CN113626155A

CN113626155A - Control method, equipment and storage medium for computing resources in edge cloud server

Info

Publication number: CN113626155A
Application number: CN202111179380.6A
Authority: CN
Inventors: 杨小枫; 马野; 黄洪; 冯刚; 张晔
Original assignee: Guoqi Intelligent Control Beijing Technology Co Ltd
Current assignee: Guoqi Intelligent Control Beijing Technology Co Ltd
Priority date: 2021-10-11
Filing date: 2021-10-11
Publication date: 2021-11-09

Abstract

The invention provides a method, equipment and a storage medium for controlling computing power resources in an edge cloud server, which are used for receiving request information sent by a vehicle; the request information includes: target automatic driving level and vehicle driving information; generating a resource scheduling instruction according to the target automatic driving level, and determining a target edge cloud server according to the vehicle driving information; sending the resource scheduling instruction to the target edge cloud server to enable the target edge cloud server to create or update a twin container for the vehicle according to the resource scheduling instruction, and starting a functional computing node in the twin container; the functional computing power node is used for processing vehicle data to enable the vehicle to run at the target automatic driving level, computing power resources in the edge cloud server can be dynamically distributed to the vehicle according to the request of the vehicle, and the problem of high cost caused by deployment of a large amount of computing power in the vehicle is solved.

Description

Control method, equipment and storage medium for computing resources in edge cloud server

Technical Field

The invention relates to the technical field of automatic driving, in particular to a method, equipment and a storage medium for controlling computing power resources in an edge cloud server.

Background

With the development of electronic technology and sensor technology, automobile technology is also developing towards intellectualization. At present, more and more vehicles are provided with automatic driving systems, so that more convenience is provided for people's traveling.

In the prior art, the automatic driving system comprises different grades, namely the grades from L1 to L5, and when the grade of the automatic driving grade is higher, the larger the data amount needing to be processed by the automatic driving system is, the higher the requirement on the calculation force deployed in the vehicle is. The computational power here is the sum of the computational resources that the vehicle can call. However, if it is necessary to deploy computationally demanding on-board equipment in a vehicle in order to make the vehicle achieve the demand for automatic driving, the manufacturing cost of the vehicle may be increased. The vehicle data are thus processed with the aid of cloud computing.

Therefore, a method for controlling computing resources in an edge cloud server is urgently needed to be provided, so as to dynamically allocate the computing resources in the edge cloud server to a vehicle, and solve the problem of high cost caused by deployment of a large amount of computing power in the vehicle.

Disclosure of Invention

The invention provides a control method, equipment and a storage medium for computing power resources in an edge cloud server, which are used for dynamically distributing the computing power resources in the edge cloud server to a vehicle so as to solve the problem of high cost caused by deployment of a large amount of computing power in the vehicle.

In a first aspect, the present invention provides a method for controlling computing resources in an edge cloud server, which is applied to a central cloud server, and the method includes:

receiving request information sent by a vehicle; the request information includes: target automatic driving level and vehicle driving information;

generating a resource scheduling instruction according to the target automatic driving level, and determining a target edge cloud server according to the vehicle driving information; the target edge cloud server is an edge cloud server that provides computing resources to the vehicle;

sending the resource scheduling instruction to the target edge cloud server to enable the target edge cloud server to create or update a twin container for the vehicle according to the resource scheduling instruction, and starting a functional computing node in the twin container; the functional force node is configured to process vehicle data to cause the vehicle to travel at the target autopilot level.

Optionally, the vehicle driving information includes a vehicle position, and the determining the target edge cloud server according to the vehicle driving information includes:

determining the position of each edge cloud server;

determining edge cloud servers covering the vehicle position according to the vehicle position and the positions of the edge cloud servers;

and determining the target edge cloud server according to the edge cloud server covering the vehicle position.

Optionally, the vehicle driving information further includes a vehicle driving direction; determining the target edge cloud server from the edge cloud servers covering the vehicle location, comprising:

determining the number of edge cloud servers covering the vehicle position;

if the number of the determined edge cloud servers is one, determining the edge cloud servers as target edge cloud servers;

if the number of the determined edge cloud servers is multiple, the direction of each edge cloud server in the multiple edge cloud servers relative to the vehicle is obtained, and the edge cloud server with the direction consistent with the vehicle running direction is determined as the target edge cloud server.

Optionally, a central manager is disposed in the central cloud server, and generates a resource scheduling instruction according to the target automatic driving level, including:

the central manager determines a target function running on the edge cloud server and the calculation force required by the vehicle according to the target automatic driving level;

determining container configuration information of the created twin container according to the calculated force required by the vehicle; the resource scheduling instruction comprises the container configuration information and a target function running on the edge cloud server.

Optionally, a twin controller is arranged in the target edge cloud server, and a cooperative control component is arranged in the vehicle; sending the resource scheduling instruction to the target edge cloud server, including:

the center manager sends the resource scheduling instruction to the twin controller, so that the twin controller creates or updates a corresponding twin container for the vehicle according to container configuration information in the resource scheduling instruction, and starts a function calculation node corresponding to a target function running on the edge cloud server in the twin container;

correspondingly, the method further comprises the following steps:

and receiving vehicle IP address information sent by the cooperative control component, and sending the vehicle IP address information to the twin controller, so that the twin controller sends the IP address information of the twin container to the vehicle according to the vehicle IP address information to create a communication channel of the vehicle and the corresponding twin container, wherein the communication channel is used for transmitting vehicle data.

In a second aspect, the present invention provides a method for controlling computing resources in an edge cloud server, which is applied to a target edge cloud server, and the method includes:

receiving a resource scheduling instruction sent by a central cloud server; the resource scheduling instruction is generated by the central cloud server based on the request information of the vehicle; the request information includes a target automatic driving level and vehicle travel information; the vehicle driving information is used for the central cloud server to determine the target edge cloud server from a plurality of edge cloud servers;

creating or updating a twin container for the vehicle according to the resource scheduling instruction, and starting a functional computing power node in the twin container;

sending information that the twin container has activated a functional force node to a vehicle to cause the vehicle to switch an autonomous driving level to the target autonomous driving level upon receiving the information;

and processing the vehicle data based on the functional computing power node to enable the vehicle to run according to the target automatic driving level.

Optionally, a twin controller is disposed in the edge cloud server, and the resource scheduling instruction includes container configuration information; creating or updating a twin container for the vehicle in accordance with the resource scheduling instructions, comprising:

the twin controller, upon receiving the container configuration information, determining whether a twin container corresponding to the vehicle exists in the vehicle;

if the twin container corresponding to the vehicle does not exist, the twin controller creates a corresponding twin container for the vehicle according to the configuration information;

and if the twin container corresponding to the vehicle exists, the twin controller acquires the current configuration information of the twin container, and if the current configuration information is inconsistent with the container configuration information, the configuration information of the twin container is updated.

Optionally, the resource scheduling instruction further includes: a target function running on the edge cloud server; initiating a functional computational force node in the twin vessel, comprising:

determining a function calculation force node corresponding to the target function running on the edge cloud server in the twin container;

and controlling the corresponding function calculation node to start so as to realize that the target function in the vehicle is operated on the edge cloud server.

Optionally, a central manager is disposed in the central cloud server, and a cooperative control component is disposed in the vehicle, where the method further includes:

receiving vehicle IP address information sent by the central manager;

acquiring IP address information of the twin container, and sending the IP address information of the twin container to a vehicle according to the vehicle IP address information so that a cooperative control component of the vehicle creates a communication channel for the vehicle and the corresponding twin container; the communication channel is used for transmitting vehicle data.

Optionally, processing vehicle data based on the functional computing power node to enable the vehicle to travel according to the target automatic driving level includes:

receiving vehicle data sent by a perception function node component of the vehicle through the communication channel;

and processing the vehicle data through the function force calculation node to generate a vehicle control signal, and sending the vehicle control signal to a control function node assembly of the vehicle, so that the vehicle is controlled to run at the target automatic driving level according to the vehicle control signal.

In a third aspect, the present invention provides a method for controlling computing power resources in an edge cloud server, which is applied to a vehicle, and the method includes:

sending request information to a central cloud server, wherein the request information comprises: target automatic driving level and vehicle driving information; enabling the central cloud server to generate a resource scheduling instruction according to the target automatic driving level, determining a target edge cloud server according to the vehicle driving information, and sending the resource scheduling instruction to the target edge cloud server, so that the target edge cloud server creates or updates a twin container for the vehicle according to the resource scheduling instruction, and starts a functional computing power node in the twin container; the functional computing power node is used for processing vehicle data to enable the vehicle to run at the target automatic driving level;

and receiving the information of the started functional computing power node of the twin container sent by the edge cloud server, switching the automatic driving level to the target automatic driving level, and releasing the functional computing power node of the vehicle.

Optionally, a cooperative control component is disposed in the vehicle, a twin controller is disposed in the edge cloud server, and a central manager is disposed in the central cloud server, and the method further includes:

sending, by the coordinated control component, vehicle IP address information to the central cloud server to cause the central manager to send the vehicle IP address information to the twin controller;

receiving IP address information of a twin container sent by the twin controller through the cooperative control component, and creating a communication channel for the vehicle and the corresponding twin container according to the vehicle IP address information and the IP address information of the twin container; the communication channel is used for transmitting vehicle data.

Optionally, the method further includes:

detecting a state of the communication channel and a state of the twin container;

when the state of the communication channel and/or the state of the twin body container is abnormal, generating an automatic driving degradation strategy;

and controlling the vehicle to enter a corresponding automatic driving level according to the automatic driving degradation strategy.

Optionally, the generating the automatic driving degradation strategy includes:

determining an anomaly level of a communication channel according to the state of the communication channel, and/or determining an anomaly level of the twin container according to the state of the twin container;

generating the autopilot degradation maneuver according to the anomaly level of the communication channel and the anomaly level of the twin container.

In a fourth aspect, the present invention provides an apparatus for controlling computing resources in an edge cloud server, which is applied to a central server, and includes:

the first receiving module is used for receiving request information sent by a vehicle; the request information includes: target automatic driving level and vehicle driving information;

the generating module is used for generating a resource scheduling instruction according to the target automatic driving level and determining a target edge cloud server according to the vehicle driving information; the target edge cloud server is an edge cloud server that provides computing resources to the vehicle;

a first sending module, configured to send the resource scheduling instruction to the target edge cloud server, so that the target edge cloud server creates or updates a twin container for the vehicle according to the resource scheduling instruction, and starts a functional computing power node in the twin container; the functional force node is configured to process vehicle data to cause the vehicle to travel at the target autopilot level.

In a fifth aspect, the present invention provides an apparatus for controlling computing resources in an edge cloud server, which is applied to a target edge cloud server, and includes:

the second receiving module is used for receiving a resource scheduling instruction sent by the central cloud server; the resource scheduling instruction is generated by the central cloud server based on the request information of the vehicle; the request information includes a target automatic driving level and vehicle travel information; the vehicle driving information is used for the central cloud server to determine the target edge cloud server from a plurality of edge cloud servers;

the creating module is used for creating or updating a twin container for the vehicle according to the resource scheduling instruction and starting a functional computing force node in the twin container;

the second sending module is used for sending the information of the activated function force calculation node of the twin container to the vehicle so that the vehicle can switch the automatic driving level to the target automatic driving level after receiving the information;

and the processing module is used for processing vehicle data based on the functional computing power node so as to enable the vehicle to run according to the target automatic driving level.

In a sixth aspect, the present invention provides an apparatus for controlling computing resources in an edge cloud server, applied to a vehicle, the apparatus including:

a third sending module, configured to send request information to a central cloud server, where the request information includes: target automatic driving level and vehicle driving information; enabling the central cloud server to generate a resource scheduling instruction according to the target automatic driving level, determining a target edge cloud server according to the vehicle driving information, and sending the resource scheduling instruction to the target edge cloud server, so that the target edge cloud server creates or updates a twin container for the vehicle according to the resource scheduling instruction, and starts a functional computing power node in the twin container; the functional computing power node is used for processing vehicle data to enable the vehicle to run at the target automatic driving level;

and the third receiving module is used for receiving the information of the function calculation force node which is started by the twin container and sent by the edge cloud server, and switching the automatic driving level into the target automatic driving level.

In a seventh aspect, the present invention provides a system for controlling computing resources in an edge cloud server, including a central cloud server, an edge cloud server, and a vehicle; the central cloud server is configured to perform the method of any of the above first aspects, the edge cloud server is configured to perform the method of any of the above second aspects, and the vehicle is configured to perform the method of any of the above third aspects.

In an eighth aspect, the present invention provides an electronic device, comprising: at least one processor and memory;

the memory stores computer-executable instructions;

the at least one processor executing the computer-executable instructions stored by the memory causes the at least one processor to perform the method of controlling computing power resources in an edge cloud server according to any of the first, second or third aspects.

In a ninth aspect, the present invention provides a computer-readable storage medium, in which computer-executable instructions are stored, and when a processor executes the computer-executable instructions, the method for controlling computing resources in an edge cloud server according to any one of the above embodiments is implemented.

According to the control method, the control device and the storage medium for computing resources in the edge cloud server, the request information sent by the vehicle is received; the request information includes: target automatic driving level and vehicle driving information; generating a resource scheduling instruction according to the target automatic driving level, and determining a target edge cloud server according to the vehicle driving information; the target edge cloud server is an edge cloud server that provides computing resources to the vehicle; sending the resource scheduling instruction to the target edge cloud server to enable the target edge cloud server to create or update a twin container for the vehicle according to the resource scheduling instruction, and starting a functional computing node in the twin container; the functional computing power node is used for processing vehicle data to enable the vehicle to run at the target automatic driving level, computing power resources in the edge cloud server are dynamically distributed to the vehicle according to the request of the vehicle, and the problem of high cost caused by deployment of a large amount of computing power in the vehicle is solved.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and together with the description, serve to explain the principles of the invention.

Fig. 1 is a schematic view of an application scenario for controlling computing resources in an edge cloud server according to an embodiment of the present invention;

fig. 2 is a schematic flowchart of a method for controlling computing resources in an edge cloud server according to an embodiment of the present invention;

fig. 3 is a schematic view of a scenario of determining a target edge cloud server according to an embodiment of the present invention;

FIG. 4 is a schematic diagram of a scenario for creating a twin container and establishing a communication channel according to an embodiment of the present invention;

fig. 5 is a schematic flowchart of another method for controlling computing resources in an edge cloud server according to an embodiment of the present invention;

fig. 6 is a schematic flowchart of a method for controlling computing resources in an edge cloud server according to another embodiment of the present invention;

fig. 7 is a control apparatus for computing resources in an edge cloud server according to an embodiment of the present invention;

fig. 8 is a control apparatus for computing resources in an edge cloud server according to another embodiment of the present invention;

fig. 9 is a control apparatus for computing resources in an edge cloud server according to another embodiment of the present invention;

fig. 10 is a schematic diagram of a hardware structure of an electronic device according to an embodiment of the present invention.

With the above figures, certain embodiments of the invention have been illustrated and described in more detail below. The drawings and the description are not intended to limit the scope of the inventive concept in any way, but rather to illustrate it by those skilled in the art with reference to specific embodiments.

Detailed Description

Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention.

The terms to which the present invention relates will be explained first:

intelligent networked automobile operating System (Intelligent Connected Vehicle Operation System, ICVOS for short): the automobile is taken as a main body, the ordered and safe running of the automobile is realized by utilizing an environment perception technology, and the diversified information service is provided for users by means of a wireless communication network and the like. The intelligent networked automobile operating system consists of an environment sensing layer, a fusion layer, an intelligent decision-making layer and a control layer: the environment perception layer is used for realizing environment perception through a camera, a laser radar, a millimeter wave radar, a night vision sensor, a GPS/BDS and 4G/5G, V2X. The fusion layer is used for fusing information sensed by a plurality of devices, such as road identification, vehicle identification, pedestrian identification, traffic sign identification, traffic signal identification and driver fatigue identification. And the intelligent decision layer is used for carrying out decision analysis and judgment based on the identified information and generating a control strategy. The control layer is used for executing control strategies, such as brake and drive control, steering control, gear control, cooperative control, safety early warning control and human-computer interaction control.

Fig. 1 is a schematic view of an application scenario of controlling computing resources in an edge cloud server according to an embodiment of the present invention, where a central cloud server, an edge cloud server, and a vehicle in fig. 1 form a computing resource control system in the edge cloud server. In order to enable the vehicle to realize the function of automatic driving, the processes of environment perception, fusion, intelligent decision and control and the like are required to be automatically realized through the vehicle ICVOS.

The current automatic driving level is divided into five levels such as L1-L5, the L1 level is a driver assistance level, and the vehicle can realize constant-speed cruising and early warning functions; the level L2 is a partial automation level, and the vehicle can realize the functions of self-adaptive cruise, lane keeping, automatic parking, automatic lane changing and the like; the level L3 is a condition automation level, can realize the monitoring of the surrounding environment, can complete some driving tasks, but also needs the driver to keep alert all the time and take back the vehicle control right at any time; the L4 class and L5 class vehicles enable steering, braking, acceleration, monitoring of the vehicle and road, and in response to events, determining when to change lanes, turn, and use signals; the driver needs to be informed to switch to the automatic driving mode at the level L4, accurate judgment cannot be automatically made under complex driving conditions, and the method is mainly used in the scene that the vehicle runs in a city or on a highway; while at the L5 level the vehicle can control all key people in any scenario, environmental monitoring and identify complex driving conditions such as traffic jams.

It can be seen that, as the automatic driving level is higher, the more operations the vehicle needs to perform, and the larger the amount of data to be processed is, the vehicle needs to rely on calculation force to implement the data processing, and if vehicle-mounted equipment with higher calculation force requirement is deployed at the vehicle end, the manufacturing cost of the vehicle may be increased.

Referring to fig. 1, in order to solve the above problem, a vehicle first sends request information to a central cloud server, the central cloud server generates a resource scheduling instruction according to the request information, an edge cloud server creates a function computing power node in a twin container and an operating twin container according to the resource scheduling instruction, and notifies the vehicle of information of the started function computing power node, the vehicle can be switched to a target automatic driving level, and then the function computing power node can process vehicle data and control the vehicle to operate at the target automatic driving level, so that computing power resources in the edge cloud server can be dynamically allocated to the vehicle, and the automatic driving level which can be supported by the vehicle is improved on the basis of reducing the manufacturing cost of the vehicle.

Fig. 2 is a schematic flowchart of a method for controlling computing resources in an edge cloud server according to an embodiment of the present invention, where an execution subject of the method is an electronic device with computing capability disposed in a center cloud server, and as shown in fig. 2, the method includes:

s201, receiving request information sent by a vehicle; the request information includes: target autopilot level and vehicle travel information.

In this step, the target automatic driving level may be set by the user according to the current road condition or the user's requirement, and the user may determine the target automatic driving level that the user wants to achieve currently by touching a preset key set on the vehicle, and may generate a corresponding signal, so that the vehicle obtains the target automatic driving level that the user wants to drive at. In addition, the request information further includes vehicle travel information, and the vehicle travel information may include vehicle position information and a vehicle travel direction, and the vehicle position information may be acquired by a positioning module provided inside the vehicle. Specifically, the positioning module can acquire vehicle position information in real time or at preset time intervals; the vehicle traveling direction may be determined by collecting position information of the vehicle at two times and superimposing the position information on a map provided inside the vehicle.

After the vehicle receives a signal which is sent by a user and represents the target automatic driving level, the vehicle position information and the vehicle driving direction can be determined in real time, and the information is used as request information and sent to the central cloud server. The central cloud server may allocate computing resources in the matched edge cloud servers to the vehicle according to the target autopilot level. The target edge cloud server may also be determined from vehicle travel information.

S202, generating a resource scheduling instruction according to the target automatic driving level, and determining a target edge cloud server according to the vehicle driving information; the target edge cloud server is an edge cloud server that provides computing resources to the vehicle.

In this step, after receiving the request information sent by the vehicle, the central cloud server may generate a resource scheduling instruction according to the request information, where the resource scheduling instruction is used to instruct the edge cloud server to allocate computing resources to the vehicle, so that some functions of the vehicle may be implemented by the computing resources in the edge cloud server.

The target automatic driving levels of different levels need different calculation resources, and when the level of the target automatic driving level is higher, the amount of data to be processed is larger, and the same calculation resources are needed. For example, the calculation power resource required when the target automated driving level is L4 is larger than that required when the target automated driving level is L2. Accordingly, upon receiving the target autopilot level, a corresponding scheduling instruction may be generated.

In addition, the central cloud server also needs to determine the target edge cloud server. The edge cloud server is a server in a machine room of the base station, such as a 5G base station. In the process of driving, the vehicle may pass through positions covered by a plurality of base stations, and therefore, the currently connected target edge cloud server may be determined according to the vehicle driving information. The target edge cloud server is an edge cloud server that provides computing resources to the vehicle.

S203, sending the resource scheduling instruction to the target edge cloud server so that the target edge cloud server creates or updates a twin container for the vehicle according to the resource scheduling instruction, and starting a functional computing node in the twin container; the functional force node is configured to process vehicle data to cause the vehicle to travel at the target autopilot level.

After determining the target edge cloud server, the central cloud server may send the determined resource scheduling instruction to the target edge cloud server. Likewise, for the edge cloud server, after receiving the resource scheduling instruction, the resource scheduling instruction may be executed. In particular, a twin container may be created or updated for the vehicle in order to operate certain functions of the vehicle in the twin container. In order to implement the operation of certain functions of the vehicle in the container, a function computation node in the container may be started, i.e. a process in the container implementing the function is started. It is thereby possible to achieve that the vehicle runs at the target autonomous driving level by utilizing the computational resources in the edge cloud server.

Furthermore, the nature of the twin container in the edge cloud is one container, with different containers being allocated to different vehicles to achieve a good isolation effect. In addition, the twin container is called because the operating system in the container is the same as that in the vehicle, and when part of the functions are operated in the edge cloud server, the twin container can be coordinated with other functions operated by the vehicle. In addition, the method also has the advantages of uniform design and realization of the operating system, and convenient upgrading and maintenance.

In practice, when there are many vehicles sending request information, the central cloud server sends a resource scheduling instruction to the target edge cloud server, but computational resources in the target edge cloud server are limited, and if the computational resources are completely allocated or the remaining computational resources are smaller than the computational resources required by the current vehicle, the edge cloud server generates information that the computational resources are insufficient and feeds the information back to the central cloud server, so that the central cloud server feeds the information back to the vehicle, and the vehicle receives the information and notifies the driver, so that the driver sends request information including a target automatic driving level with a lower level, or runs at the current automatic driving level.

In addition, when the vehicle does not use the automatic driving function, the central cloud server may send corresponding request information to the central cloud server, and the central cloud server may send a resource scheduling instruction to the target edge cloud server, where the resource scheduling instruction is used to instruct the corresponding twin container to stop operating the functional computing node and release the corresponding twin container. And according to the vehicle driving information, if the current target edge cloud server is not suitable for the vehicle, releasing a twin container corresponding to the vehicle in the target edge cloud server.

The invention provides a control method of computing resources in an edge cloud server, which comprises the steps of receiving request information sent by a vehicle; the request information includes: target automatic driving level and vehicle driving information; generating a resource scheduling instruction according to the target automatic driving level, and determining a target edge cloud server according to the vehicle driving information; the target edge cloud server is an edge cloud server that provides computing resources to the vehicle; sending the resource scheduling instruction to the target edge cloud server to enable the target edge cloud server to create or update a twin container for the vehicle according to the resource scheduling instruction, and starting a functional computing node in the twin container; the functional computing power node is used for processing vehicle data to enable the vehicle to run at the target automatic driving level, so that computing power resources are dynamically allocated to the vehicle, and the problem of high cost caused by deployment of a large number of computing power resources in the vehicle is solved.

The process of determining the target edge cloud server in the above embodiments is described in detail below.

determining the position of each edge cloud server; determining edge cloud servers covering the vehicle position according to the vehicle position and the positions of the edge cloud servers; and determining the target edge cloud server according to the edge cloud server covering the vehicle position.

In the embodiment, a method for determining the position of a target edge cloud server is provided. Specifically, the location of each edge cloud server may be obtained. Specifically, the positions of the edge cloud servers are stored in the central cloud server, and after the vehicle position is obtained, the positions of the edge cloud servers can be obtained based on the vehicle position. For example, a plurality of edge cloud servers whose locations are within a preset range centered on the vehicle location may be screened out. When the vehicle position is position a, the position of the edge cloud server that is screened is within a certain preset range with position a as the center. The preset range can be set according to actual conditions.

After the positions of the plurality of edge cloud servers are obtained, the edge cloud servers covering the positions of the vehicles can be determined, specifically, the coverage area of each edge cloud server is stored in the center cloud server, and if the position of the vehicle is judged to be in the coverage area of the edge cloud server, the edge cloud server can be determined to be the edge cloud server covering the positions of the vehicles.

After determining the edge cloud servers that cover the vehicle location, then a target edge cloud server may be determined. Specifically, the edge cloud server closest to the vehicle position may be determined as the target edge cloud server, so that the target edge cloud server may well perform data transmission with the vehicle.

Another specific method of determining a target edge cloud server is provided below.

determining the number of edge cloud servers covering the vehicle position; if the number of the determined edge cloud servers is one, determining the edge cloud servers as target edge cloud servers; if the number of the determined edge cloud servers is multiple, the direction of each edge cloud server in the multiple edge cloud servers relative to the vehicle is obtained, and the edge cloud server with the direction consistent with the vehicle running direction is determined as the target edge cloud server.

In the method, the number of edge cloud servers covering the vehicle position can be calculated firstly, and if only one edge cloud server covers the vehicle position, the edge cloud server is the target edge cloud server.

If a plurality of edge cloud servers cover the vehicle position, the edge cloud server closest to the vehicle position can be preferentially determined as the target edge cloud server, if the number of the edge cloud servers closest to the vehicle position is multiple, the direction of each edge cloud server relative to the vehicle can be determined, the edge cloud server with the direction consistent with the vehicle driving direction is determined as the target edge cloud server, and therefore the operations of creating and releasing twin containers in the edge cloud servers can be reduced.

Fig. 3 is a schematic view of a scenario for determining a target edge cloud server according to an embodiment of the present invention, as shown in fig. 3, a distance between a vehicle and an edge cloud server 1 is a distance L1, a distance between the vehicle and the edge cloud server is a distance L2 (which may be a position of a base station), the vehicle is located in a coverage area of the edge cloud server 1 and is also located in a coverage area of an edge cloud server 2, and when the distance L1 is equal to the distance L2, the target edge cloud server may be determined based on a position relationship between the edge cloud server and the vehicle. For example, when the vehicle driving direction is a direction a, the direction of the edge cloud server 1 relative to the vehicle is also a direction a, and the direction of the edge cloud server 2 relative to the vehicle is a direction B, the edge cloud server 1 may be determined as the target edge cloud server. If the edge cloud server 2 is used as a target edge cloud server, after the vehicle runs for a period of time, the vehicle cannot communicate with the vehicle, and a next edge cloud server needs to be allocated to the vehicle, so that the operation process is increased.

The determining method can allocate a proper edge cloud server for the vehicle, and can reduce the process of creating and releasing the twin body container in the edge cloud server under the condition of ensuring normal communication with the vehicle.

The process of generating the resource scheduling instruction is explained in detail below.

the central manager determines a target function running on the edge cloud server and the calculation force required by the vehicle according to the target automatic driving level; determining container configuration information of the created twin container according to the calculated force required by the vehicle; the resource scheduling instruction comprises the container configuration information and a target function running on the edge cloud server.

In this embodiment, a center manager is provided in the center cloud server, and the center manager stores therein the position information of each edge cloud server and the calculation power required to realize each automatic driving level, or the calculation power required to realize the target function of the vehicle. Meanwhile, the central manager also has computing power.

When the central manager receives the request information, it may determine the power required for the target autopilot level. In a specific implementation manner, an computation force table may be stored in the central manager, the computation force table represents computation forces required by different automatic driving levels, and the computation forces required by the automatic driving levels can be determined by querying the computation force table. For example, the calculation power may be measured using a value, which is greater when the automatic driving level is higher; the smaller the value of the calculated force when the automatic driving level is low.

In addition, after the target automatic driving level is obtained, the target function of the vehicle running in the edge cloud server can be determined, so that when the edge cloud server creates a container for the vehicle, a function calculation node corresponding to the target function of the vehicle in the container can be started. For example, when the target automatic driving level is L2, the adaptive cruise function, the lane keeping function, the automatic parking function, and the automatic lane change function may be determined as the target functions.

The target function determined to operate on the edge cloud server is determined based on a target automatic driving level, and in the target function, a default target function is determined to be the target function operating on the edge cloud server and a parameter corresponding to the function according to the automatic driving level. In addition, one or more target functions can be selected from supportable target functions at the automatic driving level according to the requirements of the user as the target functions running in the edge cloud server. If the target function is selected by the user, the required calculation power needs to be determined according to the target function selected by the user.

After determining the calculation force required by the vehicle, configuration information of the created twin container may be determined according to the required calculation force, wherein the configuration information is the memory size of the twin container and the number of cores of the allocated CPU. For example, when the calculation force required for the vehicle is larger, the memory size of the twin container and the number of CPU cores allocated may be set higher; as the calculation force required for the vehicle is smaller, the memory size of the twin container and the number of CPU cores allocated can be set lower. Wherein, there is a corresponding relation between the configuration information of the concrete setting and the required computing power, and the configuration information of the twin container can be determined by inquiring the corresponding relation.

After determining the target function and the container configuration information running on the edge cloud server, a resource scheduling instruction may be generated.

By the method for determining the resource scheduling instruction, the calculation resources of the corresponding twin container can be allocated to the vehicle so as to meet the requirement of the vehicle.

The following describes in detail a process in which the twin controller transmits a resource scheduling instruction to the target edge cloud server, and a process in which a communication channel between the edge cloud server and the vehicle is created.

correspondingly, the method further comprises the following steps:

Fig. 4 is a schematic diagram of a scenario for creating a twin container and establishing a communication channel according to an embodiment of the present invention, as shown in fig. 4, a twin controller is disposed in an edge cloud server, and a cooperative control component is disposed in a vehicle, where numbers in the diagram represent an execution sequence. Firstly, a system control component in a vehicle sends request information to a central manager, namely, an execution sequence 1; and after the central manager generates the resource scheduling instruction, the central manager sends the resource scheduling instruction to a twin controller in the target edge cloud server, namely, an execution sequence 2. And the twin controller creates or updates the twin container, namely the execution sequence 3, according to the container configuration information in the resource scheduling instruction after receiving the resource scheduling instruction.

Specifically, when a twin container is created or updated, whether a twin container corresponding to the vehicle exists in the current edge cloud server can be judged, if the corresponding twin container exists, whether the current configuration information of the twin container is consistent with the configuration information in the resource scheduling instruction is judged, and if the current configuration information of the twin container is consistent with the configuration information in the resource scheduling instruction, no processing is needed; and if the container configuration information is inconsistent with the container configuration information, updating the container configuration information. For example, if the configuration information of the twin container allocated to the vehicle when the vehicle is operated at the L2 level is configuration information 1, the configuration information of the twin container does not satisfy the requirement when the vehicle requests to be operated at the L4 level, and the configuration information needs to be updated.

In addition, when the vehicle is requested for the first time to operate at the target automatic driving level by the edge cloud server, a twin container corresponding to the vehicle does not exist in the edge cloud server, and a twin container of the corresponding configuration information needs to be created for the vehicle.

After the twin container is created, it is also necessary to activate a functional computation force node (ellipse in fig. 4) in the container, which may be regarded as a process of achieving a target function of the vehicle, and achieving one target function of the vehicle may be achieved by one functional computation force node provided in the twin container or may be achieved based on a plurality of functional computation force nodes. The target function of the vehicle can be operated on the edge cloud server by starting the corresponding function computing node.

Further, when the twin controller is activating the functional computing force node, the twin container may send information to the twin controller that it has activated. The twin controller may send information of the activated function algorithm node, i.e., execution sequence 4 in fig. 4, to the vehicle so that the vehicle knows the information and determines whether the automatic driving level may be switched.

In order to operate the target function of the vehicle on the edge cloud server, a communication channel (as a solid line between the intelligent networked automobile operating system ICVOS and the twin container in fig. 4, namely, an execution sequence 5) needs to be established between the intelligent networked automobile operating system ICVOS and the twin container, so that the perception function node of the vehicle can transmit the acquired vehicle data to the twin container, and the result of the data processing performed by the twin container can be sent to the control function node of the vehicle. Specifically, the central manager may receive vehicle IP address information transmitted by the cooperative control component and then transmit the vehicle IP address information to the twin controller, and the twin controller may acquire the created IP address information of the twin container and transmit the IP address of the twin container to the vehicle IP address based on the two pieces of address information, so that the vehicle creates a communication channel after receiving the IP address of the twin container. The communication channel may be a 5G communication channel.

After the communication channel is established, the vehicle can send the vehicle data to the corresponding twin container, the twin container can process the vehicle data to generate a vehicle control signal, the vehicle control signal is transmitted to the vehicle through the communication channel, and the vehicle runs according to the vehicle control signal.

For example: the vehicle can acquire road condition information around the vehicle through a perception function node (such as a camera), and can carry out preliminary identification on an acquired image, if a pedestrian is identified to exist in front, the identified information is sent to a twin container through a communication channel, after the twin container receives the information of the pedestrian in front, the function calculation node of an intelligent planning decision judges whether the vehicle collides with the pedestrian according to the information of the pedestrian in front and the running speed information of the vehicle, if so, a deceleration control instruction is generated, such as a braking instruction, and the braking instruction is sent to a control function node of the vehicle, and the control function node controls a corresponding vehicle component to execute the instruction. In addition, the actual instruction may be an instruction including information such as a steering angle and an accelerator.

In the above process, the twin container corresponding to the vehicle can be created or updated by sending the resource scheduling instruction to the twin controller, and the twin controller can be facilitated to send the IP address information of the twin container to the vehicle by receiving the vehicle IP address information, so that the vehicle establishes a communication channel therebetween.

Fig. 5 is a schematic flowchart of another method for controlling computing resources in an edge cloud server according to an embodiment of the present invention; as shown in fig. 5, the method is applied to a target edge cloud server, and the method includes:

step S501, receiving a resource scheduling instruction sent by a central cloud server; the resource scheduling instruction is generated by the central cloud server based on the request information of the vehicle; the request information includes a target automatic driving level and vehicle travel information; the vehicle travel information is used for the central cloud server to determine the target edge cloud server from the plurality of edge cloud servers.

When the edge cloud server is a target edge cloud server, a resource scheduling instruction sent by the center cloud server can be received. The resource scheduling instruction is generated by the central cloud server after receiving the request information of the vehicle, and the central cloud server may further determine the target edge cloud from the plurality of edge cloud servers.

Step S502, a twin container is created or updated for the vehicle according to the resource scheduling instruction, and a functional computing force node is started in the twin container.

After receiving the resource scheduling instruction, the twin container may be created or updated for the vehicle according to the resource scheduling instruction, and specifically, the twin container may be created or updated according to the configuration information of the twin container. Furthermore, it is also necessary to activate a functional force node in the twin container so that the target function of the vehicle is operated in the twin container.

And step S503, sending the information of the activated function force calculation node of the twin container to the vehicle, so that the vehicle switches the automatic driving level to the target automatic driving level after receiving the information.

After the functional computing power node is started, information of the started functional computing power node can be sent to the vehicle, so that the vehicle can be informed, the vehicle can switch the automatic driving level, and the vehicle end releases the corresponding functional computing power node.

And step S504, processing vehicle data based on the functional calculation force node so that the vehicle runs according to the target automatic driving level.

After the functional force calculation node is started, if vehicle data transmitted by the vehicle based on the communication channel is received, the vehicle data can be processed based on the functional force calculation node, a control signal is generated, and the generated control signal is sent to the vehicle, so that the vehicle can run at a target automatic driving level according to the control signal.

According to the control method of the computing power resource in the edge cloud server, provided by the invention, a twin container is created or updated for a vehicle according to a resource scheduling instruction sent by a central cloud server, a functional computing power node is started in the twin container, information of the started functional computing power node of the twin container is sent to the vehicle, so that the automatic driving level of the vehicle is switched to the target automatic driving level after the vehicle receives the information, and vehicle data is processed based on the functional computing power node, so that the vehicle runs according to the target automatic driving level, and thus the twin container is dynamically created or updated for the vehicle, and the problem of high cost caused by deployment of a large amount of computing power resource in the vehicle is solved.

The process of creating or updating the twin container is described in detail below.

the twin controller, upon receiving the container configuration information, determining whether a twin container corresponding to the vehicle exists in the vehicle; if the twin container corresponding to the vehicle does not exist, the twin controller creates a corresponding twin container for the vehicle according to the configuration information; and if the twin container corresponding to the vehicle exists, the twin controller acquires the current configuration information of the twin container, and if the current configuration information is inconsistent with the container configuration information, the configuration information of the twin container is updated.

In this step, the execution subject is a twin controller in the edge cloud server, and the twin controller may determine whether or not a twin container corresponding to the vehicle exists after receiving the container configuration information, and may determine whether or not a twin container corresponding to the vehicle exists by vehicle identification information or vehicle IP address information, for example. In addition, for the process of creating or updating the twin body container, reference may be made to the detailed description in the foregoing embodiments, and details are not repeated here.

determining a function calculation force node corresponding to the target function running on the edge cloud server in the twin container; and controlling the corresponding function calculation node to start so as to realize that the target function in the vehicle is operated on the edge cloud server.

The resource scheduling instruction received by the twin controller further comprises target functions running on the edge cloud server, wherein the target functions can be functions corresponding to target automatic driving level defaults or a plurality of target functions selected by a user from the functions supported by the automatic driving level.

Different function force calculation nodes are arranged in the twin container, and the different function force calculation nodes can realize target functions in different vehicles. Therefore, after determining the target function running on the edge cloud server, the functional computing power node corresponding to the target function may be determined, for example, the corresponding functional computing power node may be determined based on the identifier of each target function. After determining the functional computing power node, the functional computing power node can be controlled to be started so as to realize that the target function in the vehicle runs on the edge cloud server.

receiving vehicle IP address information sent by the central manager; acquiring IP address information of the twin container, and sending the IP address information of the twin container to a vehicle according to the vehicle IP address information so that a cooperative control component of the vehicle creates a communication channel for the vehicle and the corresponding twin container; the communication channel is used for transmitting vehicle data.

After the twin container is created, a communication channel between the vehicle and the twin container needs to be established, the execution subject is a twin controller, and the twin controller can receive the vehicle IP address information sent by the central manager, and meanwhile, needs to acquire the IP address information of the twin container corresponding to the vehicle and send the IP address information of the twin container to the vehicle IP address, so that the cooperative control component in the vehicle can establish the communication channel between the two IP addresses.

receiving vehicle data sent by a cooperative control component of the vehicle through the communication channel; and processing the vehicle data through the functional force calculation node to generate a vehicle control signal, and sending the vehicle control signal to a cooperative control component of the vehicle, so that the vehicle is controlled to run at the target automatic driving level according to the vehicle control signal.

In this step, the functional calculation node needs to process the received vehicle data to generate the vehicle control signal, and for a specific process, reference may be made to the process of processing the vehicle data by the functional calculation node in the above embodiment, which is not described herein again.

Fig. 6 is a schematic flowchart of a method for controlling computing resources in an edge cloud server according to another embodiment of the present invention; as shown in fig. 6, the method is applied to a vehicle, and the method includes:

step S601, request information is sent to a central cloud server, and the request information comprises: target automatic driving level and vehicle driving information; enabling the central cloud server to generate a resource scheduling instruction according to the target automatic driving level, determining a target edge cloud server according to the vehicle driving information, and sending the resource scheduling instruction to the target edge cloud server, so that the target edge cloud server creates or updates a twin container for the vehicle according to the resource scheduling instruction, and starts a functional computing power node in the twin container; the functional force node is configured to process vehicle data to cause the vehicle to travel at the target autopilot level.

The above-mentioned implementation process has been described in detail in the foregoing embodiments, and the implementation manner and principle are similar, and are not described herein again.

Step S602, receiving information that the twin container has started the functional computation power node, which is sent by the edge cloud server, and switching the automatic driving level to the target automatic driving level, and releasing the functional computation power node of the vehicle.

In this step, the vehicle may switch the automatic driving level after receiving the information of the activated function computing power node sent by the edge cloud server. For example, if the vehicle is currently running at the level of L2, and if the vehicle is requested to run at the level of L4, after the request information is transmitted, and if the information of the activated function computing power node transmitted by the edge cloud service is received, it indicates that the edge cloud server supports the vehicle to run at the level of L4, the vehicle may automatically switch to the target automatic driving level. Or, prompt information can be sent, so that the user can switch manually according to the prompt information. Meanwhile, one end of the vehicle can release the corresponding functional force computing node.

The invention provides a method for controlling computing resources in an edge cloud server, which sends request information to a center cloud server, wherein the request information comprises the following steps: target automatic driving level and vehicle driving information; enabling the central cloud server to generate a resource scheduling instruction according to the target automatic driving level, determining a target edge cloud server according to the vehicle driving information, and sending the resource scheduling instruction to the target edge cloud server, so that the target edge cloud server creates or updates a twin container for the vehicle according to the resource scheduling instruction, and starts a functional computing power node in the twin container; the functional computing power node is used for processing vehicle data to enable the vehicle to run at the target automatic driving level, so that a twin container is dynamically created or updated for the vehicle, and the problem of high cost caused by deployment of a large amount of computing power resources in the vehicle is solved.

sending, by the coordinated control component, vehicle IP address information to the central cloud server to cause the central manager to send the vehicle IP address information to the twin controller; receiving IP address information of a twin container sent by the twin controller through the cooperative control component, and creating a communication channel for the vehicle and the corresponding twin container according to the vehicle IP address information and the IP address information of the twin container; the communication channel is used for transmitting vehicle data.

Optionally, the method further includes:

detecting a state of the communication channel and a state of the twin container; when the state of the communication channel and/or the state of the twin body container is abnormal, generating an automatic driving degradation strategy; and controlling the vehicle to enter a corresponding automatic driving level according to the automatic driving degradation strategy.

In addition, after the communication channel is established and the vehicle data is sent to the edge cloud server for processing, the cooperative control component of the vehicle may also detect the state of the communication channel and the state of the twin container in real time to determine whether an abnormality exists, and if the abnormality exists, the current automatic driving level needs to be lowered. And controls the vehicle to operate at a lower level of automatic driving level. Wherein, when the vehicle autodrive level decreases, the request information may be transmitted to the center cloud server again to cause the edge cloud server to update the configuration information of the twin container.

By detecting the states of the communication channel and the twin container, the automatic driving level can be adjusted in real time to avoid danger.

Optionally, the generating the automatic driving degradation strategy includes:

determining an anomaly level of a communication channel according to the state of the communication channel, and/or determining an anomaly level of the twin container according to the state of the twin container; generating the autopilot degradation maneuver according to the anomaly level of the communication channel and the anomaly level of the twin container.

In this step, when determining the degradation strategy, the abnormal situations of the communication channel and the twin container may be determined first, and in practice, the abnormal situations may be classified into certain levels, wherein a higher abnormal level may indicate a more serious fault, conversely, a lower abnormal level may indicate a smaller fault, and for different abnormal levels, the corresponding automatic driving level may be determined. For example, when the vehicle is operated at the automatic driving level of L4, if an abnormality occurs, and the abnormality level is low, it is possible to support automatic driving at a low level, and therefore, the automatic driving degradation strategy may be determined as the automatic driving level of L2.

By determining the autopilot degradation strategy according to the abnormal situation, the state of the edge cloud server can be made to meet the switched autopilot level.

Fig. 7 is a control apparatus 70 for computing resources in an edge cloud server according to an embodiment of the present invention, as shown in fig. 7, where the apparatus is applied to a central cloud server, and the apparatus includes:

a first receiving module 701, configured to receive request information sent by a vehicle; the request information includes: target automatic driving level and vehicle driving information;

a generating module 702, configured to generate a resource scheduling instruction according to the target automatic driving level, and determine a target edge cloud server according to the vehicle driving information; the target edge cloud server is an edge cloud server that provides computing resources to the vehicle;

a first sending module 703, configured to send the resource scheduling instruction to the target edge cloud server, so that the target edge cloud server creates or updates a twin container for the vehicle according to the resource scheduling instruction, and starts a functional computing power node in the twin container; the functional force node is configured to process vehicle data to cause the vehicle to travel at the target autopilot level.

Optionally, when determining the target edge cloud server according to the vehicle driving information, the generating module 702 is specifically configured to:

Optionally, when determining the target edge cloud server according to the edge cloud server covering the vehicle position, the generating module 702 is specifically configured to:

Optionally, when the generating module 702 generates the resource scheduling instruction according to the target automatic driving level, it is specifically configured to:

determining a target function running on the edge cloud server and the calculation force required by the vehicle according to the target automatic driving level; determining container configuration information of the created twin container according to the calculated force required by the vehicle; the resource scheduling instruction comprises the container configuration information and a target function running on the edge cloud server.

Optionally, the first sending module 703 is specifically configured to:

sending the resource scheduling instruction to the twin controller, so that the twin controller creates or updates a corresponding twin container for the vehicle according to container configuration information in the resource scheduling instruction, and starts a function calculation node corresponding to a target function running on the edge cloud server in the twin container;

correspondingly, the receiving module 701 is further configured to:

The control device for computing resources in an edge cloud server provided in the embodiment of the present invention can implement the control method for computing resources in an edge cloud server according to the embodiments shown in fig. 2 to fig. 4, and the implementation principle and the technical effect are similar, and are not described here again.

Fig. 8 is another apparatus 80 for controlling computing resources in an edge cloud server according to an embodiment of the present invention, as shown in fig. 8, where the apparatus is applied to a target edge cloud server, and the apparatus includes:

a second receiving module 801, configured to receive a resource scheduling instruction sent by a central cloud server; the resource scheduling instruction is generated by the central cloud server based on the request information of the vehicle; the request information includes a target automatic driving level and vehicle travel information; the vehicle driving information is used for the central cloud server to determine the target edge cloud server from a plurality of edge cloud servers;

a creating module 802, configured to create or update a twin container for the vehicle according to the resource scheduling instruction, and start a functional computing power node in the twin container;

a second sending module 803, configured to send information that the twin container has started a functional computing power node to a vehicle, so that the vehicle switches an automatic driving level to the target automatic driving level after receiving the information;

and the processing module 804 is used for processing the vehicle data based on the functional computing power node so as to enable the vehicle to run according to the target automatic driving level.

Optionally, the creating module 802 is configured to: after receiving the container configuration information, judging whether a twin container corresponding to the vehicle exists in the vehicle; if the twin container corresponding to the vehicle does not exist, the twin controller creates a corresponding twin container for the vehicle according to the configuration information; and if the twin container corresponding to the vehicle exists, the twin controller acquires the current configuration information of the twin container, and if the current configuration information is inconsistent with the container configuration information, the configuration information of the twin container is updated.

Optionally, the creating module 802 is further configured to: determining a function calculation force node corresponding to the target function running on the edge cloud server in the twin container; and controlling the corresponding function calculation node to start so as to realize that the target function in the vehicle is operated on the edge cloud server.

Optionally, the second receiving module is further configured to: receiving vehicle IP address information sent by the central manager;

the device further comprises an acquisition module, a storage module and a control module, wherein the acquisition module is used for acquiring the IP address information of the twin container and sending the IP address information of the twin container to the vehicle according to the vehicle IP address information so as to enable a cooperative control component of the vehicle to create a communication channel for the vehicle and the corresponding twin container; the communication channel is used for transmitting vehicle data.

Optionally, the processing module 804 is specifically configured to:

after vehicle data sent by the perception function node of the vehicle are received through the communication channel, the vehicle data are processed through the function force calculation node to generate a vehicle control signal, and the vehicle control signal is sent to the control function node of the vehicle, so that the vehicle is controlled to run at the target automatic driving level according to the vehicle control signal.

The control device for computing resources in an edge cloud server provided in the embodiment of the present invention can implement the control method for computing resources in an edge cloud server in the embodiment shown in fig. 5, and the implementation principle and the technical effect are similar, and are not described here again.

Fig. 9 is a control apparatus 90 for computing resources in an edge cloud server according to another embodiment of the present invention, as shown in fig. 9, where the apparatus is applied to a vehicle, and the apparatus includes:

a third sending module 901, configured to send request information to a central cloud server, where the request information includes: target automatic driving level and vehicle driving information; enabling the central cloud server to generate a resource scheduling instruction according to the target automatic driving level, determining a target edge cloud server according to the vehicle driving information, and sending the resource scheduling instruction to the target edge cloud server, so that the target edge cloud server creates or updates a twin container for the vehicle according to the resource scheduling instruction, and starts a functional computing power node in the twin container; the functional computing power node is used for processing vehicle data to enable the vehicle to run at the target automatic driving level;

a third receiving module 902, configured to receive information that the twin container has started a function calculation force node and sent by the edge cloud server, and switch an automatic driving level to the target automatic driving level.

Optionally, the third sending module 901 is specifically configured to: transmitting vehicle IP address information to the central cloud server to cause the central manager to transmit the vehicle IP address information to the twin controller;

the third receiving module 902 is further configured to: receiving IP address information of a twin container sent by the twin controller, and creating a communication channel for the vehicle and the corresponding twin container according to the vehicle IP address information and the IP address information of the twin container; the communication channel is used for transmitting vehicle data.

Optionally, the apparatus further comprises a detection module, a generation module and a control module, wherein the detection module is configured to detect a state of the communication channel and a state of the twin container; the generation module is used for generating an automatic driving degradation strategy when the state of the communication channel and/or the state of the twin body container is abnormal; the generation module is used for controlling the vehicle to enter a corresponding automatic driving level according to the automatic driving degradation strategy.

Optionally, the generating module is specifically configured to: determining an anomaly level of a communication channel according to the state of the communication channel, and/or determining an anomaly level of the twin container according to the state of the twin container; generating the autopilot degradation maneuver according to the anomaly level of the communication channel and the anomaly level of the twin container.

The control device for computing resources in an edge cloud server provided in the embodiment of the present invention can implement the control method for computing resources in an edge cloud server in the embodiment shown in fig. 6, and the implementation principle and the technical effect are similar, and are not described here again.

The embodiment also provides a control system of computing resources in the edge cloud server, which comprises a central cloud server, the edge cloud server and a vehicle; the central cloud server is used for executing the method corresponding to any one of the embodiments in fig. 1 to 4, the edge cloud server is used for executing the method corresponding to the embodiment in fig. 5, and the vehicle is used for executing the method corresponding to the embodiment in fig. 7.

Fig. 10 is a schematic diagram of a hardware structure of an electronic device according to an embodiment of the present invention. As shown in fig. 10, the electronic device provided in this embodiment includes: at least one processor 1001 and memory 1002. The processor 1001 and the memory 1002 are connected to each other via a bus 1003.

In a specific implementation process, the at least one processor 1001 executes the computer execution instructions stored in the memory 1002, so that the at least one processor 1001 executes the method for controlling computing resources in the edge cloud server in the foregoing method embodiment.

For a specific implementation process of the processor 1001, reference may be made to the above method embodiments, which have similar implementation principles and technical effects, and details of this embodiment are not described herein again.

In the embodiment shown in fig. 10, it should be understood that the Processor may be a Central Processing Unit (CPU), other general purpose processors, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of a method disclosed in connection with the present invention may be embodied directly in a hardware processor, or in a combination of the hardware and software modules within the processor.

The memory may comprise high speed RAM memory and may also include non-volatile storage NVM, such as at least one disk memory.

The bus may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, an Extended ISA (EISA) bus, or the like. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, the buses in the figures of the present application are not limited to only one bus or one type of bus.

The embodiment of the invention also provides a computer-readable storage medium, wherein a computer execution instruction is stored in the computer-readable storage medium, and when a processor executes the computer execution instruction, the method for controlling computing resources in the edge cloud server in the embodiment of the method is realized.

The computer-readable storage medium may be implemented by any type of volatile or non-volatile memory device or combination thereof, such as Static Random Access Memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic or optical disk. Readable storage media can be any available media that can be accessed by a general purpose or special purpose computer.

An exemplary readable storage medium is coupled to the processor such the processor can read information from, and write information to, the readable storage medium. Of course, the readable storage medium may also be an integral part of the processor. The processor and the readable storage medium may reside in an Application Specific Integrated Circuits (ASIC). Of course, the processor and the readable storage medium may also reside as discrete components in the apparatus.

Those of ordinary skill in the art will understand that: all or a portion of the steps of implementing the above-described method embodiments may be performed by hardware associated with program instructions. The program may be stored in a computer-readable storage medium. When executed, the program performs steps comprising the method embodiments described above; and the aforementioned storage medium includes: various media that can store program codes, such as ROM, RAM, magnetic or optical disks.

Finally, it should be noted that: the above embodiments are only used for illustrating the technical solutions of the present application, and not for limiting the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for controlling computing power resources in an edge cloud server is applied to a central cloud server, and the method comprises the following steps:

2. The method of claim 1, wherein the vehicle travel information includes a vehicle location, and determining a target edge cloud server from the vehicle travel information comprises:

determining the position of each edge cloud server;

3. The method of claim 2, wherein the vehicle travel information further includes a vehicle travel direction; determining the target edge cloud server from the edge cloud servers covering the vehicle location, comprising:

determining the number of edge cloud servers covering the vehicle position;

4. The method according to any one of claims 1 to 3, wherein a central manager is disposed in the central cloud server, and the generating of the resource scheduling instruction according to the target automatic driving level includes:

5. The method of claim 4, wherein a twin controller is disposed in the target edge cloud server and a coordinated control component is disposed in the vehicle; sending the resource scheduling instruction to the target edge cloud server, including:

correspondingly, the method further comprises the following steps:

6. A method for controlling computing power resources in an edge cloud server is applied to a target edge cloud server, and the method comprises the following steps:

7. The method of claim 6, wherein a twin controller is disposed in the edge cloud server, and the resource scheduling instructions comprise container configuration information; creating or updating a twin container for the vehicle in accordance with the resource scheduling instructions, comprising:

if no twin container corresponding to the vehicle exists, the twin controller creates a corresponding twin container for the vehicle according to the container configuration information;

8. The method of claim 6, wherein the resource scheduling instructions further comprise: a target function running on the edge cloud server; initiating a functional computational force node in the twin vessel, comprising:

9. The method according to any one of claims 6-8, wherein a central manager is disposed in the central cloud server, and a coordinated control component is disposed in the vehicle, the method further comprising:

receiving vehicle IP address information sent by the central manager;

10. The method of claim 9, wherein processing vehicle data based on the functional force node to cause the vehicle to travel at the target autopilot level comprises:

receiving vehicle data sent by a perception function node of the vehicle through the communication channel;

and processing the vehicle data through the function force calculation node to generate a vehicle control signal, and sending the vehicle control signal to a control function node of the vehicle, so that the vehicle is controlled to run at the target automatic driving level according to the vehicle control signal.

11. A method for controlling computing power resources in an edge cloud server is applied to a vehicle, and the method comprises the following steps:

12. The method of claim 11, wherein the vehicle has a coordinated control component disposed therein, wherein the edge cloud server has a twin controller disposed therein, and wherein the center cloud server has a center manager disposed therein, the method further comprising:

13. The method of claim 12, further comprising:

14. The method of claim 13, wherein the generating an autonomous driving derating strategy comprises:

15. An apparatus for controlling computing power resources in an edge cloud server, applied to a central cloud server, the apparatus comprising:

16. An apparatus for controlling computing power resources in an edge cloud server, applied to a target edge cloud server, the apparatus comprising:

17. An apparatus for controlling computing power resources in an edge cloud server, applied to a vehicle, the apparatus comprising:

18. A control system of computing resources in an edge cloud server is characterized by comprising a center cloud server, the edge cloud server and a vehicle; the central cloud server is used for executing the method of any one of the preceding claims 1 to 5, the edge cloud server is used for executing the method of any one of the preceding claims 6 to 10, and the vehicle is used for executing the method of any one of the preceding claims 11 to 14.

19. An electronic device, comprising: at least one processor and memory;

the memory stores computer-executable instructions;

the at least one processor executing the memory-stored computer-executable instructions cause the at least one processor to perform the method of controlling computing power resources in an edge cloud server of any of claims 1-5 or 6-10 or 11-14.

20. A computer-readable storage medium, wherein the computer-readable storage medium stores computer-executable instructions, and when the computer-executable instructions are executed by a processor, the method for controlling computing resources in an edge cloud server according to any one of claims 1 to 14 is implemented.