Network resource configuration method and device based on 5G Internet of Vehicles

Abstract

The invention discloses a network resource allocation method and device based on 5G Internet of Vehicles, which are used for improving the allocation efficiency and service quality of network resources in an Internet of Vehicles environment. The method comprises the following steps: determining a service priority corresponding to an Internet of Vehicles service according to an obtained Internet of Vehicles service request, the Internet of Vehicles service request comprising vehicle driving data, traffic environment data and service type data; determining network resource reserved data corresponding to the car networking service according to the service priority; and when it is judged that the network is congested, according to the service priority and the network resource reservation data, determining a resource allocation strategy for each Internet of Vehicles service, and according to the resource allocation strategy, performing resource allocation for the Internet of Vehicles service.

Description

Technical Field

[0001] This application relates to the field of communication technology, and in particular to a method and apparatus for configuring network resources based on 5G vehicle-to-everything (V2X) networks. Background Technology

[0002] With the rapid development of intelligent transportation systems and autonomous driving technologies, vehicle-to-everything (V2X) communication plays an increasingly crucial role in improving driving safety, optimizing traffic efficiency, and enhancing information interaction experiences. Existing technologies primarily ensure the quality of V2X communication from two dimensions: network architecture optimization and resource scheduling strategies. On the one hand, by introducing edge computing and distributed network architecture, a low-latency, high-reliability communication framework is constructed to support real-time data interaction between vehicles and infrastructure, and between vehicles themselves. On the other hand, based on 5G network slicing technology, a flexible and configurable resource allocation mechanism is designed to meet the varying bandwidth, latency, and reliability requirements of different business scenarios. These solutions provide technical support for efficient communication and collaborative control in V2X environments, especially under high-density traffic flow and complex road conditions, effectively improving communication stability and response speed. Simultaneously, combining artificial intelligence algorithms for dynamic prediction and resource pre-allocation further enhances the adaptability and robustness of network services, laying the foundation for future large-scale autonomous driving applications.

[0003] While existing 5G networks can reduce latency through UPF (User-Defined Frame Shift) deployment or QoS (Quality of Service) assurance technologies, the effects are limited and insufficient to meet the high reliability requirements of low-latency vehicular network (V2V) services. Especially during network congestion, the inability to flexibly adjust resources to prioritize the real-time data transmission of critical services such as emergency braking and sudden lane changes can lead to delayed emergency decision-making and traffic accidents. Therefore, a method is urgently needed to dynamically identify service priorities and rationally allocate network resources to ensure the communication quality and safety of V2V low-latency services in complex traffic environments. Summary of the Invention

[0004] This application provides a network resource allocation method based on 5G vehicle-to-everything (V2X) technology to overcome the limitations of existing technologies. While 5G networks can reduce latency through UPF (User-Defined Flow) deployment or QoS (Quality of Service) assurance techniques, the effects are limited and cannot meet the high reliability requirements of V2X low-latency services. Especially during network congestion, the inability to flexibly adjust resources to prioritize the real-time data transmission of critical services such as emergency braking and sudden lane changes may lead to delayed emergency decisions and traffic accidents. Therefore, a method capable of dynamically identifying service priorities and rationally allocating network resources is urgently needed to ensure the communication quality and safety of V2X low-latency services in complex traffic environments.

[0005] Firstly, a method for configuring network resources based on 5G vehicle-to-everything (V2X) networks is provided. This includes: determining the service priority corresponding to the V2X service based on the acquired V2X service requests, wherein the V2X service requests include vehicle driving data, traffic environment data, and service type data; determining the network resource reservation data corresponding to the V2X service based on the service priority; and when network congestion is detected, determining a resource allocation strategy for each V2X service based on the service priority and the network resource reservation data, and configuring resources for the V2X service according to the resource allocation strategy.

[0006] Based on the methods described above, this invention provides a network resource allocation method for 5G vehicle-to-everything (V2X) networks. This method dynamically assesses the priority of V2X services based on vehicle driving data, traffic environment data, and service type data, and reserves and allocates network resources accordingly. When facing network congestion, this method intelligently formulates resource allocation strategies by combining service priority and resource reservation information, ensuring that high-priority services such as emergency braking warnings receive sufficient bandwidth and transmission guarantees. This significantly reduces communication latency and improves the reliability and real-time performance of information transmission. This method effectively addresses the problem of fluctuating communication demands in complex traffic environments, improves the overall operational efficiency and security of V2X systems, and provides solid technical support for the realization of autonomous driving and intelligent transportation.

[0007] In conjunction with the first aspect, in some possible implementations of the first aspect, the service priority corresponding to the vehicle-to-everything (V2X) service is determined based on the obtained V2X service request. Specifically, this includes: inputting vehicle driving data, traffic environment data, and service type data into a pre-trained machine learning model; and obtaining the service priority output by the machine learning model.

[0008] In conjunction with the first aspect, in some possible implementations of the first aspect, the network resource reservation data corresponding to the vehicle-to-everything (V2X) service is determined according to the service priority, including: allocating the total available network resources of the system proportionally according to the service priority corresponding to each received V2X service request, and determining the network resource reservation data corresponding to each V2X service.

[0009] In conjunction with the first aspect, in some possible implementations of the first aspect, the resource allocation strategy is a priority-based delay-tolerant network (DTN) transmission strategy; then, resource configuration is performed for vehicle-to-everything (V2X) services according to the resource allocation strategy, including: immediately forwarding data packets corresponding to V2X service requests with service priority and / or network resource reservation data exceeding a preset threshold; and caching data packets corresponding to V2X service requests with service priority and / or network resource reservation data falling below a preset threshold.

[0010] In conjunction with the first aspect, in some possible implementations of the first aspect, for data packets corresponding to vehicle-to-everything (V2X) service requests whose service priority and / or reserved network resource data are lower than a preset threshold, caching processing is performed, including: determining whether to perform caching processing based on the relationship between the remaining storage space of the network node and the size of the data packet to be cached; performing caching processing when the remaining storage space is greater than the data packet to be cached and the total amount of reserved network resource data does not exceed the preset threshold; and forwarding the data packet to be cached when the remaining storage space is greater than the data packet to be cached and the total amount of reserved network resource data exceeds the preset threshold.

[0011] Secondly, a network resource configuration device based on 5G vehicle-to-everything (V2X) is provided. The device includes: a priority determination module, used to determine the service priority corresponding to a V2X service based on an acquired V2X service request, wherein the V2X service request includes vehicle driving data, traffic environment data, and service type data; The resource reservation module is used to determine the network resource reservation data corresponding to the vehicle-to-everything (V2X) service based on the service priority; the resource configuration module is used to determine the resource allocation strategy for each V2X service based on the service priority and the network resource reservation data when network congestion is detected, and to configure resources for the V2X service according to the resource allocation strategy.

[0012] Based on the methods described above, this device, through a priority determination module, combines vehicle driving data, traffic environment data, and service type data to accurately identify the priorities of different vehicle-to-everything (V2X) services, thereby achieving intelligent scheduling of network resources. The resource reservation module pre-allocates corresponding resources according to priority, improving system response efficiency. When network congestion is detected, the resource allocation module dynamically adjusts the resource allocation strategy based on priority and reservation data, ensuring that high-priority services (such as emergency braking warnings) receive sufficient bandwidth and transmission guarantees, significantly reducing communication latency and improving the reliability and real-time performance of information transmission. This device effectively solves the problem of uneven network resource allocation in complex traffic environments, improves the overall operating efficiency and safety of the V2X system, provides solid technical support for applications such as autonomous driving and intelligent traffic management, and helps reduce traffic accidents and enhance user experience.

[0013] Thirdly, an electronic device includes a memory and a processor, wherein when the processor executes the computer program, it is used to implement the network resource configuration method for 5G vehicle-to-everything (V2X) network of any of the above aspects.

[0014] Fourthly, a computer-readable storage medium storing a computer program, which, when executed by a processor, is used to implement the 5G vehicle-to-everything (V2X) network resource configuration method of any of the above aspects.

[0015] Fifthly, a computer program product, characterized in that it includes a computer program, which, when executed by a processor, is used to implement the 5G vehicle-to-everything (V2X) network resource configuration method described above. Attached Figure Description

[0016] Figure 1 This is a schematic diagram of a network resource configuration method based on 5G vehicle-to-everything (V2X) provided in the embodiments of this application; Figure 2 This is a schematic diagram of a network resource configuration device based on 5G vehicle networking provided in the embodiments of this application. Detailed Implementation

[0017] To make the objectives, technical solutions, and advantages of this application clearer, the application will be further described in detail below with reference to the accompanying drawings. The specific operating methods in the method embodiments can also be applied to the device embodiments or system embodiments. In the description of this application, unless otherwise stated, "multiple" means two or more.

[0018] In the various embodiments of this application, unless otherwise specified or in case of logical conflict, the terminology and / or descriptions of different embodiments are consistent and can be referenced by each other. The technical features of different embodiments can be combined to form new embodiments according to their inherent logical relationship.

[0019] It is understood that the various numerical designations used in this application are merely for descriptive convenience and are not intended to limit the scope of this application. The order of the process numbers does not imply the order of execution; the execution order of each process should be determined by its function and internal logic.

[0020] The terms "first," "second," "third," "fourth," and other various terminology (if present) in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a particular order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments described herein can be implemented in a sequence other than that illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0021] To facilitate understanding of the embodiments of this application, the terminology involved in the embodiments of this application will be briefly explained below.

[0022] Delay-tolerant networks: A network technology used to ensure data delivery through store-and-forward mechanisms in situations of unstable network connectivity or intermittent disconnections. In this scheme, the improved DTN algorithm determines whether data packets are forwarded immediately or buffered based on the priority of vehicular network services and resource reservation, thus guaranteeing low-latency transmission of high-priority services.

[0023] Neural network model: A multi-layered machine learning model used to identify complex patterns and nonlinear relationships. In this scheme, the neural network model receives vehicle driving data, traffic environment data, and service type data as input, and outputs the priority probability distribution of the corresponding vehicle-to-everything (V2X) services, thereby achieving dynamic priority evaluation.

[0024] Resource reservation: This refers to the system allocating a certain amount of bandwidth and computing resources in advance for specific vehicle-to-everything (V2X) services based on business priority and within the limits of network resources. In this solution, resource reservation is dynamically adjusted and optimized according to current network conditions and changes in business needs to improve overall communication efficiency and response speed.

[0025] Service Priority: A tiered system based on the urgency and importance of connected vehicle services, used to guide network resource allocation strategies. In this solution, service priorities are dynamically evaluated by a neural network model and influence resource reservation and packet forwarding or caching decisions.

[0026] Storage space assessment: In DTN transmission strategies, the relationship between the network node's remaining storage space and the size of the data packets to be processed determines whether to perform a caching operation. In this scheme, this assessment combines network resource reservation data with preset thresholds to ensure that high-priority data packets are forwarded first, while low-priority data packets are appropriately cached to avoid network congestion.

[0027] Based on this, this application provides an adaptive network resource allocation method based on vehicle-to-everything (V2X) services to overcome the problem that although 5G networks can reduce latency through UPF (Universal Power Filter) deployment or QoS (Quality of Service) guarantee technology, the effect is limited and it is difficult to meet the high reliability requirements of low-latency V2X services.

[0028] Figure 1 This is a schematic diagram of a network resource configuration method based on 5G vehicle-to-everything (V2X) as included in an embodiment of this application. Figure 1 As shown, the method includes steps S101, S102, and S103. S101, based on the obtained vehicle-to-everything (V2X) service request, determine the service priority corresponding to the V2X service, wherein the V2X service request includes vehicle driving data, traffic environment data, and service type data. Specifically, vehicle driving data, traffic environment data, and service type data are input into a pre-trained neural network model. The neural network model processes the input features and outputs the priority probability distribution of the corresponding service, and determines the final service priority based on the probability distribution. This neural network model is trained based on historical vehicle-to-everything (V2X) service data, learning the mapping relationship between vehicle status, traffic environment, communication service information, and communication priority to achieve dynamic priority evaluation of the current service. S102, determine the network resource reservation data corresponding to the vehicle-to-everything (V2X) service based on the service priority. Specifically, based on the service priority corresponding to each vehicle-to-everything (V2X) service request, the total available network resources of the system are allocated proportionally, and the network resource reservation data corresponding to each V2X service is calculated and determined. This resource reservation algorithm converts different priorities into normalized values ​​and then calculates the resource reservation amount for each service based on their relative weights, thereby achieving resource allocation bias towards high-priority services. S103, when network congestion is detected, determine the resource allocation strategy for each vehicle-to-everything (V2X) service based on service priority and network resource reservation data, and configure resources for the V2X service according to the resource allocation strategy. Specifically, an improved delay-tolerant DTN transmission strategy is adopted as the resource allocation strategy. For data packets corresponding to vehicular network service requests with service priorities and / or network resource reservation data exceeding a preset threshold, immediate forwarding is performed; for data packets corresponding to vehicular network service requests with service priorities and / or network resource reservation data below the preset threshold, caching is performed. This strategy dynamically adjusts the forwarding or caching decisions of data packets by combining node storage space and resource reservation data to ensure timely response to high-priority services and reliable transmission of low-priority services. In some implementations, such as Figure 1 The method described involves inputting vehicle driving data, traffic environment data, and service type data into a pre-trained machine learning model; then, the service priority output by the machine learning model is obtained. This utilizes a neural network model to model complex nonlinear relationships, improving the accuracy of service priority assessment and enhancing the system's adaptability to the needs of connected vehicle services in different scenarios. In some implementations, such as Figure 1 The method described above allocates the total available network resources of the system proportionally based on the service priority of each received vehicle-to-everything (V2X) service request, and determines the network resource reservation data corresponding to each V2X service. This enables differentiated resource allocation for services of different priorities, ensuring the resource needs of high-priority services and improving the overall network service quality. In some implementations, such as Figure 1In the method shown, the resource allocation strategy is a priority-based delay-tolerant network (DTN) transmission strategy. Based on this strategy, resource allocation is performed for vehicle-to-everything (V2X) services, including: immediately forwarding data packets corresponding to V2X service requests with service priorities and / or reserved network resource data exceeding a preset threshold; and caching data packets corresponding to V2X service requests with service priorities and / or reserved network resource data falling below the preset threshold. Thus, the DTN mechanism prioritizes the transmission of high-priority data during network congestion while rationally utilizing network resources and avoiding the loss of low-priority data. In some implementations, such as Figure 1 The method described above caches data packets corresponding to vehicle-to-everything (V2X) service requests whose service priority and / or reserved network resource data are below a preset threshold. This caching process includes: determining whether to perform caching based on the relationship between the remaining storage space of the network node and the size of the data packet to be cached; performing caching when the remaining storage space is greater than the data packet to be cached and the total amount of reserved network resource data does not exceed a preset threshold; and forwarding the data packet to be cached when the remaining storage space is greater than the data packet to be cached and the total amount of reserved network resource data exceeds a preset threshold. This optimizes network resource utilization efficiency while ensuring no data loss and avoids data discarding due to insufficient cache space. In such Figure 1 The method shown achieves the technical effect of rapid response to high-priority services and reliable transmission of low-priority services by dynamically evaluating the priority of vehicle-to-everything (V2X) services, allocating network resources proportionally, and using an improved DTN strategy for resource allocation and packet forwarding.

[0029] Figure 2 This is a schematic diagram of the structure of a network resource configuration device based on 5G vehicle-to-everything (V2X) provided in an embodiment of this application. Figure 2 As shown, the device includes a priority determination module 201, a resource reservation module 202, and a resource configuration module 203. The priority determination module 201 is used to determine the service priority corresponding to the acquired vehicle-to-everything (V2X) service request. The V2X service request includes vehicle driving data, traffic environment data, and service type data. Specifically, the priority determination module 201 can be a dynamic evaluation system based on a neural network model. It collects real-time vehicle status information, traffic environment information, and communication service information, performs feature extraction and standardization on this information, and then inputs it into the neural network model. The model outputs probability distributions corresponding to low, medium, and high priorities, thereby achieving priority evaluation for different V2X services. The resource reservation module 202 is used to determine the network resource reservation data corresponding to the vehicle-to-everything (V2X) service based on the service priority. Specifically, the resource reservation module 202 can be a dynamic resource allocation algorithm that calculates the corresponding normalized weight based on the priority of each task at a specific time point, and allocates the resource reservation amount proportionally according to the total available resources to ensure that high-priority tasks can obtain sufficient bandwidth and computing resources. The resource allocation module 203 is used to determine the resource allocation strategy for each vehicle-to-everything (V2X) service based on service priority and network resource reservation data when network congestion is detected, and then allocate resources for the V2X services according to the resource allocation strategy. Specifically, the resource allocation module 203 can be an improved Delay Tolerant Network (DTN) algorithm, which, when network congestion is detected, prioritizes forwarding high-priority data packets while buffering and delaying the transmission of low-priority data packets to ensure timely response and reliable transmission of critical services. In some implementations, the priority determination module 201 adopts a neural network model, which is trained by machine learning algorithms to obtain the mapping relationship between vehicle network service characteristics and communication priorities, making the service priority assessment in different scenarios more accurate and adaptive. In some implementations, when calculating the resource reservation amount, the resource reservation module 202 uses a normalization method to convert different priorities into corresponding numerical weights, and allocates resources proportionally according to the sum of the weights of all tasks, thereby achieving resource tilting towards high-priority tasks. In some implementations, when performing resource allocation, the resource allocation module 203 adopts an improved latency-tolerant network algorithm. Through a message storage and forwarding decision mechanism, it decides whether to store or forward messages based on the remaining storage space of the node and the resource reservation of the task, so as to prioritize the transmission of high-priority data in the event of network congestion. In some implementations, the resource configuration module 203 also includes a real-time monitoring function, which is used to continuously monitor network performance indicators such as latency and packet loss rate, and dynamically adjust the resource configuration strategy based on the monitoring results to further optimize network resource utilization efficiency and communication service quality. In such Figure 2 The device shown achieves efficient, reliable, and flexible network resource configuration for vehicle-to-everything (V2X) services through dynamic priority determination, resource reservation, and adaptive resource allocation and transmission.

[0030] The method of this application will now be described in conjunction with specific embodiments. Example 1 In some implementations, dynamic priority determination includes the following steps: First, real-time vehicle status information, traffic environment information, and communication service information are collected, and this data is cleaned, features extracted, and standardized. Then, a neural network model is selected as the priority evaluation tool. This model is trained using historical data to learn the mapping relationship between vehicle-to-everything (V2X) service characteristics and communication priorities. Model parameters are optimized through methods such as cross-validation to improve prediction accuracy. During the priority evaluation process, the input feature vector contains vehicle status, traffic environment, and communication service information. The output of the neural network is a probability distribution representing the probability values ​​of different priorities. For example, in a specific scenario, an autonomous vehicle receives a warning message about a vehicle braking suddenly ahead. The system extracts relevant parameters based on vehicle status, traffic environment, and communication service characteristics, such as relative speed and time urgency, and inputs these parameters into the trained neural network model to obtain an output probability distribution. The highest priority probability indicates that the communication service requires priority processing. Based on this, the system can adjust the allocation of communication resources to ensure that high-priority communication services receive timely responses and processing.

[0031] Example 2 In some implementations, network resource reservation includes resource reservation algorithms, priority conversion and normalization calculations, and examples of resource reservation allocation. Specifically, in the resource reservation algorithm, the system dynamically adjusts bandwidth allocation based on task priority, where the resource reservation Ri(t) for task (i) at time (t) is calculated using the following formula: Ri(t) = [Pi(t) / ΣPj(t)] × total_resources(t) Where Pi(t) is the priority of task (i) at time (t), total_resources(t) is the total amount of available resources at time (t), and ΣPj(t) is the sum of the priorities of all tasks in the current system.

[0032] In priority conversion and normalization calculations, the probability distributions of different priorities are converted into normalized values ​​to facilitate subsequent resource allocation calculations. For example, low priority is converted to 1, medium priority to 10, and high priority to 100, thereby achieving quantification of priorities.

[0033] In the resource reservation allocation example, assume that at time (t), the total available resources are 100. There are three tasks (T1, T2, T3) with priority probabilities P_1 = [0.6, 0.3, 0.1], P_2 = [0.1, 0.6, 0.3], and P_3 = [0.1, 0.3, 0.6]. Based on the conversion rules described above, calculate the priority value for each task: P1(t) = 0.6×1 + 0.3×10 + 0.1×100 = 13.6 P2(t) = 0.1×1 + 0.3×10 + 0.6×100 = 36.1 P3(t) = 0.1×1 + 0.3×10 + 0.6×100 = 63.1 Adding these priority values ​​together gives a total priority value of 112.8. Then, allocating a total resource of 100 proportionally yields the resource reservation amounts for each task as follows: R1(t) = 13.6 / 112.8 × 100 ≈ 12.06 R2(t) = 36.1 / 112.8 × 100 ≈ 32.00 R3(t) = 63.1 / 112.8 × 100 ≈ 55.94 This method enables the system to dynamically reserve and allocate resources based on task priority and resource requirements, thereby improving the overall efficiency of the system and ensuring timely response to high-priority communication services.

[0034] Example 3 In some implementations, a 5G vehicle-to-everything (V2X) adaptive network resource allocation method includes the following steps: dynamic priority determination, network resource reservation, adaptive resource allocation and transmission, and real-time monitoring and feedback. Specifically, during the adaptive resource allocation and transmission process, an improved Delay Tolerant Network (DTN) algorithm is used to implement a message storage and forwarding mechanism.

[0035] During the dynamic priority determination phase, the system dynamically evaluates the priority of each vehicle-to-everything (V2X) service based on the vehicle's real-time status (such as speed, direction, and acceleration) and the type of service (such as collision warning and traffic light information) using a neural network algorithm. Specifically, the system collects vehicle status information, traffic environment information, and communication service information, and performs data cleaning, feature extraction, and standardization to generate an input feature vector. This feature vector serves as the input to the neural network model, and the trained model outputs a probability distribution corresponding to different priorities. For example, when an autonomous vehicle receives a warning message about a vehicle braking suddenly ahead, the system calculates the urgency based on the vehicle status, traffic environment, and communication service information, and inputs these features into the trained neural network model, thus determining that the probability of this communication service having a high priority is 0.6.

[0036] After priority assessment, the system dynamically adjusts bandwidth allocation based on the priority of each task. The resource reservation algorithm converts different priorities into corresponding values ​​based on task priority and total available resources, and allocates resources proportionally. For example, if three tasks have priorities of low, medium, and high, their corresponding normalized priority values ​​are 13.6, 36.1, and 63.1, respectively. Based on this, the system calculates corresponding resource reservation amounts of 12.06, 32.00, and 55.94, ensuring that high-priority tasks receive more resource support.

[0037] During the adaptive resource allocation and transmission phase, the system employs an improved DTN algorithm to prioritize the transmission of high-priority data packets during network congestion, while temporarily buffering and delaying the transmission of low-priority data packets. The message storage mechanism determines whether to store a message based on the node's remaining storage space and maximum storage capacity. For example, if a node's maximum storage capacity is 100 and its current storage space is 100, a message of size 40 can be stored; if storage space is insufficient, the message will be temporarily stored. Message forwarding decisions are based on the node's remaining storage space, resource reservation, and a preset threshold. For example, if a message's resource reservation is below the threshold and the node has sufficient storage space, the message is stored; otherwise, it is forwarded.

[0038] In the message storage and forwarding example, assume there are three nodes (N1, N2, N3) and three messages (M1, M2, M3). Node N1 has a maximum storage capacity of 100, a current storage space of 100, a message M1 size of 40, and a resource reservation of 12.06. Since the resource reservation is below the threshold of 30, the system decides to store the message. Node N2 has a maximum storage capacity of 150, a current storage space of 50, a message M2 size of 60, and a resource reservation of 32.00. Due to insufficient storage space, the system decides to store the message. Node N3 has a maximum storage capacity of 200, a current storage space of 150, a message M3 size of 80, and a resource reservation of 55.94, which exceeds the threshold. Therefore, the system decides to forward the message.

[0039] Ultimately, through the improved DTN algorithm described above, the system can ensure the rapid and reliable transmission of low-latency vehicle-to-everything (V2X) services even when network connectivity is unstable, while also ensuring that other low-priority services are not lost, thus achieving reliable transmission of all services.

[0040] Example 4 In some implementations, real-time monitoring and feedback includes the following steps: First, the system continuously collects and analyzes network performance metrics, such as data transmission latency, packet loss rate, bandwidth utilization, and network congestion. These metrics are monitored in real time by sensors, base stations, and vehicle-mounted terminal devices deployed in the network, and the collected data is uploaded to a central control platform or edge computing nodes for processing.

[0041] Secondly, based on the acquired network performance metrics and the current resource configuration, the system dynamically adjusts its resource allocation strategy using a feedback mechanism. For example, when an increase in packet loss rate or latency exceeding a preset threshold is detected in a certain area, the system automatically triggers a resource reallocation process, prioritizing increased bandwidth or computing resources for high-priority services while caching or delaying transmission for low-priority services. This feedback mechanism can be optimized using machine learning algorithms to improve response speed and decision-making accuracy.

[0042] Furthermore, the system supports two-way communication between vehicles and infrastructure to collect user feedback on network quality. For example, vehicles can report the time delay of receiving warning information and whether key data was successfully received. This feedback data will be incorporated into subsequent resource allocation models to optimize future resource reservation and allocation strategies. In addition, the system can build a network quality evaluation model based on historical feedback data, thereby enabling predictive optimization of network conditions in different regions and time periods, improving overall vehicle-to-everything (V2X) communication efficiency and service quality.

[0043] The sequence number of each process does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0044] In the various embodiments of this application, unless otherwise specified or in case of logical conflict, the terminology and / or descriptions of different embodiments are consistent and can be referenced by each other. The technical features of different embodiments can be combined to form new embodiments according to their inherent logical relationship.

[0045] Those skilled in the art will recognize that, based on the units and algorithm steps described in conjunction with the embodiments disclosed herein, this application can be implemented in hardware or a combination of hardware and computer software. Whether a function is implemented in hardware or by computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0046] The apparatus provided in the embodiments of this application will be described in detail below with reference to the accompanying drawings. The description of the apparatus embodiments corresponds to the description of the method embodiments. Therefore, for content not described in detail, please refer to the method embodiments above. For the sake of brevity, some content will not be repeated.

[0047] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0048] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0049] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces, and the indirect coupling or communication connection of apparatus or units may be electrical, mechanical, or other forms.

[0050] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0051] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0052] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, ROM, RAM, magnetic disks, or optical disks.

[0053] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method for network resource configuration based on 5G vehicle networking, characterized in that, include: Based on the obtained vehicle-to-everything (V2X) service requests, the service priority corresponding to the V2X service is determined, wherein the V2X service requests include vehicle driving data, traffic environment data, and service type data; Based on the service priority, determine the network resource reservation data corresponding to the vehicle-to-everything (V2X) service; When network congestion is detected, a resource allocation strategy for each vehicle-to-everything (V2X) service is determined based on the service priority and the network resource reservation data, and resources are configured for the V2X service according to the resource allocation strategy.

2. The method of claim 1, wherein, The step of determining the service priority corresponding to the vehicle-to-everything (V2X) service based on the obtained V2X service request specifically includes: The vehicle driving data, the traffic environment data, and the business type data are input into a pre-trained machine learning model; Obtain the business priority output by the machine learning model.

3. The method of claim 1, wherein, The step of determining the network resource reservation data corresponding to the vehicle-to-everything (V2X) service based on the service priority includes: Based on the service priority corresponding to each received vehicle-to-everything (V2X) service request, the total available network resources of the system are allocated proportionally, and the network resource reservation data corresponding to each V2X service is determined.

4. The method according to claim 1, characterized in that, The resource allocation strategy is a priority-based delay-tolerant network (DTN) transmission strategy. The step of configuring resources for the vehicle-to-everything (V2X) service according to the resource allocation strategy includes: For data packets corresponding to vehicle-to-everything (V2X) service requests whose service priority and / or network resource reservation data exceed a preset threshold, they are immediately forwarded. For vehicle-to-everything (V2X) service requests whose service priority and / or network resource reservation data are below a preset threshold, the corresponding data packets are cached.

5. The method according to claim 4, characterized in that, The caching process for data packets corresponding to vehicle network service requests with service priority and / or network resource reservation data below a preset threshold includes: Based on the relationship between the remaining storage space of the network node and the size of the data packet to be cached, determine whether to perform caching processing; When the remaining storage space is greater than the data packet to be cached, and the total amount of data reserved for current network resources does not exceed the preset threshold, caching is performed; When the remaining storage space is greater than the data packet to be cached, and the total amount of data reserved for current network resources exceeds the preset threshold, the data packet to be cached is forwarded.

6. A network resource allocation device based on 5G vehicle-to-everything (V2X) networking, characterized in that, The device includes: The priority determination module is used to determine the service priority corresponding to the vehicle network service based on the obtained vehicle network service request, wherein the vehicle network service request includes vehicle driving data, traffic environment data, and service type data; The resource reservation module is used to determine the network resource reservation data corresponding to the vehicle-to-everything (V2X) service based on the service priority. The resource allocation module is used to determine the resource allocation strategy for each vehicle-to-everything (V2X) service based on the service priority and the network resource reservation data when network congestion is detected, and to perform resource allocation for the V2X service according to the resource allocation strategy.

7. An electronic device comprising a memory and a processor, characterized in that, The memory stores computer programs; When the processor executes the computer program, it implements the steps of the 5G vehicle-to-everything (V2X) network resource configuration method as described in any one of claims 1-5.

8. A computer-readable storage medium storing a computer program thereon, characterized in that, When the computer program is executed by the processor, it is used to implement the network resource configuration method for 5G vehicle-to-everything (V2X) as described in any one of claims 1-5.

9. A computer program product, characterized in that, It includes a computer program, which, when executed by a processor, implements the network resource configuration method for 5G vehicle-to-everything (V2X) as described in any one of claims 1-5.

Images