Resource request control method and device for Internet of Vehicles

Abstract

The present application relates to a resource request control method and device for an Internet of Vehicles. The method is applied to a target vehicle, and the target vehicle is any vehicle in the Internet of Vehicles system. The method includes: obtaining the fairness index currently corresponding to all vehicles in the Internet of Vehicles system, and obtaining a set of state parameters of all vehicles in the Internet of Vehicles system; inputting the fairness index and the set of state parameters into a rate control model obtained from a server corresponding to the Internet of Vehicles system to obtain a rate adjustment strategy output by the rate control model; and adjusting the current resource request rate for sending resource requests to the Internet of Vehicles system according to the rate adjustment strategy. In this way, channel congestion can be avoided while ensuring the fairness of minimizing channel congestion, thereby enabling timely communication between vehicles, improving driving safety, and enhancing user experience.

Description

Technical Field

[0001] The present application relates to the field of vehicle technology, and in particular to a resource request control method and device for an Internet of Vehicles. Background Art

[0002] Vehicle-to-everything (V2X) is a typical application of the Internet of Things (IoT) in the field of Intelligent Transportation System (ITS). It refers to a ubiquitous intelligent vehicle network based on Intranet, Internet and mobile vehicle networks. V2X shares and exchanges data according to agreed communication protocols and data exchange standards. It realizes intelligent traffic management and services through real-time perception and collaboration between pedestrians, roadside facilities, vehicles, networks and clouds, such as improving road safety, enhancing road condition perception and reducing traffic congestion.

[0003] The Internet of Vehicles system generally communicates through V2V communication technology, but the bandwidth of the V2V channel is limited. This means that if users of multiple vehicles access the wireless channel of high-bandwidth applications (such as remote driving, VR / AR services) at the same time, it will cause channel congestion, resulting in the inability to communicate between vehicles in a timely manner, thereby failing to avoid traffic accidents in a timely manner, posing a safety hazard and affecting the user experience. Summary of the invention

[0004] The present application provides a resource request control method and device for an Internet of Vehicles to solve the technical problem in the prior art that if users of multiple vehicles simultaneously access the wireless channel of a high-bandwidth application, channel congestion will occur, resulting in the inability to communicate between vehicles in a timely manner, thereby failing to avoid traffic accidents in a timely manner, posing a safety hazard and affecting the user experience.

[0005] In a first aspect, the present application provides a resource request control method for an Internet of Vehicles, which is applied to a target vehicle, wherein the target vehicle is any vehicle in an Internet of Vehicles system, and the method comprises:

[0006] Obtaining fairness indicators currently corresponding to all vehicles in the Internet of Vehicles system, and obtaining a set of state parameters of all vehicles in the Internet of Vehicles system;

[0007] Inputting the fairness index and the state parameter set into a rate control model obtained from a server corresponding to the Internet of Vehicles system to obtain a rate adjustment strategy output by the rate control model;

[0008] The current resource request rate for sending resource requests to the Internet of Vehicles system is adjusted according to the rate adjustment strategy.

[0009] As a possible implementation manner, before obtaining the fairness indicators currently corresponding to all vehicles in the Internet of Vehicles system, the method further includes:

[0010] Determining the number of resource blocks currently to be allocated in the Internet of Vehicles system;

[0011] Determining the number of all vehicles currently in the connected vehicle system;

[0012] Comparing the number of resource blocks with the number of vehicles to obtain a comparison result;

[0013] When the comparison result indicates that the number of resource blocks is less than the number of vehicles, the step of obtaining the fairness indicators currently corresponding to all vehicles in the Internet of Vehicles system is performed.

[0014] As a possible implementation manner, the obtaining of the fairness indicators currently corresponding to all vehicles in the Internet of Vehicles system includes:

[0015] Determine the number of all vehicles currently in the Internet of Vehicles system and an initial resource request rate at which each of the vehicles sends resource requests to the Internet of Vehicles system within a preset time interval;

[0016] The number of vehicles and the initial resource request rate are input into the following formula to obtain the fairness index currently corresponding to all vehicles in the Internet of Vehicles system:

[0017]

[0018] Wherein, N is the number of vehicles, J is t is the fairness indicator, is the initial resource request rate corresponding to the i-th vehicle in the Internet of Vehicles system, and t is the preset time interval.

[0019] As a possible implementation manner, the obtaining of a set of state parameters of all vehicles in the Internet of Vehicles system includes:

[0020] Determining a signal-to-noise ratio of each resource block in the Internet of Vehicles system;

[0021] Determine the resource block whose signal-to-noise ratio is greater than a preset signal-to-noise ratio threshold as a target resource block;

[0022] Dividing the first number of the target resource blocks by the second number of all resource blocks in the Internet of Vehicles system to obtain a resource busy ratio corresponding to the Internet of Vehicles system;

[0023] Acquire an initial resource request rate at which each of the vehicles sends resource requests to the Internet of Vehicles system within a preset time interval;

[0024] Obtaining the current position information corresponding to each of the vehicles;

[0025] For each vehicle, determining a resource busy ratio, an initial resource request rate, and the location information corresponding to the vehicle as an initial parameter subset corresponding to the vehicle;

[0026] The initial parameter subset corresponding to each of the vehicles is classified into a preset state parameter set to obtain a state parameter set of all vehicles in the vehicle networking system.

[0027] As a possible implementation manner, the inputting the fairness index and the state parameter set into a rate control model obtained from a server corresponding to the Internet of Vehicles system to obtain a rate adjustment strategy output by the rate control model includes:

[0028] The fairness indicator and the state parameter set are input into a rate control model obtained in advance from a corresponding server of the Internet of Vehicles system, so that the rate control model performs the following operations:

[0029] Determining a risk value of the target vehicle according to the position information of the target vehicle in the state parameter set;

[0030] A rate adjustment strategy for the target vehicle is determined according to the resource busy ratio, the initial resource request rate, the fairness index, and the risk value, wherein the adjustment of the initial resource request rate in the rate adjustment strategy is proportional to the risk value.

[0031] As a possible implementation manner, the rate control model is obtained by training a corresponding server of the Internet of Vehicles system, and the server is trained to obtain the rate control model in the following manner:

[0032] Obtaining historical fairness indicators corresponding to all vehicles in the Internet of Vehicles system within a preset historical time period, and obtaining a set of historical state parameters of all vehicles in the Internet of Vehicles system within the historical time period;

[0033] Using the historical fairness index and the historical state parameter set, reinforcement learning is performed on a preset initial rate control model to obtain the rate control model;

[0034] The method further comprises:

[0035] The rate control model is sent to each of the vehicles in the vehicle networking system.

[0036] As a possible implementation manner, the obtaining of a set of historical status parameters of all vehicles in the Internet of Vehicles system in a preset historical time period includes:

[0037] Determine a historical signal-to-noise ratio of each resource block in the Internet of Vehicles system;

[0038] Determine the resource block whose historical signal-to-noise ratio is greater than a preset historical signal-to-noise ratio threshold as a historical target resource block;

[0039] Dividing a first historical number of the historical target resource blocks by a second historical number of all resource blocks in the Internet of Vehicles system, to obtain a historical resource busy ratio corresponding to the Internet of Vehicles system;

[0040] Obtaining a historical initial resource request rate at which each of the vehicles sends resource requests to the Internet of Vehicles system within the historical time period;

[0041] Obtaining historical location information corresponding to each of the vehicles in the historical time period;

[0042] For each vehicle, determining a historical resource busy ratio, a historical initial resource request rate, and the historical location information corresponding to the vehicle as a historical initial parameter subset corresponding to the vehicle;

[0043] The historical initial parameter subset corresponding to each of the vehicles is classified into a preset state parameter set to obtain a historical state parameter set of all vehicles in the vehicle networking system.

[0044] As a possible implementation manner, the use of the historical fairness indicator and the historical state parameter set to perform reinforcement learning on a preset initial rate control model to obtain the rate control model includes:

[0045] Determining a historical risk value of each of the vehicles according to the historical position information in the historical state parameter set;

[0046] The preset total data packet delivery rate function is used as the reward function, the historical fairness index and the historical state parameter set are used as the environmental state, the historical resource busy ratio, the historical fairness index, and the historical risk value corresponding to the environmental state are used as penalty parameters, and the preset rate control strategy set is used as the execution action to perform reinforcement learning on the preset initial rate control model to obtain the rate control model.

[0047] As a possible implementation manner, adjusting the current resource request rate of sending resource requests to the Internet of Vehicles system according to the rate adjustment strategy includes:

[0048] In a case where the rate adjustment strategy indicates increasing the current resource request rate according to a first rate, increasing the current resource request rate by the first rate;

[0049] In a case where the rate adjustment policy indicates reducing the current resource request rate according to a second rate, the current resource request rate is reduced by the second rate.

[0050] In a second aspect, an embodiment of the present application provides a resource request control device for an Internet of Vehicles, which is applied to a target vehicle, wherein the target vehicle is any vehicle in an Internet of Vehicles system, and the device includes:

[0051] An acquisition module, used to acquire the fairness indicators currently corresponding to all vehicles in the Internet of Vehicles system, and to acquire a set of state parameters of all vehicles in the Internet of Vehicles system;

[0052] An input module, configured to input the fairness index and the state parameter set into a rate control model obtained from a server corresponding to the Internet of Vehicles system, to obtain a rate adjustment strategy output by the rate control model;

[0053] An adjustment module is used to adjust a current resource request rate of sending resource requests to the Internet of Vehicles system according to the rate adjustment strategy.

[0054] The technical solution provided by the embodiment of the present application obtains the fairness indicators currently corresponding to all vehicles in the Internet of Vehicles system, and obtains a set of state parameters of all vehicles in the Internet of Vehicles system, and inputs the above-mentioned fairness indicators and state parameter set into a rate control model obtained from the corresponding server of the Internet of Vehicles system, obtains the rate adjustment strategy output by the rate control model, and adjusts the current resource request rate of sending resource requests to the Internet of Vehicles system according to the above-mentioned rate adjustment strategy. This technical solution pre-trains a rate control model through the Internet of Vehicles system and deploys the rate control model on each vehicle in the Internet of Vehicles, so that each vehicle determines the current resource request rate for sending resource requests to the Internet of Vehicles system based on the fairness indicators and state parameter sets of all vehicles. On the one hand, it determines the rate adjustment strategy of the vehicle resource request rate based on the vehicle's fairness indicators, which can achieve fairness in minimizing channel congestion. On the other hand, the rate control model is pre-trained by the Internet of Vehicles system and deployed in each vehicle respectively. Not only can the resource request rate of the vehicle sending resource requests be adjusted in time when channel congestion occurs, but also the computing resources of the vehicle's online training model can be saved, achieving the goal of avoiding channel congestion while ensuring the fairness of minimizing channel congestion, thereby achieving timely communication between vehicles, improving driving safety, and enhancing user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0056] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the prior art texts are briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0057] One or more embodiments are exemplarily described by pictures in the corresponding drawings, and these exemplified descriptions do not constitute limitations on the embodiments. Elements with the same reference numerals in the drawings represent similar elements, and unless otherwise stated, the figures in the drawings do not constitute proportional limitations.

[0058] Figure 1 A schematic diagram of the structure of a vehicle networking system provided in an embodiment of the present application;

[0059] Figure 2 A flowchart of an embodiment of a resource request control method for an Internet of Vehicles provided in an embodiment of the present application;

[0060] Figure 3 A flow chart of an embodiment of a training rate control model provided in an embodiment of the present application;

[0061] Figure 4 A block diagram of an embodiment of a resource request control device for an Internet of Vehicles provided in an embodiment of the present application;

[0062] Figure 5 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0063] In order to make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the technical scheme in the embodiments of the present application will be clearly and completely described in conjunction with the drawings in the embodiments of the present application. Obviously, the embodiments described in the text are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0064] The disclosure below provides many different embodiments or examples to implement different structures of the present invention. In order to simplify the disclosure of the present invention, the parts and settings of specific examples are described below. Of course, they are only examples, and the purpose is not to limit the present invention. In addition, the present invention can repeat reference numbers and / or letters in different examples. This repetition is for the purpose of simplification and clarity, and does not itself indicate the relationship between the various embodiments and / or settings discussed.

[0065] In order to solve the technical problem in the prior art that if users of multiple vehicles simultaneously access the wireless channel of high-bandwidth applications, channel congestion will be caused, resulting in the inability of vehicles to communicate in time, thereby failing to avoid traffic accidents in time, posing safety hazards and affecting user experience, the present application provides a resource request control method and device for an Internet of Vehicles. The rate control model can be pre-trained by the Internet of Vehicles system, and the rate control model is deployed on each vehicle in the Internet of Vehicles, so that each vehicle determines the current resource request rate of sending resource requests to the Internet of Vehicles system according to the fairness index and state parameter set of all vehicles. On the one hand, the rate adjustment strategy of the vehicle resource request rate is determined based on the fairness index of the vehicle, which can achieve fairness in minimizing channel congestion. On the other hand, the rate control model is pre-trained by the Internet of Vehicles system, and the rate control model is deployed in each vehicle respectively, which can not only timely adjust the resource request rate of the vehicle sending resource requests when channel congestion occurs, but also save the computing resources of the vehicle online training model, thereby avoiding channel congestion while ensuring the fairness of minimizing channel congestion, thereby achieving timely communication between vehicles, improving driving safety and enhancing user experience.

[0066] To facilitate understanding of the resource request control method for the Internet of Vehicles provided in an embodiment of the present application, the Internet of Vehicles system involved in the method is first illustrated below by way of example.

[0067] See also Figure 1 , is a schematic diagram of the structure of a vehicle networking system provided in an embodiment of the present application. Figure 1 As shown, the Internet of Vehicles system 10 may include: vehicle 11 , vehicle 12 , vehicle 13 , and server 14 .

[0068] The above-mentioned vehicles 11, 12 and 13 may be moving vehicles located on the driving road, or may be stationary vehicles, and the present embodiment of the application does not limit this. In addition, the present embodiment of the application does not limit the specific appearance and model of the above-mentioned multiple vehicles 11, 12 and 13.

[0069] The above-mentioned server 14 refers to the server corresponding to the Internet of Vehicles system 10. The server 14 can be a single server or a cluster composed of multiple servers, which is not limited in the embodiment of the present application.

[0070] The above-mentioned Internet of Vehicles system 10 refers to a system composed of multiple vehicles (vehicle 11, vehicle 12, and vehicle 13) communicating through a preset communication method, and the above-mentioned preset communication method can be V2V (V2V communication, V2V communication technology) that is not limited to a fixed base station. Based on this, the vehicle terminals of the above-mentioned different vehicles can directly exchange wireless information with each other without forwarding through a base station.

[0071] When the above-mentioned vehicles (such as vehicle 11 and vehicle 12, vehicle 11 and vehicle 13, or vehicle 12 and vehicle 13) communicate with each other, they can interact through cooperative sensing information, and the above-mentioned cooperative sensing information may include but is not limited to: vehicle position, vehicle speed and vehicle driving direction, etc. It should be noted that the Internet of Vehicles system 10 may include but is not limited to the above-mentioned vehicles 11, vehicle 12, and vehicle 13. This application takes the Internet of Vehicles system 10 including vehicles 11, vehicle 12, and vehicle 13 as an example for illustration.

[0072] In actual applications, when vehicles are driving, vehicle users can generally communicate through V2V communication technology. For example, vehicles in the Internet of Vehicles system can communicate freely with each other through a wireless broadcast system connected to Wi-Fi. If a driver is unaware of some potential dangers, drivers of other vehicles can use the system to warn them.

[0073] Among them, during the specific operation, the vehicle needs to first send a resource request to the Internet of Vehicles system to obtain communication resources (such as channels). After the Internet of Vehicles system allocates communication resources to the vehicle according to the received resource request, the vehicle can communicate with other vehicles through the communication resources allocated by the Internet of Vehicles system.

[0074] However, in actual applications, due to the limited bandwidth of the V2V channel, when users of multiple vehicles access the communication resources at the same time or request to obtain communication resources within a short interval, channel congestion will occur. In this regard, in the prior art, the received resource requests are generally queued, or the time interval is adjusted to reduce resource requests to avoid channel congestion.

[0075] However, the above method cannot process resource requests for safety hazards of the current vehicle in a timely manner, which makes it impossible for vehicles to communicate in a timely manner, resulting in the inability to eliminate safety hazards in a timely manner, thereby failing to avoid traffic accidents in a timely manner. The safety hazards are high and affect the user experience.

[0076] In this regard, an embodiment of the present application provides a resource request control method for the Internet of Vehicles, which can not only timely adjust the resource request rate of the vehicle sending resource requests to avoid channel congestion, but also determine the rate adjustment strategy for the resource request rate according to the fairness index of all vehicles in the Internet of Vehicles system, thereby ensuring the fairness of minimizing channel congestion, thereby realizing timely communication between vehicles, improving driving safety, and enhancing user experience.

[0077] The resource request control method for the Internet of Vehicles provided by the present application is further explained below with reference to specific embodiments in conjunction with the accompanying drawings. The embodiments do not constitute a limitation on the embodiments of the present invention.

[0078] join Figure 2 , is a flow chart of an embodiment of a method for controlling resource requests of a vehicle network provided in an embodiment of the present application. As an embodiment, the method for controlling resource requests of a vehicle network can be applied to a target vehicle, and the target vehicle can be any vehicle in the vehicle network system, such as Figure 1 The vehicle 11, the vehicle 12, or the vehicle 13 in the vehicle networking system 10 is shown. Figure 2 As shown, the process may include the following steps:

[0079] Step 201: Obtain the fairness indicators currently corresponding to all vehicles in the Internet of Vehicles system, and obtain a set of state parameters of all vehicles in the Internet of Vehicles system.

[0080] The above-mentioned fairness index refers to the fairness index established in this application to ensure the fairness of QoS (Quality of Service) of each vehicle.

[0081] The above-mentioned state parameter set refers to a set of state parameters corresponding to all vehicles included in the vehicle networking system. The above-mentioned state parameters may include but are not limited to: vehicle location information, resource request rate of the vehicle sending resource requests to the vehicle networking system, current resource busy-green ratio of the vehicle networking system, etc.

[0082] In an embodiment of the present application, in order to prevent channel congestion in the Internet of Vehicles system, the execution subject of the embodiment of the present application (that is, each vehicle included in the Internet of Vehicles system) can detect the channel usage in the Internet of Vehicles system in real time, so as to determine whether channel congestion may occur in the Internet of Vehicles system, and execute this step when it is determined that channel congestion has occurred or is about to occur.

[0083] As an exemplary implementation, the target vehicle may first determine the number of resource blocks currently to be allocated in the Internet of Vehicles system, which may be used to characterize the number of channels in the Internet of Vehicles system, that is, one resource block may correspond to one channel or may correspond to multiple channels, which is not limited in the present application embodiment. Further, for ease of calculation, one resource block may correspond to one channel.

[0084] At the same time or after determining the number of resource blocks, the number of all current vehicles in the Internet of Vehicles system can be determined. Afterwards, the number of resource blocks and the number of vehicles can be compared to obtain a comparison result, so as to determine whether there is channel congestion in the Internet of Vehicles system based on the comparison result.

[0085] Optionally, when the comparison result indicates that the number of resource blocks is less than the number of vehicles, it means that the number of resource blocks in the connected vehicle system is insufficient to allocate resource blocks to each vehicle, and therefore, it can be determined that there is channel congestion in the connected vehicle system. Based on this, this step can be performed to obtain the fairness indicators currently corresponding to all vehicles in the connected vehicle system.

[0086] On the contrary, when the comparison result indicates that the number of resource blocks is greater than or equal to the number of vehicles, it means that the number of resource blocks in the connected vehicle system is sufficient to allocate resource blocks to each vehicle. Therefore, it can be determined that there is no channel congestion in the connected vehicle system. Based on this, in order to save system resources, the target vehicle may not perform this step to obtain the fairness indicators currently corresponding to all vehicles in the connected vehicle system.

[0087] In the embodiment of the present application, in order to ensure the fairness of QoS of each vehicle, the embodiment of the present application can determine a fairness index for all vehicles included in the Internet of Vehicles system. When subsequent steps are performed on this basis, the fairness of each vehicle in the Internet of Vehicles system can be ensured.

[0088] As an optional implementation, the above fairness index may vary according to the number N of vehicles in the Internet of Vehicles system and the resource request rate issued by each vehicle.

[0089] As an exemplary implementation, the target vehicle may determine the number of all vehicles currently in the connected vehicle system and an initial resource request rate at which each vehicle sends a resource request to the connected vehicle system within a preset time interval.

[0090] When determining the initial resource request rate corresponding to each vehicle, the total number of resource requests sent by the vehicle to the Internet of Vehicles system within a preset time interval may be determined for each vehicle, and then the total number may be divided by the preset time interval to obtain the initial resource request rate corresponding to the vehicle. Specifically, the initial resource request rate of each vehicle may be calculated by the following formula (1):

[0091]

[0092] Among them, the above is the total number of resource requests sent by the i-th vehicle within the preset time interval T. is the above-mentioned preset time interval, is the initial resource request rate of the i-th vehicle.

[0093] On the basis of determining the number of vehicles and the initial resource request rate of each vehicle, the execution subject of the embodiment of the present application may input the number of vehicles and the initial resource request rate into the following formula (II), thereby obtaining the fairness index currently corresponding to all vehicles in the Internet of Vehicles system:

[0094]

[0095] Among them, N is the number of vehicles, and J is t is the above-mentioned fairness indicator. is the initial resource request rate corresponding to the i-th vehicle in the Internet of Vehicles system, and the above t is the preset time interval.

[0096] In one embodiment, the state parameter set of all vehicles in the above-mentioned Internet of Vehicles system may include parameters such as the resource busy ratio of the Internet of Vehicles system, the initial resource request rate of each vehicle sending resource requests to the Internet of Vehicles system within a preset time interval, and the location information of each vehicle.

[0097] Based on this, as an optional implementation method, when determining the above resource busy ratio, the signal interference and noise ratio of each resource block in the Internet of Vehicles system can be determined first, and the resource block with a signal interference and noise ratio greater than a preset signal interference and noise ratio threshold can be determined as the target resource block.

[0098] Afterwards, the number of the above-mentioned target resource blocks (for the convenience of description, referred to as the first number below) and the number of all resource blocks in the Internet of Vehicles system (for the convenience of description, referred to as the second number below) can be counted.

[0099] Finally, the first number can be divided by the second number to obtain the resource busy ratio corresponding to the Internet of Vehicles system, which can also be called the channel busy ratio, which uses the 3GPP standard to define the channel usage level. The 3GPP standard was established by the Third Generation Partnership Project Agreement signed by multiple telecommunications standard organizations, with the purpose of formulating globally applicable technical specifications and technical reports for the third generation mobile communication system.

[0100] As an exemplary implementation, the resource busy-green ratio corresponding to the Internet of Vehicles system may be determined by the following formula (III):

[0101]

[0102] Among them, the above Indicates whether the signal to interference noise ratio value of the kth resource block in the resource block sequence R of the connected vehicle system is greater than a preset threshold value. If so, the value is a preset first value (e.g., 1); if not, the value is a preset second value (e.g., 0); the above |R| is used to indicate the total number of resource block sequences in the connected vehicle system; the above Used to indicate the busy ratio of the above resources.

[0103] As an optional implementation method, when determining the initial resource request rate at which each vehicle sends a resource request to the Internet of Vehicles system within a preset time interval, the formula in the above formula (1) can be used to determine it, which will not be repeated here.

[0104] As an optional implementation, when determining the current location information corresponding to each vehicle, the geographic coordinates of each vehicle may be obtained through a preset GPS (Global Positioning System).

[0105] As another optional implementation, the state parameter set of all vehicles can be collected by a server in the Internet of Vehicles system through a preset data collection device. Based on this, the execution subject of the embodiment of the present application can directly obtain the state parameter set from the server. The data collection device can be a data collection device for collecting broadcast information of the drive test unit, and the specific type of the data collection device is not limited in the embodiment of the present application.

[0106] Based on the above description, after obtaining the above state parameters corresponding to each vehicle, for each vehicle, the resource busy ratio, initial resource request rate, and location information corresponding to the vehicle may be determined as an initial parameter subset corresponding to the vehicle.

[0107] On this basis, the initial parameter subset corresponding to each vehicle can be classified into a preset state parameter set, so that the state parameter set of all devices in the Internet of Vehicles system can be obtained.

[0108] Step 202: Input the above fairness index and state parameter set into the rate control model obtained from the corresponding server of the Internet of Vehicles system to obtain the rate adjustment strategy output by the rate control model.

[0109] The above-mentioned servers refer to the servers in the Internet of Vehicles system, such as Figure 1 Server 14 is shown.

[0110] The rate control model may be a pre-trained model for adjusting the resource request rate of the vehicle.

[0111] In an embodiment of the present application, in order to save the vehicle's online computing resources, the server in the Internet of Vehicles system may pre-train the above-mentioned rate control model and deploy the rate control model in each vehicle so that the vehicle can use the rate control model to adjust the resource request rate sent by the vehicle, thereby avoiding channel congestion in the Internet of Vehicles system.

[0112] Furthermore, the server may perform offline training when training the rate control model, thereby saving online computing resources of the server.

[0113] As for how the server is trained to obtain the above rate control model, it can be seen in the following Figure 3 The process shown is explained and will not be described in detail here.

[0114] In an embodiment of the present application, after obtaining the above-mentioned fairness indicators and state parameter set, the executing entity of the embodiment of the present application can directly input the above-mentioned fairness indicators and state parameter set into the rate control model obtained from the server, so that the rate control model determines the rate adjustment strategy for the target vehicle.

[0115] Furthermore, in order to facilitate the rate control model to analyze the input parameters, the execution entity of the embodiment of the present application may classify the above-mentioned fairness index as a parameter value of each vehicle into the state parameter subset corresponding to the vehicle.

[0116] For example, the state parameter subset corresponding to each vehicle can be shown in the following formula (IV), and the final state parameter set obtained can be shown in the following formula (V):

[0117]

[0118] Among them, the above is the state parameter subset of the i-th vehicle in the Internet of Vehicles system. is the location information of the i-th vehicle. is the initial resource request rate of the i-th vehicle, is the resource busy ratio, the above J t is the fairness indicator mentioned above.

[0119]

[0120] Among them, the above s t is the above state parameter set, is the state parameter subset corresponding to the first vehicle in the Internet of Vehicles system. It is the state parameter subset corresponding to the Nth vehicle in the Internet of Vehicles system.

[0121] On this basis, when the rate control model receives the fairness index and state parameter set input by the target vehicle, the risk value of the target vehicle can be determined according to the position information of the target vehicle in the above state parameter set.

[0122] As an exemplary implementation, the rate control model can determine the Euclidean distance between the target vehicle and the nearby vehicles based on the location information of the target vehicle and the location information of the nearby vehicles of the target vehicle, and determine whether the Euclidean distance is less than a preset distance threshold. The above distance threshold can be obtained by multiplying the minimum reaction time of the target vehicle and the closest speed of the vehicle, and the closest speed of the vehicle can be the average speed of the target vehicle detected by the speed sensor, or it can be the maximum speed, which is not limited in the embodiment of the present application.

[0123] Furthermore, the driving direction of the target vehicle can be determined, and the nearby vehicles can be determined based on the driving direction. For example, if the target vehicle is moving forward, the nearby vehicles can be the vehicle in front of and behind the target vehicle. For another example, if the target vehicle turns right, the nearby vehicles can be the vehicle behind the target vehicle.

[0124] Optionally, if it is less than, it means that the target vehicle has a collision risk and the risk value is high, so the risk value can be determined to be 1.

[0125] On the contrary, if the Euclidean distance is greater than the preset distance threshold, it means that the distance between the target vehicle and the target vehicle is relatively safe, there is no collision risk, and the risk value is low, so the risk value can be determined to be 0.

[0126] Afterwards, the rate adjustment strategy of the target vehicle can be determined according to the resource busy-green ratio, the initial resource request rate, the fairness index, and the risk value. The adjustment of the initial resource request rate of the target vehicle in the rate adjustment strategy is proportional to the risk value, that is, the higher the risk value of the target vehicle, the faster the rate adjustment strategy output by the rate control model adjusts the resource request rate of the target vehicle.

[0127] Step 203: Adjust the current resource request rate for sending resource requests to the Internet of Vehicles system according to the above rate adjustment strategy.

[0128] As can be seen from the description in step 202, the above rate adjustment strategy is a strategy for adjusting the initial resource request rate of the target vehicle, which is proportional to the risk value of the target vehicle. It can be seen that the above rate adjustment strategy may include increasing and decreasing the initial resource request rate.

[0129] Based on this, when the target vehicle adjusts the current resource request rate of sending resource requests to the Internet of Vehicles system according to the above-mentioned rate adjustment strategy, optionally, when the above-mentioned rate adjustment strategy indicates increasing the current resource request rate according to the first rate, the current resource request rate of the above-mentioned target vehicle can be increased by the above-mentioned first rate.

[0130] Optionally, when the rate adjustment strategy indicates that the current resource request rate is reduced according to the second rate, the current resource request rate may be reduced to the second rate.

[0131] Based on this, after determining the adjusted resource request rate, the target vehicle can send a resource request to the Internet of Vehicles system according to the adjusted resource request rate.

[0132] The technical solution provided by the embodiment of the present application obtains the fairness indicators currently corresponding to all vehicles in the Internet of Vehicles system, and obtains a set of state parameters of all vehicles in the Internet of Vehicles system, and inputs the above-mentioned fairness indicators and state parameter set into a rate control model obtained from the corresponding server of the Internet of Vehicles system, obtains the rate adjustment strategy output by the rate control model, and adjusts the current resource request rate of sending resource requests to the Internet of Vehicles system according to the above-mentioned rate adjustment strategy. This technical solution pre-trains a rate control model through the Internet of Vehicles system and deploys the rate control model on each vehicle in the Internet of Vehicles, so that each vehicle determines the current resource request rate for sending resource requests to the Internet of Vehicles system based on the fairness indicators and state parameter sets of all vehicles. On the one hand, it determines the rate adjustment strategy of the vehicle resource request rate based on the vehicle's fairness indicators, which can achieve fairness in minimizing channel congestion. On the other hand, the rate control model is pre-trained by the Internet of Vehicles system and deployed in each vehicle respectively. Not only can the resource request rate of the vehicle sending resource requests be adjusted in time when channel congestion occurs, but also the computing resources of the vehicle's online training model can be saved, achieving the goal of avoiding channel congestion while ensuring the fairness of minimizing channel congestion, thereby achieving timely communication between vehicles, improving driving safety, and enhancing user experience.

[0133] See also Figure 3 , which is a flow chart of an embodiment of a training rate control model provided in an embodiment of the present application. Figure 3 The process shown in Figure 2 Based on the process shown in the figure, this paper describes how the Internet of Vehicles system is trained to obtain the rate control model. Figure 3 As shown, the process may include the following steps:

[0134] Step 301: Obtain historical fairness indicators corresponding to all vehicles in the Internet of Vehicles system in a preset historical time period, and obtain a set of historical state parameters of all vehicles in the Internet of Vehicles system in the historical time period.

[0135] The above-mentioned historical fairness index refers to the fairness index of vehicles in historical time periods established in this application in order to ensure the fairness of QoS (Quality of Service) of each vehicle.

[0136] The above-mentioned preset historical time period can be a pre-set period of time, which can be ten minutes, twenty minutes, etc. before the current moment, and the embodiment of the present application does not limit this. Among them, the embodiment of the present application does not limit the number of historical time periods, that is, it can be one or more, and the embodiment of the present application does not limit this.

[0137] The above historical state parameter set refers to a set of historical state parameters corresponding to all vehicles included in the Internet of Vehicles system in the historical time period. The above historical state parameters may include but are not limited to: historical location information of vehicles, historical resource request rate of vehicles sending resource requests to the Internet of Vehicles system in the above historical time period, historical resource busy-green ratio of the Internet of Vehicles system in the above historical time period, etc.

[0138] In an embodiment of the present application, in order to prevent channel congestion in the Internet of Vehicles system, the server of the Internet of Vehicles system can detect the channel usage in the Internet of Vehicles system in real time, so as to determine whether channel congestion may occur in the Internet of Vehicles system, and execute this step when it is determined that channel congestion has occurred or is about to occur.

[0139] As an exemplary implementation, the server may first determine the number of resource blocks currently to be allocated in the Internet of Vehicles system, which can be used to characterize the number of channels in the Internet of Vehicles system, that is, one resource block may correspond to one channel or to multiple channels, which is not limited in the present application embodiment. Further, for ease of calculation, one resource block may correspond to one channel.

[0140] At the same time or after determining the number of resource blocks, the number of all current vehicles in the Internet of Vehicles system can be determined. Afterwards, the number of resource blocks and the number of vehicles can be compared to obtain a comparison result, so as to determine whether there is channel congestion in the Internet of Vehicles system based on the comparison result.

[0141] Optionally, when the comparison result indicates that the number of resource blocks is less than the number of vehicles, it means that the number of resource blocks in the connected vehicle system is insufficient to allocate resource blocks to each vehicle, and therefore, it can be determined that there is channel congestion in the connected vehicle system. Based on this, this step can be performed to obtain the historical fairness index corresponding to all vehicles in the connected vehicle system in the historical time period.

[0142] On the contrary, when the comparison result indicates that the number of resource blocks is greater than or equal to the number of vehicles, it means that the number of resource blocks in the connected vehicle system is sufficient to allocate resource blocks to each vehicle. Therefore, it can be determined that there is no channel congestion in the connected vehicle system. Based on this, in order to save system resources, the server may not perform this step to obtain the fairness indicators corresponding to all vehicles in the connected vehicle system in the historical time period.

[0143] In the embodiment of the present application, in order to ensure the fairness of the QoS of each vehicle, the embodiment of the present application can determine a fairness index for all vehicles included in the Internet of Vehicles system. When subsequent steps are performed on this basis, the fairness of each vehicle in the Internet of Vehicles system can be guaranteed. Therefore, when the server trains the rate control model, it can first obtain the historical fairness index corresponding to all vehicles in the Internet of Vehicles system within a preset historical time period.

[0144] As an optional implementation, the above historical fairness index may vary according to the number N of vehicles in the Internet of Vehicles system in a historical time period and the historical resource request rate issued by each vehicle.

[0145] As an exemplary implementation, the server may determine the historical number of all vehicles in the connected vehicle system in the historical time period, and the historical resource request rate at which each vehicle sends resource requests to the connected vehicle system in the historical time period.

[0146] When determining the historical initial resource request rate corresponding to each vehicle, you can refer to Figure 2 Formula (1) of the process shown will not be repeated here.

[0147] On the basis of determining the number of vehicles and the historical initial resource request rate of each vehicle, the execution subject of the embodiment of the present application may input the historical number of vehicles and the historical initial resource request rate into the following formula (VI), thereby obtaining the historical fairness index corresponding to all vehicles in the Internet of Vehicles system in the historical time period:

[0148]

[0149] Among them, N is the number of historical vehicles, and J is t is the historical fairness indicator mentioned above. is the historical initial resource request rate corresponding to the i-th vehicle in the Internet of Vehicles system, and the above t is the preset historical time interval.

[0150] In one embodiment, the set of historical status parameters of all vehicles in the above-mentioned Internet of Vehicles system may include parameters such as the historical resource busy ratio of the Internet of Vehicles system, the historical initial resource request rate of each vehicle sending resource requests to the Internet of Vehicles system within a historical time period, and the historical location information of each vehicle.

[0151] Based on this, as an optional implementation method, when determining the above-mentioned historical resource busy ratio, the historical signal to interference and noise ratio of each resource block in the Internet of Vehicles system can be determined first, and the resource block whose historical signal to interference and noise ratio is greater than a preset historical signal to interference and noise ratio threshold is determined as the historical target resource block.

[0152] Afterwards, the historical number of the above-mentioned historical target resource blocks (for the convenience of description, referred to as the first historical number hereinafter) and the historical number of all resource blocks in the Internet of Vehicles system (for the convenience of description, referred to as the second historical number hereinafter) can be counted.

[0153] Finally, the first historical number may be divided by the second historical number to obtain a historical resource busy ratio corresponding to the Internet of Vehicles system.

[0154] As an optional implementation method, when determining the historical initial resource request rate of each vehicle sending resource requests to the Internet of Vehicles system within a historical time period, the formula in the above formula (1) can be referred to for determination, which will not be repeated here.

[0155] As an optional implementation, when determining the historical location information corresponding to each vehicle, the historical geographic coordinates of each vehicle may be obtained through a preset GPS.

[0156] Furthermore, the server may collect the required data through the drive test unit.

[0157] Based on the above description, after obtaining the above status parameters corresponding to each vehicle, for each vehicle, the historical resource busy ratio, historical initial resource request rate, and historical location information corresponding to the vehicle in the historical time period can be determined as the historical initial parameter subset corresponding to the vehicle.

[0158] On this basis, the historical initial parameter subset corresponding to each vehicle can be classified into a preset state parameter set, so that the historical state parameter set of all devices in the Internet of Vehicles system can be obtained.

[0159] Step 302: Using the above historical fairness indicators and historical state parameter set, reinforcement learning is performed on the preset initial rate control model to obtain a rate control model.

[0160] The above-mentioned rate control model can be a model for adjusting the resource request rate of the vehicle obtained by the server after reinforcement learning of the preset initial rate control model using the historical fairness index and the historical state parameter set.

[0161] The above-mentioned initial rate control model may be a preset reinforcement learning model, which may include an environment state, an execution subject and an execution action.

[0162] In an embodiment of the present application, after obtaining the above-mentioned historical fairness indicators and historical state parameter sets, the server can directly use the above-mentioned historical fairness indicators and historical state parameter sets to perform reinforcement learning on the preset initial rate control model, thereby obtaining a rate control model.

[0163] Furthermore, in order to facilitate determination of the environmental state parameters of the rate control model, the server may classify the above historical fairness indicator as a historical parameter value of each vehicle into the state parameter subset corresponding to the vehicle.

[0164] For example, the historical state parameter subset corresponding to each vehicle can be shown in the following formula (VII), and the final historical state parameter set obtained can be shown in the following formula (VIII):

[0165]

[0166] Among them, the above is the historical state parameter subset of the i-th vehicle in the Internet of Vehicles system. is the historical location information of the i-th vehicle. is the historical initial resource request rate of the i-th vehicle, is the above historical resource busy ratio, and the above J t is the historical fairness indicator mentioned above.

[0167]

[0168] Among them, the above s t is the above historical state parameter set, is the subset of historical state parameters corresponding to the first vehicle in the Internet of Vehicles system. It is the subset of historical state parameters corresponding to the Nth vehicle in the Internet of Vehicles system.

[0169] On this basis, after obtaining the above historical fairness indicators and historical state parameter set, the server can determine the historical risk value of each vehicle according to the historical position information in the above historical state parameter set.

[0170] As an exemplary implementation, the server may determine the historical location information of each vehicle and the historical location information of nearby vehicles, determine the Euclidean distance between the vehicle and the nearby vehicles, and determine whether the Euclidean distance is less than a preset distance threshold. The distance threshold may be obtained by multiplying the minimum reaction time of the vehicle by the vehicle's closest historical speed, and the vehicle's closest historical speed may be the average historical speed of the vehicle detected by the speed sensor, or may be the maximum historical speed, which is not limited in the present embodiment of the application.

[0171] Furthermore, the driving direction of the vehicle can be determined, and the nearby vehicles can be determined based on the driving direction. For example, if the vehicle is driving forward, the nearby vehicles can be the vehicle in front of the vehicle and the vehicle behind the vehicle. For another example, if the vehicle turns right, the nearby vehicles can be the vehicle behind the right side of the vehicle.

[0172] Optionally, if it is less than, it means that the vehicle has a collision risk and the risk value is high, so the risk value can be determined to be 1.

[0173] On the contrary, if the Euclidean distance is greater than the preset distance threshold, it means that the vehicle distance is relatively safe, there is no collision risk, and the risk value is low, so the risk value can be determined to be 0.

[0174] Afterwards, the preset total data packet delivery rate function can be used as the reward function, the historical fairness index and the historical state parameter set as the environmental state, the historical resource busy ratio, historical fairness index, and historical risk value corresponding to the environmental state as the penalty parameter, and the preset rate control strategy set as the execution action to perform reinforcement learning on the preset initial rate control model, thereby obtaining the rate control model.

[0175] As an exemplary implementation, deep reinforcement learning may include three parts: state space, action space, and reward value:

[0176] State space: Its state parameters may include the historical position information of each vehicle. Historical initial resource request rate for each vehicle Historical resource busy ratio And the historical fairness index J t The state parameter can be expressed as The state space can be expressed as

[0177] Action space: Since adjusting the initial resource request rate of the vehicle will affect the congestion state, the action value includes three factors: reducing the initial resource request rate, increasing the initial resource request rate, and maintaining the original value, expressed as a t ={-β,0,β}, corresponding to the above three actions respectively. The action state is expressed as

[0178] Reward value: The reward value is a function of the total packet delivery rate, which is consistent with the objective function. Since each action may affect channel properties such as channel busy ratio, fairness index, and vehicle risk after adjusting the rate, it is necessary to set a penalty value to guide the agent to output "good" actions. If the channel busy ratio is greater than the set threshold, the penalty value is set to σ; if the fairness index is less than the minimum threshold, the penalty value is set to If the vehicle is at high risk of collision, set the penalty value to ρ.

[0179] The total data packet delivery rate function can be expressed as follows:

[0180]

[0181] Among them, the above is the data packet delivery rate of the i-th vehicle, is the data packet successfully received by the i-th vehicle. is the total number of data packets sent by the i-th vehicle.

[0182] Furthermore, since the goal is to adjust the number or time interval of messages sent from N vehicles to maximize the resource request rate of each vehicle, the function that determines the maximum value of the data packet delivery rate in the above formula (IX) can be used as the target reward function.

[0183] Based on the above structure, the intelligent body usually observes the state locally, outputs actions based on the obtained state information, and increases, decreases, or maintains the resource request rate value. After evaluating the channel busy ratio and various indicators, a reward value is obtained. After a period of time, the total reward value is the following formula (10). The purpose of deep reinforcement learning is to find the best strategy for each vehicle to maximize the total reward value, that is, to output a strategy so that each vehicle can output the most appropriate rate control strategy under a specific state to minimize channel congestion.

[0184]

[0185] Among them, the above Sr i t is the total reward value, the above r i t+k is the reward value of vehicle i at time t+k, the above γ t+k is the time decay constant at time t+k.

[0186] Step 303: Send the above rate control model to each vehicle in the Internet of Vehicles system.

[0187] In an embodiment of the present application, after the server obtains the rate control model through reinforcement learning, it can send the above rate control model to each vehicle in the Internet of Vehicles system, so that the vehicle can adjust the initial resource request rate according to the rate control model to avoid channel congestion in the Internet of Vehicles system.

[0188] The technical solution provided in the embodiment of the present application obtains the historical fairness index corresponding to all vehicles in the Internet of Vehicles system in a preset historical time period, and obtains the historical state parameter set of all vehicles in the Internet of Vehicles system in a historical time period, and uses the above historical fairness index and historical state parameter set to perform reinforcement learning on the preset initial rate control model to obtain the rate control model, and sends the above rate control model to each vehicle in the Internet of Vehicles system. This technical solution trains the rate control model offline in different environments on the server, collects data through the road test unit, and then deploys the pre-trained model on each vehicle. The pre-trained model can significantly reduce the computational overhead of online learning, requiring a large number of data sets to cover most traffic conditions, and improves the generalization ability of the rate control model.

[0189] See also Figure 4 , which is a block diagram of an embodiment of a resource request control device for an Internet of Vehicles provided in an embodiment of the present application. Figure 4 The device shown can be applied to a target vehicle, and the target vehicle can be any vehicle in a vehicle networking system. Figure 4 As shown, the device may include:

[0190] An acquisition module 41 is used to acquire the fairness index currently corresponding to all vehicles in the Internet of Vehicles system, and to acquire a set of state parameters of all vehicles in the Internet of Vehicles system;

[0191] An input module 42, configured to input the fairness index and the state parameter set into a rate control model obtained from a server corresponding to the Internet of Vehicles system, to obtain a rate adjustment strategy output by the rate control model;

[0192] The adjustment module 43 is used to adjust the current resource request rate of sending resource requests to the Internet of Vehicles system according to the rate adjustment strategy.

[0193] As a possible implementation, the device further includes (not shown in the figure):

[0194] A first determination module is used to determine the number of resource blocks to be currently allocated in the Internet of Vehicles system;

[0195] A second determination module is used to determine the number of all vehicles currently in the Internet of Vehicles system;

[0196] A comparison module, used for comparing the number of resource blocks with the number of vehicles to obtain a comparison result;

[0197] An execution module is used to execute the step of obtaining the fairness indicators currently corresponding to all vehicles in the Internet of Vehicles system when the comparison result indicates that the number of resource blocks is less than the number of vehicles.

[0198] As a possible implementation manner, the acquisition module 41 is specifically used for:

[0199] Determine the number of all vehicles currently in the Internet of Vehicles system and an initial resource request rate at which each of the vehicles sends resource requests to the Internet of Vehicles system within a preset time interval;

[0200] The number of vehicles and the initial resource request rate are input into the following formula to obtain the fairness index currently corresponding to all vehicles in the Internet of Vehicles system:

[0201]

[0202] Wherein, N is the number of vehicles, J is t is the fairness index, the R i t is the initial resource request rate corresponding to the i-th vehicle in the Internet of Vehicles system, and t is the preset time interval.

[0203] As a possible implementation, the acquisition module 41 is specifically used for:

[0204] Determining a signal-to-noise ratio of each resource block in the Internet of Vehicles system;

[0205] Determine the resource block whose signal-to-noise ratio is greater than a preset signal-to-noise ratio threshold as a target resource block;

[0206] Dividing the first number of the target resource blocks by the second number of all resource blocks in the Internet of Vehicles system to obtain a resource busy ratio corresponding to the Internet of Vehicles system;

[0207] Acquire an initial resource request rate at which each of the vehicles sends resource requests to the Internet of Vehicles system within a preset time interval;

[0208] Obtaining the current position information corresponding to each of the vehicles;

[0209] For each vehicle, determining a resource busy ratio, an initial resource request rate, and the location information corresponding to the vehicle as an initial parameter subset corresponding to the vehicle;

[0210] The initial parameter subset corresponding to each of the vehicles is classified into a preset state parameter set to obtain a state parameter set of all vehicles in the vehicle networking system.

[0211] As a possible implementation, the input module 42 includes:

[0212] The input submodule is used to input the fairness index and the state parameter set into a rate control model pre-acquired from the corresponding server of the Internet of Vehicles system, so that the rate control model performs the following operations:

[0213] Determining a risk value of the target vehicle according to the position information of the target vehicle in the state parameter set;

[0214] A rate adjustment strategy for the target vehicle is determined according to the resource busy ratio, the initial resource request rate, the fairness index, and the risk value, wherein the adjustment of the initial resource request rate in the rate adjustment strategy is proportional to the risk value.

[0215] As a possible implementation, the device further includes (not shown in the figure):

[0216] A data acquisition module, used for the rate control model to be trained by a corresponding server of the Internet of Vehicles system, wherein the server is trained to obtain the rate control model by: obtaining historical fairness indicators corresponding to all vehicles in the Internet of Vehicles system within a preset historical time period, and obtaining a set of historical state parameters of all vehicles in the Internet of Vehicles system within the historical time period;

[0217] A training module, configured to perform reinforcement learning on a preset initial rate control model using the historical fairness index and the historical state parameter set to obtain the rate control model;

[0218] A sending module is used to send the rate control model to each of the vehicles in the Internet of Vehicles system.

[0219] As a possible implementation, the data acquisition module is specifically used to:

[0220] Determine a historical signal-to-noise ratio of each resource block in the Internet of Vehicles system;

[0221] Determine the resource block whose historical signal-to-noise ratio is greater than a preset historical signal-to-noise ratio threshold as a historical target resource block;

[0222] Dividing a first historical number of the historical target resource blocks by a second historical number of all resource blocks in the Internet of Vehicles system, to obtain a historical resource busy ratio corresponding to the Internet of Vehicles system;

[0223] Obtaining a historical initial resource request rate at which each of the vehicles sends resource requests to the Internet of Vehicles system within the historical time period;

[0224] Obtaining historical location information corresponding to each of the vehicles in the historical time period;

[0225] For each vehicle, determining a historical resource busy ratio, a historical initial resource request rate, and the historical location information corresponding to the vehicle as a historical initial parameter subset corresponding to the vehicle;

[0226] The historical initial parameter subset corresponding to each of the vehicles is classified into a preset state parameter set to obtain a historical state parameter set of all vehicles in the vehicle networking system.

[0227] As a possible implementation, the training module is specifically used for:

[0228] Determining a historical risk value of each of the vehicles according to the historical position information in the historical state parameter set;

[0229] The preset total data packet delivery rate function is used as the reward function, the historical fairness index and the historical state parameter set are used as the environmental state, the historical resource busy ratio, the historical fairness index, and the historical risk value corresponding to the environmental state are used as penalty parameters, and the preset rate control strategy set is used as the execution action to perform reinforcement learning on the preset initial rate control model to obtain the rate control model.

[0230] As a possible implementation, the adjustment module 43 is specifically configured to:

[0231] In a case where the rate adjustment strategy indicates increasing the current resource request rate according to a first rate, increasing the current resource request rate by the first rate;

[0232] In a case where the rate adjustment policy indicates reducing the current resource request rate according to a second rate, the current resource request rate is reduced by the second rate.

[0233] like Figure 5 As shown, it is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application, including a processor 51, a communication interface 52, a memory 53 and a communication bus 54, wherein the processor 51, the communication interface 52, and the memory 53 communicate with each other through the communication bus 54.

[0234] A memory 53, for storing computer programs;

[0235] In one embodiment of the present application, the processor 51 is used to execute the program stored in the memory 53 to implement the resource request control method of the Internet of Vehicles provided by any one of the aforementioned method embodiments, including:

[0236] Obtaining fairness indicators currently corresponding to all vehicles in the Internet of Vehicles system, and obtaining a set of state parameters of all vehicles in the Internet of Vehicles system;

[0237] Inputting the fairness index and the state parameter set into a rate control model obtained from a server corresponding to the Internet of Vehicles system to obtain a rate adjustment strategy output by the rate control model;

[0238] The current resource request rate for sending resource requests to the Internet of Vehicles system is adjusted according to the rate adjustment strategy.

[0239] An embodiment of the present application also provides a storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of the resource request control method for the Internet of Vehicles provided in any of the aforementioned method embodiments are implemented.

[0240] The device embodiments described above are merely illustrative, wherein 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 modules may be selected according to actual needs to achieve the purpose of the present embodiment.

[0241] Through the text of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a general hardware platform, and of course, by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the relevant technology can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiment.

[0242] It should be understood that the terms used in the text are only for the purpose of the specific example implementation of the text, and are not intended to be limited. Unless the context clearly indicates otherwise, the singular forms "one", "an" and "said" as used in the text can also be represented to include plural forms. The terms "include", "comprise", "contain", and "have" are inclusive, and therefore specify the existence of the stated features, steps, operations, elements and / or parts, but do not exclude the existence or addition of one or more other features, steps, operations, elements, parts, and / or their combinations. The method steps, processes, and operations of the text in the text are not interpreted as necessarily requiring them to be performed in the specific order of the text or description, unless the execution order is clearly indicated. It should also be understood that additional or alternative steps can be used.

[0243] The foregoing is merely a specific embodiment of the present invention, which enables those skilled in the art to understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features claimed herein.

Claims

1. A resource request control method for an Internet of Vehicles, characterized in that: Applied to a target vehicle, the target vehicle being any vehicle in a vehicle networking system, the method comprises: Obtaining fairness indicators currently corresponding to all vehicles in the Internet of Vehicles system, and obtaining a set of state parameters of all vehicles in the Internet of Vehicles system; Inputting the fairness index and the state parameter set into a rate control model obtained from a server corresponding to the Internet of Vehicles system to obtain a rate adjustment strategy output by the rate control model; The current resource request rate for sending resource requests to the Internet of Vehicles system is adjusted according to the rate adjustment strategy.

2. The method according to claim 1, characterized in that Before obtaining the fairness indicators currently corresponding to all vehicles in the Internet of Vehicles system, the method further includes: Determining the number of resource blocks currently to be allocated in the Internet of Vehicles system; Determining the number of all vehicles currently in the connected vehicle system; Comparing the number of resource blocks with the number of vehicles to obtain a comparison result; When the comparison result indicates that the number of resource blocks is less than the number of vehicles, the step of obtaining the fairness indicators currently corresponding to all vehicles in the Internet of Vehicles system is performed.

3. The method according to claim 1, characterized in that The obtaining of the fairness index currently corresponding to all vehicles in the Internet of Vehicles system includes: Determine the number of all vehicles currently in the Internet of Vehicles system and an initial resource request rate at which each of the vehicles sends resource requests to the Internet of Vehicles system within a preset time interval; The number of vehicles and the initial resource request rate are input into the following formula to obtain the fairness index currently corresponding to all vehicles in the Internet of Vehicles system: Wherein, N is the number of vehicles, J is t is the fairness index, the R i t is the initial resource request rate corresponding to the i-th vehicle in the Internet of Vehicles system, and t is the preset time interval.

4. The method according to claim 1, characterized in that The obtaining of a set of status parameters of all vehicles in the vehicle networking system includes: Determining a signal-to-noise ratio of each resource block in the Internet of Vehicles system; Determine the resource block whose signal-to-noise ratio is greater than a preset signal-to-noise ratio threshold as a target resource block; Dividing the first number of the target resource blocks by the second number of all resource blocks in the Internet of Vehicles system to obtain a resource busy ratio corresponding to the Internet of Vehicles system; Obtaining an initial resource request rate at which each of the vehicles sends resource requests to the Internet of Vehicles system within a preset time interval; Obtaining the current position information corresponding to each of the vehicles; For each vehicle, determining a resource busy ratio, an initial resource request rate, and the location information corresponding to the vehicle as an initial parameter subset corresponding to the vehicle; The initial parameter subset corresponding to each of the vehicles is classified into a preset state parameter set to obtain a state parameter set of all vehicles in the vehicle networking system.

5. The method according to claim 4, characterized in that The step of inputting the fairness index and the state parameter set into a rate control model obtained from a server corresponding to the Internet of Vehicles system to obtain a rate adjustment strategy output by the rate control model includes: The fairness indicator and the state parameter set are input into a rate control model obtained in advance from a corresponding server of the Internet of Vehicles system, so that the rate control model performs the following operations: Determining a risk value of the target vehicle according to the position information of the target vehicle in the state parameter set; A rate adjustment strategy for the target vehicle is determined according to the resource busy ratio, the initial resource request rate, the fairness index, and the risk value, wherein the adjustment of the initial resource request rate in the rate adjustment strategy is proportional to the risk value.

6. The method according to claim 4, characterized in that The rate control model is obtained by training a corresponding server of the Internet of Vehicles system, and the server is trained to obtain the rate control model in the following manner: Obtaining historical fairness indicators corresponding to all vehicles in the Internet of Vehicles system within a preset historical time period, and obtaining a set of historical state parameters of all vehicles in the Internet of Vehicles system within the historical time period; Using the historical fairness index and the historical state parameter set, reinforcement learning is performed on a preset initial rate control model to obtain the rate control model; The method further comprises: The rate control model is sent to each of the vehicles in the vehicle networking system.

7. The method according to claim 6, characterized in that The obtaining of a set of historical status parameters of all vehicles in the Internet of Vehicles system in a preset historical time period includes: Determine a historical signal-to-noise ratio of each resource block in the Internet of Vehicles system; Determine the resource block whose historical signal-to-noise ratio is greater than a preset historical signal-to-noise ratio threshold as a historical target resource block; Dividing a first historical number of the historical target resource blocks by a second historical number of all resource blocks in the Internet of Vehicles system, to obtain a historical resource busy ratio corresponding to the Internet of Vehicles system; Obtaining a historical initial resource request rate at which each of the vehicles sends resource requests to the Internet of Vehicles system within the historical time period; Obtaining historical location information corresponding to each of the vehicles in the historical time period; For each vehicle, determining a historical resource busy ratio, a historical initial resource request rate, and the historical location information corresponding to the vehicle as a historical initial parameter subset corresponding to the vehicle; The historical initial parameter subset corresponding to each of the vehicles is classified into a preset state parameter set to obtain a historical state parameter set of all vehicles in the vehicle networking system.

8. The method according to claim 7, characterized in that The method of using the historical fairness index and the historical state parameter set to perform reinforcement learning on a preset initial rate control model to obtain the rate control model includes: Determining a historical risk value of each of the vehicles according to the historical position information in the historical state parameter set; The preset total data packet delivery rate function is used as the reward function, the historical fairness index and the historical state parameter set are used as the environmental state, the historical resource busy ratio, the historical fairness index, and the historical risk value corresponding to the environmental state are used as penalty parameters, and the preset rate control strategy set is used as the execution action to perform reinforcement learning on the preset initial rate control model to obtain the rate control model.

9. The method according to claim 1, characterized in that: The adjusting the current resource request rate of sending resource requests to the Internet of Vehicles system according to the rate adjustment strategy includes: In a case where the rate adjustment strategy indicates increasing the current resource request rate according to a first rate, increasing the current resource request rate by the first rate; In a case where the rate adjustment policy indicates reducing the current resource request rate according to a second rate, the current resource request rate is reduced by the second rate.

10. A resource request control device for an Internet of Vehicles, characterized in that: Applied to a target vehicle, the target vehicle is any vehicle in a vehicle networking system, and the device comprises: An acquisition module, used to acquire the fairness indicators currently corresponding to all vehicles in the Internet of Vehicles system, and to acquire a set of state parameters of all vehicles in the Internet of Vehicles system; An input module, configured to input the fairness index and the state parameter set into a rate control model obtained from a server corresponding to the Internet of Vehicles system, to obtain a rate adjustment strategy output by the rate control model; An adjustment module is used to adjust a current resource request rate of sending resource requests to the Internet of Vehicles system according to the rate adjustment strategy.

Images