Internet of vehicles resource scheduling method, device and system, and storage medium

Abstract

The application discloses a kind of Internet of Vehicles resource scheduling method and device, system, storage medium, comprising: according to the topology structure of each vehicle in Internet of Vehicles, the resource state information of each vehicle node is initialized;According to the resource state information of vehicle node, the vehicle node is preheated by multiple rounds of information exchange, and the intermediate state in the spectrum resource allocation under current iteration is obtained;According to the intermediate state of vehicle node spectrum resource allocation under current iteration, the importance of each node in global resource allocation is evaluated, and the scheduling sequence of resource allocation is generated;According to the scheduling sequence of resource allocation, according to the number of node in scheduling order, after receiving the completion signal of its previous numbered node, each vehicle node asynchronously executes spectrum resource allocation operation, and outputs resource scheduling result. The technical scheme of the application can efficiently solve the interference management problem in resource allocation, and optimize the performance of the whole system.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of Internet of Vehicles resource scheduling, and particularly relates to an Internet of Vehicles resource scheduling method and device, system and storage medium. BACKGROUND

[0002] As a core component of future intelligent transportation systems, Internet of Vehicles technology is widely used in automatic driving, fleet management, traffic monitoring and other fields. The multi-task communication resource allocation problem in Internet of Vehicles can be improved by effective resource scheduling to improve the performance of the system. The resource scheduling problem is similar to the graph coloring problem, that is, how to allocate different vehicles in limited spectrum resources to avoid interference and improve overall communication efficiency. The resource scheduling in Internet of Vehicles faces the challenges of optimal allocation of spectrum resources and interference management, especially in the case of frequent and dynamic communication between vehicles and base stations, how to optimize resource allocation, reduce conflicts and improve communication quality is an important problem.

[0003] With the progress of graph neural networks and reinforcement learning technology, researchers have begun to try to model each vehicle node in Internet of Vehicles as an autonomous agent, and make distributed resource allocation decisions through collaboration between agents. Literature 1 “Chao Zhu et al., “Multi-Task Communication Resource Allocation for MIMO-Based Vehicular Fog Computing,” IEEE Transactions on Vehicular Technology, vol. 73, no. 1, January 2024” proposes a multi-agent communication resource allocation framework, which uses deep learning and optimization algorithms to allocate resources for tasks in the Internet of Vehicles environment. However, these methods have the following problems in dynamic resource scheduling:

[0004] On the one hand, the traditional synchronization strategy is difficult to guarantee the stability and efficiency of resource scheduling in the complex communication environment and frequent signal interference of Internet of Vehicles; on the other hand, although some methods use node importance ranking for resource scheduling, they lack explicit modeling and measurement of vehicle “importance”, which makes it impossible to accurately prioritize scheduling key vehicles, thereby affecting the overall system performance. SUMMARY

[0005] The technical problem to be solved by the present application is to provide an Internet of Vehicles resource scheduling method and device, system and storage medium for optimizing the allocation of spectrum resources in a dynamic Internet of Vehicles environment; by introducing node importance evaluation and asynchronous multi-agent scheduling mechanism, the interference management problem in resource allocation can be efficiently solved, and the performance of the overall system can be optimized.

[0006] To achieve the above object, the application adopts the following technical solutions:

[0007] A vehicle networking resource scheduling method, comprising:

[0008] Step S1, initializing resource state information of each vehicle node according to the topological structure of each vehicle in vehicle networking;

[0009] Step S2, preheating the vehicle node through multiple rounds of information exchange according to the resource state information of the vehicle node, to obtain an intermediate state of spectrum resource allocation under the current iteration;

[0010] Step S3, evaluating the importance of each node in global resource allocation according to the intermediate state of spectrum resource allocation of the vehicle node under the current iteration, and generating a scheduling sequence of resource allocation;

[0011] Step S4, according to the scheduling sequence of resource allocation, asynchronously executing spectrum resource allocation operation by each vehicle node after receiving the completion signal of the node with the previous number in the scheduling sequence, and outputting the resource scheduling result.

[0012] Preferably, in step S3, the importance evaluation score of each vehicle node in the global resource allocation process is calculated according to the resource probability distribution overlap degree.

[0013] The application further provides a vehicle networking resource scheduling device, comprising:

[0014] A first processing module is configured to initialize resource state information of each vehicle node according to the topological structure of each vehicle in vehicle networking;

[0015] A second processing module is configured to preheat the vehicle node through multiple rounds of information exchange according to the resource state information of the vehicle node, to obtain an intermediate state of spectrum resource allocation under the current iteration;

[0016] A third processing module is configured to evaluate the importance of each node in global resource allocation according to the intermediate state of spectrum resource allocation of the vehicle node under the current iteration, and generate a scheduling sequence of resource allocation;

[0017] A fourth processing module is configured to asynchronously execute spectrum resource allocation operation by each vehicle node after receiving the completion signal of the node with the previous number in the scheduling sequence according to the scheduling sequence of resource allocation, and output the resource scheduling result.

[0018] Preferably, the third processing module calculates the importance evaluation score of each vehicle node in the global resource allocation process according to the resource probability distribution overlap degree.

[0019] The application further provides a vehicle networking resource scheduling system, comprising a memory and a processor, wherein the memory stores a computer program which is run by the processor, and the computer program performs the vehicle networking resource scheduling method when being run by the processor.

[0020] The application further provides a storage medium which stores a computer program, and the computer program performs the vehicle networking resource scheduling method when being run.

[0021] The application designs a node importance measurement of resource probability distribution overlap degree, which is used for dynamically identifying key vehicles which have significant influence in the resource scheduling process.

[0022] Compared with the traditional method, the application has the following beneficial effects:

[0023] 1) The application proposes a clear and calculable node importance index, which is based on the local conflict intensity of vehicle resource probability distribution overlap degree, and can effectively identify the vehicle nodes which have key influence in the vehicle networking spectrum resource allocation process, thereby improving the rationality of resource allocation order and the pertinence of decision.

[0024] 2) The application adopts an asynchronous multi-agent scheduling mechanism, and each node (vehicle) agent in the vehicle networking independently makes a resource scheduling decision under the asynchronous condition according to the local perception and strategy model, thereby avoiding the calculation bottleneck problem which may occur in the traditional synchronous execution, and improving the scheduling flexibility and adaptability of the system.

[0025] 3) The application introduces a local spectrum conflict probability estimation mechanism in the resource scheduling process, and when the vehicle node finds that the effective spectrum resource set is empty, the spectrum resource option can be dynamically expanded, thereby effectively controlling the conflict propagation and solution space constraint in the resource allocation process, and improving the adaptability of the model to different graph structures.

[0026] 4) The agent design and scheduling mechanism adopted by the application has good modularization characteristics, supports flexible replacement and integration of algorithm components, has theoretical basis and engineering feasibility for further extension to other graph theory decision problems (such as graph partitioning, covering, labeling, etc.), and can further optimize other resource scheduling problems in the vehicle networking. BRIEF DESCRIPTION OF DRAWINGS

[0027] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0028] Figure 1 This is a flowchart of the vehicle network resource scheduling method according to an embodiment of the present invention. Detailed Implementation

[0029] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0030] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0031] Example 1:

[0032] like Figure 1 As shown, this embodiment of the invention provides a vehicle network resource scheduling method, including:

[0033] Step S1: Initialize the resource status information of each vehicle node according to the topology of each vehicle in the vehicle network;

[0034] Step S2: Based on the resource status information of the vehicle nodes, the vehicle nodes are preheated through multiple rounds of information exchange to fully integrate the information between the nodes, thereby forming the intermediate state of spectrum resource allocation under the current iteration, that is, the resource allocation probability distribution of each node, which provides a basis for subsequent asynchronous optimization allocation.

[0035] Step S3: Based on the intermediate state of vehicle node spectrum resource allocation formed during the preheating stage, i.e. the resource allocation probability distribution of each node, assess the importance of each node in the global resource allocation, and generate the scheduling sequence required for subsequent optimization allocation accordingly.

[0036] Step S4: According to the scheduling sequence, after each vehicle node receives the completion signal from the preceding node in the scheduling sequence, it triggers an asynchronous resource selection operation and broadcasts the completion signal to all nodes after completion, so that subsequent nodes can determine whether it can be executed, and finally outputs the scheduling result.

[0037] As one embodiment of the invention, step S2 includes:

[0038] Step S21: Each vehicle node encapsulates its initial resource state information into a message containing vehicle identification, spectrum resource allocation probability vector, and neighbor node list, and broadcasts it to its neighboring vehicle nodes, and receives information from neighboring vehicle nodes, thereby achieving the first information aggregation among neighboring vehicle nodes.

[0039] Step S22: Each vehicle node updates its spectrum resource probability distribution based on the aggregated information of neighboring vehicle nodes, so that it can more accurately reflect the resource usage and interference relationship among nodes in the local network environment where it is located.

[0040] Step S23: Repeat steps S21-S22 until a preset number of iterations (e.g., 3 times) is reached, forming an intermediate state of vehicle node spectrum resource allocation, i.e., the resource allocation probability distribution of each node, for subsequent asynchronous resource optimization allocation.

[0041] As an embodiment of the application, step S3 includes:

[0042] Step S31: Obtain the current spectrum resource allocation state of all vehicle nodes in the Internet of Vehicles.

[0043] Step S32: According to the current spectrum resource allocation state, calculate the importance evaluation score of each vehicle node in the global resource allocation process through the resource probability distribution overlap degree between the vehicle node and the neighbor node.

[0044] Step S33: Sort all vehicle nodes with unallocated spectrum resources in descending order according to their importance scores to generate a scheduling sequence for resource allocation.

[0045] Further, in step S32, the importance score of the vehicle node is represented by a calculation method based on the resource probability distribution overlap degree, which is used to measure the potential impact of the node's resource allocation decision on the resource scheduling performance of the Internet of Vehicles. The calculation method is:

[0046] ;

[0047] wherein, represents the importance evaluation score of the i-th vehicle node in the global resource allocation process; represents the probability of node i selecting the k-th spectrum resource; represents the probability of node i's neighbor node j selecting the k-th spectrum resource; represents the set of neighbor nodes that have a direct communication connection relationship with node i; represents the total number of currently available spectrum resources for allocation.

[0048] As one embodiment of the present invention, step S4 specifically includes:

[0049] Step S41: After the first vehicle node in the scheduling sequence completes the aforementioned stable process of resource allocation probability distribution, it can automatically perform spectrum resource allocation operation without waiting for the completion signal, and broadcast the completion signal and its own number to the entire network after completion to start the entire scheduling process.

[0050] Step S42: For subsequent vehicle nodes in the scheduling sequence, the resource selection process can be triggered only after receiving the completion signal from the previous numbered node in the scheduling sequence. Based on its spectrum resource distribution probability and the actual resource occupancy of neighboring nodes, the optimal spectrum resource is selected for allocation decision.

[0051] Specifically, each vehicle node first selects the spectrum resource with the lowest conflict probability from its own available spectrum resource set for occupancy decision based on the pre-determined spectrum resource probability distribution (the stable probability distribution state obtained from step S21) and the currently determined resource occupancy information of neighboring nodes (i.e. the spectrum resources actually allocated by neighboring nodes).

[0052] The spectrum resource allocation decision specifically includes:

[0053] (1) The probability distribution of vehicle nodes based on the currently available spectrum resources In addition to the actual spectrum resources occupied by neighboring nodes, determine its own effective spectrum resource set. That is, the set of spectrum resources that do not conflict with the resource occupation of neighboring nodes.

[0054] (2) Vehicle nodes from the set of effective spectrum resources Select the spectrum resource with the highest occupancy probability. Specifically expressed as .

[0055] (3) If the current vehicle node has an effective spectrum resource set If the spectrum is empty (meaning all resources are occupied or conflicting with each other), the node dynamically adds new spectrum resources through the resource expansion mechanism and immediately occupies them to avoid resource conflicts.

[0056] (4) After the vehicle node completes the spectrum resource allocation decision, it immediately broadcasts the occupancy status to the neighboring nodes and updates its status for other nodes to refer to.

[0057] Step S43: After completing resource selection, the current node broadcasts a completion signal and its own number to all vehicle nodes so that the next node can determine whether it can be executed, thereby ensuring that the entire scheduling sequence proceeds in an asynchronous environment.

[0058] Step S44, if the current vehicle node finds that its valid spectrum resource set is empty (i.e. no available spectrum resource), additional spectrum resource options are dynamically introduced to expand the available spectrum set, and the one with the lowest conflict probability is immediately occupied to avoid resource allocation failure.

[0059] In summary, the embodiment of the application has the following characteristics:

[0060] 1. Dynamic scheduling optimization decision. By dynamically adjusting the spectrum resource scheduling order according to the importance of the node, the vehicle nodes that have a greater impact on the efficiency of spectrum resource allocation in the Internet of Vehicles are preferentially processed; the resource scheduling bottleneck can be quickly solved, and the problems of low efficiency and large amount of calculation caused by random or fixed scheduling order in traditional methods are avoided.

[0061] 2. Improve the utilization rate of computing resources. The application can preferentially process key nodes and update resource allocation decisions in real time, thereby reducing the backtracking calculation and resource waste caused by spectrum conflict; especially in large-scale Internet of Vehicles resource scheduling tasks, the consumption of computing resources is effectively reduced, the utilization rate of computing resources is significantly improved, and the efficient operation of the Internet of Vehicles system is ensured.

[0062] 3. Solve the conflict problem in complex Internet of Vehicles structure. The application can effectively handle the spectrum resource conflict problem between vehicle nodes in the Internet of Vehicles by introducing a dynamic spectrum expansion mechanism and a conflict-sensitive reward function, and reduce spectrum conflict in the resource scheduling process.

[0063] 4. The application adopts a decentralized scheduling strategy, independently completes resource scheduling decisions based on local information and importance scores of each node, avoiding the calculation bottleneck and synchronization problem caused by the central scheduler in traditional methods. Through an asynchronous multi-agent scheduling mechanism, each vehicle node makes resource allocation decisions based on local perception, improving scheduling flexibility and adaptability.

[0064] 5. Easy to integrate and deploy. The application has high flexibility and can quickly be compatible with existing Internet of Vehicles architecture. Through a simplified deployment process, it can efficiently execute in various Internet of Vehicles application scenarios and seamlessly interface with traditional communication platforms, while providing a convenient deployment path for practical applications.

[0065] Embodiment 2:

[0066] The embodiment of the application also provides an Internet of Vehicles resource scheduling device, comprising:

[0067] A first processing module is configured to initialize resource state information of each vehicle node according to a topology structure of vehicles in the Internet of Vehicles.

[0068] The second processing module is configured to perform preheating processing on the vehicle nodes through multiple rounds of information exchange according to the resource state information of the vehicle nodes, so as to obtain an intermediate state of spectrum resource allocation in the current iteration.

[0069] The third processing module is configured to evaluate the importance of each node in the global resource allocation according to the intermediate state of spectrum resource allocation of the vehicle nodes in the current iteration, and generate a scheduling sequence of resource allocation.

[0070] The fourth processing module is configured to perform spectrum resource allocation operation asynchronously by each vehicle node after receiving a completion signal of a node with a previous number in the scheduling sequence, and output a resource scheduling result.

[0071] As an embodiment of the present application, the third processing module calculates an importance evaluation score of each vehicle node in the global resource allocation process according to the resource probability distribution overlap degree.

[0072] Embodiment 3:

[0073] The embodiment of the present application also provides a vehicle networking resource scheduling system, which comprises a memory and a processor, and the memory stores a computer program running by the processor, and the computer program performs the vehicle networking resource scheduling method when running by the processor.

[0074] Embodiment 4:

[0075] The embodiment of the present application also provides a storage medium, which stores a computer program, and the computer program performs the vehicle networking resource scheduling method when running.

[0076] The above-described embodiments only describe the preferred modes of the present application, and do not limit the scope of the present application. Without departing from the design spirit of the present application, various modifications and improvements of the technical solutions of the present application made by those skilled in the art shall fall within the protection scope of the present application determined by the claims.

Claims

1. A method for resource scheduling in Internet of Vehicles, characterized in that, Comprising: Step S1, according to the topology structure of each vehicle in the Internet of vehicles, initialize the resource state information of each vehicle node; Step S2, according to the resource state information of the vehicle node, through multiple rounds of information exchange, the vehicle node is preheated, the preheating process includes broadcasting the resource state information of the vehicle node, receiving the resource state information of the neighbor vehicle node, and updating the resource allocation probability vector of the vehicle node based on the received information of the neighbor vehicle node, to form the intermediate state of the spectrum resource allocation in the current iteration; Step S3, according to the intermediate state of the spectrum resource allocation, the importance of each vehicle node in the global resource allocation is evaluated, and a scheduling sequence of resource allocation is generated; Step S4, according to the scheduling sequence of resource allocation, according to the number of nodes in the scheduling sequence, the spectrum resource allocation operation is executed asynchronously by each vehicle node after receiving the completion signal of the node with the previous number, and the resource scheduling result is output; Step S3 includes: Step S31, obtain the current spectrum resource allocation state of all vehicle nodes in the Internet of vehicles; Step S32, according to the current spectrum resource allocation state, calculate the importance evaluation score of each vehicle node in the global resource allocation process through the resource probability distribution overlap degree between the vehicle node and the neighbor node; Step S33, sort all vehicle nodes with unallocated spectrum resources in descending order according to their importance scores, and generate a scheduling sequence of resource allocation; In step S32, the importance score of the vehicle node is represented by a calculation method based on the resource probability distribution overlap degree, which is used to measure the potential influence of the node's resource allocation decision on the resource scheduling performance of the Internet of vehicles, and the calculation method is: ； wherein, represents the importance evaluation score of the ith vehicle node in the global resource allocation process; represents the probability of node i selecting the kth spectrum resource; represents the probability of the neighbor node j of node i selecting the kth spectrum resource; represents the neighbor node set having a direct communication connection relationship with node i; represents the total number of currently available spectrum resources for allocation; Step S4 includes: Step S41, the first vehicle node in the scheduling sequence can automatically execute the spectrum resource allocation operation after completing the aforementioned resource allocation probability distribution stabilization process without waiting for the completion signal, and broadcast the completion signal and its own number to the whole network after completion, so as to start the whole scheduling process; Step S42: for the subsequent vehicle nodes in the scheduling sequence, after receiving the completion signal of the node with the previous number in the scheduling sequence, trigger the resource selection process, select the optimal spectrum resource for allocation decision according to the spectrum resource distribution probability and the actual resource occupation of the adjacent node; Wherein, each vehicle node first selects the spectrum resource with the lowest conflict probability from the set of available spectrum resources according to the predetermined spectrum resource probability distribution and the current determined resource occupation information of the adjacent node for occupation decision; Step S43: after completing the resource selection, the current node broadcasts the completion signal and its own number to all vehicle nodes for the next node to judge whether it can be executed; Step S44, if the current vehicle node finds that its effective spectrum resource set is empty, dynamically introduce additional spectrum resource options to expand the available spectrum set, and immediately occupy the one with the lowest conflict probability.

2. A vehicle-to-everything resource scheduling apparatus implementing the vehicle-to-everything resource scheduling method of claim 1, characterized in that, Comprising: A first processing module is configured to initialize the resource state information of each vehicle node according to the topology structure of each vehicle in the Internet of vehicles; The second processing module is configured to perform preheating processing on the vehicle nodes through multiple rounds of information exchange according to resource state information of the vehicle nodes, and obtain an intermediate state of spectrum resource allocation in the current iteration; The third processing module is configured to evaluate the importance of each node in global resource allocation according to the intermediate state of spectrum resource allocation of the vehicle nodes in the current iteration, and generate a scheduling sequence of resource allocation; The fourth processing module is configured to perform spectrum resource allocation operation asynchronously by each vehicle node after receiving a completion signal of a node with a previous number in the scheduling sequence of the vehicle node, and output a resource scheduling result.

3. A vehicle-to-everything resource scheduling system, comprising: Comprise: A memory and a processor, the memory has a computer program stored thereon, which is run by the processor, and the computer program performs the vehicle networking resource scheduling method of claim 1 when being run by the processor.

4. A storage medium, characterized by The storage medium has a computer program stored thereon, which performs the vehicle networking resource scheduling method of claim 1 when being run.

Images