Vehicle-mounted task scheduling optimization methods, equipment, media and products in the Internet of Vehicles environment

Abstract

The present invention discloses a method, device, medium, and product for optimizing on-board task scheduling in a connected vehicle environment, relating to the technical field of on-board task scheduling optimization. The method comprises obtaining geographic information, road information, and vehicle network trajectory information of a target area; constructing a virtual urban traffic environment based on the geographic information; deploying roadside communication units using a genetic algorithm to obtain a first virtual urban traffic environment; clustering the roadside communication units using a principal component clustering method to obtain a second virtual urban traffic environment; and determining the multi-computation task offloading process using a vehicle and roadside communication unit state transition algorithm based on the principal component clusters. The present invention clusters multiple roadside communication units, using road and vehicle network trajectory information to provide a basis for clustering. The clusters can share the results of completed computations, thereby improving the efficiency of vehicle task delivery and saving computing resources.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle-mounted task scheduling optimization, and in particular to a method, device, medium and product for vehicle-mounted task scheduling optimization in a vehicle networking environment. Background Art

[0002] The traditional vehicle unloading process can be summarized as three steps: task uploading, waiting for calculation, and returning the calculation results. However, when the vehicle's residence time at the current roadside communication unit (RSU) is insufficient to wait for the calculation results, the vehicle chooses to abandon the upload task and choose to process the task locally or wait until the next suitable conditions to choose to transmit the task. This increases the burden on the vehicle's computing resources and also reduces the efficiency of the vehicle's computing tasks. Currently, there are proposals to use clustering methods to improve the efficiency of vehicle task transfer. By establishing clusters between vehicles with similar mobility and electing cluster heads as agents to achieve task transfer, however, in urban environments, the trajectories of vehicles vary greatly, and the unstable links between clusters lead to performance degradation. Summary of the Invention

[0003] The purpose of the present invention is to provide a method, device, medium and product for optimizing vehicle-mounted task scheduling in a connected vehicle environment. The method can use the trajectory information of roads and vehicle networks to provide a clustering basis. The results of the calculation can be shared within the cluster, thereby improving the efficiency of vehicle task delivery and saving computing resources.

[0004] To achieve the above object, the present invention provides the following solutions:

[0005] In a first aspect, the present invention provides a method for optimizing vehicle-mounted task scheduling in a connected vehicle environment, comprising:

[0006] Obtain geographic information, road information, and vehicle network trajectory information of the target area;

[0007] constructing a virtual urban traffic environment according to the geographic information;

[0008] Deploying a roadside communication unit in the virtual urban traffic environment based on a genetic algorithm deployment strategy to obtain a first virtual urban traffic environment;

[0009] Based on the road information and the vehicle network trajectory information, a principal component clustering method is used to cluster the roadside communication units in the first virtual urban traffic environment to obtain a second virtual urban traffic environment; the second virtual urban traffic environment includes a plurality of principal component clusters; the principal component clusters are composed of a plurality of roadside communication units;

[0010] According to the principal component clusters of the second virtual urban traffic environment, a vehicle state transition algorithm and a roadside communication unit state transition algorithm are adopted to determine a multi-computation task offloading process of the vehicle-borne tasks.

[0011] Optionally, the genetic algorithm deployment strategy is a deployment strategy aimed at optimizing network communication delay and coverage of roadside communication unit services.

[0012] Optionally, the optimization formula for the network communication delay is specifically:

[0013]

[0014] Where Z is the network communication delay, represents the delay value reduced in time period t after the roadside communication unit is deployed at intersection j; is the flow through intersection j during time period t; α j ∈{0, 1}, when α j When it is 1, it means that a roadside communication unit is deployed at intersection j; j represents the number of newly covered road sections at intersection j, s represents the total number of intersections, and there are T time periods in a day.

[0015] Optionally, the optimization formula for the coverage of the roadside communication unit service is specifically:

[0016]

[0017] Where Y is the coverage area of ​​the roadside communication unit service, l j represents the number of newly covered road sections at intersection j, s represents the total number of intersections, c represents the total number of road sections, and there are T time periods in a day; α j ∈{0, 1} represents that a roadside communication unit is deployed at intersection j.

[0018] Optionally, based on the road information and the vehicle network trajectory information, a principal component clustering method is used to cluster the roadside communication units in the first virtual urban traffic environment to obtain a second virtual urban traffic environment, specifically including:

[0019] Determining a plurality of initial cluster centers in the first virtual urban traffic environment based on the road information and the vehicle network trajectory information; the initial cluster centers are locations with high vehicle network trajectory density;

[0020] For each of the initial cluster centers, the roadside communication units covering the same road as the initial cluster center are added to the cluster of the initial cluster center to obtain a second virtual urban traffic environment.

[0021] Optionally, after obtaining the second virtual urban traffic environment, the method further includes:

[0022] For each cluster, based on the vehicle network trajectory information, the vehicle trajectory and the road around the roadside communication unit within a period of time, the affinity between the road and the roadside communication unit is calculated;

[0023] When the affinity between the road and the roadside communication unit is less than a set threshold, the connection between the road and the roadside communication unit is disconnected.

[0024] In a second aspect, the present invention provides a computer device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of a vehicle-mounted task scheduling optimization method in a vehicle network environment as described in the first aspect.

[0025] In a third aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of a method for optimizing vehicle task scheduling in a connected vehicle environment as described in the first aspect.

[0026] In a fourth aspect, the present invention provides a computer program product, comprising a computer program, which, when executed by a processor, implements the steps of a method for optimizing vehicle task scheduling in a connected vehicle environment as described in the first aspect.

[0027] According to the specific embodiments provided by the present invention, the present invention discloses the following technical effects:

[0028] This invention provides a method, device, medium, and product for optimizing on-board task scheduling in a connected vehicle environment. The method first collects geographic information, road information, and vehicle network trajectory data for the target area. Subsequently, a virtual urban traffic environment is constructed based on this geographic information. Next, a genetic algorithm deployment strategy is used to deploy roadside communication units (RSUs) within this virtual environment, thereby forming a first virtual urban traffic environment. To further improve efficiency, the method utilizes principal component clustering, combined with road information and vehicle network trajectory data, to cluster the RSUs in the first virtual environment, thereby forming a second virtual urban traffic environment. This new environment contains multiple principal component clusters composed of multiple RSUs. Finally, based on the principal component clusters of the second virtual environment, the method employs a vehicle state transition algorithm and an RSU state transition algorithm to determine the multi-computation offloading process for on-board tasks. The method selects relatively stable RSUs to construct clusters and performs clustering based on road and vehicle network trajectory information. This design enables the sharing of computational results within clusters, expanding the range of vehicle activity and enabling vehicles with similar tasks to share results within the region, effectively conserving computing resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0030] Figure 1 A flowchart of a method for optimizing vehicle-mounted task scheduling in a connected vehicle environment provided by the first embodiment of the present invention;

[0031] Figure 2 This is a structural diagram of the scheduling optimization method provided in Example 1 of the present invention;

[0032] Figure 3 A schematic diagram of the vehicle state machine structure provided in the first embodiment of the present invention;

[0033] Figure 4 A schematic diagram of the RSU state machine structure provided in Example 1 of the present invention;

[0034] Figure 5 A schematic diagram comparing the delay reduction and coverage of the random deployment strategy provided in the first embodiment of the present invention;

[0035] Figure 6 A schematic diagram comparing the delay reduction and coverage of the genetic algorithm deployment strategy provided in Example 1 of the present invention;

[0036] Figure 7 This is a diagram of the internal structure of a computer device provided in Example 2 of the present invention. DETAILED DESCRIPTION

[0037] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0038] The purpose of the present invention is to provide a method, device, medium and product for optimizing vehicle-mounted task scheduling in a connected vehicle environment. The method can use the trajectory information of roads and vehicle networks to provide a clustering basis. The results of the calculation can be shared within the cluster, thereby improving the efficiency of vehicle task delivery and saving computing resources.

[0039] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0040] Example 1

[0041] like Figure 1 As shown, this embodiment provides a method for optimizing vehicle-mounted task scheduling in a connected vehicle environment, including:

[0042] Step 101: Obtain geographic information, road information, and vehicle network trajectory information of a target area.

[0043] Step 102: Construct a virtual urban traffic environment based on the geographic information.

[0044] Step 103: Based on the genetic algorithm deployment strategy, deploy roadside communication units in the virtual urban traffic environment to obtain a first virtual urban traffic environment.

[0045] Step 104: Based on the road information and the vehicle network trajectory information, a principal component clustering method is used to cluster the roadside communication units in the first virtual urban traffic environment to obtain a second virtual urban traffic environment; the second virtual urban traffic environment includes multiple principal component clusters; the principal component clusters are composed of multiple roadside communication units.

[0046] Step 105: Based on the principal component clusters of the second virtual urban traffic environment, a vehicle state transition algorithm and a roadside communication unit state transition algorithm are used to determine a multi-computation task offloading process of the vehicle-borne tasks.

[0047] This embodiment consists of two sub-solutions: Figure 2 As shown in the figure, they are: principal component cluster establishment adjustment algorithm and principal component cluster-based multi-computing task offloading scheme.

[0048] When executing steps 101-102, the specific steps may be as follows:

[0049] A virtual urban traffic environment was constructed using the Simulation of Urban Mobility (SUMO) platform. The experimental road network data was based on the Luxembourg SUMO Traffic Scenario (LuST Scenario). The LuST Scenario provides real-world traffic network data for Luxembourg, which can be used to evaluate the performance of connected vehicle applications and traffic management algorithms. However, due to the large size of the scenario, only a portion of the scenario was used for the experiment. The output traffic data was used for numerical simulation of the VANET. The network communication protocol and offloading algorithm between vehicles and RSUs were then developed on the omnetpp platform, establishing the experimental environment.

[0050] When executing step 103, the specific steps may be as follows:

[0051] In real-world scenarios, RSU deployment typically considers factors such as spacing control, traffic density requirements, and traffic peaks. Therefore, there are multiple possible RSU deployment strategies that meet these requirements. Multi-access edge computing (MEC) is typically integrated with RSUs to account for communication efficiency, so it makes sense to select a reasonable RSU deployment strategy that improves solution performance. MEC stands for Multi-access Edge Computing (MEC), and mobile edge computing allows vehicles to offload these tasks to surrounding Multi-access Edge Computing (MEC) servers, reducing service latency while also reducing the vehicle's computational burden.

[0052] Specifically, the RSU deployment strategy is as follows:

[0053] This embodiment studies an RSU deployment strategy. The deployment conditions mainly consider the traffic density requirement and interval, so there are two optimization goals: first, minimizing the VANET delay, and second, maximizing the coverage of the RSU service.

[0054] Among them, there are two deployment methods, one is random deployment strategy, the other is genetic algorithm deployment strategy,

[0055] Random Deployment: Consider a random RSU deployment approach. A node is selected at an intersection in the center of the map. From this location, concentric circles of increasing radius are created, with RSUs distributed between them, as shown in Table 1. These circles are divided based on the number of nodes assigned to each circle. The position of each RSU is then calculated, and valid locations near these coordinates are checked. If no valid map location exists, the RSU is placed in the seventh circle. This scheme serves as a baseline for evaluating the performance of the RSU deployment strategy.

[0056] Table 1: RSU random deployment distribution

[0057]

[0058] (2) Genetic Algorithm Deployment: The VANET system proposed in this embodiment includes two communication modes: vehicle-to-vehicle (V2V) and vehicle-to-infrastructure (V2I) communication. Their communication standards are dedicated short-range communication (DSRC) defined in IEEE802.11p and IEEE1609.4 DSRC / Wireless Access in Vehicular Environments (WAVE). Data transmission is considered here through the Greedy Perimeter Stateless Routing (GPSR) protocol [8] because the information flow can always find the shortest transmission path based on the locations involved.

[0059] Consider minimizing VANET latency, where total latency is defined as the sum of data transmission demand delays. Assuming a constant probability of offloading tasks, the data transmission demand is related to the number of vehicles on the road. The following formula expresses the specific optimization goal:

[0060]

[0061] Where Z is the network communication delay, represents the delay value reduced in time period t after the roadside communication unit is deployed at intersection j; is the flow through intersection j during time period t; α j ∈{0, 1}, when α j When it is 1, it means that a roadside communication unit is deployed at intersection j; j represents the number of newly covered road sections at intersection j, s represents the total number of intersections, and there are T time periods in a day.

[0062] The optimization formula for the coverage of the roadside communication unit service is specifically:

[0063]

[0064] Where Y is the coverage area of ​​the roadside communication unit service, l j represents the number of newly covered road sections at intersection j, s represents the total number of intersections, c represents the total number of road sections, and there are T time periods in a day; α j ∈{0, 1} represents that a roadside communication unit is deployed at intersection j.

[0065] In addition, assuming that the total number of RSUs is finite, the formula can be as follows:

[0066]

[0067] It can be seen that this is a multi-objective optimization model. If only coverage is considered, the deployment strategy will tend to minimize overlapping coverage, which will significantly increase the target. However, such a solution does not take into account the uneven distribution of traffic. Deploying more RSUs in areas with heavy traffic can reduce latency more, but this will inevitably reduce the coverage of urban roads.

[0068] Here we choose to merge the two objectives and change to single-objective optimization:

[0069]

[0070] Where a + b = 1. This problem is a binary integer programming problem, which is an NP-hard problem. There are many heuristic algorithms to solve this problem. Here, a genetic algorithm (GA) is used to solve this problem.

[0071] The steps to solve this problem are shown in Table 2 Algorithm 1:

[0072] Table 2 Algorithm 1

[0073]

[0074] When executing step 104, the specific steps may be as follows:

[0075] Based on the road information and the vehicle network trajectory information, a plurality of initial cluster centers in the first virtual urban traffic environment are determined; the initial cluster centers are locations with high vehicle network trajectory density.

[0076] For each of the initial cluster centers, the roadside communication units covering the same road as the initial cluster center are added to the cluster of the initial cluster center to obtain a second virtual urban traffic environment.

[0077] Specifically, in this traffic scenario, two network layers are considered: a wired network consisting of RSUs (Remote State Units) and an information network formed by roads and vehicle trajectories. The information network serves as the foundation and basis for the initialization and dynamic adjustment of RSU clusters. This section focuses on how to cluster the RSU network using the information network consisting of vehicle trajectories and the road network to improve the efficiency of task offloading in the connected vehicle scenario.

[0078] The cluster building solution is mainly divided into three parts:

[0079] (1) Initialization: The initialization process first selects the initial cluster center by analyzing the data. The cluster center represents the area with relatively dense traffic in the data. Next, the roads within the coverage area of ​​each RSU are recorded. Then, the initial cluster is established, and RSUs covering the same roads as the cluster center are added to the cluster.

[0080] (2) Based on the vehicle trajectory, the correspondence between the road network and the RSU is periodically adjusted. By recording the hit data of the vehicle trajectory on the roads around the RSU during the period, the affinity between the road and the RSU is calculated, and the road coverage of the RSU is updated. Roads with low affinity to the RSU are removed, or roads with high affinity to the RSU are added.

[0081] It also includes cluster adjustment, that is, disconnecting weakly connected clusters to form new clusters.

[0082] 1) Affinity Judgment: Assume that the intersection where the RSU is deployed connects four roads, where vehicle trajectories frequently pass through three of these paths. The remaining road is considered to be non-affinity with the RSU. The simplest model counts the number of times each of the four roads is hit by a vehicle trajectory, calculates the ratio, and then uses a fixed threshold to determine affinity. This method can encounter certain problems when the data volume is too small or too large. Therefore, this method is improved here by using segmented threshold judgment. For small data volumes, an absolute threshold is used; for large data volumes, a linear threshold is used.

[0083] 2) After affinity analysis, weakly connected clusters are disconnected from some roads that were originally within their coverage area. However, some clusters may still be connected by only a few edges. These clusters lack task sharing and spatial cohesion and need to be disconnected. A dynamic update algorithm based on the connectivity graph is used to identify and disconnect weakly connected clusters.

[0084] This part of the solution is shown in Table 3 Algorithm 2:

[0085] Table 3 Algorithm 2

[0086]

[0087] When executing step 105, the specific steps may be as follows:

[0088] After the cluster is established, considering that the existing unloading process cannot make good use of the multi-computing task sharing characteristics of the cluster, this solution redesigns the unloading process of vehicles and RSUs for the principal component cluster. Vehicle unloading: The scene is mainly composed of two types of nodes, vehicles and RSUs. The process of node task unloading and execution can be abstracted as a Mealy machine. That is, the next state is determined by the input message and the current state. Since different states actually correspond to different messages, we can identify the current state by the message type. The design of the vehicle state machine is as follows Figure 3 As shown: A two-level state machine is used here to identify the state of the vehicle. The main state machine changes its own state by judging whether the vehicle is within the communication coverage of the RSU. The main state machine has two states. When the vehicle is outside the communication range of the RSU, it is in the outR state. When in the outR state, when the vehicle enters the communication range of the RSU, the state changes to inR. The difference between the slave state machines inR and outR is mainly reflected in that when the vehicle is within the communication range of the RSU, it can choose to offload tasks to the RSU. The difference between the slave state machines inR and outR is mainly reflected in that when the vehicle is within the communication range of the RSU, it can choose to offload tasks to the RSU. Algorithm 3 gives the details of the vehicle state changes, and Table 4 Algorithm 3 is shown below:

[0089] Table 4 Algorithm 3

[0090]

[0091] Among them, RSU unloading: RSU state machine setting is as follows Figure 4 As shown:

[0092] The initial state of the RSU is the idle state, which periodically enters the selfB state and sends Beacon to nearby vehicles to indicate their resource usage status. When a task request message is received, it enters the onP state, and enters the onRes state after the task processing is completed; in the onRes state, if the vehicle is still within the communication range of this RSU, it will directly forward it back to the idle state, otherwise it will forward the task processing results to other RSUs in the cluster; when receiving a forwarded message from other RSU nodes, it will check the forwarded message type and make corresponding processing; when receiving a result request message from a vehicle, if it can serve the request, it will directly return, otherwise it will forward the request message if it cannot. Algorithm 4 gives the specific details of the RSU state changes, and Table 5 Algorithm 4 is shown below:

[0093] Table 5 Algorithm 4

[0094]

[0095] In addition, this embodiment aims to determine the impact of deployment strategies on the solution. Therefore, a suitable deployment strategy needs to be selected. Therefore, the effects of random deployment and deployment using genetic algorithms are compared. Next, the performance indicators of the algorithms will be compared when the number of vehicles in the scene changes and when the parameters change. Finally, the efficiency of other clustering algorithms will be compared. Figure 5-6 As shown in the figure, the RSU deployed by GA algorithm is better than random in terms of delay reduction and coverage. However, as the number of RSUs gradually increases, the map coverage of both approaches 100%, and the effects of the two are close. Figure 5-6 As shown in the figure: The main objects in the simulation experiment are vehicles and RSUs, and the other elements such as the red vehicle trajectory are the environment. The yellow node in the figure is the RSU, and the color of the box outside the RSU represents the cluster it belongs to at this time. Figure 5-6 It can be seen that as the vehicle continues to move, the cluster division of RSUs is also changing.

[0096] In one embodiment, a computer device is provided. The computer device may be a database, and its internal structure diagram may be as follows: Figure 7As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, abbreviated as I / O) and a communication interface. The processor, memory and input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. 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 pending transactions. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a data processing method is implemented.

[0097] In one embodiment, a computer device is also provided, including a memory and a processor, wherein a computer program is stored in the memory and can be run on the processor, and the processor implements the steps in the above method embodiments when executing the computer program.

[0098] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0099] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0100] It should be noted that the object information (including but not limited to object device information, object personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the object or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant laws, regulations and standards of relevant countries and regions.

[0101] 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 this application may include at least one of non-volatile and volatile memory. Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory may include random access memory (RAM) or external cache memory, etc. 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 the various embodiments provided herein 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 the various embodiments provided herein may be 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., but are not limited to these.

[0102] 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.

[0103] This document uses specific examples to illustrate the principles and implementation methods of the present invention. The above examples are only intended to help understand the method and core concept of the present invention. At the same time, those skilled in the art will find that the specific implementation methods and application scopes may vary based on the concept of the present invention. In summary, the contents of this specification should not be construed as limiting the present invention.

Claims

1. A method for optimizing vehicle-mounted task scheduling in a connected vehicle environment, characterized in that: include: Obtain geographic information, road information, and vehicle network trajectory information of the target area; constructing a virtual urban traffic environment according to the geographic information; Deploying a roadside communication unit in the virtual urban traffic environment based on a genetic algorithm deployment strategy to obtain a first virtual urban traffic environment; Based on the road information and the vehicle network trajectory information, a principal component clustering method is used to cluster the roadside communication units in the first virtual urban traffic environment to obtain a second virtual urban traffic environment; the second virtual urban traffic environment includes a plurality of principal component clusters; the principal component clusters are composed of a plurality of roadside communication units; Determining a multi-computation task offloading process for vehicle-borne tasks using a vehicle state transition algorithm and a roadside communication unit state transition algorithm based on the principal component clusters in the second virtual urban traffic environment; A two-level state machine is used to identify the status of the vehicle. The main state machine changes its state by determining whether the vehicle is within the communication coverage of the RSU. The main state machine has two states. When the vehicle is outside the communication range of the RSU, it is in the outR state. When the vehicle is in the outR state, the state changes to inR when it enters the communication range of the RSU. When the vehicle is within the communication range of the RSU, the task is unloaded to the RSU. The initial state of RSU is idle state. The state of RSU will periodically enter selfB state and send Beacon to nearby vehicles to indicate its resource usage status. When receiving task request information, RSU will enter onP state. When the task processing is completed, RSU will enter onRes. In onRes state, if the vehicle is still within the communication range of this RSU, it will directly forward back to idle state, otherwise it will forward the task processing result to other RSUs in the main component cluster. When receiving forwarded messages from other RSU nodes, it will check the forwarded message type. When receiving result request messages from vehicles, if it can serve the request, it will return directly; if not, it will forward the request message.

2. The method for optimizing vehicle task scheduling in a connected vehicle environment according to claim 1, characterized in that: The genetic algorithm deployment strategy is a deployment strategy aimed at optimizing network communication delay and coverage of roadside communication unit services.

3. The method for optimizing vehicle task scheduling in a connected vehicle environment according to claim 2, characterized in that: The optimization formula for the network communication delay is specifically: Where Z is the network communication delay, represents the delay value reduced in time period t after the roadside communication unit is deployed at intersection j; is the flow through intersection j during time period t; α j ∈{0,1}, when α j When it is 1, it means that a roadside communication unit is deployed at intersection j; s represents the total number of intersections, and there are T time periods in a day.

4. The method for optimizing vehicle task scheduling in a connected vehicle environment according to claim 2, wherein: The optimization formula for the coverage of the roadside communication unit service is specifically: Where Y is the coverage area of ​​the roadside communication unit service, l j represents the number of newly covered road sections at intersection j, s represents the total number of intersections, and c represents the total number of road sections; α j ∈{0,1}, when α j When it is 1, it means that a roadside communication unit is deployed at intersection j.

5. The method for optimizing vehicle task scheduling in a connected vehicle environment according to claim 1, characterized in that: Based on the road information and the vehicle network trajectory information, a principal component clustering method is used to cluster the roadside communication units in the first virtual urban traffic environment to obtain a second virtual urban traffic environment, specifically including: Determining a plurality of initial cluster centers in the first virtual urban traffic environment based on the road information and the vehicle network trajectory information; the initial cluster centers are locations with high vehicle network trajectory density; For each of the initial cluster centers, the roadside communication units covering the same road as the initial cluster center are added to the cluster of the initial cluster center to obtain a second virtual urban traffic environment.

6. The vehicle-mounted task scheduling optimization method in a connected vehicle environment according to claim 1 or 5, characterized in that: After obtaining the second virtual city traffic environment, the following steps are also included: For each cluster, based on the vehicle network trajectory information, the vehicle trajectory and the road around the roadside communication unit within a period of time, the affinity between the road and the roadside communication unit is calculated; When the affinity between the road and the roadside communication unit is less than a set threshold, the connection between the road and the roadside communication unit is disconnected.

7. A computer device comprising: A memory and a processor are provided with a computer program stored in the memory and runnable on the processor, characterized in that the processor executes the computer program to implement the steps of a vehicle-mounted task scheduling optimization method in a vehicle networking environment as described in any one of claims 1-6.

8. 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 vehicle-mounted task scheduling optimization method in a vehicle network environment as described in any one of claims 1 to 6 are implemented.

9. A computer program product comprising a computer program, characterized in that When the computer program / instruction is executed by a processor, the steps of a method for optimizing vehicle task scheduling in a connected vehicle environment as described in any one of claims 1 to 6 are implemented.

Images