Air-ground integrated vehicle networking performance analysis and optimization method and system

By constructing an intelligent connected vehicle model and optimizing UAV flight paths and spectrum allocation, the problems of interference and channel state information in the air-ground integrated vehicle network were solved, achieving more efficient communication performance and stability, and enhancing communication coverage and spectrum utilization.

CN119012157APending Publication Date: 2024-11-22JIAXING UNIV
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410999821.4
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-24
Publication Date
2024-11-22

AI Technical Summary

Technical Problem

Existing technologies in air-ground integrated vehicle-to-everything (V2X) networks suffer from interference between users and the inability of channel status information to function, thus affecting communication performance.

Method used

We construct an intelligent connected vehicle model that includes a lead vehicle, a drone, and subordinate vehicles. We adopt a NOMA-enhanced relay drone vehicle-to-everything (V2X) model and maximize downlink security rate and communication performance by optimizing drone flight paths and spectrum allocation, combined with reinforcement learning and graph theory.

Benefits of technology

It improves communication range and spectrum utilization, enhances communication coverage and stability, optimizes traffic flow and energy consumption, reduces interference between users, and provides higher quality communication services.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119012157A_ABST
    Figure CN119012157A_ABST
Patent Text Reader

Abstract

The invention discloses an air-ground integrated vehicle networking performance analysis and optimization method and system, and belongs to the technical field of air-ground cooperative network communication. An intelligent network connection vehicle model is constructed, and a relay unmanned aerial vehicle networking model based on NOMA enhancement is constructed based on the intelligent network connection vehicle model; constructing a downlink safety rate and an objective function and an optimization condition of an optimization problem based on an NOMA enhanced relay unmanned aerial vehicle networking model; the method comprises the following steps: obtaining an analytic solution of a downlink rate through stochastic geometry based on a downlink security rate and an objective function and an optimization condition of an optimization problem, and performing approximate processing on the analytic solution of the downlink rate through Gaussian-Chebyshev integral to obtain an approximate solution, thereby realizing performance analysis of the air-ground integrated Internet of Vehicles based on non-orthogonal multiple access; and based on the constructed objective function, the optimization condition and the approximate solution of the downlink rate, iterative solution is carried out through reinforcement learning and a graph theory, the track and spectrum allocation of the unmanned aerial vehicle are optimized, and the downlink rate sum is maximized.
Need to check novelty before this filing date? Find Prior Art

Description

Background Art

[0002] In recent years, in certain long-distance transport sections, convoys have enhanced road safety through vehicle control and communication technologies, among which relay drones play a key role. Generally, using drones as relays for convoys to transmit data between the leading vehicle and the following vehicle can effectively expand the communication range, enhance communication coverage, and provide stable communication links in complex or blocked environments. However, in the NOMA enhanced vehicle network, due to limited wireless resources and high vehicle mobility, a series of problems such as accurate performance analysis and reasonable optimization of the network for relay drone-assisted vehicle platoons still need to be solved, posing challenges to researchers in this field.

[0003] The first existing technology is dedicated to improving the spectrum utilization efficiency in the air-ground integrated vehicle network. This technology adopts an uplink cooperative non-orthogonal multiple access (NOMA) scheme and constructs a drone-assisted vehicle platoon model based on NOMA.

[0004] The second existing technology is dedicated to improving the accuracy of complex dynamic vehicle network performance analysis, while optimizing network parameters to adapt to the changing environment. The second technology proposes to adopt physical layer (PSL) technology that does not rely on encryption keys, thereby promoting low-latency and high-security transmission.

[0005] However, the existing technology has the following problems:

[0006] First, the existing technology 1 mainly uses NOMA technology to transmit tasks. However, NOMA technology introduces non-orthogonal signal superposition and ignores the interference problem between users. Secondly, technology 2 usually assumes that there is perfect channel state information between legitimate users and eavesdroppers, but this assumption is not valid in all cases, and since the ground channel is assumed to be Rayleigh fading, it shows that a model that better reflects real-world conditions is needed. Summary of the invention

[0007] The technical problem to be solved by the present invention is to provide a method and system for analyzing and optimizing the performance of an air-ground integrated vehicle network in view of the deficiencies in the above-mentioned prior art, so as to solve the technical problems of interference between existing users and the inability to validate channel status information.

[0008] The present invention adopts the following technical solutions:

[0009] A method for analyzing and optimizing air-ground integrated vehicle networking performance includes the following steps:

[0010] Construct an intelligent connected vehicle model including 1 pilot vehicle, 1 relay drone and V subordinate vehicles, where the vehicles move in a convoy and the drones follow the convoy;

[0011] Based on the obtained intelligent connected vehicle model, a NOMA-enhanced relay drone vehicle networking model is constructed;

[0012] Based on the obtained NOMA enhanced relay drone Internet of Vehicles model, the objective function and optimization conditions of the downlink safety rate and optimization problem are constructed;

[0013] Based on the objective function and optimization conditions of the downlink safety rate and optimization problem, the analytical solution of the downlink rate is obtained through random geometry, and the approximate solution of the analytical solution of the downlink rate is approximated by the Gauss-Chebyshev integral to achieve the performance analysis of the air-ground integrated vehicle network based on non-orthogonal multiple access; through reinforcement learning and graph theory, iterative solutions are obtained to optimize the trajectory and spectrum allocation of the UAV, maximize the downlink rate and, thus, maximizing the downlink rate and of the air-ground integrated vehicle network based on non-orthogonal multiple access.

[0014] Preferably, in the intelligent networked vehicle model, a set of intelligent networked vehicles is defined The pilot vehicle uses non-orthogonal multiple access technology for data transmission. The slave vehicles receive two different messages in two time slots. The pilot vehicle has M spectrums for data transmission. The spectrum allocation strategy is:

[0015]

[0016] in, is the collection of spectrum, A collection of intelligent connected vehicles. is the set of spectrum allocation schemes, N m,v is the spectrum allocation scheme; when the mth spectrum is allocated to the vth slave vehicle, N m,v =1, otherwise N m,v =0.

[0017] Preferably, in the NOMA-enhanced relay drone Internet of Vehicles model,

[0018] Define the leader vehicle to transmit overlapping signals D to the vth slave vehicle and relay UAV in the first time slot L,v , determine the signal received by the UAV and the vth slave vehicle in the first time slot and r L,v ;

[0019] Define the relay drone to send data symbols to the vth slave vehicle in the second time slot Set data symbol is perfectly decoded; in the second time slot, the received signal r of the vth slave vehicle is determined U,v ;

[0020] Define the data rate of the vth slave vehicle in, and Data symbols and rate.

[0021] Preferably, the signal received by the drone and the vth slave vehicle in the first time slot and r L,v Respectively expressed as:

[0022]

[0023]

[0024] in, is the independent Rician fading channel coefficient of the pilot vehicle-UAV link on the mth spectrum, h L,v is the independent Rician fading channel coefficient of the pilot vehicle-vth slave vehicle link, η L,U and η L,v is a function with zero mean and variance σ 2 Additive Gaussian white noise, is the power distribution coefficient of the vth slave vehicle, P v is the transmission power allocated by the pilot vehicle to the vth slave vehicle, represents the jth data symbol with normalized power.

[0025] Preferably, the received signal r of the vth slave vehicle U,v for:

[0026]

[0027] in, is the independent Rician fading channel coefficient of the UAV-vth slave vehicle link on the mth spectrum, η U,v is a function with zero mean and variance σ 2 Additive Gaussian white noise, P v is the transmission power allocated by the pilot vehicle to the vth slave vehicle, represents the jth data symbol with normalized power.

[0028] Preferably, the data symbol and Rate and They are:

[0029]

[0030]

[0031] Among them, γ L,v Data symbol The received signal-to-interference-noise ratio at the vth slave vehicle, Data symbol The received signal-to-interference-noise ratio at the drone, For data signal The received signal-to-interference-to-noise ratio at the drone, γ U,v For data signal Received signal-to-interference-and-noise ratio at the vth slave vehicle.

[0032] Preferably, the objective function and optimization conditions for constructing the downlink safety rate and optimization problem are specifically:

[0033] By optimizing the trajectory and spectrum allocation Maximizing the downlink safety rate and C of the connected vehicle network with relay drones and non-orthogonal multiple access technology sum , determine the downlink safety rate and optimization problem P1;

[0034] For downlink rate and C sum Analyze and define and Get ω 1 The cumulative distribution function F(ω 1 );

[0035] Based on the simplified numerical calculation of Gauss-Chebyshev integral, we can get The approximate solution of and Rate and The approximate solution of .

[0036] Preferably, the downlink safety rate and optimization problem P1 are:

[0037]

[0038] in, is the minimum value of the horizontal axis, vertical axis and vertical axis of the feasible area of ​​the UAV track, is the maximum value of the horizontal, vertical and vertical axes of the feasible area of ​​the UAV track, is the maximum flight speed of the UAV, C sum is the downlink safety rate and, To optimize the trajectory, is the spectrum allocation, C vis the data rate of the vth slave vehicle, is a set, N m,v is the spectrum allocation scheme, M is the number of spectrums, is the collection of spectrum, is the collection of intelligent connected vehicles, C sec is the target safety rate, C th is the maximum allowed eavesdropping rate.

[0039] Preferably, the iterative solution is performed through Gauss-Chebyshev integration, reinforcement learning, graph theory, and Hungarian algorithm as follows:

[0040] Decouple the downlink rate and maximization problem P1 into the trajectory optimization problem P2 and the spectrum allocation problem P3;

[0041] For the trajectory optimization problem P2, the Q-learning method is used to solve it;

[0042] First, the trajectory optimization problem P2 is transformed into a Markov decision process;

[0043] Then, construct the Q value table Q tab , Q tab is a two-dimensional matrix consisting of states and actions. The drone starts from the starting point and follows Q tab Update the strategy to explore the environment, generating a state-action-reward sequence from the start state to the end state, where the end state is when the drone reaches the destination;

[0044] For spectrum allocation problem P3, the spectrum allocation problem is regarded as a bipartite graph matching problem, and the optimal matching is obtained based on the Hungarian algorithm.

[0045] In a second aspect, an embodiment of the present invention provides an air-ground integrated vehicle networking performance analysis and optimization system, including:

[0046] Building a module, constructing an intelligent connected vehicle model including 1 pilot vehicle, 1 relay drone and V slave vehicles, where the vehicles move in a convoy and the drones follow the convoy;

[0047] The enhancement module builds a NOMA-enhanced relay drone Internet of Vehicles model based on the obtained intelligent connected vehicle model;

[0048] The optimization module constructs the objective function and optimization conditions of the downlink safety rate and optimization problem based on the obtained NOMA enhanced relay drone Internet of Vehicles model;

[0049] Output module, output module, based on the objective function and optimization conditions of the downlink safety rate and optimization problem, obtains the analytical solution of the downlink rate through random geometry, and approximates the analytical solution of the downlink rate through Gauss-Chebyshev integral to obtain an approximate solution, thereby realizing the performance analysis of the air-ground integrated vehicle network based on non-orthogonal multiple access; through iterative solution through reinforcement learning and graph theory, optimizes the trajectory and spectrum allocation of the UAV, maximizes the downlink rate and, realizes the maximization of the downlink rate and of the air-ground integrated vehicle network based on non-orthogonal multiple access.

[0050] Compared with the prior art, the present invention has at least the following beneficial effects:

[0051] A performance analysis and optimization method for air-ground integrated vehicle networking adopts NOMA to enhance the performance of vehicle networking drone-assisted fleet and reasonably optimize the design. Then, the analytical solution of the average achievable rate from the pilot vehicle to the subordinate vehicle on the Rayleigh fading channel is derived, and the optimization problem with the goal of maximizing the downlink rate and is combined with consideration of trajectory optimization, spectrum allocation and information security. After that, the Hungarian algorithm is solved through an iterative optimization method. Finally, compared with the existing mechanism, the present invention can achieve downlink rate and optimization.

[0052] Furthermore, air-ground collaboration has obvious advantages, especially in wireless communications. Specifically, in the scenario of a specific long-distance transport section, the pilot vehicle uses non-orthogonal multiple access technology for data transmission, so that the subordinate vehicle can receive 2 different messages in 2 time slots, which can effectively expand the communication range, enhance signal coverage, and provide a stable communication link in a complex or obstructive environment. In addition, there is a possibility of emergencies in specific sections, such as obstacles on the road, collapse of surrounding rock walls, and the influence of other obstructions, resulting in non-line-of-sight signal transmission, while drones can avoid ground obstacles and form a direct communication link. In direct transmission, the signal is transmitted directly from the drone to the pilot vehicle, with higher signal power and less interference. In addition, through precise vehicle control and communication technology, the fleet can enhance road safety, optimize traffic flow, and reduce energy consumption, thereby providing a wider range of communication services.

[0053] Furthermore, in the air-ground integrated vehicle network, the use of NOMA technology can provide better communication services; specifically, in the scenario of a specific transportation section, due to limited spectrum resources and low spectrum utilization, the use of NOMA technology allows the subordinate vehicle to receive two different messages in two time slots, which can effectively expand the communication range and improve spectrum utilization. In addition, NOMA technology dynamically allocates spectrum and adjusts the modulation method, so that the pilot vehicle and the subordinate vehicle can transmit collaboratively in the same frequency band, reduce interference between users, and thus ensure the reliability of communication.

[0054] Furthermore, in the air-ground integrated vehicle network, the present invention aims to maximize the downlink rate and; due to the adoption of NOMA technology, it is necessary to consider optimizing the trajectory. The reason is that the movement trajectory of the drone is used as a new dimension to optimize the system performance. The optimized trajectory can further improve the transmission rate of the drone communication system to provide higher quality communication services and reduce interference with surrounding vehicles. In addition, spectrum allocation needs to be optimized. The reason is that optimizing spectrum allocation can enhance spectrum efficiency, increase system capacity and provide higher quality communication services. In addition, for drones, optimizing their three-dimensional deployment is essential. The reason is that by optimizing the three-dimensional deployment of drones, the coverage of communications can be maximized, and signal blocking and obstacles in the propagation path can be avoided, the path loss of signal transmission can be reduced, and the communication quality and stability can be improved.

[0055] Furthermore, the modeled uplink rate and maximization problem are non-convex and difficult to solve directly using traditional convex optimization algorithms; the reason is that due to N m,v ∈{0,1}, so the data rate and maximization problem modeled is a continuous variable Discrete variables The mixed integer nonlinear rule problem with non-deterministic polynomial characteristics is usually intractable and difficult to solve directly. Therefore, the non-convex problem is decoupled into two sub-problems, and the rate and maximization are achieved through closed-form solution derivation, Hungarian algorithm, vector generation based on Gauss-Chebyshev integral, reinforcement learning and graph theory.

[0056] Furthermore, the use of physical layer security (PLS) technology can effectively ensure user privacy. The reason is that unauthorized users may pose a threat to the security of data transmitted to authorized users, which will lead to network vulnerabilities, such as hacking, eavesdropping, and interference with transmitted information. Wireless communications are in urgent need of security protection measures that are consistent with their transmission characteristics and propagation mechanisms. PLS originates from but is higher than the security concept of wireless communication itself. Starting from the characteristics of wireless communication propagation, PLS uses the immeasurable and non-replicable inherent security properties of wireless channels to explore the inherent security mechanism of wireless communication from the physical layer and promote the integration of security and communication. In addition, in the spectrum allocation problem, PLS often requires more accurate channel estimation in order to obtain a sufficiently good security effect. Therefore, the more spectrum resources are allocated, the more reasonable, the more accurate the channel, and the narrower the main lobe, the better the security effect.

[0057] It can be understood that the beneficial effects of the second aspect mentioned above can be found in the relevant description of the first aspect mentioned above, and will not be repeated here.

[0058] In summary, the present invention can meet the communication needs of specific long-distance transportation, and is aimed at the communication needs of a large number of nodes in the long-distance transportation communication network. It adopts drones with flexible deployment characteristics as relays to assist the communication transmission of the fleet and optimize the traffic flow. The pilot vehicle adopts non-orthogonal multiple access technology for data transmission, allowing the subordinate vehicle to receive 2 different information in 2 time slots, and can accurately obtain the achievable maximum data rate.

[0059] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] Figure 1 A flowchart of a method for analyzing and optimizing air-ground integrated vehicle networking performance based on non-orthogonal multiple access provided by an embodiment of the present invention;

[0061] Figure 2 A schematic diagram of a vehicle networking model with a relay drone and non-orthogonal multiple access technology enabled provided by an embodiment of the present invention;

[0062] Figure 3 A comparison diagram of the error between the approximate result and the analysis result of the downlink rate provided in the embodiment of the present invention;

[0063] Figure 4 A comparison chart of the average running time of the approximate result of the sum of the downlink rates provided by the embodiment of the present invention and the analysis result;

[0064] Figure 5 A performance comparison diagram of maximizing downlink rate and compared with Comparative Scheme 1, Comparative Scheme 2, Comparative Scheme 3, and Comparative Scheme 4 provided in an embodiment of the present invention;

[0065] Figure 6 A comparison diagram of maximizing downlink rate and maximum allowed wiretap rate provided by the embodiment of the present invention with comparison scheme 1, comparison scheme 2, comparison scheme 3, and comparison scheme 4;

[0066] Figure 7 A schematic diagram of a computer device provided by an embodiment of the present invention;

[0067] Figure 8 The present invention is a block diagram of an electronic device provided according to an embodiment. DETAILED DESCRIPTION

[0068] The present invention provides a performance analysis and optimization method for an air-ground integrated vehicle network, and analyzes and optimizes the performance of a UAV-assisted vehicle queue in a NOMA-enhanced vehicle network. First, in order to improve spectrum utilization, the NOMA technology is used to allow a subordinate vehicle to receive two different signals from a pilot vehicle in continuous time slots. Second, the method derives an analytical solution for the average achievable rate from the pilot vehicle to the subordinate vehicle on a Rayleigh fading channel. Based on the derived analytical solution, the method uses the Gauss-Chebyshev integral to further approximate the solution. Then, by jointly considering trajectory optimization, spectrum allocation, and information security, a problem of maximizing the sum of security rates is formulated. In the formulated problem, the CSI of potential eavesdroppers needs to be estimated, and by using the PLS technology, interference between users is minimized and the personal privacy of users is protected. By using O-learning and graph theory, trajectories and spectra are processed in sequence, which is suitable for personal performance analysis or optimization within the vehicle network.

[0069] See also Figure 1 The present invention provides an air-ground integrated vehicle network performance analysis and optimization method, which decouples the downlink rate and maximization problem (P1) into a track optimization problem (P2) and a spectrum allocation problem (P3); for P2, a Q-learning method is used to solve P2; first, P2 is converted into a Markov decision process (MDP), and then a Q value table Q is constructed. tab , where Q tab is a two-dimensional matrix consisting of states and actions; therefore, the drone starts from the starting point and follows Q tab Update the strategy to explore the environment and generate a state-action-reward sequence from the start state to the end state; the end state is when the drone reaches the destination; for P3, the spectrum allocation problem can be regarded as a bipartite graph matching problem, and the optimal matching is obtained based on the Hungarian algorithm; the specific steps are as follows:

[0070] S1. Construct an intelligent connected vehicle (ICVs) model consisting of a lead vehicle, a relay drone, and V follower vehicles, where the vehicles move in a convoy and the drones follow the convoy.

[0071] S101. The set of intelligent connected vehicles is defined as The pilot vehicle uses non-orthogonal multiple access (NOMA) technology for data transmission, so that the vth The slave vehicle receives 2 different messages in 2 time slots;

[0072] S102, using a Cartesian coordinate system, and dividing the three-dimensional track of the relay drone into T segments, Defined in segment t The three-dimensional coordinates of the relay drone are in, Respectively represent the horizontal, vertical and vertical coordinates of the relay UAV in the tth segment;

[0073] S103. The lead vehicle has M spectrums for data transmission, and the spectrum allocation strategy is defined as:

[0074]

[0075] When the mth The spectrum is allocated to the vth slave vehicle, N m,v =1, otherwise N m,v =0.

[0076] According to step S101, step S102, and step S103, the present invention constructs an intelligent connected vehicle model consisting of 1 pilot vehicle, 1 relay drone, and V slave vehicles.

[0077] S2, based on the intelligent connected vehicle model obtained in step S1, a NOMA-enhanced relay drone vehicle networking model is constructed;

[0078] S201, define the pilot vehicle to transmit overlapping signals to the vth slave vehicle and the relay UAV in the first time slot in, represents the jth (j∈{1,2}) data symbol with normalized power P v The transmission power allocated by the pilot vehicle to the vth slave vehicle; is the power distribution coefficient of the vth slave vehicle,

[0079] Generally speaking, due to the channel power gain G of the pilot vehicle-UAV link L,U Higher than the channel power gain G of the pilot vehicle-vth slave vehicle L,v ,have to Therefore, the signals received by the UAV and the vth slave vehicle in the first time slot are expressed as:

[0080]

[0081] and

[0082]

[0083] in, The pilot vehicle-drone link is at the mth Spectrally independent Rician fading channel coefficients with power gain h L,v is the independent Rician fading channel coefficient of the pilot vehicle-vth slave vehicle link, with power gain Ω L,v ; η L,U and η L,v is a function with zero mean and variance σ 2 Additive white Gaussian noise.

[0084] S202, define the relay drone to send data symbols to the vth slave vehicle in the second time slot And assume that the data symbol is perfectly decoded; therefore, in the second time slot, the received signal r of the vth slave vehicle U,v It is expressed as:

[0085]

[0086] in, is the independent Rician fading channel coefficient of the UAV-vth slave vehicle link on the mth spectrum, with power gain η U,v is a function with zero mean and variance σ 2 For the convenience of calculation, it is assumed that the transmission power allocated by the UAV to the vth slave vehicle is still P v .

[0087] S203: Define the data rate of the vth slave vehicle in, and Data symbols and The rate is expressed as:

[0088]

[0089] and

[0090]

[0091] In equations (4) and (5), γ L,v Data symbol The received signal-to-interference-noise ratio at the vth slave vehicle,

[0092] Data symbol The received signal-to-interference-noise ratio at the drone,

[0093] For data signal The received signal-to-interference-noise ratio at the drone,

[0094] γ U,v For data signal The received signal-to-interference-noise ratio at the vth slave vehicle,

[0095] According to step S201, step S202 and step S203, the method of the present invention constructs a NOMA-enhanced relay drone vehicle networking model.

[0096] S3. Construct the objective function and optimization conditions of the downlink safety rate and optimization problem based on the NOMA-enhanced relay drone Internet of Vehicles model;

[0097] S301, by optimizing the track and spectrum allocation Aims to maximize the downlink safety rate and C of the connected vehicle network with relay drones and non-orthogonal multiple access technology. sum , the problem is modeled as:

[0098]

[0099]

[0100]

[0101]

[0102]

[0103] in, It is the minimum value of the horizontal axis, vertical axis and vertical axis of the feasible area of ​​the UAV track; It is the maximum value of the horizontal axis, vertical axis and vertical axis of the feasible area of ​​the UAV track; is the maximum flight speed of the UAV, and the three-dimensional track of the relay UAV is divided into T segments. Defined in segment t The three-dimensional coordinates of the relay drone are Respectively represent the horizontal, vertical and vertical coordinates of the relay UAV in the tth segment; N m,v is the spectrum allocation scheme; when the mth spectrum is allocated to the vth slave vehicle, N m,v =1, otherwise N m,v =0, M is the number of spectra, is the set of spectrum, v is the set of intelligent connected vehicles, C sec is the target safety rate, C th is the maximum allowed eavesdropping rate.

[0104] In problem P1, (6b) and (6c) limit the flight speed and flight area of ​​the drone respectively; (6d) defines the spectrum allocation method; and (6e) uses physical layer security technology to ensure the security of data transmission.

[0105] S302: First, the downlink rate and C sum Analyze and define and ω 1 The cumulative distribution function (CDF) F(ω 1 ) is represented as:

[0106]

[0107] in, In addition, K represents a Rician fading factor, and Γ(·) represents a gamma function.

[0108] By using the incomplete gamma function, equation (7) can be further rewritten as:

[0109]

[0110] Similarly, ω 2 The cumulative distribution function F(ω 2 ) is expressed as:

[0111]

[0112] in, By using the incomplete gamma function, equation (9) can be further rewritten as:

[0113]

[0114] Substituting formula (8) into formula (4), is further rewritten as:

[0115]

[0116] in, is the transmit signal-to-noise ratio, definition Substituting formula (8) into We can get:

[0117]

[0118] In formula (12), due to the integral It is difficult to calculate directly, so formula (13) is used for processing.

[0119]

[0120] Among them, χ>0 and According to formula (13), is rewritten as:

[0121]

[0122] According to formulas (12)-(14), is rewritten as:

[0123]

[0124] Similarly, The analytical solution is:

[0125]

[0126] S303, accurately calculate the downlink rate and C according to step S302 sum ,but The computational complexity of the function is high. Therefore, based on the Gauss-Chebyshev integral, the numerical calculation is simplified and the following is obtained:

[0127]

[0128] Where W is the approximation order.

[0129] Then, substitute equation (17) into equation (14) to approximate have to The approximate solution is:

[0130]

[0131] Then,

[0132] Similarly, is approximated as:

[0133]

[0134] S4. Based on the objective function and optimization conditions of the downlink safety rate and optimization problem, the downlink rate and are approximated by Gauss-Chebyshev integral, and the trajectory and spectrum allocation are iteratively optimized using reinforcement learning and graph theory to obtain the maximized downlink rate and. For P1 (i.e., a mixed integer nonlinear programming (MINLP) problem related to continuous variables and discrete variables), an iterative optimization method is used to process it. First, the Q-learning method is used to solve P1, and then the Hungarian algorithm is used to obtain the optimal spectrum matching, thereby realizing the performance analysis and optimization of the air-ground integrated vehicle network based on non-orthogonal multiple access.

[0135] S401, given The trajectory optimization problem is expressed as:

[0136]

[0137] The present invention adopts the Q-learning method to solve P1, as follows:

[0138] First, transform P1 into a Markov decision process (MDP). The MDP model consists of a tuple {S, A, P, R}, where S is the state set of the system; A is the action set of the agent; P is the state transition matrix, and P(s t |s t-1 ,a t-1 ) indicates state s t-1 Take action a t-1 After entering state s t ; R represents the reward function, R(s t ,a t ) is in state s t Take action t All returns after.

[0139] Specifically, the state S consists of the current position and maximum flight speed of the UAV, indicating the range of the area where the UAV can fly at a certain moment, which is defined as Action A consists of the velocities of the drone in three directions, defined as In each state, if constraint (6e) cannot be satisfied, then P(s g |s g-1 ,a g-1 )=0, the reward function R is composed of the objective function, defined

[0140] Then, construct the Q value table Q tab , where Q tab It is a two-dimensional matrix consisting of states and actions.

[0141]

[0142] Where ξ represents the discount factor, 0≤ξ<1; α is the learning rate, 0<α≤1; a represents an action, that is, a movement of the drone from time t to time t+1; R(s t ,a t ) is to execute action a t In state s t Immediate returns after For the next state s t+1 The maximum Q value of all possible actions reflects the expected return of the optimal behavior in the future. Therefore, the drone starts from the starting point and follows the Q tab Update the policy to explore the environment, generating a state-action-reward sequence from the start state to the end state. The end state is when the drone reaches the destination.

[0143] S402, given The spectrum allocation problem is formulated as:

[0144]

[0145] Introduce a set of weight coefficients Will Substitute P3 to ensure security, and constraint (6e) can be omitted. In this case, the spectrum allocation problem is regarded as a bipartite graph matching problem, and the optimal matching is obtained based on the Hungarian algorithm

[0146] The performance optimization algorithm by jointly considering trajectory optimization and spectrum allocation is summarized as follows:

[0147]

[0148] The complexity of Algorithm 1 depends mainly on Steps 5 and 7 In step 5, the computational complexity of Q-learning is O(|S|×|A|×T tot ), where T tot is the total number of iterations in step 5. In step 7, the computational complexity of the Hungarian algorithm is O((M+V) 3 ). Therefore, the total computational complexity of Algorithm 1 is O(|S|×|A|×T tot )+O((M+V) 3In the performance optimization algorithm that jointly considers trajectory optimization and spectrum allocation, each iteration moves toward the desired goal (maximizing C sum ) and in the iterative process the objective function value C sum is monotonically increasing. At the same time, the objective function value C sum is bounded. According to monotonicity and boundedness, Algorithm 1 is convergent.

[0149] It will be appreciated by those skilled in the art that various aspects of the present invention may be implemented as systems, methods or program products. Therefore, various aspects of the present invention may be specifically implemented in the following forms, namely: complete hardware implementation, complete software implementation (including firmware, microcode, etc.), or a combination of hardware and software implementations, which may be collectively referred to herein as "circuits", "modules" or "platforms".

[0150] In another embodiment of the present invention, a system for analyzing and optimizing the performance of an air-ground integrated vehicle network is provided. The system can be used to implement the above-mentioned method for analyzing and optimizing the performance of an air-ground integrated vehicle network. Specifically, the system for analyzing and optimizing the performance of an air-ground integrated vehicle network includes a construction module, an enhancement module, an optimization module and an output module.

[0151] Among them, the construction module constructs an intelligent connected vehicle model including 1 pilot vehicle, 1 relay drone and V subordinate vehicles, where the vehicles move in a convoy and the drones follow the convoy;

[0152] The enhancement module builds a NOMA-enhanced relay drone Internet of Vehicles model based on the obtained intelligent connected vehicle model;

[0153] The optimization module constructs the objective function and optimization conditions of the downlink safety rate and optimization problem based on the obtained NOMA enhanced relay drone Internet of Vehicles model;

[0154] The output module obtains the analytical solution of the downlink rate through random geometry based on the objective function and optimization conditions of the downlink safety rate and optimization problem, and approximates the analytical solution of the downlink rate through Gauss-Chebyshev integral to obtain an approximate solution, thereby realizing the performance analysis of the air-ground integrated vehicle network based on non-orthogonal multiple access; through iterative solution through reinforcement learning and graph theory, the trajectory and spectrum allocation of the UAV are optimized to maximize the downlink rate and, thereby realizing the maximization of the downlink rate and of the air-ground integrated vehicle network based on non-orthogonal multiple access.

[0155] In another embodiment of the present invention, a terminal device is provided, which includes a processor and a memory, wherein the memory is used to store a computer program, the computer program includes program instructions, and the processor is used to execute the program instructions stored in the computer storage medium. The processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. It is the computing core and control core of the terminal, which is suitable for implementing one or more instructions, and is specifically suitable for loading and executing one or more instructions to implement the corresponding method flow or corresponding function; the processor described in the embodiment of the present invention can be used for the operation of the air-ground integrated vehicle network performance analysis and optimization method, including:

[0156] A smart connected vehicle model is constructed, including 1 pilot vehicle, 1 relay drone and V subordinate vehicles, in which the vehicles move in a convoy and the drones follow the convoy; based on the obtained smart connected vehicle model, a NOMA-enhanced relay drone vehicle network model is constructed; based on the obtained NOMA-enhanced relay drone vehicle network model, the objective function and optimization conditions of the downlink safety rate and optimization problem are constructed; based on the objective function and optimization conditions of the downlink safety rate and optimization problem, the analytical solution of the downlink rate is obtained through random geometry, and the approximate solution of the analytical solution of the downlink rate is approximated by Gauss-Chebyshev integral to achieve the performance analysis of the air-ground integrated vehicle network based on non-orthogonal multiple access; through reinforcement learning and graph theory, iterative solutions are obtained to optimize the trajectory and spectrum allocation of the drone, maximize the downlink rate and, thus, maximizing the downlink rate and of the air-ground integrated vehicle network based on non-orthogonal multiple access.

[0157] In another embodiment of the present invention, the present invention also provides a storage medium, specifically a computer-readable storage medium (Memory), which is a memory device in a terminal device for storing programs and data. It is understandable that the computer-readable storage medium here can include both the built-in storage medium in the terminal device and the extended storage medium supported by the terminal device, and can be any tangible medium containing or storing a program, which can be used by an instruction execution system, device or device or used in combination with it. The computer-readable storage medium provides a storage space, which stores the operating system of the terminal. In addition, one or more instructions suitable for being loaded and executed by the processor are also stored in the storage space, and these instructions can be one or more computer programs (including program codes). It should be noted that more specific examples (non-exhaustive list) of the computer-readable storage medium here include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0158] Computer readable storage media also include data signals propagated in baseband or as part of a carrier wave, which carry readable program codes. Such propagated data signals can take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The readable storage medium can also be any readable medium other than a readable storage medium, which can send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, device, or device. The program code contained on the readable storage medium can be transmitted using any appropriate medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination of the above.

[0159] Program code for performing the operations of the present invention may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., through the Internet using an Internet service provider).

[0160] The processor may load and execute one or more instructions stored in a computer-readable storage medium to implement the corresponding steps of the air-ground integrated vehicle network performance analysis and optimization method in the above embodiment; the processor may load and execute the following steps:

[0161] A smart connected vehicle model is constructed, including 1 pilot vehicle, 1 relay drone and V subordinate vehicles, in which the vehicles move in a convoy and the drones follow the convoy; based on the obtained smart connected vehicle model, a NOMA-enhanced relay drone vehicle network model is constructed; based on the obtained NOMA-enhanced relay drone vehicle network model, the objective function and optimization conditions of the downlink safety rate and optimization problem are constructed; based on the objective function and optimization conditions of the downlink safety rate and optimization problem, the analytical solution of the downlink rate is obtained through random geometry, and the approximate solution of the analytical solution of the downlink rate is approximated by Gauss-Chebyshev integral to achieve the performance analysis of the air-ground integrated vehicle network based on non-orthogonal multiple access; through reinforcement learning and graph theory, iterative solutions are obtained to optimize the trajectory and spectrum allocation of the drone, maximize the downlink rate and, thus, maximizing the downlink rate and of the air-ground integrated vehicle network based on non-orthogonal multiple access.

[0162] See also Figure 7 , the terminal device is a computer device, and the computer device 60 of this embodiment includes: a processor 61, a memory 62, and a computer program 63 stored in the memory 62 and executable on the processor 61. When the computer program 63 is executed by the processor 61, the method for calculating the composition of fluid in the reservoir transformation wellbore in the embodiment is realized. To avoid repetition, it is not described one by one here. Alternatively, when the computer program 63 is executed by the processor 61, the functions of each model / unit in the calculation system for the composition of fluid in the reservoir transformation wellbore in the embodiment are realized. To avoid repetition, it is not described one by one here.

[0163] The computer device 60 may be a computing device such as a desktop computer, a notebook, a PDA, or a cloud server. The computer device 60 may include, but is not limited to, a processor 61 and a memory 62. Those skilled in the art will appreciate that Figure 7 This is only an example of the computer device 60 and does not constitute a limitation of the computer device 60. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the computer device may also include input and output devices, network access devices, buses, etc.

[0164] The processor 61 may be a central processing unit (CPU), or other general-purpose processors, central processing units, graphics processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, data processing logic based on quantum computing, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may be any conventional processor, etc.

[0165] The memory 62 may be an internal storage unit of the computer device 60, such as a hard disk or memory of the computer device 60. The memory 62 may also be an external storage device of the computer device 60, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc., equipped on the computer device 60.

[0166] Furthermore, the memory 62 may include both an internal storage unit of the computer device 60 and an external storage device. The memory 62 is used to store computer programs and other programs and data required by the computer device. The memory 62 may also be used to temporarily store data that has been output or is to be output.

[0167] Any reference to memory, database or other media used in the embodiments provided in the present application may include at least one of non-volatile and volatile memory. Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory may include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM may be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc.

[0168] The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. The non-relational database may include a distributed database based on blockchain, etc., but is not limited thereto. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but is not limited thereto.

[0169] See also Figure 8 The terminal device 600 is an electronic device, and the electronic device is in the form of a general computing device. The components of the electronic device may include but are not limited to: at least one processing unit 610, at least one storage unit 620, a bus 630 connecting different platform components (including the storage unit 620 and the processing unit 610), a display unit 640, etc.

[0170] The storage unit stores program codes, which can be executed by the processing unit 610, so that the processing unit 610 performs the steps according to various exemplary embodiments of the present invention described in the above method section of this specification. For example, the processing unit 610 can perform the following steps: Figure 1 Follow the steps shown in .

[0171] The storage unit 620 may include a readable medium in the form of a volatile storage unit, such as a random access memory unit (RAM) 6201 and / or a cache memory unit 6202 , and may further include a read-only memory unit (ROM) 6203 .

[0172] The storage unit 620 may also include a program / utility 6204 having a set (at least one) of program modules 6205, such program modules 6205 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment.

[0173] Bus 630 may represent one or more of several types of bus structures, including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.

[0174] The electronic device 600 may also communicate with one or more external devices 700 (e.g., keyboards, pointing devices, Bluetooth devices, etc.), may also communicate with one or more devices that enable a user to interact with the electronic device 600, and / or communicate with any device that enables the electronic device 600 to communicate with one or more other computing devices (e.g., routers, modems, etc.). Such communication may be performed via an input / output (I / O) interface 650. Furthermore, the electronic device 600 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) via a network adapter 660. The network adapter 660 may communicate with other modules of the electronic device 600 via a bus 630. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the electronic device 600, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage platforms, etc.

[0175] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of the embodiments. The components of the embodiments of the present invention described and shown in the drawings here can usually be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the drawings is not intended to limit the scope of the claimed invention, but merely represents selected embodiments of the present invention. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0176] The technical effects of the present invention are described in detail below in conjunction with simulation.

[0177] In this experiment, the approximate results are compared with the analytical results to verify their accuracy.

[0178] The approximate solution and the analytical solution error of the downlink rate and obtained in the embodiment of the present invention are compared and analyzed, as shown in FIG. Figure 3 shown.

[0179] See also Figure 3 , Figure 3 The downlink rate and error comparison between the approximate result and the analytical result are shown.

[0180] The diagram shows that when the number of vehicles is 29, the sum of the downlink rates of the approximate result and the analytical result differ by 4.18%, and the sum of the downlink rates of the analytical result is higher than the approximate result; when the number of vehicles is 35, the sum of the downlink rates of the approximate result and the analytical result differ by 4.22%, and the sum of the downlink rates of the analytical result is higher than the approximate result. Since the errors of the downlink rate and the approximate result and the analytical result are within the controllable error range, it is reasonable and meaningful to apply the present invention in practice.

[0181] The approximate solution of the downlink rate and obtained by the present invention is compared with the average running time of the analytical solution, such as Figure 4 shown.

[0182] See also Figure 4 ,It can be observed that the average running time of the approximate result of the downlink rate and the analytical result is quite different, and the average running time of the analytical result is much higher than that of the approximate result. It can be seen that the analytical result is complex and has a large amount of calculation. When the number of vehicles is 29 and 35, the approximate result increases from 3.87% to 4.64%, and the average running time is slightly different.

[0183] This experiment simulates a performance analysis and optimization method and system for air-ground integrated vehicle networking based on non-orthogonal multiple access and an existing mechanism based on the same network parameters to verify the superiority of the method of the present invention. The specific steps are as follows:

[0184] To ensure fairness, all comparison schemes adopted physical layer security technology. f c =2Ghz, V = [20,50], M = [15,55], K L,v =2, σ 2 =-174dBm / Hz.

[0185] The performance of the present invention is compared with that of comparative scheme 1, comparative scheme 2, comparative scheme 3 and comparative scheme 4. The specific comparative schemes are as follows:

[0186] a) Comparative Scheme 1: This scheme uses roadside units as relays and uses NOMA technology to transmit two different data symbols;

[0187] b) Comparative solution 2: This solution uses mobile drones as relays and optimizes the trajectory and spectrum allocation;

[0188] c) Comparative Scheme 3: This scheme uses mobile drones as relays and adopts the NOMA technology that optimizes drone deployment and channel allocation to improve the transmission rate between the pilot vehicle and the slave vehicles.

[0189] See also Figure 5 , and the relationship between the downlink rate and the number of vehicles is given. It can be observed that under different numbers of vehicles, the performance of the present invention is significantly better than that of the four comparative schemes, that is, it has the highest downlink rate and. Specifically, compared with comparative scheme 1, comparative scheme 2 and comparative scheme 3, the downlink rates and are increased by 59.3%, 40.5% and 16.2% respectively.

[0190] See also Figure 6 , gives the relationship between the maximum eavesdropping rate and the downlink rate and. It can be observed that when the eavesdropping rate reaches 0.8, the safety of some vehicles cannot be guaranteed, and the downlink rate and increase with the increase of the number of vehicles. It is particularly worth mentioning that with the increase of the number of vehicles, the present invention gradually has the highest downlink rate and.

[0191] In summary, the present invention provides an air-ground integrated vehicle network performance analysis and optimization method and system, which adopts NOMA to enhance the transmission and task processing performance of the air-ground collaborative network, and formalizes the rate optimization problem of slave vehicles receiving data into a track optimization and spectrum allocation problem, and combines closed-form solution derivation, Hungarian algorithm, Gauss-Chebyshev integral, reinforcement learning and graph theory to perform iterative solution, thereby achieving the purpose of downlink rate and maximization.

[0192] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0193] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0194] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed in the present invention can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0195] In the embodiments provided by the present invention, it should be understood that the disclosed devices / terminals and methods can be implemented in other ways. For example, the device / terminal embodiments described above are only schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0196] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0197] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0198] If the integrated module / unit is implemented in the form of 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 present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium, etc. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.

[0199] The above contents are only for explaining the technical idea of ​​the present invention and cannot be used to limit the protection scope of the present invention. Any changes made on the basis of the technical solution in accordance with the technical idea proposed by the present invention shall fall within the protection scope of the claims of the present invention.

Claims

1. A method for analyzing and optimizing the performance of an air-ground integrated vehicle network, characterized in that: The following steps are involved: Construct an intelligent connected vehicle model including 1 pilot vehicle, 1 relay drone and V slave vehicles, where the vehicles move in a convoy and the drones follow the convoy; Based on the obtained intelligent connected vehicle model, a NOMA-enhanced relay drone vehicle networking model is constructed; Based on the obtained NOMA enhanced relay drone Internet of Vehicles model, the objective function and optimization conditions of the downlink safety rate and optimization problem are constructed; Based on the objective function and optimization conditions of the downlink safety rate and optimization problem, the analytical solution of the downlink rate is obtained through random geometry, and the approximate solution of the analytical solution of the downlink rate is approximated by the Gauss-Chebyshev integral to achieve the performance analysis of the air-ground integrated vehicle network based on non-orthogonal multiple access; through reinforcement learning and graph theory, iterative solutions are obtained to optimize the trajectory and spectrum allocation of the UAV, maximize the downlink rate and, thus, maximizing the downlink rate and of the air-ground integrated vehicle network based on non-orthogonal multiple access.

2. The air-ground integrated vehicle networking performance analysis and optimization method according to claim 1 is characterized in that: In the intelligent connected vehicle model, define the set of intelligent connected vehicles The pilot vehicle uses non-orthogonal multiple access technology for data transmission. The slave vehicles receive two different messages in two time slots. The pilot vehicle has M spectrums for data transmission. The spectrum allocation strategy is: in, is the collection of spectrum, A collection of intelligent connected vehicles. is the set of spectrum allocation schemes, N m,v is the spectrum allocation scheme; when the mth spectrum is allocated to the vth slave vehicle, N m,v =1, otherwise N m,v =0.

3. The air-ground integrated vehicle networking performance analysis and optimization method according to claim 1 is characterized in that: In the NOMA-enhanced relay drone vehicle networking model, Define the leader vehicle to transmit overlapping signals D to the vth slave vehicle and relay UAV in the first time slot L,v , determine the signal received by the UAV and the vth slave vehicle in the first time slot and r L,v ; Define the relay drone to send data symbols to the vth slave vehicle in the second time slot Set data symbol is perfectly decoded; in the second time slot, the received signal r of the vth slave vehicle is determined U,v ; Define the data rate of the vth slave vehicle in, and Data symbols and rate.

4. The air-ground integrated vehicle networking performance analysis and optimization method according to claim 3 is characterized in that: The signals received by the UAV and the vth slave vehicle in the first time slot and r L,v Respectively expressed as: in, is the independent Rician fading channel coefficient of the pilot vehicle-UAV link on the mth spectrum, h L,v is the independent Rician fading channel coefficient of the pilot vehicle-vth slave vehicle link, η L,U and η L,v is a function with zero mean and variance σ 2 Additive Gaussian white noise, is the power distribution coefficient of the vth slave vehicle, P v is the transmission power allocated by the pilot vehicle to the vth slave vehicle, represents the jth data symbol with normalized power.

5. The air-ground integrated vehicle networking performance analysis and optimization method according to claim 3 is characterized in that: The received signal r of the vth slave vehicle U,v for: in, is the independent Rician fading channel coefficient of the UAV-vth slave vehicle link on the mth spectrum, η U,v is a function with zero mean and variance σ 2 Additive Gaussian white noise, P v is the transmission power allocated by the pilot vehicle to the vth slave vehicle, represents the jth data symbol with normalized power.

6. The air-ground integrated vehicle networking performance analysis and optimization method according to claim 3 is characterized in that: Data Symbols and Rate and They are: Among them, γ L,v Data symbol The received signal-to-interference-noise ratio at the vth slave vehicle, Data symbol The received signal-to-interference-noise ratio at the drone, For data signal The received signal-to-interference-noise ratio at the drone, γ U,v For data signal Received signal-to-interference-and-noise ratio at the vth slave vehicle.

7. The air-ground integrated vehicle networking performance analysis and optimization method according to claim 1 is characterized in that: The objective function and optimization conditions for constructing the downlink safety rate and optimization problem are as follows: By optimizing the trajectory and spectrum allocation Maximizing the downlink safety rate and C of the connected vehicle network with relay drones and non-orthogonal multiple access technology sum , determine the downlink safety rate and optimization problem P1; For downlink rate and C sum Analyze and define and Get the cumulative distribution function F(ω1) of ω1; Based on the simplified numerical calculation of Gauss-Chebyshev integral, we can get The approximate solution of and Rate and The approximate solution of .

8. The method for analyzing and optimizing the performance of the air-ground integrated vehicle network according to claim 7 is characterized in that: The downlink safety rate and optimization problem P1 are: in, is the minimum value of the horizontal axis, vertical axis and vertical axis of the feasible area of ​​the UAV track, is the maximum value of the horizontal axis, vertical axis and vertical axis of the feasible area of ​​the UAV track, is the maximum flight speed of the UAV, C sum is the downlink safety rate and, To optimize the trajectory, is the spectrum allocation, C v is the data rate of the vth slave vehicle, is a set, N m,v is the spectrum allocation scheme, M is the number of spectrums, is the collection of spectrum, is the collection of intelligent connected vehicles, C sec is the target safety rate, C th is the maximum allowed eavesdropping rate.

9. The air-ground integrated vehicle networking performance analysis and optimization method according to claim 1 is characterized in that: The specific solution is iteratively solved through Gauss-Chebyshev integration, reinforcement learning, graph theory, and Hungarian algorithm: Decouple the downlink rate and maximization problem P1 into the trajectory optimization problem P2 and the spectrum allocation problem P3; For the trajectory optimization problem P2, the Q-learning method is used to solve it; First, the trajectory optimization problem P2 is transformed into a Markov decision process; Then, construct the Q value table Q tab , Q tab is a two-dimensional matrix consisting of states and actions. The drone starts from the starting point and follows Q tab Update the strategy to explore the environment, generating a state-action-reward sequence from the start state to the end state, where the end state is when the drone reaches the destination; For spectrum allocation problem P3, the spectrum allocation problem is regarded as a bipartite graph matching problem, and the optimal matching is obtained based on the Hungarian algorithm.

10. An air-ground integrated vehicle networking performance analysis and optimization system, characterized in that: include: Building a module, constructing an intelligent connected vehicle model including 1 pilot vehicle, 1 relay drone and V slave vehicles, where the vehicles move in a convoy and the drones follow the convoy; The enhancement module builds a NOMA-enhanced relay drone Internet of Vehicles model based on the obtained intelligent connected vehicle model; The optimization module constructs the objective function and optimization conditions of the downlink safety rate and optimization problem based on the obtained NOMA enhanced relay drone Internet of Vehicles model; The output module obtains the analytical solution of the downlink rate through random geometry based on the objective function and optimization conditions of the downlink safety rate and optimization problem, and approximates the analytical solution of the downlink rate through Gauss-Chebyshev integral to obtain an approximate solution, thereby realizing the performance analysis of the air-ground integrated vehicle network based on non-orthogonal multiple access; through iterative solution through reinforcement learning and graph theory, the trajectory and spectrum allocation of the UAV are optimized to maximize the downlink rate and, thereby realizing the maximization of the downlink rate and of the air-ground integrated vehicle network based on non-orthogonal multiple access.