Vehicle-mounted terminal network delay optimization method and device, equipment and storage medium

Abstract

The invention relates to the technical field of Internet of Vehicles, in particular to a vehicle-mounted terminal network delay optimization method, device and equipment and a storage medium, and the method comprises the steps: carrying out the clustering of each vehicle-mounted terminal based on the task information of each vehicle-mounted terminal, and obtaining a sensing terminal cluster and a calculation intensive terminal cluster; respectively matching at least one subcarrier for each compute-intensive terminal in the compute-intensive terminal cluster for task transmission; determining the computing dense terminal with the minimum channel interference with the sensing terminal in the sensing terminal cluster from the computing dense terminal cluster as a subcarrier multiplexing terminal, and controlling the sensing terminal to multiplex a subcarrier matched with the corresponding subcarrier multiplexing terminal for task transmission; and determining transmission information during task transmission between each computing intensive terminal and each sensing terminal, and based on the transmission information and a time delay optimization network, generating vehicle-mounted terminal target control information. According to the invention, the communication time delay, the task processing time delay, the communication energy consumption and the task processing energy consumption of the whole Internet of Vehicles can be effectively reduced.

Description

Technical Field

[0001] The present application relates to the field of vehicle networking technology, and in particular to a method, device, equipment and storage medium for optimizing vehicle-mounted terminal network delay. Background Art

[0002] In recent years, with the in-depth research on fifth- and sixth-generation mobile communication technologies, integrated sensing, communication, and computation (ISCC) technology has forced the Internet of Vehicles (IoV) environment to become increasingly complex. Furthermore, the continuous integration and innovation of artificial intelligence (AI) technology with the IoV has diversified intelligent applications, promoting the implementation of a series of computationally intensive applications such as digital twin (DT) monitoring platforms, autonomous driving, and real-time navigation, thereby reducing traffic accident rates and improving transmission efficiency and security. However, meeting the growing computing demand also poses significant challenges to the support capabilities and service quality of the intelligent IoV, including the economic cost, energy consumption, and processing power of on-board terminals.

[0003] In traditional vehicle-road-cloud collaborative Internet of Vehicles research, cloud servers rely on their powerful computing capabilities to provide computing services for computing-intensive tasks on vehicle terminals, thereby greatly improving the utilization rate and computing performance of computing resources; however, the communication delay, task processing delay, communication energy consumption, and task processing energy consumption of the entire Internet of Vehicles are relatively high.

[0004] At present, one way to reduce communication delay, task processing delay, communication energy consumption, and task processing energy consumption is to perform system modeling on the obtained open source data set (transmission channel model and transmission channel characteristics) to obtain initial time slot control information, wherein the initial time slot control information is the control information for controlling each vehicle-mounted terminal in the Internet of Vehicles network in a time slot, and the control information specifically includes task offloading decision, vehicle-mounted terminal transmission power, computing resources, and communication resources; then, the initial time slot control information is optimized through a preset optimization algorithm, such as an ant colony algorithm, to obtain the optimal solution as the target time slot control information; the target time slot control information is used to control each vehicle-mounted terminal in the next time slot, thereby reducing the communication delay, task processing delay, communication energy consumption, and task processing energy consumption of the entire Internet of Vehicles.

[0005] However, due to the high complexity and slow convergence speed of the optimization algorithm, the above method will cause the communication delay, task processing delay, communication energy consumption and task processing energy consumption of the entire Internet of Vehicles to remain high. Summary of the Invention

[0006] In order to effectively reduce the communication delay, task processing delay, communication energy consumption, and task processing energy consumption of the entire Internet of Vehicles, the present application provides a vehicle-mounted terminal network delay optimization method, device, equipment, and storage medium.

[0007] In a first aspect, the present application provides a method for optimizing network delay of an in-vehicle terminal, comprising:

[0008] Clustering each of the vehicle-mounted terminals based on their task information to obtain a perception terminal cluster and a computationally intensive terminal cluster;

[0009] Matching at least one subcarrier for each computing-intensive terminal in the computing-intensive terminal cluster to perform task transmission;

[0010] Determine, from the computing-intensive terminal cluster, a computing-intensive terminal with the smallest channel interference with a sensing terminal in the sensing terminal cluster, as a subcarrier multiplexing terminal, and control the sensing terminal to multiplex the subcarrier matched with the corresponding subcarrier multiplexing terminal for task transmission;

[0011] Determine the transmission information when each of the computing-intensive terminals and each of the perception terminals transmits tasks, and generate vehicle-mounted terminal target control information based on the transmission information and the delay optimization network.

[0012] In a second aspect, the present application provides a vehicle-mounted terminal network delay optimization device, comprising:

[0013] A terminal clustering module, configured to cluster each vehicle-mounted terminal based on its task information to obtain a perception terminal cluster and a computationally intensive terminal cluster;

[0014] A carrier matching module, configured to match at least one subcarrier for each computing-intensive terminal in the computing-intensive terminal cluster to perform task transmission;

[0015] A carrier multiplexing module is used to determine, from the computing-intensive terminal cluster, a computing-intensive terminal with the smallest channel interference with the sensing terminal in the sensing terminal cluster as a subcarrier multiplexing terminal, and control the sensing terminal to multiplex the subcarrier matched by the corresponding subcarrier multiplexing terminal for task transmission;

[0016] The information generation module is used to determine the transmission information when each of the computing-intensive terminals and each of the perception terminals transmits tasks, and generate vehicle-mounted terminal target control information based on the transmission information and the delay optimization network.

[0017] In a third aspect, the present application provides a computer device, which includes a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps in the above method when executing the computer program.

[0018] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which implements the steps in the above-mentioned method when executed by a processor.

[0019] In a fifth aspect, the present application further provides a computer program product, which includes a computer program that implements the steps of any of the above method embodiments when executed by a processor.

[0020] The above-mentioned vehicle-mounted terminal network delay optimization method, device, equipment and storage medium cluster each vehicle-mounted terminal based on the task information of each vehicle-mounted terminal to obtain a perception terminal cluster and a computing-intensive terminal cluster; match at least one subcarrier for each computing-intensive terminal in the computing-intensive terminal cluster for task transmission; determine the computing-intensive terminal with the smallest channel interference with the perception terminals in the perception terminal cluster from the computing-intensive terminal cluster, as the subcarrier multiplexing terminal, control the perception terminal to multiplex the corresponding subcarrier multiplexing terminal matched with the subcarrier for task transmission; determine the transmission information when each computing-intensive terminal and each perception terminal perform task transmission, and generate vehicle-mounted terminal target control information based on the transmission information and the delay optimization network. Through the above implementation, each perception terminal reuses the subcarrier of the computationally intensive terminal with the least interference with its channel when performing task transmission. This can fully reduce the signal interference of the entire vehicle terminal network during task transmission, thereby reducing the transmission delay of the entire vehicle terminal network. In addition, the delay optimization network takes reducing the transmission delay of the entire vehicle terminal network as the optimization goal, processes the transmission information of each vehicle terminal to generate vehicle terminal target control information, and controls the task transmission process of each vehicle terminal in the next time slot through the vehicle terminal target control information, which can further fully reduce the transmission delay of the vehicle terminal network. Through these two aspects of delay reduction measures, the communication delay, task processing delay, communication energy consumption, and task processing energy consumption of the entire vehicle network can be effectively reduced.

[0021] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments. It should be understood that the following drawings only illustrate certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can be obtained based on these drawings without paying any creative work.

[0023] Figure 1 This is a flow chart of a vehicle terminal network delay optimization method provided in an embodiment of the present application;

[0024] Figure 2 A schematic diagram of a vehicle network structure provided in an embodiment of the present application;

[0025] Figure 3 This is a structural diagram of a vehicle-mounted terminal network delay optimization device provided in an embodiment of the present application;

[0026] Figure 4 A schematic diagram of the structure of a computer device provided in an embodiment of the present application;

[0027] Figure 5 This is a diagram of the internal structure of a computer-readable storage medium provided in an embodiment of the present application. DETAILED DESCRIPTION

[0028] In order to make the purpose, technical solutions and advantages of the present disclosure more clearly understood, the present disclosure is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present disclosure and are not intended to limit the present disclosure.

[0029] It should be noted that the terms "first," "second," and the like in the specification and claims herein and in the accompanying drawings are used to distinguish similar objects and are not necessarily used to describe a particular order or precedence. It should be understood that the terms used in this manner are interchangeable where appropriate so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having," as well as any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, apparatus, product, or device comprising a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units that are not explicitly listed or that are inherent to these processes, methods, products, or devices.

[0030] In this document, the term "and / or" simply describes a relationship between related objects, indicating that three possible relationships exist. For example, "A and / or B" could mean: A exists alone, A and B exist simultaneously, or B exists alone. Furthermore, the character " / " in this document generally indicates an "or" relationship between the related objects.

[0031] Example 1

[0032] Figure 1 This is a flow chart of a vehicle terminal network delay optimization method provided in Example 1 of this application, refer to Figure 1The method may be performed by a device for performing the method, and the device may be implemented by software and / or hardware. The method includes:

[0033] S110 , clustering the vehicle-mounted terminals based on task information of the vehicle-mounted terminals to obtain a perception terminal cluster and a computationally intensive terminal cluster.

[0034] Among them, vehicles on the road sometimes require higher computing resources to meet their high real-time computing needs. For example, the high real-time computing needs are to process the collected road images to generate real-time maps. The computing resources of the vehicle itself are limited, and it is difficult to meet the high real-time computing needs while ensuring low computing latency. Therefore, this embodiment provides a method such as Figure 2 The Internet of Vehicles network shown in the figure includes several edge computing terminals arranged on one side of the road and on-board terminals in vehicles that are communicatively connected to the edge computing terminals; wherein the edge computing terminals are composed of a roadside unit (RSU) and a server that is communicatively connected to the roadside unit, and the server is a MEC server / digital twin server.

[0035] Taking one of the edge computing terminals as an example, the roadside unit in the edge computing terminal has its signal coverage range, which is Figure 2 In the oval dotted area on the road shown, the vehicle terminals of each vehicle within the signal coverage range can form a vehicle terminal network; for example, the vehicle terminal is the vehicle computer. Taking a vehicle terminal network as an example, within a time slot, any two vehicle terminals in the vehicle terminal network can directly establish a communication network such as Figure 2 As shown, a V2V (vehicle-to-vehicle) uplink is provided, and one of the vehicle-mounted terminals can transmit a task to another vehicle-mounted terminal through the V2V uplink. For example, the task can be detection information detected by the vehicle sending the task through its vehicle-mounted detector. For example, the detection information is vehicle-mounted radar detection data, etc., which is not specifically limited.

[0036] It should be noted that when the task to be processed by the vehicle terminal in the vehicle terminal network does not require high computing resources, the task is directly sent to another vehicle terminal through the V2V uplink; if the task to be processed by the vehicle terminal requires high computing resources and needs to ensure low processing latency, the vehicle terminal and the edge computing end are established as follows: Figure 2 The V2I (vehicle-to-infrastructure) uplink shown offloads its tasks to the edge computing end for processing. Since the edge computing end usually has more powerful computing resources, it can ensure low latency in processing this task. For example, this task is to calculate the collected radar point cloud in real time and build the corresponding real-time map.

[0037] Taking one of the tasks as an example, when the task is generated, it is accompanied by corresponding task information. For example, the task information includes: task type, task size, computing power required for the task, etc.; the task information can be used to determine whether the corresponding task requires higher computing resources; if not, it means that the corresponding task does not require higher computing resources. Generally, this type of task is suitable for the vehicle-mounted terminal that needs to send the task to directly send the task to another vehicle-mounted terminal through the V2V uplink, and this type of task is recorded as a perception task; if yes, it means that the corresponding task requires higher computing resources. Generally, this type of task is suitable for the vehicle-mounted terminal that needs to send the task to the edge computing end for processing through the V2I uplink, and this type of task is recorded as a computing-intensive task.

[0038] In order to reduce the communication delay and task processing delay of the entire Internet of Vehicles network, it is necessary to first determine the vehicle terminals that send perception tasks and the vehicle terminals that send computing-intensive tasks in the vehicle terminal network. To this end, it is necessary to cluster the vehicle terminals in the vehicle terminal network; taking a vehicle terminal as an example, if the task information of the task sent by the vehicle terminal determines that the task does not require higher computing resources, the vehicle terminal is clustered to the perception terminal cluster; if the task information of the task sent by the vehicle terminal determines that the task requires higher computing resources, the vehicle terminal is clustered to the computing-intensive terminal cluster.

[0039] S120: Match at least one subcarrier for each computation-intensive terminal in the computation-intensive terminal cluster to perform task transmission.

[0040] Among them, each vehicle-mounted terminal in the computing-intensive terminal cluster is recorded as a computing-intensive terminal. When the computing-intensive terminal sends a task to the edge computing end through the V2V uplink, it needs to use the corresponding carrier, and the carrier is recorded as a subcarrier. In this embodiment, each computing-intensive terminal in the computing-intensive terminal cluster is matched with at least one subcarrier. In order to prevent the subcarriers from interfering with each other, the subcarriers in this embodiment are orthogonal to each other.

[0041] S130. Determine, from the computing-intensive terminal cluster, a computing-intensive terminal with the least channel interference with the perception terminals in the perception terminal cluster as a subcarrier multiplexing terminal, and control the perception terminal to multiplex the subcarriers matched by the corresponding subcarrier multiplexing terminal for task transmission.

[0042] Among them, each vehicle-mounted terminal in the perception terminal cluster is recorded as a perception terminal. The perception terminal may use the corresponding subcarrier when performing task transmission. In this embodiment, the subcarrier required by the perception terminal needs to be selected from the subcarriers matched by the above-mentioned computing-intensive terminals; taking one of the perception terminals as an example, if the subcarrier used by the perception terminal is consistent with the subcarrier used by one of the computing-intensive terminals, if the time of the transmission tasks of the two overlaps, there will be channel interference between each other; in order to reduce the channel interference to the minimum, it is necessary to first determine the computing-intensive terminal with the least channel interference with the perception terminals in the perception terminal cluster from the computing-intensive terminal cluster, and record the computing-intensive terminal as a subcarrier multiplexing terminal; subsequently, when the perception terminal performs task transmission, the subcarrier matched by the subcarrier multiplexing terminal can be used.

[0043] Specifically, taking a perception terminal as an example, the channel interference between the perception terminal and each computationally intensive terminal in the computationally intensive terminal cluster is calculated respectively to obtain a channel interference set, and then the minimum channel interference is determined from the channel interference set as the target channel interference. After that, the computationally intensive terminal corresponding to the target channel interference is determined as the subcarrier multiplexing terminal.

[0044] S140. Determine the transmission information when each of the computationally intensive terminals and each of the perception terminals transmit tasks, and generate vehicle-mounted terminal target control information based on the transmission information and the delay optimization network.

[0045] Among them, each computing-intensive terminal and each perception terminal can extract the transmission information corresponding to the task when transmitting the task. For example, the transmission information includes the task, task size, task type, computing power required for the task, and vehicle terminal location, etc.; this embodiment presets a delay optimization network for processing the transmission information. When processing the transmission information, the delay optimization network optimizes the transmission delay of the entire vehicle network as the optimization goal, and continuously iterates the vehicle terminal control information generated by the transmission information until the transmission delay is minimized, thereby obtaining the final vehicle terminal control information, and the final generated vehicle terminal control information is recorded as the vehicle terminal target control information.

[0046] It should be noted that this embodiment clusters each vehicle-mounted terminal based on the task information of each vehicle-mounted terminal to obtain a perception terminal cluster and a computing-intensive terminal cluster; matches at least one subcarrier for each computing-intensive terminal in the computing-intensive terminal cluster for task transmission; determines from the computing-intensive terminal cluster the computing-intensive terminal with the least channel interference with the perception terminals in the perception terminal cluster, and controls the perception terminal to multiplex the corresponding subcarrier multiplexing terminal matched with the subcarrier for task transmission; determines the transmission information when each computing-intensive terminal and each perception terminal perform task transmission, and generates vehicle-mounted terminal target control information based on the transmission information and the delay optimization network. Through the above implementation, each perception terminal reuses the subcarrier of the computationally intensive terminal with the least interference with its channel when performing task transmission. This can fully reduce the signal interference of the entire vehicle terminal network during task transmission, thereby reducing the transmission delay of the entire vehicle terminal network. In addition, the delay optimization network takes reducing the transmission delay of the entire vehicle terminal network as the optimization goal, processes the transmission information of each vehicle terminal to generate vehicle terminal target control information, and controls the task transmission process of each vehicle terminal in the next time slot through the vehicle terminal target control information, which can further fully reduce the transmission delay of the vehicle terminal network. Through these two aspects of delay reduction measures, the communication delay, task processing delay, communication energy consumption, and task processing energy consumption of the entire vehicle network can be effectively reduced.

[0047] Example 2

[0048] A second embodiment of the present application provides a method for optimizing vehicle terminal network latency. This method optimizes the method of "clustering each vehicle terminal based on its task information to obtain a perception terminal cluster and a computation-intensive terminal cluster" in the first embodiment. It should be noted that for portions not described in detail in this embodiment, reference may be made to the descriptions of other embodiments. The method includes:

[0049] S211 . Extract corresponding task types from task information of each vehicle-mounted terminal, where the task types include perception-based tasks and computation-intensive tasks.

[0050] For example, the task information accompanying a task includes the task type. In this embodiment, the task types include perception-based tasks and computation-intensive tasks. In other embodiments, the specific types are not limited. Perception-based tasks are suitable for direct transmission and processing between any two vehicle networks in the vehicle terminal network, while computation-intensive tasks are suitable for first being sent from the vehicle terminal to the edge computing end, where they are processed with the edge computing end's stronger computing resources to ensure low latency in processing.

[0051] S212: Cluster the corresponding vehicle-mounted terminals based on the task types to obtain a perception terminal cluster and a computationally intensive terminal cluster.

[0052] Among them, the task information attached to each task includes the task type. Taking a task as an example, the task type in the task information attached to it is extracted. In response to the task type being a perception-type task, the vehicle-mounted terminal responsible for sending the task will be clustered into the perception terminal cluster. In response to the task type being a computation-intensive task, the vehicle-mounted terminal responsible for sending the task will be clustered into the computation-intensive terminal cluster.

[0053] S220: Match at least one subcarrier for each computation-intensive terminal in the computation-intensive terminal cluster to perform task transmission.

[0054] S230. Determine, from the computing-intensive terminal cluster, a computing-intensive terminal with the least channel interference with the perception terminals in the perception terminal cluster as a subcarrier multiplexing terminal, and control the perception terminal to multiplex the subcarriers matched by the corresponding subcarrier multiplexing terminal for task transmission.

[0055] S240. Determine the transmission information when each of the computationally intensive terminals and each of the perception terminals transmit tasks, and generate vehicle-mounted terminal target control information based on the transmission information and the delay optimization network.

[0056] Example 3

[0057] A vehicle-mounted terminal network delay optimization method is provided in a third embodiment of the present application. This method optimizes the "matching at least one subcarrier for each computing-intensive terminal in the computing-intensive terminal cluster for task transmission" in the first embodiment. It should be noted that for portions not described in detail in this embodiment, reference may be made to the descriptions of other embodiments. The method includes:

[0058] S310 , clustering the vehicle-mounted terminals based on task information of the vehicle-mounted terminals to obtain a perception terminal cluster and a computationally intensive terminal cluster.

[0059] S321. Determine the computing power required for the task of each computing-intensive terminal based on the task information of each computing-intensive terminal in the computing-intensive terminal cluster.

[0060] For example, a computationally intensive terminal sends a task with accompanying task information. By extracting this task information, the required computing power can be extracted. The required computing power of a task represents the amount of computing power consumed by the computing device to process the task.

[0061] S322: Cluster the computing-intensive terminals based on the computing power required for the tasks of the computing-intensive terminals and the remaining computing power of the edge computing terminal to obtain a non-local terminal cluster.

[0062] It should be noted that the computing power resources of the edge computing end are also limited. If each computing-intensive terminal sends a large number of tasks, the remaining computing power of the edge computing end may not be able to meet the computing power required for the tasks of the computing-intensive terminals in the later order. At this time, the edge computing end cannot process the tasks of the computing-intensive terminal. The edge computing end can only process the tasks locally and cluster the edge computing end into a local terminal cluster; if the remaining computing power of the edge computing end can meet the computing power required for the tasks of the computing-intensive terminal, the edge computing end can be clustered into a non-local terminal cluster, and each vehicle-mounted terminal in the non-local terminal cluster is recorded as a non-local terminal, and the tasks of each non-local terminal can be processed normally by the edge computing end.

[0063] S323: Based on the number of non-local terminals in the non-local terminal cluster and a preset transmission bandwidth, match at least one subcarrier for each non-local terminal to perform task transmission.

[0064] Among them, there are a certain number of non-local terminals in the non-local terminal cluster. In order to enable each non-local terminal to transmit tasks, it is necessary to match at least one subcarrier for each non-local terminal. To match subcarriers for the non-local terminals, this embodiment presets a transmission bandwidth and uses orthogonal multiple access to allocate subcarriers to the transmission bandwidth, thereby matching at least one subcarrier for each non-local terminal.

[0065] S330. Determine, from the computing-intensive terminal cluster, a computing-intensive terminal with the least channel interference with the perception terminals in the perception terminal cluster as a subcarrier multiplexing terminal, and control the perception terminal to multiplex the subcarriers matched by the corresponding subcarrier multiplexing terminal for task transmission.

[0066] S340. Determine the transmission information when each of the computing-intensive terminals and each of the perception terminals transmits tasks, and generate vehicle-mounted terminal target control information based on the transmission information and the delay optimization network.

[0067] Example 4

[0068] A fourth embodiment of the present application provides a method for optimizing network delay of an in-vehicle terminal. This method optimizes the step of "determining, from the computing-intensive terminal cluster, a computing-intensive terminal with minimal channel interference with a sensing terminal in the sensing terminal cluster, as a subcarrier multiplexing terminal" in the third embodiment. It should be noted that for portions not described in detail in this embodiment, reference may be made to the descriptions of other embodiments. The method includes:

[0069] S410 , clustering the vehicle-mounted terminals based on task information of the vehicle-mounted terminals to obtain a perception terminal cluster and a computation-intensive terminal cluster.

[0070] S421: Determine the computing power required for the task of each computing-intensive terminal based on the task information of each computing-intensive terminal in the computing-intensive terminal cluster.

[0071] S422: Cluster the computing-intensive terminals based on the computing power required for the tasks of the computing-intensive terminals and the remaining computing power of the edge computing terminal to obtain a non-local terminal cluster.

[0072] S423: Based on the number of non-local terminals in the non-local terminal cluster and a preset transmission bandwidth, match at least one subcarrier for each non-local terminal to perform task transmission.

[0073] S431. Based on the subcarriers matched to each of the non-local terminals in the computing-intensive terminal cluster, the communication distance between the perception terminals in the perception terminal cluster and each of the non-local terminals in the computing-intensive terminal cluster, the antenna heights and the speed of light of the perception terminals in the perception terminal cluster and each of the non-local terminals in the computing-intensive terminal cluster, the channel interference between the perception terminals in the perception terminal cluster and each of the non-local terminals in the computing-intensive terminal cluster is calculated respectively to obtain a channel interference set.

[0074] Among them, the perception terminal in the perception terminal cluster needs to select a subcarrier from the subcarriers allocated to each computing-intensive terminal as the subcarrier required for its transmission task, but it is necessary to ensure that the selected subcarrier has the least interference with the corresponding computing-intensive terminal during task transmission. To this end, it is necessary to first calculate the channel interference between the perception terminal and each computing-intensive terminal; taking a perception terminal and a computing-intensive terminal as an example, to calculate the channel interference between the two, it is necessary to first determine the subcarrier matched by the computing-intensive terminal, the communication distance between the perception terminal and the computing-intensive terminal, the antenna height of the perception terminal and the computing-intensive terminal, and the speed of light, and then use the preset channel interference calculation formula to calculate the channel interference between the two; the channel interference between the perception terminal and each computing-intensive terminal is calculated separately in the above manner as a channel interference set.

[0075] S432: Use the non-local terminal corresponding to the minimum channel interference in the channel interference set as a subcarrier multiplexing terminal.

[0076] The subcarrier multiplexing terminal is a non-local terminal corresponding to the smallest channel interference in the channel interference set.

[0077] S433: Control the perception terminal to multiplex the corresponding subcarriers and the subcarriers matched by the multiplexing terminal to perform task transmission.

[0078] S440. Determine the transmission information when each of the computationally intensive terminals and each of the perception terminals transmits tasks, and generate vehicle-mounted terminal target control information based on the transmission information and the delay optimization network.

[0079] Example 5

[0080] A fifth embodiment of the present application provides a method for optimizing network latency of an in-vehicle terminal. This method optimizes the "determining transmission information when each computing-intensive terminal and each sensing terminal perform task transmission" in the first embodiment. It should be noted that for portions not described in detail in this embodiment, reference may be made to the descriptions of other embodiments. The method includes:

[0081] S510 , clustering the vehicle-mounted terminals based on task information of the vehicle-mounted terminals to obtain a perception terminal cluster and a computationally intensive terminal cluster.

[0082] S520: Match at least one subcarrier for each computation-intensive terminal in the computation-intensive terminal cluster to perform task transmission.

[0083] S530. Determine, from the computing-intensive terminal cluster, a computing-intensive terminal with the least channel interference with the perception terminals in the perception terminal cluster as a subcarrier multiplexing terminal, and control the perception terminal to multiplex the subcarriers matched by the corresponding subcarrier multiplexing terminal for task transmission.

[0084] S541. In response to the update of the digital twins corresponding to each of the computing-intensive terminals and each of the sensing terminals in the current time slot, transmission information of the vehicle-mounted terminals corresponding to each of the digital twins when performing task transmission is obtained respectively.

[0085] Among them, taking an edge computing end as an example, the roadside unit in the edge computing end is communicatively connected to the server, and the server stores the digital twin of the vehicle-mounted terminal that is communicatively connected to the edge computing end; the method shown in this embodiment occurs in one of several time slots, and in response to the current moment reaching the end moment of the time slot, the digital twin in the server needs to be updated once; the digital twin can provide transmission information of the task corresponding to the time slot. In this embodiment, the transmission information includes: task, task size, computing power required for the task, task type, and vehicle-mounted terminal location; in other embodiments, there is no specific limitation.

[0086] S542. Generate vehicle terminal target control information based on the transmission information and the delay optimization network.

[0087] Example 6

[0088] A sixth embodiment of the present application provides a method for optimizing vehicle-mounted terminal network delay. This method optimizes the "generating vehicle-mounted terminal target control information based on the transmission information and the delay optimization network" in the first embodiment. It should be noted that for portions not described in detail in this embodiment, reference may be made to the descriptions of other embodiments. The method includes:

[0089] S610 , clustering the vehicle-mounted terminals based on task information of the vehicle-mounted terminals to obtain a perception terminal cluster and a computationally intensive terminal cluster.

[0090] S620: Match at least one subcarrier for each computation-intensive terminal in the computation-intensive terminal cluster to perform task transmission.

[0091] S630. Determine, from the computing-intensive terminal cluster, a computing-intensive terminal with the least channel interference with the perception terminals in the perception terminal cluster as a subcarrier multiplexing terminal, and control the perception terminal to multiplex the subcarriers matched by the corresponding subcarrier multiplexing terminal for task transmission.

[0092] S641. Determine transmission information when each of the computing-intensive terminals transmits tasks to each of the sensing terminals.

[0093] S642. Process the transmission information based on the delay optimization network to obtain initial control information of the vehicle terminal.

[0094] In this example, the delay optimization network consists of two networks. The delay optimization network includes a control information generation network and a scoring network. The control information generation network is used to process transmission information and preliminarily generate initial control information for the vehicle terminal. In this embodiment, the initial control information of the vehicle terminal includes task offloading decision, vehicle terminal transmission power, edge computing resources, and communication resources. The task offloading decision is used to indicate whether the corresponding vehicle terminal needs to offload the task to the edge computing end for processing in the next time slot. The vehicle terminal transmission power is used to indicate the transmission power of the vehicle terminal corresponding to the next time slot when transmitting the task. The edge computing resources indicate the edge computing resources (edge ​​computing end and computing power required for the task, etc.) required to be allocated for the task transmitted by the vehicle terminal corresponding to the next time slot. The communication resources indicate the communication resources (subcarriers, etc.) required to be allocated for the task transmitted by the vehicle terminal corresponding to the next time slot.

[0095] S643. Iteratively optimize the initial control information of the vehicle terminal based on the delay optimization network to obtain target control information of the vehicle terminal.

[0096] It should be noted that the scoring network in the delay optimization network is used to process the initial control information of the vehicle terminal and generate a score corresponding to the initial control information of the vehicle terminal. The score is used to evaluate the transmission delay caused by using the initial control information of the vehicle terminal to control the entire Internet of Vehicles network in the next time slot; if the transmission delay is high, the control information generation network in the delay optimization network continues to iteratively generate new initial control information of the vehicle terminal until the transmission delay is as low as expected, and the initial control information of the vehicle terminal obtained by the iterative update at this time is recorded as the target control information of the vehicle terminal.

[0097] It should be understood that, although the various steps in the flowcharts involved in the various embodiments described above are displayed in sequence according to the instructions of the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be executed in other orders. Moreover, at least a portion of the steps in the flowcharts involved in the various embodiments described above can include multiple steps or multiple stages, and these steps or stages are not necessarily executed and completed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a portion of steps or stages in other steps.

[0098] Example 7

[0099] Based on the same inventive concept, this embodiment also provides an on-vehicle terminal network delay optimization device for implementing the above-mentioned on-vehicle terminal network delay optimization method. The solution provided by this device is similar to the solution described in the above-mentioned method. Therefore, the specific limitations of one or more of the following embodiments of the on-vehicle terminal network delay optimization device can be found in the above-mentioned limitations of the on-vehicle terminal network delay optimization method and will not be repeated here.

[0100] In this embodiment, Figure 3 As shown, a vehicle-mounted terminal network delay optimization device is provided, comprising:

[0101] A terminal clustering module, configured to cluster each vehicle-mounted terminal based on its task information to obtain a perception terminal cluster and a computationally intensive terminal cluster;

[0102] A carrier matching module, configured to match at least one subcarrier for each computing-intensive terminal in the computing-intensive terminal cluster to perform task transmission;

[0103] A carrier multiplexing module is used to determine, from the computing-intensive terminal cluster, a computing-intensive terminal with the smallest channel interference with the sensing terminal in the sensing terminal cluster as a subcarrier multiplexing terminal, and control the sensing terminal to multiplex the subcarrier matched by the corresponding subcarrier multiplexing terminal for task transmission;

[0104] The information generation module is used to determine the transmission information when each of the computing-intensive terminals and each of the perception terminals transmits tasks, and generate vehicle-mounted terminal target control information based on the transmission information and the delay optimization network.

[0105] Each module in the aforementioned vehicle-mounted terminal network delay optimization device can be implemented in whole or in part through software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in hardware form, or stored in a computer device memory in software form, so that the processor can call and execute the corresponding operations of each module.

[0106] It should be noted that this embodiment clusters each vehicle-mounted terminal based on the task information of each vehicle-mounted terminal to obtain a perception terminal cluster and a computing-intensive terminal cluster; matches at least one subcarrier for each computing-intensive terminal in the computing-intensive terminal cluster for task transmission; determines from the computing-intensive terminal cluster the computing-intensive terminal with the least channel interference with the perception terminals in the perception terminal cluster, and controls the perception terminal to multiplex the corresponding subcarrier multiplexing terminal matched with the subcarrier for task transmission; determines the transmission information when each computing-intensive terminal and each perception terminal perform task transmission, and generates vehicle-mounted terminal target control information based on the transmission information and the delay optimization network. Through the above implementation, each perception terminal reuses the subcarrier of the computationally intensive terminal with the least interference with its channel when performing task transmission. This can fully reduce the signal interference of the entire vehicle terminal network during task transmission, thereby reducing the transmission delay of the entire vehicle terminal network. In addition, the delay optimization network takes reducing the transmission delay of the entire vehicle terminal network as the optimization goal, processes the transmission information of each vehicle terminal to generate vehicle terminal target control information, and controls the task transmission process of each vehicle terminal in the next time slot through the vehicle terminal target control information, which can further fully reduce the transmission delay of the vehicle terminal network. Through these two aspects of delay reduction measures, the communication delay, task processing delay, communication energy consumption, and task processing energy consumption of the entire vehicle network can be effectively reduced.

[0107] Example 8

[0108] In this embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 4 As shown. The computer device includes a processor, a memory, and a network interface connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The database of the computer device is used to store data. The network interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, a method for optimizing network delay of an in-vehicle terminal is implemented.

[0109] Those skilled in the art will understand that Figure 4 The structure shown in the figure is merely a block diagram of a portion of the structure related to the solution of the present disclosure, and does not constitute a limitation on the computer device to which the solution of the present disclosure is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0110] Example 9

[0111] In this embodiment, a computer readable storage medium is provided. Figure 5 As shown, a computer program is stored thereon, and when the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0112] Example 10

[0113] In this embodiment, a computer program product is provided, including a computer program. When the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0114] It should be noted that the information collected is information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of relevant data comply with the relevant laws, regulations and standards of relevant countries and regions, take necessary confidentiality measures, do not violate public order and good customs, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0115] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, database or other media used in the embodiments provided in the present disclosure may include at least one of non-volatile and volatile memory. Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory may include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this disclosure may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, distributed databases based on blockchains. The processor involved in each embodiment provided in this disclosure may be, but are not limited to, a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic unit, a data processing logic unit based on quantum computing, etc.

[0116] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0117] The above-described embodiments merely represent several implementation methods of the present disclosure. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present disclosure. It should be noted that a person of ordinary skill in the art may make various modifications and improvements without departing from the spirit of the present disclosure, all of which fall within the scope of protection of the present disclosure. Therefore, the scope of protection of the present disclosure shall be determined by the appended claims.

Claims

1. A vehicle terminal network delay optimization method, characterized in that: include: Clustering each of the vehicle-mounted terminals based on their task information to obtain a perception terminal cluster and a computationally intensive terminal cluster; Matching at least one subcarrier for each computing-intensive terminal in the computing-intensive terminal cluster to perform task transmission; Determine, from the computing-intensive terminal cluster, a computing-intensive terminal with the smallest channel interference with a sensing terminal in the sensing terminal cluster, as a subcarrier multiplexing terminal, and control the sensing terminal to multiplex the subcarrier matched with the corresponding subcarrier multiplexing terminal for task transmission; Determine the transmission information when each of the computing-intensive terminals and each of the perception terminals transmits tasks, and generate vehicle-mounted terminal target control information based on the transmission information and the delay optimization network.

2. The method according to claim 1, characterized in that The clustering of the vehicle-mounted terminals based on the task information of each vehicle-mounted terminal to obtain a perception terminal cluster and a computation-intensive terminal cluster includes: Extracting corresponding task types from task information of each vehicle terminal, wherein the task types include perception-based tasks and computation-intensive tasks; The corresponding vehicle terminals are clustered based on the task types to obtain perception terminal clusters and computation-intensive terminal clusters.

3. The method according to claim 1, characterized in that The matching at least one subcarrier for each computing-intensive terminal in the computing-intensive terminal cluster to perform task transmission includes: Determining the computing power required for the task of each computing-intensive terminal based on the task information of each computing-intensive terminal in the computing-intensive terminal cluster; Clustering the computing-intensive terminals based on the computing power required for the tasks of the computing-intensive terminals and the remaining computing power of the edge computing terminal to obtain a non-local terminal cluster; Based on the number of non-local terminals in the non-local terminal cluster and a preset transmission bandwidth, at least one subcarrier is matched for each non-local terminal to perform task transmission.

4. The method according to claim 3, characterized in that The determining, from the computing-intensive terminal cluster, a computing-intensive terminal having the smallest channel interference with a sensing terminal in the sensing terminal cluster as a subcarrier multiplexing terminal includes: Based on the subcarrier matched to each non-local terminal in the computing-intensive terminal cluster, the communication distance between the sensing terminal in the sensing terminal cluster and each non-local terminal in the computing-intensive terminal cluster, the antenna height and the speed of light of the sensing terminal in the sensing terminal cluster and each non-local terminal in the computing-intensive terminal cluster, respectively calculating the channel interference between the sensing terminal in the sensing terminal cluster and each non-local terminal in the computing-intensive terminal cluster, and obtaining a channel interference set; The non-local terminal corresponding to the minimum channel interference in the channel interference set is used as a subcarrier multiplexing terminal.

5. The method according to claim 1, wherein The determining of transmission information when each of the computing-intensive terminals and each of the sensing terminals performs task transmission includes: In response to the update of the digital twins corresponding to each of the computing-intensive terminals and each of the perception terminals in the current time slot, transmission information of the vehicle-mounted terminals corresponding to each of the digital twins when performing task transmission is obtained respectively.

6. The method according to claim 1, characterized in that The generating of vehicle terminal target control information based on the transmission information and the delay optimization network includes: Processing the transmission information based on the delay optimization network to obtain initial control information of the vehicle terminal; The initial control information of the vehicle terminal is iteratively optimized based on the delay optimization network to obtain the target control information of the vehicle terminal.

7. A vehicle-mounted terminal network delay optimization device, characterized in that: The device comprises: A terminal clustering module, configured to cluster each vehicle-mounted terminal based on its task information to obtain a perception terminal cluster and a computationally intensive terminal cluster; A carrier matching module, configured to match at least one subcarrier for each computing-intensive terminal in the computing-intensive terminal cluster to perform task transmission; A carrier multiplexing module is used to determine, from the computing-intensive terminal cluster, a computing-intensive terminal with the smallest channel interference with the sensing terminal in the sensing terminal cluster as a subcarrier multiplexing terminal, and control the sensing terminal to multiplex the subcarrier matched by the corresponding subcarrier multiplexing terminal for task transmission; The information generation module is used to determine the transmission information when each of the computing-intensive terminals and each of the perception terminals transmits tasks, and generate vehicle-mounted terminal target control information based on the transmission information and the delay optimization network.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

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

Images