule settings for the dynamic allocation of spectrum resources, lack the ability to predict spectrum usage trends, resulting in inefficient resource allocation. Summary of the invention

[0004] In view of the above existing problems, the present invention is proposed.

[0005] Therefore, the present invention provides a wireless communication method for drone fleets to solve the problem that traditional systems mostly use static frequency band allocation and fixed communication parameter configuration, lack real-time perception of wireless signal strength, interference characteristics and spectrum utilization, resulting in reduced communication performance in dynamic environments.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] In a first aspect, the present invention provides a wireless communication method for a drone fleet, comprising:

[0008] Collect the RF signal, own position and antenna direction data of the target area in real time and perform pre-processing;

[0009] Use machine learning algorithms to build a three-dimensional RF environment model, input the preprocessed data into the three-dimensional RF environment model, and predict signal distribution, interference location, and spectrum usage;

[0010] Based on the prediction results, the cross-layer optimization CLO is used to dynamically optimize the communication parameters of the UAV;

[0011] Based on the optimized communication parameters, the drones set up a multi-hop transmission network;

[0012] Based on real-time data in multi-hop transmission networks, a three-dimensional radio frequency environment model is used to predict spectrum usage trends;

[0013] Dynamically allocate frequency band resources based on predicted spectrum usage trends.

[0014] As a preferred solution of the wireless communication method for a drone fleet described in the present invention, wherein:

[0015] The real-time collection of the RF signal, the position and the antenna direction data of the target area and the pre-processing are as follows:

[0016] According to the mission requirements of the target area, select the acquisition frequency band range, set the frequency sampling interval and time sampling interval;

[0017] Use a spectrum analyzer to collect wireless signal strength, interference signal strength, and RF spectrum utilization;

[0018] The GPS and antenna direction sensors are used to collect the drone position coordinates and antenna direction angles respectively;

[0019] The wireless signal strength and interference signal strength are smoothed using the sliding average method, and all collected data are normalized;

[0020] The standardized data is integrated into the data set D, which is expressed as:

[0021] D={S(f,t),I(f,t),U(f),(x,y,z),θ,φ};

[0022] Among them, S(f,t) represents the change of the normalized wireless signal strength of the target frequency band f with time t, I(f,t) represents the change of the normalized interference signal strength of the target frequency band f with time t, U(f) represents the normalized spectrum utilization of the target frequency band f, (x,y,z) represents the normalized position coordinates, θ and φ represent the normalized antenna pitch angle and elevation angle, respectively.

[0023] As a preferred solution of the wireless communication method for a drone fleet described in the present invention, the three-dimensional radio frequency environment model is constructed by using a machine learning algorithm, and the pre-processed data is input into the three-dimensional radio frequency environment model to predict signal distribution, interference location and spectrum usage. The specific steps are as follows:

[0024] Select the 3D convolutional neural network 3D-CNN as the basic model of the 3D RF environment model;

[0025] The preprocessed data set D is converted into a tensor T(D), expressed as:

[0026] T(D)∈R M×N×K =T(S(f,t),I(f,t),U(f),(x,y,z),θ,φ);

[0027] Among them, ∈ indicates belonging, R indicates that each element in the tensor is a real number, M indicates the number of target frequency bands f, N indicates the length of the sampling time series, and K indicates the spatial and directional feature dimensions;

[0028] Input the tensor T(D) into the three-dimensional RF environment model and output the prediction result. The expression is:

[0029]

[0030] Among them, Y mnk represents the signal distribution, interference location, and spectrum usage in the mth frequency band, the nth time point, and the kth spatial direction, W mnk represents the adaptive weight function in the mth frequency band, the nth time point, and the kth spatial direction, T mnk It represents the data corresponding to the mth frequency band, the nth time point, and the kth spatial direction extracted from T(D), and ∈ represents a natural constant (used to prevent the denominator from being zero).

[0031] As a preferred solution of the wireless communication method for a drone fleet described in the present invention, wherein: the communication parameters of the drones are dynamically optimized using cross-layer optimization CLO according to the prediction results, and the specific steps are:

[0032] Based on the prediction result Y mnk , set the cross-layer optimization objective function, and maximize the SINR by dynamically optimizing the frequency band selection, transmit power and antenna direction through cross-layer joint. The expression is:

[0033]

[0034] Among them, ξ1 represents the optimal frequency band, represents the optimized transmit power, θ1 and φ1 represent the optimized antenna pitch angle and elevation angle, SINR represents the signal-to-noise ratio plus interference ratio of the communication link, ξ represents the number of the target frequency band, represents the transmission power, θ and φ represent the pitch angle and elevation angle of the line, H represents the channel gain, J represents the interference intensity, η represents the background noise power in the communication link, Indicates the optimal frequency band, transmit power, antenna pitch angle and elevation angle.

[0035] As a preferred solution of the wireless communication method for a drone fleet described in the present invention, wherein: based on the optimized communication parameters, the drones form a multi-hop transmission network, and the specific steps are:

[0036] According to the optimized communication parameters, neighboring nodes are discovered through broadcast signals, and each drone measures the link quality of neighboring nodes to build a communication link;

[0037] According to the optimized frequency band selection, a communication frequency band is allocated for each link, and the UAV transmits the mission data from the source node to the target node through a multi-hop transmission network.

[0038] As a preferred solution of the wireless communication method for drone fleets described in the present invention, wherein: the three-dimensional radio frequency environment model is used to predict the spectrum usage trend based on real-time data in the multi-hop transmission network, and the specific steps are:

[0039] Collect real-time data in multi-hop transmission networks, use the sliding average method to smooth the wireless signal strength and interference signal strength, normalize all collected data, and integrate the standardized real-time data into a real-time data set;

[0040] The preprocessed real-time data set is converted into a real-time tensor, and the real-time tensor is input into the three-dimensional radio frequency environment model to output the predicted real-time spectrum usage trend.

[0041] As a preferred solution of the wireless communication method for a drone fleet described in the present invention, the specific steps of dynamically allocating frequency band resources according to the predicted spectrum usage trend are as follows:

[0042] Based on the real-time spectrum usage trend predicted by the three-dimensional RF environment model, the frequency band allocation priority is set. The expression is:

[0043]

[0044] Among them, Q(f,t) represents the allocation priority value of frequency band f at time t. The higher the value, the higher the priority. represents the predicted real-time signal strength of frequency band f at time t, represents the real-time interference intensity predicted for frequency band f at time t, and L(f,t) represents the communication link quality of the target frequency band;

[0045] All frequency bands are sorted in descending order according to the priority value Q(f,t), and the frequency bands are allocated in order from high to low priority values;

[0046] The allocated frequency bands are monitored in real time. When the communication performance decreases, the priority value is recalculated and the frequency band with the second highest priority is selected from the sorted list for dynamic adjustment.

[0047] In a second aspect, the present invention provides a wireless communication system for a drone fleet, comprising a collection module, a three-dimensional radio frequency module, an optimization module, a multi-hop transmission module, a prediction module and a distribution module.

[0048] The acquisition module is responsible for collecting the radio frequency signal, position and antenna direction data of the target area in real time, and performing smoothing and normalization on the collected data;

[0049] The three-dimensional radio frequency module is used for the 3D-CNN model to construct a three-dimensional radio frequency environment model, convert the preprocessed data set into a tensor, and input it into the model to predict signal distribution, interference location and spectrum usage;

[0050] The optimization module is used to dynamically adjust the communication parameters of the UAV to optimize the communication performance by adopting a cross-layer optimization strategy according to the model prediction results;

[0051] The multi-hop transmission module is used to enable the drone to discover neighboring nodes and establish communication links based on the optimized communication parameters, and to organize the drones to form a multi-hop transmission network by allocating appropriate communication frequency bands to ensure the effective transmission of mission data;

[0052] The prediction module is used to combine the three-dimensional radio frequency environment model and the data collected in real time to predict the usage trend of each frequency band in the future;

[0053] The allocation module is used to dynamically allocate frequency band resources according to the prediction results, set the frequency band allocation priority, and monitor and adjust the allocated frequency bands.

[0054] In a third aspect, the present invention provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program is executed by the processor, any step of the wireless communication method for a drone fleet as described in the first aspect of the present invention is implemented.

[0055] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, it implements any step of the wireless communication method for a drone fleet as described in the first aspect of the present invention.

[0056] The beneficial effects of the present invention are as follows: the present invention realizes accurate perception of the dynamic radio frequency environment by collecting radio frequency signals, positions and antenna direction data of the target area, and uses the sliding average method to smooth and normalize and integrate them into a data set, thereby providing high-quality data for three-dimensional modeling, improving the accuracy of model prediction, and ensuring the communication optimization effect. The preprocessed data is converted into tensors by using 3D-CNN, and signal distribution, interference position and spectrum usage are predicted. The adaptive weights are dynamically adjusted to accurately capture dynamic changes in the environment, solve the problem of insufficient representation of two-dimensional modeling, improve the prediction accuracy of the radio frequency environment, and provide a reliable basis for communication optimization. Based on the prediction results, the objective function is set to dynamically optimize the frequency band selection, transmission power and antenna direction to maximize the SINR, jointly optimize multi-dimensional communication parameters, improve link quality, enhance communication stability, reduce interference and energy consumption, establish a multi-hop network and dynamically allocate frequency band resources in combination with spectrum trend prediction, adjust priorities in real time, realize cooperative communication of unmanned aerial vehicles, optimize the use of spectrum resources, expand communication coverage, improve task transmission efficiency, and enhance system flexibility. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0058] Figure 1 This is a flow chart of the wireless communication method for a drone fleet in Example 1.

[0059] Figure 2 Schematic diagram of the wireless communication system for a drone fleet in Example 1. DETAILED DESCRIPTION

[0060] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0061] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0062] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0063] Example 1, reference Figure 1 and Figure 2 , which is the first embodiment of the present invention, and provides a wireless communication method for a drone fleet, comprising the following steps:

[0064] S1 collects the RF signal, its own position and antenna direction data of the target area in real time and performs pre-processing;

[0065] According to the mission requirements of the target area, select the acquisition frequency band range, set the frequency sampling interval and time sampling interval;

[0066] Use a spectrum analyzer to collect wireless signal strength, interference signal strength, and RF spectrum utilization;

[0067] The GPS and antenna direction sensors are used to collect the drone position coordinates and antenna direction angles respectively;

[0068] The wireless signal strength and interference signal strength are smoothed using the sliding average method, and all collected data are normalized;

[0069] In the existing technology, signal acquisition data is often interfered by noise, and the signal characteristics of each frequency band are different, which leads to unstable model prediction. Data preprocessing reduces the impact of noise, unifies the data scale, and provides high-quality input for subsequent modeling.

[0070] The sliding average method can smooth signal fluctuations and eliminate short-term outliers, while the normalization process improves the generalization ability and prediction accuracy of the model;

[0071] The standardized data is integrated into the data set D, which is expressed as:

[0072] D={S(f,t),I(f,t),U(f),(x,y,z),θ,φ};

[0073] Among them, S(f,t) represents the change of the normalized wireless signal strength of the target frequency band f with time t, I(f,t) represents the change of the normalized interference signal strength of the target frequency band f with time t, U(f) represents the normalized spectrum utilization of the target frequency band f, (x,y,z) represents the normalized position coordinates, θ and φ represent the normalized antenna pitch angle and elevation angle, respectively.

[0074] S2 uses machine learning algorithms to build a three-dimensional RF environment model, inputs preprocessed data into the three-dimensional RF environment model, and predicts signal distribution, interference location, and spectrum usage;

[0075] Select the 3D convolutional neural network 3D-CNN as the basic model of the 3D RF environment model;

[0076] Traditional RF modeling methods are mostly two-dimensional or linear models, which cannot accurately describe complex three-dimensional RF environments. By introducing 3D-CNN and utilizing its multi-dimensional modeling capabilities of spatial, temporal and spectral characteristics, the accuracy of predicting signal distribution is improved.

[0077] The preprocessed data set D is converted into a tensor T(D), expressed as:

[0078] T(D)∈R M×N×K =T(S(f,t),I(f,t),U(f),(x,y,z),θ,φ);

[0079] Among them, ∈ indicates belonging, R indicates that each element in the tensor is a real number, M indicates the number of target frequency bands f, N indicates the length of the sampling time series, and K indicates the spatial and directional feature dimensions (including position and antenna direction);

[0080] Input the tensor T(D) into the three-dimensional RF environment model and output the prediction result. The expression is:

[0081]

[0082] Among them, Y mnk represents the signal distribution, interference location, and spectrum usage in the mth frequency band, the nth time point, and the kth spatial direction, W mnk represents the adaptive weight function in the mth frequency band, the nth time point, and the kth spatial direction (used to adjust the influence of different frequency bands, time and spatial directions on the overall prediction), T mnk represents the data corresponding to the mth frequency band, the nth time point, and the kth spatial direction extracted from T(D), ∈ represents a natural constant (used to prevent the denominator from being zero);

[0083] The 3D-CNN model can capture the global characteristics and local correlations of the RF environment, and the prediction results have higher spatial resolution, providing high-quality support for cross-layer optimization of communication parameters.

[0084] S3 uses cross-layer optimization CLO to dynamically optimize the communication parameters of the UAV based on the prediction results;

[0085] Traditional communication optimization strategies usually optimize a single parameter independently, ignoring the correlation between communication parameters. This step can achieve global optimization of communication performance in complex RF environments through cross-layer joint optimization.

[0086] Based on the prediction result Y mnk , set the cross-layer optimization objective function, and maximize the SINR by dynamically optimizing the frequency band selection, transmit power and antenna direction through cross-layer joint. The expression is:

[0087]

[0088] Among them, ξ1 represents the optimal frequency band, which maximizes the channel gain H(ξ,θ,φ) and minimizes the interference strength J(ξ,θ,φ). θ1 represents the optimized transmit power to ensure the maximization of SINR. θ1 and φ1 represent the optimized antenna pitch angle and elevation angle to maximize the channel gain H(ξ,θ,φ) and avoid interference. SINR represents the signal-to-noise ratio plus interference ratio of the communication link. ξ represents the number of the target frequency band. represents the transmission power, θ and φ represent the pitch angle and elevation angle of the line, H represents the channel gain, J represents the interference intensity, and η represents the background noise power in the communication link, which is a fixed value. Indicates the optimal frequency band, transmit power, antenna pitch angle and elevation angle;

[0089] Jointly optimizing frequency band selection, transmit power, and antenna direction can simultaneously improve signal coverage and anti-interference capabilities, significantly improving the reliability of communication links in high-interference environments.

[0090] S4 uses the optimized communication parameters to build a multi-hop transmission network with drones;

[0091] According to the optimized communication parameters, neighboring nodes are discovered through broadcast signals, and each drone measures the link quality of neighboring nodes to build a communication link;

[0092] According to the optimized frequency band selection, a communication frequency band is allocated to each link, and the UAV transmits the mission data from the source node to the target node through the multi-hop transmission network;

[0093] The frequency band allocation of existing multi-hop networks often ignores the dynamic changes of link quality, which can easily lead to communication bottlenecks. This step combines link quality measurement and frequency band optimization allocation to significantly improve network transmission efficiency.

[0094] Dynamic allocation of frequency band resources can optimize network performance according to mission requirements and environmental changes, reduce communication delays and improve data transmission reliability.

[0095] S5 uses a three-dimensional RF environment model to predict spectrum usage trends based on real-time data in multi-hop transmission networks;

[0096] Collect real-time data in multi-hop transmission networks, use the sliding average method to smooth the wireless signal strength and interference signal strength, normalize all collected data, and integrate the standardized real-time data into a real-time data set;

[0097] Convert the preprocessed real-time data set into a real-time tensor, and input the real-time tensor into a three-dimensional radio frequency environment model to output a predicted real-time spectrum usage trend;

[0098] Existing frequency band allocation methods are mostly based on static or real-time data and lack the ability to predict spectrum usage trends. This step improves the rationality and predictability of spectrum resource allocation through trend prediction.

[0099] Spectrum usage trend prediction can avoid blind frequency band allocation, reduce spectrum resource conflicts, and improve spectrum utilization efficiency.

[0100] S6 dynamically allocates frequency band resources based on predicted spectrum usage trends;

[0101] Based on the real-time spectrum usage trend predicted by the three-dimensional RF environment model, the frequency band allocation priority is set. The expression is:

[0102]

[0103] Among them, Q(f,t) represents the allocation priority value of frequency band f at time t. The higher the value, the higher the priority. represents the predicted real-time signal strength of frequency band f at time t, represents the real-time interference intensity predicted for frequency band f at time t, and L(f,t) represents the communication link quality of the target frequency band;

[0104] All frequency bands are sorted in descending order according to the priority value Q(f,t), and the frequency bands are allocated in order from high to low priority values;

[0105] The allocated frequency bands are monitored in real time. When the communication performance decreases, the priority value is recalculated and the frequency band with the second highest priority is selected from the sorted list for dynamic adjustment.

[0106] Traditional frequency band allocation methods are mostly static allocation, which is difficult to adapt to dynamic changes in the environment. This step realizes real-time optimization and allocation of spectrum resources through a dynamic priority adjustment mechanism.

[0107] The frequency band allocation priority value comprehensively considers signal strength, interference intensity, spectrum utilization and link quality factors to ensure the efficiency of resource allocation. The real-time monitoring mechanism further improves the stability and reliability of the communication link.

[0108] This embodiment also provides a wireless communication system for a drone fleet, including a collection module, a three-dimensional radio frequency module, an optimization module, a multi-hop transmission module, a prediction module and a distribution module.

[0109] The acquisition module is responsible for collecting the RF signal, location and antenna direction data of the target area in real time, and smoothing and normalizing the collected data;

[0110] 3D RF module, which is used in 3D-CNN model to build 3D RF environment model, convert the preprocessed data set into tensor and input it into the model to predict signal distribution, interference location and spectrum usage;

[0111] The optimization module is used to dynamically adjust the communication parameters of the UAV to optimize the communication performance based on the model prediction results using a cross-layer optimization strategy;

[0112] The multi-hop transmission module is used to enable the drone to find neighboring nodes and establish communication links based on the optimized communication parameters. By allocating appropriate communication frequency bands, the drones are organized to form a multi-hop transmission network to ensure the effective transmission of mission data.

[0113] The prediction module is used to combine the three-dimensional RF environment model and the real-time collected data to predict the usage trend of each frequency band in the future;

[0114] The allocation module is used to dynamically allocate frequency band resources according to the prediction results, set the frequency band allocation priority, and monitor and adjust the allocated frequency bands.

[0115] This embodiment also provides a computer device, which is suitable for the wireless communication method for a drone swarm, including: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute computer-executable instructions to implement the wireless communication method for a drone swarm as proposed in the above embodiment.

[0116] The computer device may be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covering the display screen, or a key, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0117] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, the wireless communication method for a drone fleet proposed in the above embodiment is implemented; the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, referred to as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, referred to as EEPROM), erasable programmable read-only memory (Erasable Programmable Read Only Memory, referred to as EPROM), programmable read-only memory (Programmable Red-Only Memory, referred to as PROM), read-only memory (Read-Only Memory, referred to as ROM), magnetic storage, flash memory, magnetic disk or optical disk.

[0118] In summary, the present invention realizes accurate perception of the dynamic RF environment by: collecting RF signals, positions and antenna direction data in the target area, and using the sliding average method to smooth and normalize and integrate them into a data set, providing high-quality data for three-dimensional modeling, improving the accuracy of model prediction, and ensuring the communication optimization effect. The preprocessed data is converted into tensors using 3D-CNN, and signal distribution, interference position and spectrum usage are predicted. The adaptive weights are dynamically adjusted to accurately capture dynamic changes in the environment, solve the problem of insufficient representation of two-dimensional modeling, improve the prediction accuracy of the RF environment, and provide a reliable basis for communication optimization. Based on the prediction results, the objective function is set to dynamically optimize the frequency band selection, transmission power and antenna direction to maximize the SINR, jointly optimize multi-dimensional communication parameters, improve link quality, enhance communication stability, reduce interference and energy consumption, establish a multi-hop network and dynamically allocate frequency band resources in combination with spectrum trend prediction, adjust priorities in real time, realize UAV collaborative communication, optimize spectrum resource usage, expand communication coverage, improve task transmission efficiency, and enhance system flexibility.

[0119] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A wireless communication method for a drone fleet, characterized in that: include, Collect the RF signal, own position and antenna direction data of the target area in real time and perform pre-processing; Use machine learning algorithms to build a three-dimensional RF environment model, input the preprocessed data into the three-dimensional RF environment model, and predict signal distribution, interference location, and spectrum usage; Based on the prediction results, the cross-layer optimization CLO is used to dynamically optimize the communication parameters of the UAV; Based on the optimized communication parameters, the drones set up a multi-hop transmission network; Based on real-time data in multi-hop transmission networks, a three-dimensional radio frequency environment model is used to predict spectrum usage trends; Dynamically allocate frequency band resources based on predicted spectrum usage trends.

2. The wireless communication method for a drone fleet according to claim 1, characterized in that: The real-time collection of the radio frequency signal, the location and the antenna direction data of the target area and the pre-processing are carried out, and the specific steps are as follows: According to the mission requirements of the target area, select the acquisition frequency band range, set the frequency sampling interval and time sampling interval; Use a spectrum analyzer to collect wireless signal strength, interference signal strength, and RF spectrum utilization; The GPS and antenna direction sensors are used to collect the drone position coordinates and antenna direction angles respectively; The wireless signal strength and interference signal strength are smoothed using the sliding average method, and all collected data are normalized; The standardized data is integrated into the data set D, which is expressed as: D={S(f,t),I(f,t),U(f),(x,y,z),θ,φ}; Among them, S(f,t) represents the change of the normalized wireless signal strength of the target frequency band f with time t, I(f,t) represents the change of the normalized interference signal strength of the target frequency band f with time t, U(f) represents the normalized spectrum utilization of the target frequency band f, (x,y,z) represents the normalized position coordinates, θ and φ represent the normalized antenna pitch angle and elevation angle, respectively.

3. The wireless communication method for a drone fleet according to claim 2, characterized in that: The three-dimensional radio frequency environment model is constructed by using a machine learning algorithm, and the preprocessed data is input into the three-dimensional radio frequency environment model to predict signal distribution, interference location and spectrum usage. The specific steps are: Select the 3D convolutional neural network 3D-CNN as the basic model of the 3D RF environment model; The preprocessed data set D is converted into a tensor T(D), expressed as: T(D)∈R M×N×K =T(S(f,t),I(f,t),U(f),(x,y,z),θ,φ); Among them, ∈ indicates belonging, R indicates that each element in the tensor is a real number, M indicates the number of target frequency bands f, N indicates the length of the sampling time series, and K indicates the spatial and directional feature dimensions; The tensor T(D) is input into the three-dimensional RF environment model and the prediction result is output. The expression is: Among them, Y mnk represents the signal distribution, interference location, and spectrum usage in the mth frequency band, the nth time point, and the kth spatial direction, W mnk represents the adaptive weight function in the mth frequency band, the nth time point, and the kth spatial direction, T mnk It represents the data corresponding to the mth frequency band, the nth time point, and the kth spatial direction extracted from T(D), and ∈ represents a natural constant (used to prevent the denominator from being zero).

4. The wireless communication method for a drone fleet according to claim 3, characterized in that: The cross-layer optimization CLO is used to dynamically optimize the communication parameters of the UAV according to the prediction results. The specific steps are: Based on the prediction result Y mnk , set the cross-layer optimization objective function, and maximize the SINR by dynamically optimizing the frequency band selection, transmit power and antenna direction through cross-layer joint. The expression is: Among them, ξ1 represents the optimal frequency band, represents the optimized transmit power, θ1 and φ1 represent the optimized antenna pitch angle and elevation angle, SINR represents the signal-to-noise ratio plus interference ratio of the communication link, ξ represents the number of the target frequency band, represents the transmission power, θ and φ represent the pitch angle and elevation angle of the line, H represents the channel gain, J represents the interference intensity, η represents the background noise power in the communication link, Indicates the optimal frequency band, transmit power, antenna pitch angle and elevation angle.

5. The wireless communication method for a drone fleet according to claim 4, characterized in that: According to the optimized communication parameters, the drones form a multi-hop transmission network, and the specific steps are as follows: According to the optimized communication parameters, neighboring nodes are discovered through broadcast signals, and each drone measures the link quality of neighboring nodes to build a communication link; According to the optimized frequency band selection, a communication frequency band is allocated for each link, and the UAV transmits the mission data from the source node to the target node through a multi-hop transmission network.

6. The wireless communication method for a drone fleet according to claim 5, characterized in that: The method of using a three-dimensional radio frequency environment model to predict spectrum usage trends based on real-time data in a multi-hop transmission network comprises the following specific steps: Collect real-time data in multi-hop transmission networks, use the sliding average method to smooth the wireless signal strength and interference signal strength, normalize all collected data, and integrate the standardized real-time data into a real-time data set; The preprocessed real-time data set is converted into a real-time tensor, and the real-time tensor is input into the three-dimensional radio frequency environment model to output the predicted real-time spectrum usage trend.

7. The wireless communication method for a drone fleet according to claim 6, characterized in that: The specific steps of dynamically allocating frequency band resources according to the predicted spectrum usage trend are as follows: Based on the real-time spectrum usage trend predicted by the three-dimensional RF environment model, the frequency band allocation priority is set. The expression is: Among them, Q(f,t) represents the allocation priority value of frequency band f at time t. The higher the value, the higher the priority. represents the predicted real-time signal strength of frequency band f at time t, represents the real-time interference intensity predicted for frequency band f at time t, and L(f,t) represents the communication link quality of the target frequency band; All frequency bands are sorted in descending order according to the priority value Q(f,t), and the frequency bands are allocated in order from high to low priority values; The allocated frequency bands are monitored in real time. When the communication performance decreases, the priority value is recalculated and the frequency band with the second highest priority is selected from the sorted list for dynamic adjustment.

8. A wireless communication system for a drone swarm, based on the wireless communication method for a drone swarm according to any one of claims 1 to 7, characterized in that: It includes acquisition module, 3D RF module, optimization module, multi-hop transmission module, prediction module and allocation module. The acquisition module is responsible for collecting the radio frequency signal, position and antenna direction data of the target area in real time, and performing smoothing and normalization on the collected data; The three-dimensional radio frequency module is used for the 3D-CNN model to construct a three-dimensional radio frequency environment model, convert the preprocessed data set into a tensor, and input it into the model to predict signal distribution, interference location and spectrum usage; The optimization module is used to dynamically adjust the communication parameters of the UAV to optimize the communication performance by adopting a cross-layer optimization strategy according to the model prediction results; The multi-hop transmission module is used to enable the drone to discover neighboring nodes and establish communication links based on the optimized communication parameters, and to organize the drones to form a multi-hop transmission network by allocating appropriate communication frequency bands to ensure the effective transmission of mission data; The prediction module is used to combine the three-dimensional radio frequency environment model and the data collected in real time to predict the usage trend of each frequency band in the future; The allocation module is used to dynamically allocate frequency band resources according to the prediction results, set the frequency band allocation priority, and monitor and adjust the allocated frequency bands.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the wireless communication method for a drone fleet described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the wireless communication method for a drone fleet described in any one of claims 1 to 7 are implemented.

Images