Channel Access Method, Device, Equipment and Medium for Vehicles in Cognitive Vehicular Networks

Abstract

The present application provides a method, apparatus, device and medium for a vehicle in a cognitive vehicle network to access a channel, belonging to the field of communication technologies. The method is applied to a cognitive vehicle and includes: detecting the occupancy situation of a target channel at the current moment, where the target channel is a channel selected by the cognitive vehicle for access at the current moment based on a reinforcement learning model; in the case that the target channel is occupied by other vehicles, determining whether the communication distance between the cognitive vehicle and the base station associated with the target channel is greater than a set distance threshold, where the other vehicles include at least one of other cognitive vehicles and authorized vehicles; in the case that the communication distance between the cognitive vehicle and the base station associated with the target channel is not greater than the set distance threshold, the cognitive vehicle accesses the target channel.

Description

Technical Field

[0001] The present application relates to the field of communication technologies, and in particular, to a method, apparatus, device, and medium for channel access of vehicles in a cognitive vehicle-to-everything (V2X) network. Background Art

[0002] Currently, research on channel access of vehicles in a cognitive V2X network mainly focuses on the case where a single vehicle accesses a single channel. For example, based on whether the channel is idle, it is determined whether a vehicle can access the channel.

[0003] However, with the increasing number of vehicles and considering the scarcity of spectrum resources, this traditional channel access method that restricts a channel to be accessed by only one vehicle at the same time has a low utilization rate of spectrum resources, which further leads to the difficulty for the cognitive V2X network to meet the communication requirements among vehicles under limited spectrum resources. Summary of the Invention

[0004] In view of the above problems, embodiments of the present application provide a method, apparatus, device, and medium for channel access of vehicles in a cognitive V2X network to overcome or at least partially solve the above problems.

[0005] In a first aspect of embodiments of the present application, there is provided a method for channel access of vehicles in a cognitive V2X network, which is applied to a cognitive vehicle. The method includes:

[0006] Detect the occupancy of a target channel at the current moment, where the target channel is a channel selected by the cognitive vehicle for access at the current moment based on a reinforcement learning model;

[0007] When the target channel is occupied by other vehicles, determine whether the communication distance between the cognitive vehicle and the base station associated with the target channel is greater than a set distance threshold, where the other vehicles include at least one of other cognitive vehicles and authorized vehicles;

[0008] When the communication distance between the cognitive vehicle and the base station associated with the target channel is not greater than the set distance threshold, the cognitive vehicle accesses the target channel.

[0009] In a second aspect of embodiments of the present application, there is provided a device for channel access of vehicles in a cognitive V2X network, which is applied to a cognitive vehicle. The device includes:

[0010] A first detection module, configured to detect the occupancy of a target channel at the current moment, where the target channel is a channel selected by the cognitive vehicle for access at the current moment;

[0011] A first judgment module, configured to judge whether a communication distance between the cognitive vehicle and a base station associated with the target channel is greater than a set distance threshold when the target channel is occupied by other vehicles, where the other vehicles include at least one of other cognitive vehicles and authorized vehicles;

[0012] A first access module, configured to enable the cognitive vehicle to access the target channel when the communication distance between the cognitive vehicle and the base station associated with the target channel is not greater than the set distance threshold.

[0013] In a third aspect of the embodiments of the present application, an electronic device is provided, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, the steps of the method for a vehicle to access a channel in a cognitive vehicle network in the first aspect are implemented.

[0014] In a fourth aspect of the embodiments of the present application, a computer-readable storage medium is provided, on which a computer program / instructions are stored. When the computer program / instructions are executed by a processor, the steps of the method for a vehicle to access a channel in a cognitive vehicle network as described in the first aspect are implemented.

[0015] The embodiments of the present application have the following advantages: Considering the influence of the communication distance between a vehicle and a base station on the success rate of channel access and communication quality, the present application compares the communication distance between a cognitive vehicle and a base station associated with a target channel with a set distance threshold, and enables the cognitive vehicle to access a channel occupied by other vehicles when the communication distance is not greater than the set distance threshold. Thus, on the premise of ensuring the success rate of channel access and communication quality of the cognitive vehicle, a channel can be accessed by multiple vehicles at the same time point, thereby improving the utilization rate of spectrum resources, and further enabling the cognitive vehicle network to meet the communication needs between vehicles under limited spectrum resources. Description of the Drawings

[0016] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for the description of the embodiments of the present application will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0017] Figure 1 is an implementation flowchart of a method for a vehicle to access a channel in a cognitive vehicle network in an embodiment of the present application;

[0018] Figure 2 is a schematic diagram of an implementation process of multi-vehicle dynamic spectrum access in an embodiment of the present application;

[0019] Figure 3 It is a schematic diagram of a vehicle in an embodiment of the present application interacting with a cognitive vehicle network communication environment;

[0020] Figure 4 It is a schematic diagram of a cognitive vehicle network communication scenario in an embodiment of the present application;

[0021] Figure 5 It is a schematic structural diagram of a channel access device of a vehicle in a cognitive vehicle network in an embodiment of the present application;

[0022] Figure 6 It is a schematic diagram of an electronic device in an embodiment of the present application. Detailed implementation manners

[0023] To facilitate understanding of the technical solutions provided by the present application, the main technical concepts involved in the embodiments of the present application are briefly described below.

[0024] Frequency band: A specific frequency range of radio waves.

[0025] Channel: A further subdivision within a given frequency band. For example, it can refer to a specific frequency used for data transmission within a given frequency band.

[0026] Authorized vehicle: Prioritize accessing and using the channel associated with the authorized frequency band for data transmission.

[0027] Cognitive vehicle: Based on the dynamic spectrum access method, dynamically access and use relevant channels for data transmission. For example, a cognitive vehicle can sense the channel state in real time and select to access the channel associated with the frequency band not occupied by authorized vehicles for data transmission.

[0028] Next, in conjunction with the accompanying drawings, through some embodiments and their application scenarios, a channel access method, device, equipment, and medium for vehicles in a cognitive vehicle network provided by the embodiments of the present application are described in detail.

[0029] In a first aspect, referring to Figure 1 as shown, it is an implementation flowchart of a channel access method for a vehicle in a cognitive vehicle network provided by an embodiment of the present application. The channel access method for a vehicle in the cognitive vehicle network is applied to a cognitive vehicle, and the method may include the following steps:

[0030] Step S11: Detect the occupancy situation of the target channel at the current moment, where the target channel is: the channel selected by the cognitive vehicle to access at the current moment based on the reinforcement learning model.

[0031] In specific implementation, the cognitive vehicle can maximize performance metric values such as throughput as the optimization goal, and determine the channel to access at the current moment (i.e., the target channel) based on the reinforcement learning model. After determining the target channel, it detects the occupancy situation of the target channel at the current moment, that is, detects whether the target channel is in an idle state. If the target channel is in an idle state, it means that the target channel is not occupied by other vehicles; if the target channel is not in an idle state, it means that the target channel is occupied by other vehicles.

[0032] Step S12: When the target channel is occupied by other vehicles, determine whether the communication distance between the cognitive vehicle and the base station associated with the target channel is greater than a set distance threshold, where the other vehicles include at least one of other cognitive vehicles and authorized vehicles.

[0033] In specific implementation, when the target channel is occupied by other vehicles (other cognitive vehicles and / or authorized vehicles), the cognitive vehicle determines its own communication distance from the base station associated with the target channel at the current moment based on relevant ranging technologies such as wireless impulse ranging technology, and then determines whether the communication distance between the cognitive vehicle and the base station associated with the target channel is greater than a set distance threshold.

[0034] Step S13: When the communication distance between the cognitive vehicle and the base station associated with the target channel is not greater than the set distance threshold, the cognitive vehicle accesses the target channel.

[0035] In this embodiment, the present application takes into account that in an actual communication scenario, if the cognitive vehicle is far from the base station, the probability of it accessing the channel associated with the base station is very small or even impossible to access (i.e., the success rate of channel access is low), and in this case, even if the cognitive vehicle accesses the channel, the communication quality of the cognitive vehicle will be very poor, and at the same time, it will also interfere with the communication quality of other vehicles accessing the same channel.

[0036] To solve the foregoing problems, the present application introduces a set distance threshold to limit the channels accessed by the cognitive vehicle by restricting the communication distance between the cognitive vehicle and the base station. By enabling the cognitive vehicle to access the channel occupied by other vehicles when the communication distance between the cognitive vehicle and the relevant base station is not greater than the set distance threshold, the success rate and communication quality of the cognitive vehicle accessing the channel can be improved, and multiple vehicles can access the same channel at the same time point, thereby improving the utilization rate of spectrum resources.

[0037] As a possible implementation manner, when the target channel is not occupied by other vehicles, since there will be no interference between multiple vehicles accessing the same channel at this time, the cognitive vehicle can directly access the target channel to further improve the utilization rate of spectrum resources.

[0038] Adopting the technical solution of the embodiment of the present application, considering the influence of the communication distance between the vehicle and the base station on the success rate of channel access and communication quality, the present application compares the communication distance between the cognitive vehicle and the base station associated with the target channel with a set distance threshold, and enables the cognitive vehicle to access the channel occupied by other vehicles when the communication distance is not greater than the set distance threshold. Thus, on the premise of ensuring the success rate of channel access and communication quality of the cognitive vehicle, a channel can be accessed by multiple vehicles at the same time point, thereby improving the utilization rate of spectrum resources, and further enabling the cognitive vehicle network to meet the communication requirements between vehicles under limited spectrum resources.

[0039] As a possible implementation manner, before detecting the occupancy situation of the target channel at the current moment, the method further includes:

[0040] Obtain the state parameters at the current moment for each channel respectively, where the state parameters include: channel gain, the duration of the cognitive vehicle transmitting data, and the communication distances between the vehicles associated with the channel and between each vehicle and the base station associated with the channel; [[ID=eleven]]

[0041] Taking the overall maximization of the sum of the throughputs associated with each cognitive vehicle including the cognitive vehicle as the optimization objective, and determining the action parameter of the cognitive vehicle at the current moment according to the state parameters at the current moment through the reinforcement learning model, where the action parameter is used to represent whether the cognitive vehicle selects to access the channel and, in the case of selecting to access the channel, the channel selected to access;

[0042] Among them, the sum of the throughputs associated with a single cognitive vehicle includes: the sum of the throughputs of the single cognitive vehicle and other vehicles (such as authorized vehicles and / or other cognitive vehicles) accessing the channel selected by the single cognitive vehicle.

[0043] In specific implementation, referring to Figure 2 the schematic diagram of the implementation process of multi-vehicle dynamic spectrum access shown, a cognitive vehicle network communication model including each base station, each authorized vehicle, each cognitive vehicle and each channel is established in advance, and the coordinates of the vehicle are determined based on the position information of each vehicle. Then the above optimization objective is established, and relevant indicators are calculated to determine the state parameters. Subsequently, the above set distance threshold is combined with the reinforcement learning technology and applied to the cognitive vehicle network communication model to realize the dynamic spectrum access of multi-vehicle.

[0044] It should be noted that the framework of the reinforcement learning model consists of two parts: the vehicle and the cognitive vehicle networking communication environment, and these two parts can interact with each other. Referring to Figure 3 the schematic diagram of the interaction between the vehicle and the cognitive vehicle networking communication environment as shown, at the t-th moment, the n-th cognitive vehicle needs to select a channel to access. First, the n-th cognitive vehicle obtains the state parameters of each channel in the cognitive vehicle networking communication environment at the current moment , where represents the channel gain, represents the duration of data transmission of the n-th cognitive vehicle, represents the communication distances between the vehicles associated with the channel (including the n-th cognitive vehicle) and between each vehicle and the base station associated with the channel.

[0045] The cognitive vehicle inputs the state parameters corresponding to each currently obtained channel into the reinforcement learning model. Based on the input state parameters and the optimization objective, the reinforcement learning model determines the action parameters according to the policy and outputs them. Then, the cognitive vehicle determines whether to select a channel to access according to the action parameters output by the reinforcement learning model , and determines the selected access channel in the case of selecting a channel to access.

[0046] Among them, the action parameter ; the policy is a mapping function related to the state space and the action space , which describes the mapping relationship between the state parameters and the action parameters. The reinforcement learning model will continuously learn according to the interaction between the vehicle and the environment (i.e., update the policy ), so as to ensure that it can determine the optimal action parameters for the optimization objective.

[0047] Exemplarily, the action parameter can be expressed as follows:

[0048]

[0049] Among them, , W represents the number of channels in the cognitive vehicle networking communication model, being equal to 0 means not selecting any channel to access, not being equal to 0 means selecting a channel to access and selecting to access the -th channel.

[0050] It is understandable that at different time periods, each cognitive vehicle will take different actions (characterized by action parameters), and all possible actions constitute the action space. , so in the above example, the action space size . And after the cognitive vehicle performs a channel access operation based on the action parameters (such as choosing not to access the channel or choosing to access a certain channel), this channel access operation will interact with and act on the environment. For example, the state parameters related to the environment will change from (corresponding to the environmental state at the t-th moment) to (corresponding to the environmental state at the t+1-th moment). The reinforcement learning model will accordingly feedback the reward at the t+1-th moment to the cognitive vehicle.

[0051] Subsequently, the interaction and actions between the vehicle and the environment will continue in a similar manner as above, that is: , where represents the state parameters at each moment, represents the action parameters at each moment, represents the reward values at each moment.

[0052] In this embodiment, the present application improves the optimization objective by identifying the impact of the channel access actions of cognitive vehicles on the overall throughput of each vehicle rather than only identifying the impact on the throughput related to a single cognitive vehicle (i.e., avoiding cognitive vehicles from interfering with the throughput optimization of other cognitive vehicles in order to maximize their own related throughput). Specifically, the overall maximization of the sum of the throughputs associated with each cognitive vehicle including the cognitive vehicle (such as maximizing the average value or the weighted sum value, etc.) is used as the optimization objective, and then the reinforcement learning model determines the globally optimal action parameters based on the optimization objective, thereby realizing the optimization of the overall throughput of each vehicle in the cognitive vehicle network communication scenario (or the cognitive vehicle network communication model established based on this scenario).

[0053] As a possible implementation, the channel gain in the state parameters includes: the channel gain of the useful signal of the cognitive vehicle, the channel gain of the useful signals of other vehicles accessing the channel selected by the cognitive vehicle, and the channel gain of the interference signal from any vehicle among the cognitive vehicle and other vehicles accessing the channel selected by the cognitive vehicle to another vehicle;

[0054] Among them, the channel gain of the useful signal of a single vehicle is determined by the following formula:

[0055]

[0056] where The channel gain of the useful signal of the single vehicle The transmission power of the single vehicle The bandwidth of the channel The power spectral density of the background noise in the channel The communication distance between the single vehicle and the base station associated with the channel The path loss exponent, usually between 2 and 4

[0057] Among the cognitive vehicle and other vehicles accessing the channel selected by the cognitive vehicle, the channel gain of the interference signal from the m-th vehicle to the n-th vehicle is determined by the following formula:

[0058]

[0059] Wherein The channel gain of the interference signal from the m-th vehicle to the n-th vehicle The transmission power of the m-th vehicle The bandwidth of the channel The power spectral density of the background noise in the channel The communication distance between the m-th vehicle and the n-th vehicle The path loss exponent, usually between 2 and 4

[0060] In this embodiment, based on the Rayleigh fading model, the channel gains of the cognitive vehicle itself and other vehicles accessing the channel selected by the cognitive vehicle are determined, and the determined channel gains are used as the channel gains to be included in the state parameters, so that the reinforcement learning model can more accurately analyze the transmission capabilities of the signals related to each vehicle in the channel according to the channel gains included in the input state parameters, thereby helping to improve the optimization effect of the reinforcement learning model on the overall throughput.

[0061] Optionally, maximizing the overall sum of the throughputs associated with each cognitive vehicle including the cognitive vehicle as the optimization target includes: maximizing the average value of the cumulative discounted reward values of each cognitive vehicle including the cognitive vehicle as the optimization target, and the cumulative discounted reward value of a single cognitive vehicle is determined by the following formula:

[0062]

[0063] Wherein The cumulative discounted reward value of the single cognitive vehicle The discount factor corresponding to the (t - 1)-th moment Represents the reward value of the single cognitive vehicle at the (t + 1)-th moment, where the reward value is determined according to the total throughput associated with the single cognitive vehicle at the (t + 1)-th moment.

[0064] It can be understood that in the cognitive vehicle-to-everything (V2X) communication scenario, there is no terminal state in the environment, and the total reward (which can also be referred to as the cumulative reward or long-term reward) will be infinite. Therefore, at the above moments ). On this basis, this application introduces a discount factor to flexibly control the weight of the long-term reward. , when is close to 1, the reinforcement learning model pays more attention to the long-term reward, and when is close to 0, the current reward becomes more important in the total reward.

[0065] In specific implementation, this application maps the total throughput between the single cognitive vehicle and other vehicles accessing the channel selected by the single cognitive vehicle at a single moment to the reward value (which can also be referred to as the immediate reward value) obtained by the cognitive vehicle at the single moment. And considering that in addition to the immediate reward, the long-term cumulative reward should also be considered, because only by ensuring the stability of the long-term reward in the cognitive V2X communication scenario can the long-term optimization effect on the overall throughput be ensured. Therefore, this application maximizes the average value of the cumulative discounted reward values of each cognitive vehicle including the cognitive vehicle as the optimization goal, so as to ensure the stability of the long-term reward by optimizing the average cumulative reward of the cognitive vehicle.

[0066] It should be noted that the reinforcement learning model mainly controls the performance of the system by designing a reward function. In the embodiment of this application, the reinforcement learning model aims to learn a policy to maximize the expected cumulative discounted reward value.

[0067] Specifically, the reinforcement learning model optimizes the policy through the value, and while the value is closely related to the state parameter and the action parameter obtained by the cognitive vehicle at the current moment (i.e., the t-th moment), and can be denoted as . The value can be approximately equal to the expected total reward of the cognitive vehicle that performs the channel access operation based on the action parameter under the state parameter .

[0068] The reinforcement learning model will select the action parameter with the largest value to update the policy , and then update the value with the new policy, and repeat this process until The value converges to the optimal value . Once obtained, the optimal policy can be found. Exemplarily,

[0069]

[0070] wherein, represents the learning rate, represents the discount factor, represents the maximum value at the next moment (i.e., at the (t + 1)-th moment).

[0071] In specific implementation, a value table can be used to store the obtained values. The size of the value table is , represents the size of the action space, represents the size of the state space. As the state-action space increases, the size of the value table will increase significantly. In the channel access problem of multiple cognitive vehicle communications, the state space is large and uncertain. Therefore, it is necessary to let the cognitive vehicle and the environment interact fully to obtain the most accurate state.

[0072] As a possible implementation, in order to enable the cognitive vehicle to fully understand the channel occupancy situation in the cognitive vehicle network communication scenario (i.e., to let the cognitive vehicle and the environment interact fully), a greedy algorithm can be used. Specifically, the cognitive vehicle is made to select the action parameter with the maximum value with a probability of , and randomly select an action parameter from the action space with a probability of . The reinforcement learning model then iteratively updates the

[0073] values and policies at each moment based on the aforementioned action parameter selection method to gradually converge to the optimal policy.

[0074]

[0075] wherein, represents selecting the action parameter with the maximum value at the state parameter , is a decimal number between 0 and 1, indicating the corresponding probability is for the case, indicating the corresponding probability is for the case, indicating randomly selecting action parameters from the action space as follows.

[0076] As a possible implementation, the reward value of the single cognitive vehicle at a single moment is determined through the following steps:

[0077] When the single cognitive vehicle selects an access channel at the single moment, and the communication distance between the single cognitive vehicle and the base station associated with the selected access channel is not greater than the set distance threshold, the reward value of the single cognitive vehicle at the single moment is determined through a first reward function, and the first reward function is expressed as follows:

[0078]

[0079] When the single cognitive vehicle selects an access channel at the single moment, and the communication distance between the single cognitive vehicle and the base station associated with the selected access channel is greater than the set distance threshold, the reward value of the single cognitive vehicle at the single moment is determined through a second reward function, and the second reward function is expressed as follows:

[0080]

[0081] When the single cognitive vehicle does not select an access channel at the single moment, the reward value of the single cognitive vehicle at the single moment is determined through a third reward function, and the third reward function is expressed as follows:

[0082]

[0083] wherein, represents the reward value of the single cognitive vehicle at the single moment, represents the throughput of the single cognitive vehicle at the single moment, represents the throughput of other vehicles accessing the channel selected by the single cognitive vehicle at the single moment.

[0084] In this embodiment, the present application classifies cases based on whether a cognitive vehicle selects to access a channel and whether the selected access channel meets the distance constraint (i.e., whether the communication distance between the associated base station and the cognitive vehicle is not greater than the set distance threshold), and designs the corresponding reward functions for the above different cases in combination with the total throughput associated with the single cognitive vehicle at a single moment (i.e., the total throughput between the single cognitive vehicle and other vehicles accessing the channel selected by the single cognitive vehicle at a single moment).

[0085] It can be understood that improving the reinforcement learning model based on the corresponding reward functions for the above different cases means that the reinforcement learning model determines the immediate reward at each moment according to the improved reward functions (i.e., the first reward function, the second reward function, and the third reward function), and then obtains the total reward (i.e., the value) for updating and optimizing the policy, so that the improved reinforcement learning model can optimize the overall throughput as the goal under the premise of meeting the distance constraint, continuously update the policy and output the globally optimal action parameters, thereby achieving the long-term optimization of the overall throughput, channel access success rate, and communication quality of each cognitive vehicle in the cognitive vehicle network communication scenario.

[0086] Exemplarily, referring to Figure 4 the schematic diagram of the cognitive vehicle network communication scenario shown, the cognitive vehicle network communication scenario includes a situation where authorized vehicles and cognitive vehicles simultaneously access the same channel for communication, and the corresponding cognitive vehicle network communication model includes: 1 base station, W authorized vehicles, L cognitive vehicles, and W channels.

[0087] Taking the th authorized vehicle and the th cognitive vehicle in the cognitive vehicle network communication model accessing the target channel selected by the th cognitive vehicle at the current moment t as an example, respectively representing the throughput of the th authorized vehicle, the th cognitive vehicle, and the th cognitive vehicle at the current moment t, then the reward function value obtained by the th cognitive vehicle at the current moment t is associated with the following two cases:

[0088] Case 1: When the communication distance between the th cognitive vehicle attempting to access the target channel and the relevant base station is not greater than the set distance threshold, it can be considered that the cognitive vehicle successfully accesses the channel. Then the The reward function value obtained by a cognitive vehicle at the current moment t is determined by the first reward function to generate positive feedback, i.e.:

[0089]

[0090] Case 2: When the communication distance between the th cognitive vehicle attempting to access the target channel and the relevant base station is greater than the set distance threshold, it can be considered that the cognitive vehicle fails to access the channel. Then, the reward function value obtained by the th cognitive vehicle at the current moment t is determined by the second reward function to generate negative feedback, i.e.:

[0091]

[0092] It can be understood that if the th cognitive vehicle does not select any channel access based on the action parameters output by the reinforcement learning model at the current moment, then the reward function value obtained by the th cognitive vehicle at the current moment t is associated with the following Case 3:

[0093] Case 3: If the th cognitive vehicle does not select any channel access, then the reward function value obtained by the th cognitive vehicle at the current moment t is determined by the third reward function, i.e.:

[0094]

[0095] Furthermore, the cumulative discounted reward value obtained by the th cognitive vehicle can be determined by the following formula:

[0096]

[0097] where, represents the cumulative discounted reward value of the th cognitive vehicle; represents the discount factor corresponding to the (t - 1)th moment; represents the reward value of the th cognitive vehicle at the (t + 1)th moment, and the reward value is determined using the improved reward function (i.e., the above first reward function, the above second reward function, and the above third reward function).

[0098] Optionally, the throughput of a single vehicle is determined by the following steps:

[0099] When the single vehicle is an authorized vehicle, the signal-to-interference-plus-noise ratio of the single vehicle is determined by the first formula;

[0100] In the case where the single vehicle is a cognitive vehicle, the signal-to-interference-plus-noise ratio (SINR) of the single vehicle is determined by a second formula;

[0101] Based on the SINR of the single vehicle and the bandwidth of the channel, the throughput of the single vehicle is determined. For example, the throughput of the single vehicle can be determined according to Shannon's theorem;

[0102] Among them, the first formula is expressed as follows:

[0103]

[0104] Among them, represents the SINR of the authorized vehicle, represents the transmit power of the authorized vehicle, represents the channel gain of the useful signal of the authorized vehicle, represents the bandwidth of the channel, represents the power spectral density of the background noise in the channel, represents the total interference generated by all cognitive vehicles accessing the same channel as the authorized vehicle to the authorized vehicle, and N1 represents the number of all cognitive vehicles accessing the same channel as the authorized vehicle;

[0105] The second formula is expressed as follows:

[0106]

[0107] Among them, represents the SINR of the cognitive vehicle, represents the transmit power of the cognitive vehicle, represents the channel gain of the useful signal of the cognitive vehicle, represents the bandwidth of the channel, represents the power spectral density of the background noise in the channel, represents the transmit power of the authorized vehicle accessing the same channel as the cognitive vehicle, represents the channel gain of the interference signal from the authorized vehicle to the cognitive vehicle, represents the total interference generated by other cognitive vehicles accessing the same channel as the cognitive vehicle to the cognitive vehicle, and N2 represents the number of all cognitive vehicles accessing the channel.

[0108] Exemplarily, taking the cognitive vehicle network communication model corresponding to the cognitive vehicle network communication scenario shown above Figure 4 as an example, the acquisition methods of the above state parameters and throughput are illustrated. Among them, the cognitive vehicle network communication model includes: 1 base station, authorized vehicles, cognitive vehicles and channels.

[0109] The th authorized vehicle and the th cognitive vehicle in the cognitive vehicle-to-everything (V2X) communication model access the target channel selected by the th cognitive vehicle at the current moment t. Then, the state parameters of each channel for the th cognitive vehicle can be expressed as follows:

[0110]

[0111] Where represents the channel gain at the current moment t; represents the communication distances between each vehicle (i.e., the th authorized vehicle, the th cognitive vehicle, and the th cognitive vehicle) at the current moment t and between each vehicle and the base station associated with the target channel; represents the duration for the th cognitive vehicle to transmit data.

[0112] It can be understood that in different time periods, the environmental states observed by each cognitive vehicle (characterized by state parameters) will be different, and these possible states constitute the state space , and in this example, the size of the state space is .

[0113] For , it is calculated based on the position coordinates of the th authorized vehicle, the position coordinates of the th cognitive vehicle, and the position coordinates of the th cognitive vehicle. Specifically:

[0114] The communication distance ( ) between the th authorized vehicle and the base station associated with the target channel at the current moment t can be expressed as follows:

[0115]

[0116] The communication distance ( ) between the th cognitive vehicle and the base station associated with the target channel at the current moment t can be expressed as follows:

[0117]

[0118] The communication distance between the The communication distance between the th authorized vehicle and the th cognitive vehicle can be expressed as follows:

[0119]

[0120] The communication distance between the th cognitive vehicle and the base station associated with the target channel at the current time t ( ) can be expressed as follows:

[0121]

[0122] The communication distance between the th authorized vehicle and the th cognitive vehicle at the current time t ( ) can be expressed as follows:

[0123]

[0124] The communication distance between the th cognitive vehicle and the th cognitive vehicle at the current time t ( ) can be expressed as follows:

[0125]

[0126] For , the channel gain of the useful signal of the th authorized vehicle at the current time t it contains can be expressed as follows:

[0127]

[0128] Where represents the transmit power of the th authorized vehicle, represents the bandwidth of the channel, represents the power spectral density of the background noise in the channel, represents the communication distance between the th authorized vehicle and the base station associated with the channel, represents the path loss exponent.

[0129] For , the channel gain of the useful signal of the th cognitive vehicle at the current time t it contains can be expressed as follows:

[0130]

[0131] Among them, represents the transmission power of the th cognitive vehicle, represents the bandwidth of the channel, represents the power spectral density of the background noise in the channel, represents the communication distance between the th cognitive vehicle and the base station associated with the channel, represents the path loss exponent.

[0132] For , the channel gain of the interference signal from the th authorized vehicle to the th cognitive vehicle at the current moment t it contains can be expressed as follows:

[0133]

[0134] Among them, represents the transmission power of the th authorized vehicle, represents the bandwidth of the channel, represents the power spectral density of the background noise in the channel, represents the communication distance between the th authorized vehicle and the th cognitive vehicle, represents the path loss exponent.

[0135] For , the channel gain of the useful signal of the th cognitive vehicle at the current moment t it contains can be expressed as follows:

[0136]

[0137] Among them, represents the transmission power of the th cognitive vehicle, represents the bandwidth of the channel, represents the power spectral density of the background noise in the channel, represents the communication distance between the th cognitive vehicle and the base station associated with the channel, represents the path loss exponent.

[0138] For , the channel gain of the interference signal from the th authorized vehicle to the th cognitive vehicle at the current moment t it contains can be expressed as follows:

[0139]

[0140] Among them, represents the transmission power of the th authorized vehicle, represents the bandwidth of the channel, represents the power spectral density of the background noise in the channel, represents the th authorized vehicle and the th cognitive vehicle communication distance, represents the path loss exponent.

[0141] For , the channel gain of the interference signal from the th cognitive vehicle to the th authorized vehicle at the current moment t it contains can be expressed as follows:

[0142]

[0143] Among them, represents the transmission power of the th cognitive vehicle, represents the bandwidth of the channel, represents the power spectral density of the background noise in the channel, represents the th authorized vehicle and the th cognitive vehicle communication distance, represents the path loss exponent.

[0144] For , the channel gain of the interference signal from the th cognitive vehicle to the th cognitive vehicle at the current moment t it contains can be expressed as follows:

[0145]

[0146] Among them, represents the transmission power of the th cognitive vehicle, represents the bandwidth of the channel, represents the power spectral density of the background noise in the channel, represents the th authorized vehicle and the th cognitive vehicle communication distance, represents the path loss exponent.

[0147] For , the channel gains of the interference signals of the rd cognitive vehicle to the th cognitive vehicle at the current moment t can be expressed as follows: It can be expressed as follows:

[0148]

[0149] Among them, represents the transmission power of the th cognitive vehicle, represents the bandwidth of the channel, represents the power spectral density of the background noise in the channel, represents the th cognitive vehicle and the th cognitive vehicle, the communication distance between them, represents the path loss exponent.

[0150] Furthermore, according to Shannon's theorem, the throughput of the th authorized vehicle , the throughput of the th cognitive vehicle and the throughput of the th cognitive vehicle can be expressed as follows:

[0151]

[0152]

[0153]

[0154] Among them, represents the bandwidth of the channel; the signal-to-interference-plus-noise ratio (SINR) of the th authorized vehicle , the signal-to-interference-plus-noise ratio (SINR) of the th cognitive vehicle and the signal-to-interference-plus-noise ratio (SINR) of the th cognitive vehicle can be expressed as follows:

[0155]

[0156]

[0157]

[0158] Among them, respectively represent the th authorized vehicle, the th cognitive vehicle, the The transmission power of a cognitive vehicle, represents the bandwidth of the channel, represents the power spectral density of the background noise in the channel, and the total interference generated by all cognitive vehicles accessing the current channel on the th authorized vehicle , the total interference generated by other cognitive vehicles accessing the current channel on the th cognitive vehicle , the total interference generated by other cognitive vehicles accessing the current channel on the th cognitive vehicle , respectively represent the channel gains of the useful signals of the th authorized vehicle, the th cognitive vehicle, and the th cognitive vehicle, represents the channel gain of the interference signal from the th authorized vehicle to the th cognitive vehicle, represents the channel gain of the interference signal from the th authorized vehicle to the th cognitive vehicle, represents the channel gain of the interference signal from the th cognitive vehicle to the th authorized vehicle, represents the channel gain of the interference signal from the th cognitive vehicle to the th authorized vehicle, represents the channel gain of the interference signal from the th cognitive vehicle to the th cognitive vehicle, represents the channel gain of the interference signal from the th cognitive vehicle to the th cognitive vehicle.

[0159] For the method embodiments, for simplicity of description, they are all expressed as a series of action combinations. However, those skilled in the art should know that the embodiments of the present application are not limited by the described action sequence, because according to the embodiments of the present application, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions involved are not necessarily essential for the embodiments of the present application.

[0160] In a second aspect, Figure 5 is a schematic structural diagram of a channel access device for vehicles in a cognitive vehicle network according to an embodiment of the present application. The channel access device for vehicles in the cognitive vehicle network is applied to cognitive vehicles, and the device includes:

[0161] The first detection module 100 is configured to detect the occupancy of the target channel at the current moment, where the target channel is the channel selected by the cognitive vehicle for access at the current moment;

[0162] The first determination module 200 is configured to, when the target channel is occupied by other vehicles, determine whether the communication distance between the cognitive vehicle and the base station associated with the target channel is greater than a set distance threshold, where the other vehicles include at least one of other cognitive vehicles and authorized vehicles;

[0163] The first access module 300 is configured to, when the communication distance between the cognitive vehicle and the base station associated with the target channel is not greater than the set distance threshold, enable the cognitive vehicle to access the target channel.

[0164] By adopting the technical solution of the embodiment of the present application, considering the influence of the communication distance between the vehicle and the base station on the success rate of channel access and the communication quality, the present application compares the communication distance between the cognitive vehicle and the base station associated with the target channel with the set distance threshold, and enables the cognitive vehicle to access the channel occupied by other vehicles when the communication distance is not greater than the set distance threshold, so as to enable multiple vehicles to access the same channel at the same time point on the premise of ensuring the success rate of channel access and the communication quality of the cognitive vehicle, thereby improving the utilization rate of spectrum resources, and further enabling the cognitive vehicle network to meet the communication requirements between vehicles under limited spectrum resources.

[0165] Optionally, the device further includes:

[0166] The parameter acquisition module 410 is configured to respectively acquire the state parameters of each channel at the current moment, where the state parameters include: channel gain, the duration of data transmission of the cognitive vehicle, and the communication distances between the vehicles associated with the channel and between each vehicle and the base station associated with the channel;

[0167] The model decision module 420 is configured to maximize the overall sum of the throughputs associated with each cognitive vehicle including the cognitive vehicle as an optimization goal, and determine the action parameter of the cognitive vehicle at the current moment through the reinforcement learning model according to the state parameters at the current moment, where the action parameter is used to represent whether the cognitive vehicle selects to access the channel and, in the case of selecting to access the channel, the channel selected for access;

[0168] Wherein, the sum of the throughputs associated with a single cognitive vehicle includes: the sum of the throughputs of the single cognitive vehicle and other vehicles accessing the channel selected by the single cognitive vehicle.

[0169] Optionally, the model decision module 420 is further configured to: maximize the average value of the cumulative discounted reward values of each cognitive vehicle including the cognitive vehicle as an optimization objective, and the cumulative discounted reward value of a single cognitive vehicle is determined by the following formula:

[0170]

[0171] wherein, represents the cumulative discounted reward value of the single cognitive vehicle; represents the discount factor corresponding to the (t - 1)-th moment; represents the reward value of the single cognitive vehicle at the (t + 1)-th moment, and the reward value is determined according to the total throughput associated with the single cognitive vehicle at the (t + 1)-th moment.

[0172] Optionally, the model decision module 420 is further configured to perform the following steps:

[0173] When the single cognitive vehicle selects to access a channel at the single moment, and the communication distance between the single cognitive vehicle and the base station associated with the selected access channel is not greater than the set distance threshold, determine the reward value of the single cognitive vehicle at the single moment through a first reward function, and the first reward function is expressed as follows:

[0174]

[0175] When the single cognitive vehicle selects to access a channel at the single moment, and the communication distance between the single cognitive vehicle and the base station associated with the selected access channel is greater than the set distance threshold, determine the reward value of the single cognitive vehicle at the single moment through a second reward function, and the second reward function is expressed as follows:

[0176]

[0177] When the single cognitive vehicle does not select to access a channel at the single moment, determine the reward value of the single cognitive vehicle at the single moment through a third reward function, and the third reward function is expressed as follows:

[0178]

[0179] wherein, represents the reward value of the single cognitive vehicle at the single moment, represents the throughput of the single cognitive vehicle at the single moment, represents the throughput of other vehicles accessing the channel selected by the single cognitive vehicle at the single moment.

[0180] Optionally, the channel gain in the state parameters includes: the channel gain of the useful signal of the cognitive vehicle, the channel gain of the useful signals of other vehicles accessing the channel selected by the cognitive vehicle, and the channel gain of the interference signal from any vehicle among the cognitive vehicle and other vehicles accessing the channel selected by the cognitive vehicle to another vehicle;

[0181] Among them, the channel gain of the useful signal of a single vehicle is determined by the following formula:

[0182]

[0183] Among them, represents the channel gain of the useful signal of the single vehicle, represents the transmission power of the single vehicle, represents the bandwidth of the channel, represents the power spectral density of the background noise in the channel, represents the communication distance between the single vehicle and the base station associated with the channel, represents the path loss exponent;

[0184] Among the cognitive vehicle and other vehicles accessing the channel selected by the cognitive vehicle, the channel gain of the interference signal from the m-th vehicle to the n-th vehicle is determined by the following formula:

[0185]

[0186] Among them, represents the channel gain of the interference signal from the m-th vehicle to the n-th vehicle, represents the transmission power of the m-th vehicle, represents the bandwidth of the channel, represents the power spectral density of the background noise in the channel, represents the communication distance between the m-th vehicle and the n-th vehicle, represents the path loss exponent.

[0187] Optionally, the device further includes:

[0188] The first processing module 510 is configured to determine the signal-to-interference-plus-noise ratio of the single vehicle by a first formula when the single vehicle is an authorized vehicle;

[0189] The second processing module 520 is configured to determine the signal-to-interference-plus-noise ratio of the single vehicle by a second formula when the single vehicle is a cognitive vehicle;

[0190] The third processing module 530 is configured to determine the throughput of the single vehicle according to the signal-to-interference-plus-noise ratio of the single vehicle and the bandwidth of the channel;

[0191] Among them, the first formula is expressed as follows:

[0192]

[0193] Among them, represents the signal-to-interference-plus-noise ratio (SINR) of the authorized vehicle, represents the transmit power of the authorized vehicle, represents the channel gain of the useful signal of the authorized vehicle, represents the bandwidth of the channel, represents the power spectral density of the background noise in the channel, represents the total interference generated by all cognitive vehicles accessing the same channel as the authorized vehicle to the authorized vehicle, and N1 represents the number of all cognitive vehicles accessing the same channel as the authorized vehicle;

[0194] The second formula is expressed as follows:

[0195]

[0196] Among them, represents the signal-to-interference-plus-noise ratio (SINR) of the cognitive vehicle, represents the transmit power of the cognitive vehicle, represents the channel gain of the useful signal of the cognitive vehicle, represents the bandwidth of the channel, represents the power spectral density of the background noise in the channel, represents the transmit power of the authorized vehicle accessing the same channel as the cognitive vehicle, represents the channel gain of the interference signal from the authorized vehicle to the cognitive vehicle, represents the total interference generated by other cognitive vehicles accessing the same channel as the cognitive vehicle to the cognitive vehicle, and N2 represents the number of all cognitive vehicles accessing the channel.

[0197] Optionally, the device further includes:

[0198] A second access module 600, configured to enable the cognitive vehicle to access the target channel when the target channel is not occupied by other vehicles.

[0199] It should be noted that the device embodiment is similar to the method embodiment, so the description is relatively simple. For related parts, please refer to the method embodiment.

[0200] An embodiment of the present application further provides an electronic device. Referring to Figure 6 , Figure 6 is a schematic diagram of the electronic device proposed in the embodiment of the present application. As Figure 6As shown, the electronic device 100 includes: a memory 110 and a processor 120. The memory 110 and the processor 120 are communicatively connected via a bus. A computer program is stored in the memory 110, and this computer program can run on the processor 120, thereby implementing the steps in the method for a vehicle to access a channel in the cognitive vehicle-to-everything network disclosed in the embodiments of the present application.

[0201] The embodiments of the present application further provide a computer-readable storage medium, on which a computer program / instructions are stored. When the computer program / instructions are executed by a processor, the method for a vehicle to access a channel in the cognitive vehicle-to-everything network disclosed in the embodiments of the present application is implemented.

[0202] The embodiments of the present application further provide a computer program product, including a computer program / instructions. When the computer program / instructions are executed by a processor, the method for a vehicle to access a channel in the cognitive vehicle-to-everything network disclosed in the embodiments of the present application is implemented.

[0203] Each embodiment in this specification is described in a progressive manner. The key point of each embodiment is to illustrate the differences from other embodiments. The same or similar parts among the embodiments can be referred to each other.

[0204] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a device, or a computer program product. Therefore, the embodiments of the present application can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the embodiments of the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk memories, CD-ROMs, optical memories, etc.) containing computer-usable program codes.

[0205] The embodiments of the present application are described with reference to the flowcharts and / or block diagrams of methods, systems, devices, storage media, and program products according to the embodiments of the present application. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as the combination of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing terminal devices to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing terminal devices generate a device for implementing the specified functions in Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0206] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing terminal device to work in a specific manner, such that the instructions stored in the computer-readable memory produce a manufacture including an instruction device that implements the functions specified in one or more processes and / or blocks Figure 1 in one or more processes and / or blocks Figure 1 in one or more blocks or multiple blocks.

[0207] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal device, such that a series of operational steps are executed on the computer or other programmable terminal device to produce a computer-implemented process, and thus the instructions executed on the computer or other programmable terminal device provide steps for implementing the functions specified in one or more processes and / or blocks Figure 1 in one or more processes and / or blocks Figure 1 in one or more blocks or multiple blocks.

[0208] Although the preferred embodiments of the embodiments of the present application have been described, those skilled in the art can make additional changes and modifications once they learn the basic creative concepts. Therefore, the appended claims are intended to be construed as including the preferred embodiments and all changes and modifications falling within the scope of the embodiments of the present application.

[0209] Finally, it should also be noted that in this document, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, such that a process, method, article or terminal device comprising a series of elements not only includes those elements, but also includes other elements not expressly listed, or elements inherent to such process, method, article or terminal device. Without further limitation, an element defined by the statement "comprising an..." does not exclude the presence of additional identical elements in the process, method, article or terminal device comprising the element.

[0210] The above has introduced in detail a method, apparatus, device and medium for a vehicle to access a channel in a cognitive vehicle network provided by the present application. Specific examples are used in this article to elaborate on the principle and implementation manner of the present application. The description of the above embodiments is only used to help understand the method and its core idea of the present application; at the same time, for those of ordinary skill in the art, according to the idea of the present application, there will be changes in the specific implementation manner and application scope. In summary, the content of this specification should not be construed as a limitation to the present application.

Claims

1. A method for a vehicle to access a channel in a cognitive vehicle-to-everything network, characterized in that Applied to cognitive vehicles, the method includes: Obtaining the state parameters at the current moment for each channel respectively, where the state parameters include: channel gain, the duration for the cognitive vehicle to transmit data, and the communication distances between the vehicles associated with the channel and between each of the vehicles and the base station associated with the channel; Taking the overall maximization of the sum of throughputs associated with each cognitive vehicle including the cognitive vehicle as the optimization objective, and determining the action parameters of the cognitive vehicle at the current moment according to the state parameters at the current moment through a reinforcement learning model, where the action parameters are used to represent whether the cognitive vehicle selects to access the channel and, in the case of selecting to access the channel, the channel selected to access; wherein, the sum of throughputs associated with a single cognitive vehicle includes: the sum of throughputs of the single cognitive vehicle and other vehicles accessing the channel selected by the single cognitive vehicle; Detecting the occupancy situation of the target channel at the current moment, where the target channel is the channel that the cognitive vehicle determines to select to access at the current moment based on the reinforcement learning model; In the case where the target channel is occupied by other vehicles, determining whether the communication distance between the cognitive vehicle and the base station associated with the target channel is greater than a set distance threshold, where the other vehicles include at least one of other cognitive vehicles and authorized vehicles; In the case where the communication distance between the cognitive vehicle and the base station associated with the target channel is not greater than the set distance threshold, the cognitive vehicle accesses the target channel.

2. The method according to claim 1, wherein Taking the overall maximization of the sum of throughputs associated with each cognitive vehicle including the cognitive vehicle as the optimization objective includes: taking the maximization of the average value of the cumulative discounted reward values of each cognitive vehicle including the cognitive vehicle as the optimization objective, and the cumulative discounted reward value of a single cognitive vehicle is determined by the following formula: where R represents the cumulative discounted reward value of the single cognitive vehicle; γ t-1 represents the discount factor corresponding to the (t-1)-th moment; r t+1 represents the reward value of the single cognitive vehicle at the (t + 1)-th moment, and the reward value is determined according to the total throughput associated with the single cognitive vehicle at the (t + 1)-th moment.

3. The method according to claim 2, wherein The reward value of the single cognitive vehicle at a single moment is determined by the following steps: In the case where the single cognitive vehicle selects to access the channel at the single moment and the communication distance between the single cognitive vehicle and the base station associated with the selected channel is not greater than the set distance threshold, determining the reward value of the single cognitive vehicle at the single moment through a first reward function, and the first reward function is expressed as follows: r = C R + C Q1 + … + C Qn In the case where the single cognitive vehicle selects to access the channel at the single moment and the communication distance between the single cognitive vehicle and the base station associated with the selected channel is greater than the set distance threshold, determining the reward value of the single cognitive vehicle at the single moment through a second reward function, and the second reward function is expressed as follows: r = -(C R + C Q1 + … + C Qn ) In the case where the single cognitive vehicle does not select to access the channel at the single moment, determining the reward value of the single cognitive vehicle at the single moment through a third reward function, and the third reward function is expressed as follows: r＝0 where r represents the reward value of the single cognitive vehicle at the single moment, and C R represents the throughput of the single cognitive vehicle at the single moment, and C Q1 ,..., C Qn represents the throughputs of other vehicles accessing the channel selected by the single cognitive vehicle at the single moment.

4. The method according to claim 1, characterized in that, The channel gain in the state parameters includes: the channel gain of the useful signal of the cognitive vehicle, the channel gain of the useful signals of other vehicles accessing the channel selected by the cognitive vehicle, and the channel gain of the interference signal from any vehicle to another vehicle among the cognitive vehicle and other vehicles accessing the channel selected by the cognitive vehicle; Among them, the channel gain of the useful signal of a single vehicle is determined by the following formula: where h c represents the channel gain of the useful signal of the single vehicle, P c represents the transmission power of the single vehicle, B 0 represents the bandwidth of the channel, N 0 represents the power spectral density of the background noise in the channel, d c represents the communication distance between the single vehicle and the base station associated with the channel, and α represents the path loss exponent; Among the cognitive vehicle and other vehicles accessing the channel selected by the cognitive vehicle, the channel gain of the interference signal from the m-th vehicle to the n-th vehicle is determined by the following formula: Among them, h m，n represents the channel gain of the interference signal from the m-th vehicle to the n-th vehicle, P m represents the transmission power of the m-th vehicle, B 0 represents the bandwidth of the channel, N 0 represents the power spectral density of the background noise in the channel, d c m，n represents the communication distance between the m-th vehicle and the n-th vehicle, and α represents the path loss exponent.

5. The method according to claim 1, characterized in that The throughput of a single vehicle is determined by the following steps: In the case where the single vehicle is an authorized vehicle, the signal-to-interference-plus-noise ratio of the single vehicle is determined by the first formula; In the case where the single vehicle is a cognitive vehicle, the signal-to-interference-plus-noise ratio of the single vehicle is determined by the second formula; According to the signal-to-interference-plus-noise ratio of the single vehicle and the bandwidth of the channel, the throughput of the single vehicle is determined; Among them, the first formula is expressed as follows: Among them, γ s represents the signal-to-interference-plus-noise ratio of the authorized vehicle, P s represents the transmission power of the authorized vehicle, h s represents the channel gain of the useful signal of the authorized vehicle, B 0 represents the bandwidth of the channel, N 0 represents the power spectral density of the background noise in the channel, represents the total interference generated by all cognitive vehicles accessing the same channel as the authorized vehicle to the authorized vehicle, and N1 represents the number of all cognitive vehicles accessing the same channel as the authorized vehicle; The second formula is expressed as follows: where γ n represents the signal-to-interference-plus-noise ratio of the cognitive vehicle, P n represents the transmission power of the cognitive vehicle, h n represents the channel gain of the useful signal of the cognitive vehicle, B 0 represents the bandwidth of the channel, N 0 represents the power spectral density of the background noise in the channel, P s represents the transmission power of the authorized vehicle accessing the same channel as the cognitive vehicle, h s，n represents the channel gain of the interference signal from the authorized vehicle to the cognitive vehicle, represents the total interference generated by other cognitive vehicles accessing the same channel as the cognitive vehicle to the cognitive vehicle, and N2 represents the number of all cognitive vehicles accessing the channel.

6. The method according to any one of claims 1-5, characterized in that The method further includes: In the case where the target channel is not occupied by other vehicles, the cognitive vehicle accesses the target channel.

7. A channel access device for vehicles in a cognitive vehicle-to-everything network, characterized in that Applied to a cognitive vehicle, the device includes: A parameter acquisition module 410, configured to respectively acquire the state parameters at the current moment for each channel, where the state parameters include: channel gain, the duration of data transmission of the cognitive vehicle, and the communication distances between the vehicles associated with the channel and between each vehicle and the base station associated with the channel; A model decision module 420, configured to maximize the overall sum of the throughputs associated with each cognitive vehicle including the cognitive vehicle as an optimization goal, and determine the action parameters of the cognitive vehicle at the current moment through a reinforcement learning model according to the state parameters at the current moment, where the action parameters are used to characterize whether the cognitive vehicle selects to access a channel and, in the case of selecting to access a channel, the channel selected; among them, the sum of the throughputs associated with a single cognitive vehicle includes: the sum of the throughputs of the single cognitive vehicle and other vehicles accessing the channel selected by the single cognitive vehicle; A first detection module, configured to detect the occupancy situation of the target channel at the current moment, where the target channel is: the channel selected by the cognitive vehicle to access at the current moment based on the reinforcement learning model; A first judgment module, configured to, in the case where the target channel is occupied by other vehicles, judge whether the communication distance between the cognitive vehicle and the base station associated with the target channel is greater than a set distance threshold, where the other vehicles include at least one of other cognitive vehicles and authorized vehicles; A first access module, configured to, in the case where the communication distance between the cognitive vehicle and the base station associated with the target channel is not greater than the set distance threshold, the cognitive vehicle accesses the target channel.

8. An electronic device, comprising a memory, a processor, and a computer program stored on the memory, characterized in that, The processor executes the computer program to implement the channel access method for vehicles in the cognitive vehicle network as described in any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program / instructions stored thereon, characterized in that, When the computer program / instructions are executed by a processor, the method for a vehicle to access a channel in a cognitive vehicle-to-everything network according to any one of claims 1 to 6 is implemented.

Images