CN-121985382-A - Internet of vehicles resource management method, system, equipment and medium

CN121985382ACN 121985382 ACN121985382 ACN 121985382ACN-121985382-A

Abstract

The application discloses a method, a system, equipment and a medium for managing resources of the Internet of vehicles, wherein the method comprises the steps of obtaining a first node state of a first node, a second node state of a second node, a base station state of a third node and a request type of a resource request; the method comprises the steps of inputting a first node state, a second node state, a base station state of a third node and a request type into a node determining model to obtain a target node output by the node determining model, predicting future requests of each vehicle in the first node and future requests of each vehicle in the second node according to the first node state and the second node state respectively, determining a management strategy of resources corresponding to the resource requests according to the resource requests, the target node state of the target node, the future requests of each vehicle in the first node and the future requests of each vehicle in the second node, and determining optimal unloading nodes by combining the resource states of all nodes in the Internet of vehicles to improve the request processing efficiency and optimize the resource allocation.

Inventors

CAO DUN
XIAO WEIJIA
PENG CHI
ZHANG XINDI
WANG JIN

Assignees

长沙理工大学

Dates

Publication Date: 20260505
Application Date: 20260119

Claims (10)

1. A method for managing internet of vehicles resources, the method comprising: the method comprises the steps of responding to a resource request of a first node, acquiring a first node state of the first node, a second node state of a second node, a base station state of a third node and a request type of the resource request, wherein the first node comprises a vehicle initiating the resource request; inputting the first node state, the second node state, the base station state of the third node and the request type into a node determination model to obtain a target node output by the node determination model; predicting future requests of each vehicle in the first node and future requests of each vehicle in the second node according to the first node state and the second node state respectively; And determining a management strategy of resources corresponding to the resource request according to the resource request, the target node state of the target node, the future request of each vehicle in the first node and the future request of each vehicle in the second node.
2. The internet of vehicles resource management method according to claim 1, wherein the node determination model is constructed based on a cooperative game algorithm and a depth deterministic strategy gradient algorithm, and the node determination model determines that the target node is obtained by: Calculating a communication transmission rate between the first node and the second node according to the first node state and the second node state, and calculating a communication transmission rate between the first node and the third node according to the first node state and the base station state of the third node; A target node of the resource request is determined based on the first node status, a communication transmission rate between the first node and the second node, a communication transmission rate between the first node and the third node, and the request type.
3. The method of claim 2, wherein the node state comprises a node cache state, the base station state comprises a base station cache state, and the determining the target node for the resource request based on the first node state, the communication transmission rate between the first node and the second node, the communication transmission rate between the first node and the third node, and the request type comprises: Based on the request type, respectively calculating a time slot of the first node executing the resource request, a time slot of the second node executing the resource request and a time slot of the third node executing the resource request according to a node cache state of the first node, a node cache state of the second node, a base station cache state of the third node, a communication transmission rate between the first node and the second node, and a communication transmission rate between the first node and the third node; Determining a target node of the resource request based on the time slot of the first node executing the resource request, the time slot of the second node executing the resource request, and the time slot of the third node executing the resource request.
4. The internet of vehicle resource management method according to claim 3, wherein the request type includes a content request, and the calculating, based on the request type, a time slot in which the first node performs the resource request, a time slot in which the second node performs the resource request, and a time slot in which the third node performs the resource request according to a node cache state of the first node, a node cache state of the second node, a base station cache state of the third node, a communication transmission rate between the first node and the second node, and a communication transmission rate between the first node and the third node, respectively, includes: Determining a time slot for the first node to execute the resource request according to the node cache state of the first node under the condition that the request type is a content request; Calculating a time slot for the second node to execute the resource request according to the node cache state of the second node and the communication transmission rate between the first node and the second node; and calculating a time slot for the third node to execute the resource request according to the base station buffer status of the third node and the communication transmission rate between the first node and the third node.
5. The method according to claim 3, wherein the node status further includes a calculation rate, the request type includes a service request, and the calculating, based on the request type, a time slot in which the first node performs the resource request, a time slot in which the second node performs the resource request, and a time slot in which the third node performs the resource request according to the node cache status of the first node, the node cache status of the second node, the base station cache status of the third node, the communication transmission rate between the first node and the second node, and the communication transmission rate between the first node and the third node, respectively, includes: Under the condition that the request type is a service request, determining a transmission time slot for the first node to transmit the resource request according to the node cache state of the first node, and calculating a request time slot for the first node to request the resource corresponding to the resource request according to the data size of the resource request, the complexity of the resource request and the calculation rate of the first node; According to the transmission time slot of the first node for transmitting the resource request and the request time slot of the first node for requesting the resource corresponding to the resource request, calculating to obtain the time slot of the first node for executing the resource request; Calculating a transmission time slot of the second node for transmitting the resource request corresponding to the resource according to the node cache state of the second node and the communication transmission rate between the first node and the second node, and calculating the transmission time delay of the second node for transmitting the resource request according to the data size of the resource request and the communication transmission rate between the first node and the second node; Calculating a request time slot of the second node for requesting the resource corresponding to the resource request according to the data size of the resource request, the complexity of the resource request and the calculation rate of the second node; Calculating a time slot of the second node executing the resource request based on a transmission time slot of the second node transmitting the resource request corresponding to the resource, a transmission time delay of the second node transmitting the resource request, and a request time slot of the second node requesting the resource request corresponding to the resource; calculating a transmission time slot of the third node for transmitting the resource request corresponding to the resource according to the node cache state of the third node and the communication transmission rate between the first node and the third node, and calculating the transmission time delay of the third node for transmitting the resource request according to the data size of the resource request and the communication transmission rate between the first node and the third node; Calculating a transmission time slot of the third node for requesting the resource request according to the base station buffer status of the third node and the communication transmission rate between the first node and the third node; And calculating the time slot of the third node executing the resource request based on the transmission time slot of the resource request corresponding to the resource request transmitted by the third node, the transmission time delay of the resource request transmitted by the third node and the transmission time slot of the resource request requested by the third node.
6. The method of claim 1, wherein predicting future requests for each vehicle in the first node and future requests for each vehicle in the second node based on the first node state and the second node state, respectively, comprises: constructing a request prediction model through Ji Pufu distribution and a Hox model; Inputting the first node state into the request prediction model to obtain a future request of each vehicle in the first node output by the request prediction model after a preset time interval from the current moment; And inputting the state of the second node into the request prediction model to obtain a future request, which is output by the request prediction model, of each vehicle in the second node after a preset time interval from the current moment.
7. The method for managing resources of the internet of vehicles according to claim 1, wherein determining the management policy of the resources corresponding to the resource request according to the resource request, the target node state of the target node, the future request of each vehicle in the first node, and the future request of each vehicle in the second node comprises: constructing a resource management model based on a greedy algorithm; And inputting the resource request, the target node state of the target node, the future request of each vehicle in the first node and the future request of each vehicle in the second node into the resource management model to obtain a management strategy output by the resource management model.
8. An internet of vehicles resource management system, the system comprising: The system comprises an acquisition module, a third node, a cloud server and a communication module, wherein the acquisition module is used for responding to a resource request of a first node and acquiring a first node state of the first node, a second node state of the second node, a base station state of the third node and a request type of the resource request; the determining module is used for inputting the first node state, the second node state, the base station state of the third node and the request type into a node determining model to obtain a target node output by the node determining model; The prediction module is used for predicting future requests of each vehicle in the first node and future requests of each vehicle in the second node according to the first node state and the second node state respectively; And the management module is used for determining a management strategy of the resource corresponding to the resource request according to the resource request, the target node state of the target node, the future request of each vehicle in the first node and the future request of each vehicle in the second node.
9. An electronic device comprising at least one control processor and a memory communicatively coupled to the at least one control processor, the memory storing instructions executable by the at least one control processor to enable the at least one control processor to perform a method of internet of vehicles resource management as claimed in any one of claims 1 to 7.
10. A computer-readable storage medium storing computer-executable instructions for causing a computer to perform a method of managing internet of vehicles resources according to any one of claims 1 to 7.

Description

Internet of vehicles resource management method, system, equipment and medium Technical Field The application relates to the technical field of Internet of vehicles resource management, in particular to an Internet of vehicles resource management method, system, equipment and medium. Background The vigorous development of the Internet of vehicles has prompted various real-time applications such as intelligent navigation, collaborative awareness and the like, and the applications have strict requirements on calculation, cache resources and network delay. Because the vehicle resources are limited and the network environment is dynamically changeable, the traditional centralized cloud computing is difficult to meet the demands, and the mobile edge computing becomes a key technology for supporting real-time service of the Internet of vehicles by sinking the resources to edge nodes such as Road Side Units (RSUs), cooperative vehicles and the like. The vehicle requests are divided into content requests needing no computation and service requests needing further computation, and the system performance needs to be optimized through collaborative caching and computation unloading. However, the existing resource management technology jointly makes a buffer and unloading decision under a single time scale, so that the strategy updating cost is huge, or a double time scale separation frame is adopted to separate low-frequency buffer updating from high-frequency unloading decision, so that inter-time-slot internal connection is split, the system cost is increased, the response delay is increased, and the application scene of high concurrency and dynamic change of the Internet of vehicles is difficult to adapt. Disclosure of Invention The following is a summary of the subject matter described in detail herein. This summary is not intended to limit the scope of the claims. The main purpose of the disclosed embodiments is to provide a method, a system, a device and a storage medium for managing resources of a vehicle networking, which can determine an optimal unloading node by combining the resource states of all nodes in the vehicle networking to perform cooperative game, thereby improving the request processing efficiency and further optimizing the resource allocation. A first aspect of an embodiment of the present application provides a method for managing resources of an internet of vehicles, where the method includes: the method comprises the steps of responding to a resource request of a first node, acquiring a first node state of the first node, a second node state of a second node, a base station state of a third node and a request type of the resource request, wherein the first node comprises a vehicle initiating the resource request; inputting the first node state, the second node state, the base station state of the third node and the request type into a node determination model to obtain a target node output by the node determination model; predicting future requests of each vehicle in the first node and future requests of each vehicle in the second node according to the first node state and the second node state respectively; And determining a management strategy of resources corresponding to the resource request according to the resource request, the target node state of the target node, the future request of each vehicle in the first node and the future request of each vehicle in the second node. In some embodiments of the present application, the node determining model is constructed based on a cooperative game algorithm and a depth deterministic strategy gradient algorithm, and the node determining model determines the target node by the following steps: Calculating a communication transmission rate between the first node and the second node according to the first node state and the second node state, and calculating a communication transmission rate between the first node and the third node according to the first node state and the base station state of the third node; A target node of the resource request is determined based on the first node status, a communication transmission rate between the first node and the second node, a communication transmission rate between the first node and the third node, and the request type. In some embodiments of the present application, the node state includes a node cache state, the base station state includes a base station cache state, and the determining the target node of the resource request based on the first node state, the communication transmission rate between the first node and the second node, the communication transmission rate between the first node and the third node, and the request type includes: Based on the request type, respectively calculating a time slot of the first node executing the resource request, a time slot of the second node executing the resource request and a time slot of the third node executing the resource request according to a node