KR20210056708A - A method for distributing workload on a server, and a method for support6ing workload of a server on a vehicle and the vehicle thereof - Google Patents

Abstract

Disclosed is a method of supporting to distribute a workload of a server by executing an artificial intelligence (AI) algorithm and/or a machine learning algorithm in a connected 5G environment for the Internet of Things. A server workload distribution method according to an embodiment of the present invention comprises: a step of receiving a service request from a first vehicle; a step of determining the service performance possibility of a server for the service request based on an available computing resource of the server; a step of determining an outsourcing service based on the determination of the service performance possibility; a step of determining a second vehicle based on the available computing resource of the vehicle in communication with the server; and a step of requesting the second vehicle to perform the outsourcing service.

Description

Server workload distribution method, vehicle server workload support method, and server workload support vehicle {A METHOD FOR DISTRIBUTING WORKLOAD ON A SERVER, AND A METHOD FOR SUPPORT6ING WORKLOAD OF A SERVER ON A VEHICLE AND THE VEHICLE AND THE VEHICLE THEREOF}

The present invention relates to a server workload distribution method, a server workload support method of a vehicle, and a server workload support vehicle, which enable distributed processing of the workload of an edge server to a vehicle by utilizing the available computational resources of the vehicle. will be.

When new technologies such as AI, Internet of Things, and autonomous driving become popular in the future, the amount of data coming and going through the network will increase explosively. Since the computing server must be able to process such enormous data without delay, a technology to complement cloud computing, which processes all data centrally, is needed. As a complementary measure, edge computing technology has recently attracted attention.

Edge computing is a computing method that supports data flow acceleration by processing data generated from various terminal devices in real time at the site or near the location of the data without sending it to a centralized data center such as the cloud.

An object of the present disclosure is to enable distributed processing of the workload of the edge server to the vehicle by utilizing the available computational resources of the vehicle.

An object of the present disclosure is to enable the distributed processing of the workload of the edge server to the vehicle in the event of an overload of the edge server, thereby enabling parallel processing of services between the edge server and the vehicle.

An object of the present disclosure is to access a service to be actually performed and data to be processed when analyzing available resources of a vehicle that will distribute the workload of an edge server.

An object of the present disclosure is to enable a vehicle to perform a real-time operation task that cannot be performed by an edge server in an overload situation of an edge server.

An object of the present disclosure is to recognize an overload situation through resource monitoring of a computational resource currently in use and a service to be provided to enable optimal distributed processing to a vehicle for service requests classified according to a preset criterion. .

The object of the embodiments of the present disclosure is not limited to the above-mentioned problems, and other objects and advantages of the present invention that are not mentioned can be understood by the following description, and will be more clearly understood by the embodiments of the present invention. will be. In addition, it will be appreciated that the objects and advantages of the present invention can be realized by the means shown in the claims and combinations thereof.

A method of distributing a workload of a server according to an exemplary embodiment of the present disclosure may include distributing and processing the workload of an edge server to a vehicle by using available computational resources of a vehicle.

Specifically, the method of distributing a workload of a server according to an embodiment of the present disclosure includes receiving a service request from a first vehicle, and performing a service of a server for a service request based on the computing resource available of the server. It may include the step of determining the likelihood.

In addition, the server workload distribution method includes determining at least one outsourcing service not to be performed by the server among services related to a service request or among services being performed by the server based on the determination of the service performance possibility, and communicating with the server. Determining a second vehicle based on the available computational resources of the vehicles, requesting the second vehicle to perform an outsourcing service, and transmitting data access information including a path accessible to the data required for the outsourcing service to the second vehicle. It may include the step of.

Through the method of distributing the workload of the server according to an embodiment of the present disclosure, it is possible to distribute the workload of the edge server to the vehicle by using the available computational resources of the vehicle in the event of an overload of the edge server, thereby providing real-time safety-related services. Sex can be guaranteed.

In addition, another method for implementing the present invention, another system, and a computer-readable recording medium storing a computer program for executing the method may be further provided.

Other aspects, features, and advantages other than those described above will become apparent from the following drawings, claims, and detailed description of the invention.

According to an embodiment of the present disclosure, it is possible to ensure real-time safety-related services by distributing and processing the workload of the edge server to the vehicle by utilizing the available computational resources of the vehicle in the event of an overload of the edge server.

In addition, it is possible to distribute the workload of the edge server to the vehicle in the event of an overload of the edge server, thereby enabling parallel processing of services between the edge server and the vehicle, thereby improving the performance of the server workload distribution system.

In addition, by recognizing an overload situation through resource monitoring of a computational resource currently in use and a service to be provided, and requesting a service classified according to a preset criterion to the vehicle, the optimal distributed processing to the vehicle may be possible.

In addition, it is possible to improve product reliability by enabling a vehicle to perform real-time computation tasks that cannot be performed by the edge server in an overload situation of the edge server.

In addition, by performing server workload distribution through 5G network-based communication, rapid data processing is possible, and thus the performance of the server workload distribution system can be further improved.

In addition, although the server workload supporting vehicle itself is a mass-produced uniform product, the user recognizes the server workload supporting vehicle as a personalized device, so that the effect of a user-customized product can be achieved.

The effects of the present invention are not limited to those mentioned above, and other effects not mentioned will be clearly understood by those skilled in the art from the following description.

1 is an exemplary diagram of an AI system-based server workload distribution system environment including a cloud network according to an embodiment of the present invention.
2 is a diagram schematically illustrating a communication environment of a server workload distribution system according to an embodiment of the present invention.
3 is a schematic block diagram of a server workload distribution system according to an embodiment of the present invention.
4 shows an example of a basic operation of an autonomous vehicle and a 5G network in a 5G communication system.
5 shows an example of an application operation of an autonomous vehicle and a 5G network in a 5G communication system.
6 to 9 show an example of an operation of an autonomous vehicle using 5G communication.
10 is a schematic block diagram illustrating a processor of a vehicle according to an embodiment of the present invention.
11 is an exemplary diagram of a service application list according to an embodiment of the present invention.
12 is a flowchart illustrating a method of distributing a workload of a server according to an embodiment of the present invention.
13 is a flowchart illustrating a method of supporting a server workload of a vehicle according to an embodiment of the present invention.
14 is a flowchart illustrating a server workload distribution system according to an embodiment of the present invention.

Advantages and features of the present invention, and a method of achieving them will be apparent with reference to embodiments described in detail together with the accompanying drawings. However, it should be understood that the present invention is not limited to the embodiments presented below, but may be implemented in various different forms, and includes all transformations, equivalents, and substitutes included in the spirit and scope of the present invention. . The embodiments presented below are provided to complete the disclosure of the present invention, and to completely inform the scope of the invention to those of ordinary skill in the art to which the present invention pertains. In describing the present invention, when it is determined that a detailed description of a related known technology may obscure the subject matter of the present invention, a detailed description thereof will be omitted.

The terms used in the present application are only used to describe specific embodiments, and are not intended to limit the present invention. Singular expressions include plural expressions unless the context clearly indicates otherwise. In the present application, terms such as include or have are intended to designate the existence of features, numbers, steps, actions, components, parts, or combinations thereof described in the specification, and one or more other features, numbers, and steps. It is to be understood that it does not preclude the possibility of the presence or addition of, operations, components, parts, or combinations thereof. Terms such as first and second may be used to describe various elements, but the elements should not be limited by the terms. The above terms are used only for the purpose of distinguishing one component from another component.

Vehicles described herein may be concepts including automobiles and motorcycles. Hereinafter, the vehicle is mainly described with respect to the vehicle.

The vehicle described in the present specification may be a concept including all of an internal combustion engine vehicle including an engine as a power source, a hybrid vehicle including an engine and an electric motor as a power source, an electric vehicle including an electric motor as a power source, and the like.

Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings, and in the description with reference to the accompanying drawings, the same or corresponding components are given the same reference numbers, and redundant descriptions thereof are omitted. I will do it.

1 is an exemplary diagram of an AI system-based server workload distribution system environment including a cloud network according to an embodiment of the present invention.

1, the server workload distribution system environment is an AI server 20, a robot 30a, an autonomous vehicle 30b, an XR device 30c, a user terminal 30d or a home appliance 30e, and a cloud network. (10) may be included. At this time, in the server workload distribution system environment, at least one of the AI server 20, the robot 30a, the autonomous vehicle 30b, the XR device 30c, the user terminal 30d, or the home appliance 30e is cloud It can be connected to the network 10. Here, the robot 30a to which the AI technology is applied, the autonomous vehicle 30b, the XR device 30c, the user terminal 30d, or the home appliance 30e may be referred to as AI devices 30a to 30e.

In this case, the robot 30a may refer to a machine that automatically processes or operates a task given by its own capabilities. In particular, a robot having a function of recognizing the environment and performing an operation by self-determining may be referred to as an intelligent robot. The robot 30a can be classified into industrial, medical, household, military, etc. depending on the purpose or field of use.

The autonomous driving vehicle 30b refers to a vehicle that is driven without a user's manipulation or with a user's minimal manipulation, and may also be referred to as an autonomous driving vehicle. For example, in autonomous driving, a technology that maintains a driving lane, a technology that automatically adjusts the speed such as adaptive cruise control, a technology that automatically travels along a specified route, and a technology that automatically sets a route when a destination is set, etc. All of these can be included. In this case, the autonomous vehicle can be viewed as a robot having an autonomous driving function.

The XR device 30c is a device that uses eXtended Reality (XR), and the extended reality is a generic term for virtual reality (VR), augmented reality (AR), and mixed reality (MR). do. VR technology provides only CG images of real-world objects or backgrounds, AR technology provides virtually created CG images on top of real object images, and MR technology is a computer that mixes and combines virtual objects in the real world. It's a graphic technology. XR technology can be applied to HMD (Head-Mount Display), HUD (Head-Up Display), mobile phones, tablet PCs, laptops, desktops, TVs, digital signage, etc. It can be called as.

The user terminal 30d may be provided with a service for operating or controlling the server workload distribution system through an authentication process after accessing the server workload distribution system application or the server workload distribution system site. In the present embodiment, the user terminal 30d having completed the authentication process may operate and control the server workload distribution system 1. In this embodiment, the user terminal 30d is a desktop computer, a smart phone, a notebook computer, a tablet PC, a smart TV, a mobile phone, a personal digital assistant (PDA), a laptop, a media player, a micro server, and a global positioning system (GPS). system) devices, e-book terminals, digital broadcasting terminals, navigation systems, kiosks, MP3 players, digital cameras, home appliances, and other mobile or non-mobile computing devices, but are not limited thereto. In addition, the user terminal 30d may be a wearable terminal such as a watch, glasses, hair band, and ring having a communication function and a data processing function. The user terminal 30d is not limited to the above-described contents, and a terminal capable of web browsing may be borrowed without limitation.

The home appliance 30e may include any one of all electronic devices provided in the home, and in particular, may include a terminal capable of implementing voice recognition and artificial intelligence, and a terminal that outputs one or more of an audio signal and a video signal. have. In addition, the home appliance 30e is not limited to a specific electronic device and may include various home appliances (eg, a washing machine, a dryer, a clothes processing device, an air conditioner, a kimchi refrigerator, etc.).

The cloud network 10 may constitute a part of the cloud computing infrastructure or may mean a network that exists in the cloud computing infrastructure. Here, the cloud network 10 may be configured using a 3G network, a 4G or Long Term Evolution (LTE) network, or a 5G network. That is, the devices 30a to 30e and 20 constituting the server workload distribution system environment may be connected to each other through the cloud network 10. In particular, the devices 30a to 30e and 20 may communicate with each other through a base station, but may communicate with each other directly without through a base station.

Such cloud networks 10 include wired networks such as local area networks (LANs), wide area networks (WANs), metropolitan area networks (MANs), and integrated service digital networks (ISDNs), wireless LANs, CDMA, Bluetooth, and satellite. A wireless network such as communication may be covered, but the scope of the present invention is not limited thereto. In addition, the cloud network 10 may transmit and receive information using short-range communication and/or long-distance communication. Here, short-range communication may include Bluetooth, radio frequency identification (RFID), infrared data association (IrDA), ultra-wideband (UWB), ZigBee, and wireless fidelity (Wi-Fi) technologies, and Communication includes code division multiple access (CDMA), frequency division multiple access (FDMA), time division multiple access (TDMA), orthogonal frequency division multiple access (OFDMA), single carrier frequency division multiple access (SC-FDMA) technology. I can.

Further, the cloud network 10 may include the connection of network elements such as hubs, bridges, routers, switches and gateways. The cloud network 10 may include one or more connected networks, such as a multi-network environment, including a public network such as the Internet and a private network such as a secure corporate private network. Access to the cloud network 10 may be provided through one or more wired or wireless access networks. Furthermore, the cloud network 10 may support an Internet of Things (IoT) network and/or 5G communication that exchanges and processes information between distributed components such as objects.

The AI server 20 may include a server that performs AI processing and a server that performs an operation on big data. In addition, the AI server 20 may be a database server that provides big data required to apply various artificial intelligence algorithms and data for operating the server workload distribution system 1. In addition, the AI server 20 allows remote control of the operation of the server workload distribution system 1 using a server workload distribution system application installed on the user terminal 30d or a server workload distribution system web browser. It may include a web server or an application server.

In addition, the AI server 20 includes at least one of the AI devices constituting the server workload distribution system environment, such as a robot 30a, an autonomous vehicle 30b, an XR device 30c, a user terminal 30d, or a home appliance 30e. One or more are connected through the cloud network 10 and may help at least part of the AI processing of the connected AI devices 30a to 30e. At this time, the AI server 20 may train an artificial neural network according to a machine learning algorithm in place of the AI devices 30a to 30e, and may directly store the learning model or transmit it to the AI devices 30a to 30e. At this time, the AI server 20 receives input data from the AI devices 30a to 30e, infers a result value for the received input data using a learning model, and provides a response or control command based on the inferred result value. It can be generated and transmitted to the AI devices 30a to 30e. Alternatively, the AI devices 30a to 30e may infer a result value for input data using a direct learning model, and generate a response or a control command based on the inferred result value.

Here, artificial intelligence (AI) is a field of computer science and information technology that studies how computers can do the thinking, learning, and self-development that human intelligence can do. It could mean being able to imitate intelligent behavior.

In addition, artificial intelligence does not exist by itself, but is directly or indirectly related to other fields of computer science. In particular, in modern times, attempts to introduce artificial intelligence elements in various fields of information technology and use them to solve problems in the field are being made very actively.

Machine learning is a branch of artificial intelligence that can include a field of research that gives computers the ability to learn without explicit programming. Specifically, machine learning can be said to be a technology that studies and builds a system that learns based on empirical data, performs prediction, and improves its own performance, and algorithms for it. Rather than executing strictly defined static program instructions, machine learning algorithms can take a way to build specific models to derive predictions or decisions based on input data.

2 is a diagram schematically illustrating a communication environment of a server workload distribution system according to an embodiment of the present invention. Parts that overlap with the description of FIG. 1 will be omitted.

Referring to FIG. 2, the server workload distribution system 1 essentially includes a first vehicle 100-1, a second vehicle 100-2, a first server 200, and a second server 300. can do.

In the present embodiment, in an overload situation of the edge server (hereinafter referred to as the first server 200) due to vehicle congestion, a real-time operation task of additional services not related to safety (eg, intelligent driving, infotainment service, etc.) is performed. Can't. Therefore, in the present embodiment, in a situation where the first server 200 is overloaded, the second vehicle 100-2 utilizes the available computational resources of a vehicle (hereinafter referred to as the second vehicle, 100-2) capable of supporting workload distribution. Instead, it can enable real-time computational tasks. That is, in the present embodiment, the second vehicle 100-2 may download an execution service and data of the first server 200 from the application server (hereinafter, referred to as the second server 300) to perform workload distribution processing.

In other words, in the present embodiment, the server workload distribution system 1 is based on the available computing resources of the first server 200 according to the service request from the first vehicle 100-1. Load distribution can be performed. At this time, the server workload distribution system 1 may download an application for supporting server workload distribution from the second server 300 so that the second vehicle 100-2 can perform workload distribution support. . That is, the server workload distribution system 1 may distribute the workload from the first server 200 to the second vehicle 100-2 by utilizing the available computational resources of the second vehicle 100-2. . The server workload distribution system 1 updates the autonomous driving information to the second server 300 in the above process, and the first server 200 transmits the data access path to the second vehicle 100-2 to provide the second The service application is downloaded from the vehicle 100-2, and the service can be performed by accessing the shared data.

In addition, the server workload distribution system 1 may further include other components such as a user terminal, a network, and nth vehicles 100-n. Further, in the present embodiment, symbols are differently indicated to distinguish between a vehicle requesting a service and a vehicle performing the service. However, the first vehicle 100-1 and the second vehicle 100-2 are included in the vehicle 100. Can be included.

In this embodiment, the first server 200 may be a Mobile Edge Computing (MEC) server, and may include the AI server 20 of FIG. 1, a server for a processor of the server workload distribution system 1, and the like. have. In addition, the second server 300 may include an AI server 20, a server for a processor of the server workload distribution system 1, a control server, and the like, and may mean collectively. When the first server 200 and the second server 300 are other servers not specified in the present embodiment, the connection relationship shown in FIG. 2 may be different.

The AI server may receive data collected from the vehicle 100 and perform learning for optimal workload distribution in a server overload situation.

The MEC server can serve as a general server, and is connected to a base station (BS) next to the road within a radio access network (RAN), providing flexible vehicle-related services and efficiently managing the network. Makes it possible to operate. In particular, network-slicing and traffic scheduling policies supported by the MEC server can help optimize the network. The MEC server is integrated in the RAN and may be located in an S1-User plane interface (eg, between a core network and a base station) in a 3GPP system. However, the present invention is not limited thereto and may be located in a base station. Each MEC server can be regarded as an independent network element, and does not affect the connection of an existing wireless network. The independent MEC server is connected to the base station through a dedicated communication network, and can provide specific services to several end-users located in the cell. These MEC servers and cloud servers can be connected to each other and share information through an internet-backbone. In addition, the MEC server is independently operated and can control a plurality of base stations. In particular, it is possible to perform services for autonomous vehicles, application operations such as virtual machines (VMs), and operations at the edge of a mobile network based on a virtualization platform. The base station (BS) is connected to both MEC servers and the core network to enable flexible user traffic scheduling required for performing a provided service. When a large amount of user traffic occurs in a specific cell, the MEC server may perform task offloading and cooperative processing based on an interface between adjacent base stations. That is, since the MEC server has an open operating environment based on software, new services from application providers can be easily provided. In addition, since the MEC server performs a service near the end-user, the data round trip time is shortened and the service provision speed is fast, so that the service waiting time can be reduced. In addition, MEC applications and Virtual Network Functions (VNF) can provide flexibility and geographical distribution in the service environment. Using this virtualization technology, not only various applications and network functions can be programmed, but only specific user groups can be selected or compiled only for them. Therefore, the provided service can be more closely applied to user requirements. And, along with the central control capability, the MEC server can minimize the interaction between base stations. This can simplify a process for performing basic functions of a network such as handover between cells. These functions can be particularly useful in autonomous driving systems with a large number of users. In addition, in the autonomous driving system, terminals on the road can periodically generate a large number of small packets. By performing a specific service in the RAN, the MEC server can reduce the amount of traffic that must be delivered to the core network, thereby reducing the processing burden of the cloud in the centralized cloud system and minimizing network congestion. . In addition, the MEC server integrates network control functions and individual services, thereby increasing the profitability of Mobile Network Operators (MNOs), and enabling rapid and efficient maintenance and upgrades through installation density adjustment. have. In addition, in this embodiment, the second server 300 may be a service application server that enables service applications that can be executed in the vehicle 100 to be provided.

The vehicle 100 may include a vehicle communication module, a vehicle control module, a vehicle user interface module, a driving operation module, a vehicle driving module, a driving module, a navigation module, a sensing module, and the like. Depending on the embodiment, the vehicle 100 may include other components other than the above components, or may not include some of the components described below.

Here, the vehicle 100 may be an autonomous vehicle, and may be switched from an autonomous driving mode to a manual mode or from a manual mode to an autonomous driving mode according to a user input received through the vehicle user interface module. In addition, the vehicle 100 may be switched from an autonomous driving mode to a manual mode or may be switched from a manual mode to an autonomous driving mode according to a driving situation. Here, the driving condition may be determined by at least one of information received by the vehicle communication module, external object information detected by the sensing module, and navigation information obtained by the navigation module.

When the vehicle 100 is operated in the autonomous driving mode, the vehicle 100 may be operated under the control of a driving module that controls driving, unloading, and parking operations. On the other hand, when the vehicle 100 is operated in a manual mode, the vehicle 100 may be driven by an input through a driver's driving operation module. The vehicle 100 may be connected to an external server through a communication network, and may be able to move along a preset route without driver intervention by using autonomous driving technology.

The vehicle user interface module is for communication between the vehicle 100 and the vehicle user, receives an input signal from the user, transmits the received input signal to the vehicle control module, and transmits the received input signal to the vehicle control module. 100) can provide information held. In this embodiment, a charging service providing service may be requested or charging service information may be received through the vehicle user interface module.

The driving module may control various operations of the vehicle 100, and in particular, may control various operations of the vehicle 100 in an autonomous driving mode. The driving module may include a driving module, an exit module, and a parking module, but is not limited thereto. In addition, the driving module may include a processor that is controlled by the vehicle control module. Each module of the driving module may individually include a processor. According to an embodiment, when the driving module is implemented in software, it may be a sub-concept of the vehicle control module. In this case, the driving module, the taking-out module, and the parking module may perform driving, taking out, and parking of the vehicle 100, respectively. In addition, the driving module, the taking-out module, and the parking module may each receive object information from a sensing module and provide a control signal to the vehicle driving module to perform driving, unloading, and parking of the vehicle 100. In addition, the driving module, the unloading module, and the parking module each receive a signal from an external device through a vehicle communication module, and provide a control signal to the vehicle driving module to perform driving, unloading, and parking of the vehicle 100. have. In addition, the driving module, the taking-out module, and the parking module may each receive navigation information from the navigation module and provide a control signal to the vehicle driving module to perform driving, unloading, and parking of the vehicle 100. The navigation module may provide navigation information to the vehicle control module. The navigation information may include at least one of map information, set destination information, route information according to destination setting, information on various objects on the route, lane information, and current location information of the vehicle.

The sensing module senses the state of the vehicle 100 using a sensor mounted on the vehicle 100, that is, detects a signal related to the state of the vehicle 100, and moves the vehicle 100 according to the detected signal. Information can be obtained. In addition, the sensing module may provide the acquired movement path information to the vehicle control module. In addition, the sensing module may sense objects around the vehicle 100 using a sensor mounted on the vehicle 100.

3 is a schematic block diagram of a server workload distribution system according to an embodiment of the present invention. In the following description, portions overlapping with the descriptions of FIGS. 1 and 2 will be omitted.

3, the server workload distribution system 1 includes a vehicle 100 including a first vehicle 100-1 and a second vehicle 100-2, a first server 200, and a second server. It may include (300). The vehicle 100 differs only in requesting a service or performing a service, but the configuration is the same, so that the description will be integrated into the vehicle 100.

The vehicle 100 may include a communication interface 110, a memory 120 and a processor 130.

The communication interface 110 may enable communication between the first server 200, the second server 300, and a vehicle. In addition, the communication interface 110 may be a communication module for performing communication with other external devices.

The communication interface 110 supports communication by a plurality of communication modes, receives server signals from the first server 200 and the second server 300, and receives the first server 200 and the second server 300. You can send a signal to it. In addition, the communication interface 110 may receive signals from one or more other vehicles, transmit signals to other vehicles, receive signals from user terminals, and transmit signals to user terminals. In addition, the communication interface 110 may include a communication module for communication in a vehicle.

Here, the plurality of communication modes are a vehicle-to-vehicle communication mode that communicates with other vehicles, a server communication mode that communicates with an external server, a short-range communication mode that communicates with a user terminal such as an in-vehicle user terminal, and an in-vehicle unit. It may include an in-vehicle communication mode, etc. for communicating with them. That is, the communication interface 110 may include a wireless communication module, a V2X communication module, and a short-range communication module.

The wireless communication module may transmit and receive signals to and from a user terminal or a server through a mobile communication network. Here, the mobile communication network is a multiple access system capable of supporting communication of multiple users by sharing used system resources (bandwidth, transmission power, etc.). Examples of multiple access systems include Code Division Multiple Access (CDMA) systems, Frequency Division Multiple Access (FDMA) systems, Time Division Multiple Access (TDMA) systems, Orthogonal Frequency Division Multiple Access (OFDMA) systems, and Single Carrier (SC-FDMA) systems. Frequency Division Multiple Access) system and MC-FDMA (Multi Carrier Frequency Division Multiple Access) system.

The V2X communication module transmits and receives mutual signals with the RSU through the V2I communication protocol in a wireless manner, transmits and receives mutual signals with other vehicles through the V2V communication protocol, and mutual signals with the user terminal, that is, pedestrians or users through the V2P communication protocol. Can send and receive. That is, the V2X communication module may include an RF circuit capable of implementing communication with infrastructure (V2I), vehicle-to-vehicle communication (V2V), and communication with user terminal (V2P) protocols. That is, the communication interface 110 may include at least one of a transmission antenna, a reception antenna, a radio frequency (RF) circuit capable of implementing various communication protocols, and an RF element to perform communication.

In addition, the short-range communication module may be connected to the driver's user terminal through a short-range wireless communication module, for example. In this case, the short-range communication module may be connected to the user terminal through wired communication as well as wireless communication. For example, when the driver's user terminal is registered in advance, the short-range communication module automatically connects to the vehicle 100 when the registered user terminal is recognized within a certain distance from the vehicle 100 (for example, in the vehicle). You can do it. That is, the communication interface 110 may perform short range communication, GPS signal reception, V2X communication, optical communication, broadcast transmission/reception, and Intelligent Transport Systems (ITS) communication functions. The communication interface 110 includes Bluetooth, Radio Frequency Identification (RFID), Infrared Data Association (IrDA), Ultra-Wideband (UWB), ZigBee, Near Field Communication (NFC), and Wireless-Fi (Wi-Fi). Fidelity), Wi-Fi Direct, and Wireless Universal Serial Bus (USB) technologies may be used to support short-range communication. Depending on the embodiment, the communication interface 110 may further support other functions other than the described functions, or may not support some of the described functions.

In addition, according to an embodiment, the overall operation of each module of the communication interface 110 may be controlled by a separate processor provided in the communication interface 110. The communication interface 110 may or may not include a plurality of processors. When a processor is not included in the communication interface 110, the communication interface 110 may be operated according to a processor of another device in the vehicle 100 or a processor 130 of the vehicle 100.

Meanwhile, FIG. 4 is a diagram showing an example of a basic operation of an autonomous vehicle and a 5G network in a 5G communication system.

When the vehicle 100 is operated in an autonomous driving mode, the communication interface 110 may transmit specific information to the 5G network (S1).

In this case, the specific information may include information related to autonomous driving.

The information related to autonomous driving may be information directly related to driving control of the vehicle. For example, the autonomous driving related information may include one or more of object data indicating objects around the vehicle, map data, vehicle state data, vehicle location data, and driving plan data. .

The information related to autonomous driving may further include service information necessary for autonomous driving. For example, the specific information may include information on a destination and a safety level of the vehicle input through the user interface unit.

In addition, the 5G network may determine whether to remotely control the vehicle 100 (S2).

Here, the 5G network may include a server or module that performs remote control related to autonomous driving.

In addition, the 5G network may transmit information (or signals) related to remote control to the autonomous vehicle (S3).

As described above, the information related to the remote control may be a signal directly applied to the autonomous vehicle, and may further include service information required for autonomous driving. In an embodiment of the present invention, the autonomous vehicle may provide a service related to autonomous driving by receiving service information such as insurance for each section selected on a driving route and information on dangerous sections through a server connected to a 5G network.

Hereinafter, an essential process for 5G communication between a vehicle 100 capable of autonomous driving and a 5G network (eg, an initial connection procedure between a vehicle and a 5G network) will be schematically described as follows with reference to FIGS. 5 to 9 same.

First, an example of a vehicle 100 capable of autonomous driving performed in a 5G communication system and an application operation through a 5G network is as follows.

The vehicle 100 performs an initial access procedure with the 5G network (initial access step, S20). In this case, the initial access procedure includes a cell search process for obtaining downlink (DL) synchronization and a process of obtaining system information.

In addition, the vehicle 100 performs a 5G network and a random access procedure (random access step, S21). In this case, the random access procedure includes an uplink (UL) synchronization acquisition process, a preamble transmission process for UL data transmission, a random access response reception process, and the like.

Meanwhile, the 5G network transmits an UL grant for scheduling transmission of specific information to the vehicle 100 capable of autonomous driving (UL grant reception step, S22).

The procedure for the vehicle 100 to receive the UL grant includes a scheduling procedure in which time/frequency resources are allocated for transmission of UL data to the 5G network.

In addition, the vehicle 100 capable of autonomous driving may transmit specific information to the 5G network based on the UL grant (specific information transmission step, S23).

Meanwhile, the 5G network may determine whether to remotely control the vehicle 100 based on specific information transmitted from the vehicle 100 (determining whether or not to remotely control the vehicle, S24).

In addition, the vehicle 100 capable of autonomous driving may receive a DL grant through a physical downlink control channel in order to receive a response to specific information previously transmitted from the 5G network (DL grant reception step, S25).

Thereafter, the 5G network may transmit information (or signals) related to remote control to the vehicle 100 capable of autonomous driving based on the DL grant (a step of transmitting information related to remote control, S26).

Meanwhile, a procedure in which an initial access process and/or a random access process and a downlink grant reception process are combined between the vehicle 100 capable of autonomous driving and the 5G network has been exemplarily described above, but the present invention is not limited thereto.

For example, an initial access process and/or a random access process may be performed through an initial access step, a UL grant reception step, a specific information transmission step, a determining whether to remotely control a vehicle, and a remote control-related information transmission step. In addition, the initial access process and/or the random access process may be performed through, for example, a random access step, a UL grant receiving step, a specific information transmission step, a determining whether to remotely control a vehicle, and a remote control-related information transmission step. . In addition, through the step of transmitting specific information, determining whether to remotely control the vehicle, receiving the DL grant, and transmitting the information related to the remote control, the vehicle 100 capable of autonomous driving is performed by combining the AI operation and the DL grant receiving process. Control can be made.

In addition, since the operation of the vehicle 100 capable of autonomous driving described above is merely exemplary, the present invention is not limited thereto.

For example, the operation of the vehicle 100 capable of autonomous driving may include an initial connection step, a random access step, a UL grant receiving step, or a DL grant receiving step, a specific information transmission step or a remote control-related information transmission step and selectively. Can be combined to operate. In addition, the operation of the vehicle 100 capable of autonomous driving may include a random access step, a UL grant reception step, a specific information transmission step, and a remote control-related information transmission step. Meanwhile, the operation of the vehicle 100 capable of autonomous driving may include an initial access step, a random access step, a specific information transmission step, and a remote control-related information transmission step. In addition, the operation of the vehicle 100 capable of autonomous driving may include a UL grant reception step, a specific information transmission step, a DL grant reception step, and a remote control-related information transmission step.

As shown in FIG. 6, the vehicle 100 including the autonomous driving module may perform an initial access procedure with a 5G network based on a synchronization signal block (SSB) in order to obtain DL synchronization and system information Connection step, S30).

In addition, the vehicle 100 capable of autonomous driving may perform a random access procedure with a 5G network to obtain UL synchronization and/or transmit UL (random access step, S31).

Meanwhile, the vehicle 100 capable of autonomous driving may receive a UL grant from a 5G network in order to transmit specific information (UL grant reception step, S32).

In addition, the vehicle 100 capable of autonomous driving transmits specific information to the 5G network based on the UL grant (specific information transmission step, S33).

In addition, the vehicle 100 capable of autonomous driving receives a DL grant for receiving a response to specific information from the 5G network (DL grant reception step, S34).

In addition, the vehicle 100 capable of autonomous driving receives remote control-related information (or signals) from the 5G network based on the DL grant (remote control-related information receiving step, S35).

A beam management (BM) process may be added to the initial access stage, and a beam failure recovery process related to PRACH (Physical Random Access CHannel) transmission may be added to the random access stage, and UL grant In the reception step, a Quasi Co-Located (QCL) relationship may be added in relation to the beam reception direction of the PDCCH (Physical Downlink Control CHannel) including the UL grant, and PUCCH/PUSCH including specific information in the specific information transmission step ( A QCL relationship may be added in relation to the beam transmission direction of Physical Uplink Shared CHannel). In addition, in the DL grant reception step, a QCL relationship may be added in relation to the beam reception direction of the PDCCH including the DL grant.

As shown in FIG. 7, the vehicle 100 capable of autonomous driving performs an initial access procedure with the 5G network based on the SSB in order to obtain DL synchronization and system information (initial access step, S40).

In addition, the vehicle 100 capable of autonomous driving performs a random access procedure with the 5G network to obtain UL synchronization and/or transmit UL (random access step, S41).

In addition, the vehicle 100 capable of autonomous driving transmits specific information to the 5G network based on a configured grant (UL grant reception step, S42). That is, instead of receiving the UL grant from the 5G network, a set grant may be received.

In addition, the vehicle 100 capable of autonomous driving receives remote control-related information (or signals) from the 5G network based on a setting grant (remote control-related information receiving step, S43).

As shown in FIG. 8, the vehicle 100 capable of autonomous driving may perform an initial access procedure with the 5G network based on the SSB in order to obtain DL synchronization and system information (initial access step, S50).

In addition, the vehicle 100 capable of autonomous driving performs a random access procedure with the 5G network to acquire UL synchronization and/or transmit UL (random access step, S51).

In addition, the vehicle 100 capable of autonomous driving receives a DL Preemption (DL) Information Element (IE) from the 5G network (DL preemption IE reception, S52).

In addition, the vehicle 100 capable of autonomous driving receives the DCI (Downlink Control Information) format 2_1 including the preemption instruction based on the DL preemption IE from the 5G network (DCI format 2_1 reception step, S53).

In addition, the autonomous vehicle 100 does not perform (or expect or assume) the reception of eMBB data in the resource (PRB and/or OFDM symbol) indicated by the pre-emption indication (eMBB data Reception not performed step, S54).

In addition, the vehicle 100 capable of autonomous driving receives a UL grant through a 5G network to transmit specific information (UL grant reception step, S55).

In addition, the vehicle 100 capable of autonomous driving transmits specific information to the 5G network based on the UL grant (specific information transmission step, S56).

In addition, the vehicle 100 capable of autonomous driving receives a DL grant for receiving a response to specific information from the 5G network (DL grant reception step, S57).

In addition, the vehicle 100 capable of autonomous driving receives remote control-related information (or signals) from the 5G network based on the DL grant (remote control-related information receiving step, S58).

As shown in FIG. 9, the vehicle 100 capable of autonomous driving performs an initial access procedure with the 5G network based on the SSB in order to obtain DL synchronization and system information (initial access step, S60).

In addition, the vehicle 100 capable of autonomous driving performs a random access procedure with the 5G network to acquire UL synchronization and/or transmit UL (random access step, S61).

In addition, the vehicle 100 capable of autonomous driving receives a UL grant through a 5G network to transmit specific information (UL grant reception step, S62).

When the transmission of specific information is repeatedly performed, the UL grant includes information on the number of repetitions, and the specific information is repeatedly transmitted based on the information on the number of repetitions (repetitive transmission of specific information, step S63).

In addition, the vehicle 100 capable of autonomous driving transmits specific information to the 5G network based on the UL grant.

In addition, repetitive transmission of specific information may be performed through frequency hopping, transmission of first specific information may be transmitted on a first frequency resource, and transmission of second specific information may be transmitted on a second frequency resource.

Specific information may be transmitted through a narrowband of 6RB (Resource Block) or 1RB (Resource Block).

In addition, the vehicle 100 capable of autonomous driving receives a DL grant for receiving a response to specific information from the 5G network (DL grant reception step, S64).

In addition, the vehicle 100 capable of autonomous driving receives information (or signals) related to remote control from the 5G network based on the DL grant (remote control related information receiving step, S65).

The 5G communication technology described above may be applied in combination with the embodiments proposed in the present specification to be described later in FIGS. 1 to 14, or may be supplemented to specify or clarify the technical features of the embodiments proposed in the present specification.

The memory 120 is connected to one or more processors 130 and stores codes that cause the processor 130 to control the server workload distribution system 1 when executed by the processor 130. I can.

For example, the memory 120 transmits vehicle information and collaborative operation information of the vehicle 100 to the first server 200, and requests to perform outsourcing services from the first server 200 and data necessary for the outsourcing service. Receiving data access information including a path accessible to, performing an outsourcing service based on the data access information, and at least of the calculation result of the outsourcing service to the service target vehicle 100 or the second server 300 of the outsourcing service. You can store codes that cause some to be transmitted.

In addition, the memory 120 may store codes that cause the available computational resources of the vehicle 100 to be periodically updated to the first server 200. And before the operation of transmitting the operation result, the memory 120 transmits the completion of the outsourcing service to the first server 200, and receives information for communication with the service target vehicle from the first server 200. You can store the resulting codes. In addition, the memory 120 stores codes that cause the vehicle 100 to transmit the intermediate result of the performed outsourcing service to the second server 300 as the vehicle 100 reports the deviation from the coverage of the first server 200. I can. In addition, the memory 120 may store codes that cause the authentication information for vehicle authentication to be transmitted to the second server 300 and to download an application. In addition, the memory 120 may store a pretrained deep neural network model to perform server workload distribution in an optimal manner.

That is, the memory 120 stores various codes and various information necessary for the server workload distribution system 1 and may include a volatile or nonvolatile recording medium.

Here, the memory 120 may include a magnetic storage medium or a flash storage medium, but the scope of the present invention is not limited thereto. The memory 120 may include internal memory and/or external memory, and volatile memory such as DRAM, SRAM, or SDRAM, one time programmable ROM (OTPROM), PROM, EPROM, EEPROM, mask ROM, flash ROM, Non-volatile memory such as NAND flash memory, or NOR flash memory, SSD. A flash drive such as a compact flash (CF) card, an SD card, a Micro-SD card, a Mini-SD card, an Xd card, or a memory stick, or a storage device such as an HDD.

The processor 130 may control the operation of the vehicle 100 so that the vehicle 100 supports workload distribution of the first server 200. That is, the processor 130 transmits vehicle information and operation information for collaboration to the first server 200, and the data including a path accessible to the data required for the outsourcing service and requesting the execution of the outsourcing service from the first server 200 Can receive access information. In addition, the processor 130 may perform an outsourcing service based on the data access information. In addition, the processor 130 may transmit at least a part of the calculation result of the outsourcing service to the service target vehicle of the outsourcing service or the second server 300.

The processor 130 is a kind of central processing unit and may control the operation of the entire vehicle 100 by driving control software installed in the memory 120. The processor 130 may include all types of devices capable of processing data. Here, the'processor' may refer to a data processing device embedded in hardware having a circuit physically structured to perform a function represented by, for example, a code included in a program or an instruction. As an example of a data processing device built into the hardware as described above, a microprocessor, a central processing unit (CPU), a processor core, a multiprocessor, and an application-specific integrated (ASIC) circuit), Digital Signal Processors (DSPs), Digital Signal Processing Devices (DSPDs), Programmable Logic Devices (PLDs), Processors, Controllers, Micro-controllers, Field Programmable Gate Array (FPGA) It may cover a processing device such as, but the scope of the present invention is not limited thereto.

In this embodiment, the processor 130 may perform machine learning such as deep learning so that the server workload distribution system 1 performs optimal server workload distribution, and the memory is a machine. Data used for running, result data, etc. can be stored.

Deep learning technology, a kind of machine learning, can learn by going down to the deep level in multiple stages based on data. Deep learning can represent a set of machine learning algorithms that extract core data from a plurality of data as the level increases.

The deep learning structure may include an artificial neural network (ANN), and for example, the deep learning structure consists of a deep neural network (DNN) such as a convolutional neural network (CNN), a recurrent neural network (RNN), and a deep belief network (DBN). Can be. The deep learning structure according to the present embodiment may use various known structures. For example, the deep learning structure according to the present invention may include CNN, RNN, DBN, and the like. RNN is widely used for natural language processing, etc., and is an effective structure for processing time-series data that changes with the passage of time, and can construct an artificial neural network structure by stacking layers every moment. The DBN may include a deep learning structure constituted by stacking RBM (restricted boltzman machine), which is a deep learning technique, in multiple layers. By repeating RBM learning, when a certain number of layers is reached, a DBN having the corresponding number of layers can be configured. CNN can include a model that simulates human brain function, which is made based on the assumption that when a person recognizes an object, it extracts the basic features of an object, then performs complex calculations in the brain and recognizes the object based on the result. .

On the other hand, learning of the artificial neural network can be accomplished by adjusting the weight of the connection line between nodes (if necessary, adjusting the bias value) so that a desired output is produced for a given input. In addition, the artificial neural network can continuously update the weight value by learning. In addition, a method such as back propagation may be used for learning of the artificial neural network.

That is, the server workload distribution system 1 may be equipped with an artificial neural network, that is, the processor 130 is an artificial neural network, for example, a deep neural network (DNN) such as CNN, RNN, and DBN. ) Can be included. Therefore, the processor 130 may learn the deep neural network for optimal server workload distribution in the server workload distribution system 1. Both unsupervised learning and supervised learning can be used as a machine learning method of such an artificial neural network. The processor 130 may control to update the artificial neural network structure after learning according to the setting.

Meanwhile, in the present embodiment, parameters for training a pre-trained deep neural network may be collected. At this time, in this embodiment, data used by an actual user may be collected in order to refine the learning model. When receiving user data from a user, in this embodiment, the input data may be stored in the server and/or memory regardless of the result of the learning model. That is, in this embodiment, the server workload distribution system 1 stores data for optimal server workload distribution in the server to configure big data, and executes deep learning at the server side to distribute the related parameters to the server workload. It can be updated inside the system (1) so that it is gradually elaborated. However, in the present embodiment, the edge of the vehicle 100, that is, the first server 200 may execute deep learning by itself to perform the update. That is, in the present embodiment, when the server workload distribution system 1 is initially set, deep learning parameters of laboratory conditions are embedded, and the update can be performed through data that is accumulated as an operation for server workload distribution is performed. . Accordingly, in the present embodiment, the collected data can be labeled to obtain a result through supervised learning, and the evolving algorithm can be completed by storing it in its own memory of the server workload distribution system. That is, the server workload distribution system 1 may collect data for optimal server workload distribution to generate a training data set, and train the training data set through a machine learning algorithm to determine a trained model. In addition, the server workload distribution system 1 may generate a retrained model by collecting data used by an actual user and retraining it in the server. Accordingly, in the present embodiment, even after determining as a trained model, data is continuously collected and retrained by applying a machine learning model, thereby improving performance with the retrained model. Hereinafter, details of the processor 130 will be described with reference to FIG. 10.

10 is a schematic block diagram illustrating a processor of a vehicle according to an embodiment of the present invention. In the following description, descriptions of portions overlapping with those of FIGS. 1 to 9 will be omitted.

Referring to FIG. 10, the processor 130 of the vehicle 100 includes an available resource management unit 131, a support request receiving unit 132, an access information receiving unit 133, a download management unit 134, a service execution unit 135, A processing result providing unit 136, an update management unit 137, a vehicle communication management unit 138, and a controller 139 may be included. Meanwhile, the vehicle 100 in FIG. 10 may refer to a second vehicle 100-2 that is requested to perform an outsourcing service.

The available resource management unit 131 may transmit vehicle information and collaborative operation information of the vehicle 100 to the first server 200. That is, as the vehicle 100 enters the coverage of the first server 200, vehicle information of the vehicle 100 and operation information for cooperation may be registered. In this case, the vehicle information may include at least one of an identifier of the vehicle 100, a type of the vehicle 100, a purpose of the vehicle 100, a production year of the vehicle 100, and a brand of the vehicle 100. In addition, the operation information for collaboration may include at least one of an operation resource of the vehicle 100, an executable distributed computing platform, and an available communication protocol. For example, the operation information for collaboration may include information such as CPU, GPU, and NPU, and may include platform information such as a VM and container capable of distributed software execution.

In addition, the available resource management unit 131 may periodically update the available computational resources of the vehicle 100 to the first server 200. In this case, the available resource management unit 131 may transmit the most recent available computational resource of the vehicle 100 or may transmit an average value of the available computational resources of the vehicle 100 for a predetermined period.

The support request receiving unit 132 may receive a request to perform an outsourcing service from the first server 200.

The access information receiving unit 133 may receive data access information including a path accessible to data required for an outsourcing service from the first server 200. In addition, the access information receiving unit 133 may receive a path and authentication information for downloading an application related to an outsourcing service. Here, the data access information may include information on the second server 300, a service application, and data.

The download management unit 134 may manage an application to be serviced downloaded from the second server 300. That is, the download management unit 134 may receive and manage a path for downloading an application related to the outsourcing service and authentication information for downloading, together with a request to perform the outsourcing service. At this time, the application to be serviced may include data and images, and it must be a format that can be executed in a VM or container environment of the platform of the vehicle to be serviced, and the application can be executed in a vehicle equipped with the execution environment.

The service execution unit 135 may perform an outsourcing service based on data access information including a path accessible to data required for the outsourcing service. The service execution unit 135 may connect to the second server 300 based on the data access information received from the first server 200. At this time, the second server 300 may perform authentication whether the vehicle 100 is a licensed vehicle. The service execution unit 135 may access data to the second server 300 to download an application related to an outsourcing service from the second server 300 and execute the application. In addition, the service execution unit 135 may run a corresponding service. That is, the service execution unit 135 may execute an application and perform an outsourcing service using data related to the outsourcing service stored in the second server 300.

After the outsourcing service is performed by the service execution unit 135, the processing result providing unit 136 performs an outsourcing service calculation result to a service target vehicle (eg, a first vehicle) or a second server 300 of the outsourcing service. At least some of the can be transmitted. In addition, the processing result providing unit 136 may transmit the completion of the outsourcing service to the first server 200 before transmitting the operation result. That is, the processing result providing unit 136 may report the execution status of the outsourcing service to the first server 200. Meanwhile, when the vehicle 100 deviates from the coverage of the first server 200, the processing result providing unit 136 may transmit an intermediate result of the performed outsourcing service to the second server 300.

The update management unit 137 may transmit and update service execution details to the first server 200 and the second server 300. In addition, the update management unit 137 may transmit an operation result of the outsourcing service to the service requesting vehicle.

The vehicle communication management unit 138 may receive information for communication with a service target vehicle from the first server 200. That is, the vehicle communication management unit 138 may receive communication information enabling communication between the service requesting vehicle and the service performing vehicle from the first server 200.

The controller 139 controls the overall operation of the processor 130 and may be formed integrally with the processor 130 or may be provided separately. However, in this embodiment, it may mean a control module provided in the processor 130.

The first server 200 may provide a vehicle real-time service and a non-real-time service that can be executed in the vehicle 100, and may include a resource monitoring unit 210, a workload management unit 220, and a data management unit 230. have. In this embodiment, the first server 200 may be an edge server.

In the IT infrastructure, the edge can mean a server or node located in the network closest to the user. The infrastructure can be configured so that the data or content requested by the user can be transmitted and processed closest to the user. In addition, edge computing refers to a computing method in which data is processed by a small facility at several points rather than a cloud computing method in which data is centrally processed. When entering the IoT era in earnest, the amount of data collected centrally through various routes increases, and in an IoT environment where real-time processing is important, concentrated data must be processed without delay. In other words, to compensate for this problem, the edge server installed in several places can process data immediately and notify the result.

That is, the first server 200 receives a service request from the first vehicle 100-1, and the server's service execution possibility for the service request based on the available computing resources of the first server 200 Can be judged. In other words, the first server 200 monitors the computational resource of the first server 200, checks whether the computational resource currently providing the service can perform the requested service, and executes it in the first server 200. If possible, you can run the service. On the other hand, when the requested service cannot be performed (for example, an overload situation), a vehicle capable of performing the service can be found through resource monitoring.

In addition, the first server 200 may determine the second vehicle 100-2 based on the available computational resources of the second vehicle 100-2. At this time, the first server 200 may determine an available calculation threshold based on the determined outsourcing service, and among vehicles communicating with the first server 200, the available calculation resources may determine service execution target vehicles having an available calculation threshold or more. . In addition, the first server 200 predicts the remaining time within the coverage of the first server 200 of the service target vehicles based on driving information of the service target vehicles, and the first among the service target vehicles based on the remaining time. 2 Vehicle 100-2 can be selected.

In addition, the first server 200 may provide at least one outsourcing service that is not to be performed by the first server 200 among services related to the service request or among the services being performed by the first server 200 based on the determination of the possibility of performing the service. You can decide. In addition, the first server 200 requests the second vehicle 100-2 to perform an outsourcing service, and transmits data access information including a path accessible to the data required for the outsourcing service to the second vehicle 100-2. Can be transmitted. In addition, the first server 200 may receive an execution status of an outsourcing service from the second vehicle 100-2.

The resource monitoring unit 210 may monitor resources of the first server 200 and the first vehicle 100-1 and the second vehicle 100-2. In this case, the first vehicle 100-1 and the second vehicle 100-2 may refer to vehicles that have entered the coverage of the first server 200.

In particular, the resource monitoring unit 210 may receive vehicle information and collaborative operation information of the second vehicle 100-2. Here, the vehicle information may include at least one of an identifier of the vehicle 100, a type of the vehicle 100, a purpose of the vehicle 100, a production year of the vehicle 100, and a brand of the vehicle 100. . In addition, the operation information for collaboration may include at least one of an operation resource of the vehicle 100, an executable distributed computing platform, and an available communication protocol. Here, the computational resource of the vehicle 100 may mean a maximum computational resource of the vehicle 100 or an average available computational resource excluding computational resources used for driving.

In addition, the resource monitoring unit 210 may periodically monitor and update the available computational resources of the second vehicle 100-2 communicating with the first server 200. At this time, the resource monitoring unit 210 stores the most recently monitored available computational resources of the second vehicle 100-2 or the average value of the available computational resources monitored for a certain period of the second vehicle 100-2. I can. In addition, the resource monitoring unit 210 may monitor a resource for a service currently being serviced by the first server 200.

The workload management unit 220 may determine an outsourcing service based on a safety relevance of a service related to a service request or a service being performed in the first server 200 and a need for real-time provision. In this case, the workload management unit 220 may determine a service related to a service request or a service set in advance as not related to safety among services being executed by the first server 200 as an outsourcing service. In addition, the workload management unit 220 may determine an outsourcing service in consideration of at least one of a network bandwidth required to perform each service and a security sensitivity of each service.

In other words, the workload management unit 220 determines that the service request received from the first vehicle 100-1 cannot be performed by the first server 200. The outsourced services that can be requested can be determined based at least on the priorities of the services. In this case, the workload management unit 220 may determine an outsourcing service from a service having a low need for real-time provision among services set in advance as not related to safety. Here, the priority may be determined based on the properties of the service (whether it is a core service related to safety or an additional service not related to safety), the urgency of the service (whether it should be processed immediately), and the complexity of the service. For example, when the load for providing safety-related core services increases, the workload management unit 220 may consider network bandwidth and real-time properties for each requested service application. In addition, the workload management unit 220 may select a service application to offload an additional service that is not related to safety, and find a vehicle capable of executing the service application according to the selected emergency degree value.

11 is an exemplary diagram of a service application list according to an embodiment of the present invention. Referring to FIG. 11, core services related to safety and additional services not related to safety may be classified. For example, key safety-related services include traffic light management, vehicle tracking, HD map update, platooning, and emergency vehicle warning. I have a service application. In addition, additional services not related to safety include intelligent driving, parking lot`s information, infotainment services, health monitoring system, VR, AR, video streaming. streaming), driver behavior. In addition, in the present embodiment, network bandwidth, real-time provisioning necessity, security sensitivity, and the like may be stored for each application. That is, in the present embodiment, the workload management unit 220, in processing workload distribution, when the load to be processed of the safety-related service in the first server 200 increases, the available vehicle that can be processed, that is, the second It is possible to find the vehicle 100-2 and delegate and execute a service not related to safety, which is being executed in the first server 200, to the second vehicle 100-2 in the order of low priority. In addition, by performing parallel processing between the first server 200 and the second vehicle 100-2, it is possible to ensure real-time safety-related services.

The first server 200 receives completion of the outsourcing service, transmits information for communication with the first vehicle 100-1 to the second vehicle 100-2, and transmits the second vehicle 100-2. ) May be transmitted to the first vehicle 100-1.

The data management unit 230 manages data and applications used in a service, and may upload a service application in a format executable in the second vehicle 100-2 to the second server 300. That is, the data management unit 230 may determine the format of the application and data based on an executable distributed computing platform previously registered for the second vehicle 100-2 and upload it to the second server 300.

In addition, the data management unit 230 may update cruising data, biometric data, control data, camera data, and sensor data to the second server 300.

The second server 300 may be a service application server, and may include an application for vehicle service, that is, data and application images. Here, the image may mean the minimum unit in which codes necessary for the system and service are collected. For example, the second server 300 may receive a service application in a format executable in the second vehicle 100-2 for workload distribution from the first server 200. In addition, the second server 300 receives and updates cruising data, biometric data, control data, camera data, and sensor data from the first server 200. I can.

Meanwhile, in the present embodiment, when there is no available resource, it may wait until a service being executed ends or an available vehicle, that is, a vehicle capable of executing the service, is generated.

12 is a flowchart illustrating a method of distributing a workload of a server according to an embodiment of the present invention. In the following description, portions overlapping with the descriptions of FIGS. 1 to 11 will be omitted.

Referring to FIG. 12, in step S100, the first server 200 receives a service request from the first vehicle 100-1. In this case, the service received from the first vehicle 100-1 may be classified into a safety-related service and a non-safety-related service, which may be set in advance.

In step S110, the first server 200 determines the possibility of performing the service of the first server 200. That is, the first server 200 may monitor the computational resource of the first server 200 and check whether the computational resource currently providing the service can perform the requested service.

In step S120, the first server 200 determines the second vehicle 100-2. That is, when the first server 200 cannot perform the requested service (eg, an overload situation), the first server 200 may find a vehicle capable of executing the service through resource monitoring. In this case, the first server 200 may determine the second vehicle 100-2 based on the available computational resources of the second vehicle 100-2. More specifically, the first server 200 determines an available computational threshold based on the determined outsourcing service, and determines service execution target vehicles whose available computational resources are equal to or greater than the available computational threshold among vehicles communicating with the first server 200. I can. In addition, the first server 200 predicts the remaining time within the coverage of the first server 200 of the service target vehicles based on driving information of the service target vehicles, and the first among the service target vehicles based on the remaining time. 2 Vehicle 100-2 can be selected.

In step S130, the first server 200 determines an outsourcing service. That is, the first server 200 may determine an outsourcing service based on a service related to a service request or a safety relevance of services being performed by the first server 200 and a need for real-time provision. In this case, the first server 200 may determine a service related to a service request or a service set in advance as not related to safety among services being executed by the first server 200 as an outsourcing service. In addition, the first server 200 may determine an outsourcing service in consideration of at least one of a network bandwidth required to perform each service and a security sensitivity of each service. In addition, the first server 200 may determine an outsourcing service that can be requested from the outside among the services being performed by the first server 200 based on at least the priority of the services, and services set in advance as not related to safety. Among them, a service with a low need for real-time provision can be determined as an outsourcing service.

Meanwhile, in the present embodiment, the second vehicle 100-2 is determined and then the outsourcing service is determined in an order, but is not limited thereto. That is, in this embodiment, after determining the outsourcing service, the second vehicle 100-2 may be determined. In other words, the step of selecting the second vehicle 100-2 may be both before or after the step of determining the outsourcing service. In addition, in this embodiment, determining the second vehicle 100-2 and determining the outsourcing service may be performed at the same time.

In step S140, the first server 200 requests the second vehicle 100-2 to perform an outsourcing service.

In step S150, the first server 200 transmits data access information to the second vehicle 100-2. That is, the first server 200 may transmit data access information including a path accessible to data required for an outsourcing service to the second vehicle 100-2. In addition, the first server 200 may transmit a path and authentication information for downloading an application related to an outsourcing service to the second vehicle 100-2. Here, the data access information may include information on the second server 300, a service application, and data.

In step S160, the first server 200 checks whether an outsourcing service completion has been received from the second vehicle 100-2. That is, the first server 200 may receive the execution status of the outsourcing service from the second vehicle 100-2, and when the execution completion is received, it may confirm that the service execution has been completed.

13 is a flowchart illustrating a method of supporting a server workload of a vehicle according to an embodiment of the present invention. In the following description, portions overlapping with the descriptions of FIGS. 1 to 12 will be omitted.

Referring to FIG. 13, in step S200, the second vehicle 100-2 transmits vehicle information and operation information for cooperation to the first server 200.

In step S210, the second vehicle 100-2 receives a request to perform an outsourcing service from the first server 200. In this case, the second vehicle 100-2 may be a vehicle that has entered the coverage of the first server 200. In addition, when the second vehicle 100-2 enters the coverage of the first server 200, vehicle information and collaborative operation information may be transmitted to the first server 200. That is, in this embodiment, the second vehicle 100-2 may periodically transmit computational resource information, and the first server 200 may monitor computational resource information of the second vehicle 100-2. .

In step S220, the second vehicle 100-2 receives data access information from the first server 200. That is, the second vehicle 100-2 may receive data access information including a path accessible to data required for outsourcing service from the first server 200. In addition, the second vehicle 100-2 may receive a path and authentication information for downloading an application related to an outsourcing service.

In step S230, the second vehicle 100-2 performs an outsourcing service. That is, the second vehicle 100-2 may perform the outsourcing service based on data access information including a path accessible to data required for the outsourcing service. In this case, the second vehicle 100-2 may execute an application downloaded from the second server 300 and perform an outsourcing service using data related to the outsourcing service stored in the second server 300.

In step S240, the second vehicle 100-2 checks whether the coverage of the first server 200 has been deviated.

In step S250, the second vehicle 100-2 transmits an intermediate result of the outsourcing service to the second server 300 (example of step S240). That is, when the second vehicle 100-2 leaves the coverage of the first server 200, the second vehicle 100-2 may transmit an intermediate result of the outsourcing service execution to the second server 300.

In step S260, the second vehicle 100-2 checks whether the outsourcing service has been performed (No in step S240).

In step S270, the second vehicle 100-2 transmits the completion of the outsourcing service to the first server 200 (example of step S260). That is, when the outsourcing service is completed, the second vehicle 100-2 may report and notify the completion of the outsourcing service to the first server 200.

In step S280, the second vehicle 100-2 transmits the outsourcing service calculation result to the service target vehicle of the outsourcing service or the second server 300. That is, after performing the outsourcing service, the second vehicle 100-2 transmits at least a part of the calculation result of the outsourcing service to the service target vehicle (eg, the first vehicle) of the outsourcing service or the second server 300. Can be transmitted.

14 is a flowchart illustrating a server workload distribution system according to an embodiment of the present invention. In the following description, portions overlapping with the descriptions of FIGS. 1 to 13 will be omitted.

Referring to FIG. 14, in steps S1 and S2, the first vehicle 100-1 and the second vehicle 100-2 register computational resources in the first server 200.

In step S3, the first server 200 monitors the computational resources of the first vehicle 100-1, the second vehicle 100-2, and the first server 200. That is, the first server 200 is configured by periodically updating available computational resources of the first vehicle 100-1 and the second vehicle 100-2, and the first vehicle 100-1 and the second vehicle 100- 2) You can monitor the available computational resources. At this time, the first vehicle 100-1 and the second vehicle 100-2 transmit the most recent available computational resources of each of the first vehicle 100-1 and the second vehicle 100-2, or Each of the vehicle 100-1 and the second vehicle 100-2 may transmit an average value of available computational resources for a predetermined period.

In step S4, the first vehicle 100-1 requests a service from the first server 200.

In step S5, the first server 200 determines the possibility of performing a service. That is, the first server 200 may receive a service request from the first vehicle 100-1 and determine the possibility of the server performing a service for the service request based on the available computational resources of the first server 200. have.

In step S6, the second vehicle 100-2 transmits vehicle information and operation information for cooperation to the first server 200. That is, the second vehicle 100-2 may register vehicle information and cooperation operation information of the second vehicle 100-2.

In step S7, the first server 200 determines the second vehicle 100-2. In this case, the first server 200 may determine the second vehicle 100-2 based on the available computational resources of the second vehicle 100-2. More specifically, the first server 200 determines an available computational threshold based on the determined outsourcing service, and determines service execution target vehicles whose available computational resources are equal to or greater than the available computational threshold among vehicles communicating with the first server 200. I can. In addition, the first server 200 predicts the remaining time within the coverage of the first server 200 of the service target vehicles based on driving information of the service target vehicles, and the first among the service target vehicles based on the remaining time. 2 Vehicle 100-2 can be selected.

In step S8, the first server 200 determines an outsourcing service. That is, the first server 200 provides at least one outsourcing service that is not to be performed by the first server 200 among services related to the service request or among the services being performed by the first server 200 based on the determination of the possibility of performing the service. You can decide.

In step S9, the first server 200 uploads the application to the second server 300.

In step S10, the second server 300 updates the uploaded application.

The first server 200 may upload a service application in a format executable in the second vehicle 100-2 to the second server 300. That is, the first server 200 may determine the format of the application and data based on an executable distributed computing platform previously registered for the second vehicle 100-2 and upload it to the second server 300. In addition, the first server 200 may update cruising data, biometric data, control data, camera data, and sensor data to the second server 300. .

In step S11, the first server 200 requests the second vehicle 100-2 to perform an outsourcing service. That is, the first server 200 may request execution of at least one outsourcing service that is not to be performed by the first server 200 among services related to a service request or among services being performed by the first server 200.

In step S12, the first server 200 transmits data access information to the second vehicle 100-2. The first server 200 may transmit data access information together while requesting the second vehicle 100-2 to perform an outsourcing service.

In step S13, the second vehicle 100-2 accesses the second server 300 based on the data access information. That is, the second vehicle 100-2 may attempt to access data and images of the second server 300.

In step S14, the second server 300 authenticates the second vehicle 100-2. The second server 300 may authenticate whether the second vehicle 100-2 is an authorized vehicle based on a preset authentication method or identification information of the second vehicle 100-2.

In step S15, the second vehicle 100-2 downloads an application from the second server 300. The second vehicle 100-2 may download an application in an executable format.

In step S16, the second vehicle 100-2 performs an outsourcing service. That is, the second vehicle 100-2 may access data to the second server 300 to download an application related to the outsourcing service from the second server 300 and execute the application. In addition, the second vehicle 100-2 may execute the application and perform the outsourcing service by using data related to the outsourcing service stored in the second server 300.

In step S17, the second vehicle 100-2 reports the completion of the execution to the first server 200.

In step S18, the first server 200 transmits communication information for communication between the first vehicle 100-1 and the second vehicle 100-2. That is, the first server 200 may receive information for communication between the first vehicle 100-1 and the second vehicle 100-2. That is, the first server 200 may transmit communication information enabling communication between the service requesting vehicle and the service performing vehicle.

In step S19, the second vehicle 100-2 transmits the calculation result to the first vehicle 100-1 and the second server 300. That is, the second vehicle 100-2 may transmit and update the service execution content to the first server 200 and the second server 300. In addition, the second vehicle 100-2 may transmit a result of the outsourcing service operation to the service requesting vehicle to update the service execution content.

According to an embodiment of the present disclosure, it is possible to ensure real-time safety-related services by distributing and processing the workload of the edge server to the vehicle by utilizing the available computational resources of the vehicle in the event of an overload of the edge server.

In addition, it is possible to distribute the workload of the edge server to the vehicle in the event of an overload of the edge server, thereby enabling parallel processing of services between the edge server and the vehicle, thereby improving the performance of the server workload distribution system.

In addition, by recognizing an overload situation through resource monitoring of a computational resource currently in use and a service to be provided, and requesting a service classified according to a preset criterion to the vehicle, the optimal distributed processing to the vehicle may be possible.

In addition, it is possible to improve product reliability by enabling a vehicle to perform real-time computation tasks that cannot be performed by the edge server in an overload situation of the edge server.

In addition, by performing server workload distribution through 5G network-based communication, rapid data processing is possible, and thus the performance of the server workload distribution system can be further improved.

In addition, although the server workload supporting vehicle itself is a mass-produced uniform product, the user recognizes the server workload supporting vehicle as a personalized device, so that the effect of a user-customized product can be achieved.

The effects of the present invention are not limited to those mentioned above, and other effects not mentioned will be clearly understood by those skilled in the art from the following description.

The embodiment according to the present invention described above may be implemented in the form of a computer program that can be executed through various components on a computer, and such a computer program may be recorded in a computer-readable medium. In this case, the medium is a magnetic medium such as a hard disk, a floppy disk, and a magnetic tape, an optical recording medium such as a CD-ROM and a DVD, a magnetic-optical medium such as a floptical disk, and a ROM. It may include a hardware device specially configured to store and execute program instructions, such as, RAM, flash memory, and the like.

Meanwhile, the computer program may be specially designed and configured for the present invention, or may be known and usable to a person skilled in the computer software field. Examples of the computer program may include not only machine language codes such as those produced by a compiler, but also high-level language codes that can be executed by a computer using an interpreter or the like.

In the specification of the present invention (especially in the claims), the use of the term "above" and the reference term similar thereto may correspond to both the singular and the plural. In addition, when a range is described in the present invention, the invention to which an individual value falling within the range is applied (unless otherwise stated), and each individual value constituting the range is described in the detailed description of the invention. Same as.

If there is no explicit order or contradictory description of the steps constituting the method according to the present invention, the steps may be performed in a suitable order. The present invention is not necessarily limited according to the order of description of the steps. The use of all examples or illustrative terms (for example, etc.) in the present invention is merely for describing the present invention in detail, and the scope of the present invention is limited by the above examples or illustrative terms unless limited by the claims. It does not become. In addition, those skilled in the art can recognize that various modifications, combinations, and changes may be configured according to design conditions and factors within the scope of the appended claims or their equivalents.

Accordingly, the spirit of the present invention is limited to the above-described embodiments and should not be defined, and all ranges equivalent to or equivalently changed from the claims to be described later as well as the claims to be described later are the scope of the spirit of the present invention. It will be said to belong to.

1: Server workload distribution system
10: Cloud Network
20: AI Server
30a: Robot
30b: Self-Driving Vehicle
30c: XR Device
30d: Smartphone
30e: Home Appliance

Claims (20)

As a method of distributing the workload of the server,
Receiving a service request from the first vehicle;
Determining a possibility of performing a service by the server in response to the service request based on available computing resources of the server;
Determining at least one outsourcing service not to be performed by the server from among services related to the service request or services being performed by the server based on the determination of the possibility of performing the service;
Determining a second vehicle based on available computational resources of vehicles communicating with the server; And
Requesting the second vehicle to perform the outsourcing service, and transmitting data access information including a path accessible to the data required for the outsourcing service to the second vehicle,
How to distribute the workload of the server.
The method of claim 1,
Further comprising the step of receiving vehicle information and collaborative operation information of the second vehicle,
The vehicle information includes at least one of the vehicle identifier, vehicle type, vehicle usage, vehicle production year, and vehicle brand,
The collaborative operation information includes at least one of an operation resource of the vehicle, an executable distributed computing platform, and an available communication protocol,
How to distribute the workload of the server.
The method of claim 1,
Further comprising the step of periodically monitoring and updating the available computational resources of the second vehicle in communication with the server,
The updating step,
Storing the most recently monitored available computational resources of the second vehicle; or
Including the step of storing an average value of the available computational resources monitored for a predetermined period of the second vehicle,
How to distribute the workload of the server.
The method of claim 1,
The step of determining the outsourcing service,
Including the step of determining the outsourcing service based on the safety relevance of the service related to the service request or the services being performed in the server and the need for real-time provision,
How to distribute the workload of the server.
The method of claim 1,
The step of determining the outsourcing service,
Including the step of determining as the outsourcing service a service related to the service request or a service set in advance as not related to safety among services being performed by the server,
How to distribute the workload of the server.
The method of claim 1,
The step of determining the outsourcing service,
Including the step of determining the outsourcing service in consideration of at least one of a network bandwidth required to perform each service and a security sensitivity of each service,
How to distribute the workload of the server.
The method of claim 1,
Receiving completion of the outsourcing service;
Transmitting information for communication with the first vehicle to the second vehicle; And
Further comprising the step of transmitting information for communication with the second vehicle to the first vehicle,
How to distribute the workload of the server.
The method of claim 1,
The step of determining the second vehicle,
Determining an available computation threshold based on the determined outsourcing service;
Determining a service execution target vehicle in which an available computation resource is equal to or greater than the available computation threshold among vehicles communicating with the server;
Estimating a remaining time in coverage of a server of the service target vehicles based on driving information of the service target vehicles; And
Including the step of selecting the second vehicle from among the vehicles to perform the service based on the remaining time,
How to distribute the workload of the server.
As a method for the vehicle to support the workload distribution of the first server,
Transmitting, by the vehicle, vehicle information and collaborative operation information to a first server;
Receiving data access information including a request to perform an outsourcing service and a path accessible to data required for the outsourcing service from the first server;
Performing the outsourcing service based on the data access information; And
Transmitting at least a part of the calculation result of the outsourcing service to a service target vehicle of the outsourcing service or a second server,
How to support the vehicle's server workload.
The method of claim 9,
The vehicle information includes at least one of the vehicle identifier, vehicle type, vehicle usage, vehicle production year, and vehicle brand,
The collaborative operation information includes at least one of an operation resource of the vehicle, an executable distributed computing platform, and an available communication protocol,
How to support the vehicle's server workload.
The method of claim 9,
Further comprising periodically updating the available computational resources of the vehicle to the first server,
The updating step,
Transmitting the most recent available computational resource of the vehicle; or
Including the step of transmitting an average value of the available computational resources for a certain period of the vehicle,
How to support the vehicle's server workload.
The method of claim 9,
Before the step of transmitting the calculation result,
Transmitting completion of the outsourcing service to the first server; And
Further comprising the step of receiving information for communication with the service target vehicle from the first server,
How to support the vehicle's server workload.
The method of claim 9,
Reporting, by the vehicle, a departure from coverage of the first server; And
Further comprising transmitting an intermediate result of the outsourcing service performed by the vehicle to the second server,
How to support the vehicle's server workload.
The method of claim 9,
Receiving the data access information from the first server,
Including the step of receiving a path and authentication information for downloading an application related to the outsourcing service,
Further comprising the step of transmitting the authentication information to the second server and downloading the application,
How to support the vehicle's server workload.
As a vehicle that supports workload distribution of the first server,
A communication interface in communication with the first server;
One or more processors; And
Including a memory connected to the one or more processors,
The memory, when executed by the processor, causes the processor to:
Transmitting vehicle information and cooperation operation information of the vehicle to the first server,
Receiving data access information including a request to perform an outsourcing service and a path accessible to data necessary for the outsourcing service from the first server,
Performing the outsourcing service based on the data access information,
Storing codes that cause at least a part of the operation result of the outsourcing service to be transmitted to a service target vehicle of the outsourcing service or a second server,
Server workload support vehicle.
The method of claim 15,
The vehicle information includes at least one of the vehicle identifier, vehicle type, vehicle usage, vehicle production year, and vehicle brand,
The collaborative operation information includes at least one of an operation resource of the vehicle, an executable distributed computing platform, and an available communication protocol,
Server workload support vehicle.
The method of claim 15,
The memory, when executed by the processor, causes the processor to:
Storing codes that cause the vehicle's available computational resources to be periodically updated to the first server,
The updating operation,
Transmitting the most recent available computational resources of the vehicle, or transmitting an average value of the available computational resources for a predetermined period of the vehicle,
Server workload support vehicle.
The method of claim 15,
The memory, when executed by the processor, causes the processor to:
Before the operation of transmitting the calculation result,
Transmitting completion of the outsourcing service to the first server,
Storing codes that cause to receive information for communication with the service target vehicle from the first server,
Server workload support vehicle.
The method of claim 15,
The memory, when executed by the processor, causes the processor to:
Storing codes that cause the vehicle to transmit an intermediate result of the outsourcing service performed as the vehicle reports departure from the coverage of the first server to the second server,
Server workload support vehicle.
The method of claim 15,
The operation of receiving the data access information from the first server,
Including an operation of receiving a path and authentication information for downloading an application related to the outsourcing service,
The memory, when executed by the processor, causes the processor to:
Storing codes that cause the authentication information to be transmitted to the second server and to cause the application to be downloaded,
Server workload support vehicle.

Images