WO2022060046A1

WO2022060046A1 - Edge computing system and handover method for edge computing device

Info

Publication number: WO2022060046A1
Application number: PCT/KR2021/012461
Authority: WO
Inventors: 이종원; 김무현; 송가진; 이선기
Original assignee: 삼성전자 주식회사
Priority date: 2020-09-15
Filing date: 2021-09-14
Publication date: 2022-03-24
Also published as: KR20220036136A

Abstract

An electronic device according to various embodiments comprises a communication module, a memory, and a processor operatively connected to the communication module and the memory. The processor may be configured to: identify an handover event of an edge computing service being performed by a first external device and a second external device on a local network; identify whether or not the electronic device can perform the edge computing service; and, when the electronic device can perform the edge computing service, perform the edge computing service in connection with the second external device operating as a leaf device for the edge computing service.

Description

Edge Computing System and Handover Method of Edge Computing Device

This document is about an edge computing system, and more specifically, an edge computing system that can perform edge computing services by an edge device connected to data acquired from a leaf device, and an edge device connected to a leaf device in the edge computing system. It is about how to handover to another edge device.

Cloud computing technology is a technology for providing computing services such as servers, storage, software, or analysis by providing computing resources that exist in a different location to the user through a network. User data or contents collected from IoT devices are stored in cloud servers, and cloud services are provided to users through data processing.

Cloud computing is being utilized to process data generated in the Internet of Things (IoT). In cloud computing, as the amount of data and devices constituting the IoT increases, a load is created on the system, and security or privacy issues may occur in the process of data delivery and/or storage, an error may occur in the cloud server, or the Internet If it is not connected to , there may be a problem that the service cannot be provided.

In order to solve the problems of cloud computing, edge computing technology is being used. Edge computing is an open architecture that extends cloud computing and some of its services to devices at the edge of a network. For example, when edge computing technology is utilized in IoT, applications or services processed in a cloud server, where low latency and privacy are important, can be partially distributed on the edge device.

Although edge computing technology is being used in IoT, the conventional edge computing service provides a service using a module fixed to an edge device fixed to a leaf device. In this case, after connecting the leaf device and the edge device for the edge computing service, in order to connect the leaf device with the new edge device, the process of disconnecting the previously connected edge device and then reconnecting with the new edge device is required do.

Various embodiments of the present document provide a method for performing edge computing services by being connected to a new edge device in charge of edge computing functions when the edge device connected to the leaf device cannot perform the edge computing function temporarily or under specific conditions. An object of the present invention is to provide an edge computing system and a handover method of an edge computing device.

An electronic device according to various embodiments includes a communication module, a memory, and a processor operatively connected to the communication module and the memory, wherein the processor includes a first external device and a second external device on a local network. Check the handover event of the edge computing service being performed by the device, check whether the electronic device can perform the edge computing service, and when the electronic device can perform the edge computing service, the edge computing service It may be configured to perform the edge computing service in connection with the second external device operating as a leaf device of the computing service.

An electronic device according to various embodiments includes a communication module, a memory, and a processor operatively connected to the communication module and the memory, wherein the processor is Based on the received data, an edge computing service is performed, a handover event of the edge computing service is detected, and in response to the detection of the handover event, it is connected to the first external device through the communication module and the A second external device capable of performing an edge computing service is identified, and information related to the identified second external device and information related to the handover event is provided to the first external device, the second external device, or an external server. It may be set to transmit to at least one of

An electronic device according to various embodiments includes a communication module, a sensor, and a processor operatively connected to the communication module and the sensor, wherein the processor transmits data obtained through the sensor to the communication module to perform the edge computing service by transmitting to the first external device through and to request a connection for the edge computing service from the second external device.

According to various embodiments of the present document, when the edge device connected to the leaf device determines that it is necessary to change the edge computing function, the edge computing function is handed over so that the edge computing service can be performed by the new edge device. A computing system and a handover method of an edge computing device may be provided.

In addition, various technical effects identified directly or indirectly through this document may be provided.

1 illustrates devices in an IoT environment according to various embodiments.

2A and 2B illustrate respective devices of an edge computing system according to various embodiments.

3 is a block diagram of a user device within a network environment, in accordance with various embodiments.

4 is a block diagram of an edge device according to various embodiments of the present disclosure;

5 is a block diagram of a leaf device according to various embodiments.

6 is a flowchart of a handover method of an edge device according to various embodiments.

7 is a flowchart of a method of determining a handover event according to movement of an edge device according to various embodiments of the present disclosure;

8 is a flowchart of a method of determining a handover event according to a resource of an edge device according to various embodiments of the present disclosure;

9 is a flowchart of a method of determining a handover event according to a power state or resource of an edge device according to various embodiments of the present disclosure;

10 is a diagram illustrating a change process of an edge device when an edge handover is initiated by a second edge device according to various embodiments of the present disclosure.

11 is a diagram illustrating a process of changing an edge device when an edge handover is initiated by a second edge device according to various embodiments of the present disclosure.

12 is a diagram illustrating a change process of an edge device when an edge handover is initiated by a leaf device according to various embodiments of the present disclosure.

13 is a diagram illustrating a change process of an edge device when an edge handover is initiated by a leaf device according to various embodiments of the present disclosure.

14 is a diagram illustrating a process of changing an edge device when an edge handover is initiated by an IoT server according to various embodiments of the present disclosure.

15 illustrates a process of handing over some of the edge computing services being performed by the first edge device to the second edge device according to various embodiments of the present disclosure.

16 illustrates a process of handing over some of the edge computing services being performed by the first edge device to the second edge device according to various embodiments of the present disclosure.

1 illustrates devices in an IoT environment (or IoT system) according to various embodiments.

Referring to FIG. 1 , an internet of things (IoT) system (or edge computing system) 100 includes at least one leaf device 120 (leaf device), at least one edge device 110 (edge device), and a user. It may include a device 130 (user device) and a cloud network 140 (cloud network). For example, the leaf device 120 , the edge device 110 , and the user device 130 may be disposed in adjacent locations (eg, in a house) and connected to the same home network (eg, the same access point (AP)). The cloud network 140 may be remotely located, but may be connected to the leaf device 120 , the edge device 110 , and the user device 130 through the Internet.

In this document, edge computing service is used to transmit data acquired from leaf devices to edge devices located adjacent to and located on the same home network of leaf devices, and to provide a series of data processing and other services on the edge devices It can mean the skill to Although this document defines a device that acquires data through a sensor (eg, a camera 121, a refrigerator 122, a light bulb 123a, and a digital thermometer 123b) as a leaf device, the leaf device is a client of an edge computing service. It may be defined by other names such as device, end device, sensor device, IoT device, and slave device. In addition, although defined as an edge device in this document, an edge device may be defined by other names, such as an edge server, a server device, a master device, a hub device, and a service device of an edge computing service.

In this document, the leaf device 120, the edge device 110, and the user device 130 are classified and described according to the function and operation of each device in the edge computing system 100, but the same device (eg, a smart phone, a tablet PC) may operate as any one of the leaf device 120 , the edge device 110 , and the user device 130 in some cases. In other words, the names and definitions of devices described in this document do not limit the functions and/or operations of the devices.

According to various embodiments, the leaf device 120 may collect various data using a sensor as an end point of the IoT system 100 and transmit it to the edge device 110 or the cloud network 140 . Also, the leaf device 120 may perform various operations according to a command transmitted from the cloud network 140 or the user device 130 . Referring to FIG. 1 , a device such as a camera 121 , a refrigerator 122 , a light bulb 123a , and a digital thermometer 123b may be the leaf device 120 .

According to various embodiments, the leaf device 120 may access the cloud network 140 through the Internet, and devices that do not support Internet Protocol (IP) among the leaf devices 120 (eg, the light bulb 123a, digital The thermometer 123b) transmits the sensed data to the hub device 124 through supported non-IP-based communication (eg, bluetooth, zigbee), and the hub device 124 sends each leaf to the cloud network 140 via the Internet. Sensing data of the

devices

123a and 123b may be transmitted. The detailed configuration and operation of the leaf device 120 will be described in more detail with reference to FIG. 5 .

According to various embodiments, the cloud network 140 is located on the network and may include various server devices (eg, IoT management server and IoT hub server) supporting cloud computing services in the IoT system 100 . The cloud network 140 may perform computing processing on the sensing data received from the leaf device 120 and transmit a command for controlling the leaf device 120 .

According to various embodiments, the cloud network 140 may perform a function of operating and managing a specific device in the home network to operate as the edge device 110 . For example, the cloud network 140 includes an IoT server (eg, an IoT management server or an IoT hub server), and the IoT server is an edge device such as registration, connection, and management of the edge device 110 and the leaf device 120 . A computing service may be performed and a module (eg, a device module, a service module) necessary for the edge computing service may be provided to the edge device 110 .

According to various embodiments, the edge device 110 may directly process data received from the leaf device 120 or transmit it to the cloud network 140 (eg, an IoT server). The edge device 110 may be a device including hardware and/or software resources necessary for an edge computing service, such as a TV 112 and a tablet PC 111 . The edge device 110 may be connected to the cloud network 140 through the Internet, and may form a home network with the leaf device 120 .

According to various embodiments, a plurality of edge devices 110 may exist in the home network, and the leaf device 120 may be connected to any one of the plurality of edge devices 110 to transmit data. For example, when a specific leaf device 120 is connected, the edge device 110 may download and execute a module (eg, a device module, a service module) required for an edge computing service from the cloud network 140 .

According to various embodiments, the edge device 110 may perform a device-specific function (eg, an image output function of a TV), and may perform hardware at least partially concurrently with the performance of the unique function or during an idle time that does not perform the unique function. and/or may perform edge computing services through software resources.

A detailed configuration and operation of the edge device 110 will be described in more detail with reference to FIG. 4 .

According to various embodiments, the user device 130 may provide various user interfaces related to edge computing services through applications. For example, the user device 130 may obtain data (eg, camera image streaming) acquired from the leaf device 120 or data as a result of processing the data in the edge device 110 or the cloud network 140 (eg, a person). recognition) can be displayed on the display. In addition, the user device 130 may receive a user input such as connection of the edge device 110 and/or the leaf device 120 and server registration, and transmit it to the cloud network 140 . A detailed configuration and operation of the user device 130 will be described in more detail with reference to FIG. 3 .

According to various embodiments, the leaf device 120 may be connected to any one of a plurality of edge devices 110 located in the home network to perform an edge computing service, and may switch to another edge device according to the state of each edge device. A connection can be handed over. Here, in the handover, in a state in which the leaf device 120 and a specific edge device are connected and the edge computing service is being performed, the leaf device 120 switches the connection to another edge device to continuously perform the edge computing service being performed. can mean doing For example, while connected to the leaf device 120 and the first edge device (eg, the tablet PC 111) and performing edge computing services, the movement of the first edge device, network departure, lack of resources, change of power state, and Similarly, when the first edge device cannot perform the edge computing function, according to the handover event, the leaf device 120 is connected to the second edge device (eg, the TV 112) in the home network to provide an edge computing service. can be performed.

Referring to FIG. 2A , the edge computing system may include a leaf device 220 , an edge device 210 , a user device 230 , an IoT hub server 250 , and an IoT management server 240 . As described with reference to FIG. 1 , various IoT devices may exist on the home network, and in FIG. 2 , one leaf device (eg, the camera 121 of FIG. 1 ) and one edge device ) (eg, the TV 112 of FIG. 1 ) will be described as an example.

According to various embodiments, the IoT management server 240 (eg, SmartThings ^TM server) is a server device that provides various services for determining, connecting and/or operating edge computing services, and includes a provision manager 242, a module It may include a manager 244 and an edge-leaf manager 246 .

According to various embodiments, the provision manager 242 may perform a relay function in the middle so that the edge device 210 can be connected to the IoT hub server 250 . For example, when the edge device 210 is first registered with the IoT management server 240 , the provision manager 242 provides a connection string ( connection string) to the edge device 210 .

According to various embodiments, the module manager 244 may manage information on various modules provided for edge computing services and devices supporting each service. Here, the module required to perform the edge computing service is a device module 219 that enables the edge device 210 to transmit data transmitted from the leaf device 220 to an external server (eg, IoT hub server 250). and a service module 218 including programs executed to implement a service in the edge device 210 based on data transmitted from the leaf device 220 .

According to various embodiments, the edge-leaf manager 246 may manage the connection state between the edge device 210 and the leaf device 220 existing in several home networks. For example, when the edge device 210 and the leaf device 220 registered in the IoT management server 240 are connected or disconnected from each other, the edge device 210 and/or the leaf device 220 connects or connects. The release information is transmitted to the IoT management server 240, and the IoT management server 240 can store information about which edge device 210 and leaf device 220 are connected in real time, and which service is being performed. there is.

According to various embodiments, the leaf device 220 is connected to a specific edge device (eg, the tablet PC 111 of FIG. 1 ) to perform an edge computing service, and then disconnects from the corresponding edge device according to a handover event and releases the connection to another edge device. When an edge computing service is performed by being connected to an edge device (eg, the TV 112 in FIG. 1 ), the IoT management server 240 connects the edge device 210 and the leaf device 240 changed according to the handover event. Information can be updated.

According to various embodiments, the IoT hub server 250 supports a cloud computing platform, and provides data necessary for the leaf device 220 and the edge device 210 in the cloud environment to be connected to each other. can The IoT hub server 250 may include an IoT hub 252 and a module registry 254 .

According to various embodiments, the module registry 254 may be a storage of modules (eg, the device module 219 and the service module 218 ) required to perform an edge computing service.

According to various embodiments, the IoT hub 252 maintains a connection with the edge device 210 , provides a module stored in the module registry 254 to the edge device 210 , and provides multiple edge devices 210 . ) can maintain information of installed modules.

According to various embodiments, the edge device 210 (eg, the edge device 110 of FIG. 1 ) has device-specific functions such as a TV, a tablet PC, and a laptop PC, and configures hardware and/or software for an edge computing service. It can be a device containing (eg edge runtime, base module). The edge computing service may be performed through hardware and/or software resources at least partially concurrently with the performance of the intrinsic function or during idle time when the intrinsic function is not performed.

According to various embodiments, the edge device 210 includes an interface 212 and an operating system (OS) 214 for communicating with the cloud (eg, the IoT management server 240 and the IoT hub server 250 ). and edge runtime 216 . For example, the edge device 210 may require hardware conditions (eg, CPU performance) for operating the operating system 214 , and may be configured as a real time operating system (RTOS).

An edge runtime 216 (edge runtime) and a basic module for edge computing may be installed in the edge device 210 through a process process or software upgrade of the edge device 210 . Here, the edge runtime 216 may include a daemon program for interworking with the IoT server, and the basic module may be configured as a container as a program necessary for communication with the IoT server. For example, the basic module may be a container installed in the edge runtime 216 environment.

According to various embodiments, when the edge device 210 is connected to a specific leaf device 220 , it may receive and install at least one module for performing an edge computing service from the IoT hub server 250 .

For example, the at least one module may be determined according to the type of the leaf apparatus 220 to be connected and/or the type of service that can be performed, and a device module 219 corresponding to the leaf apparatus 220 and / or may include a service module 218 corresponding to the type of service to be performed. When the edge device 210 is connected to the plurality of leaf devices 220 , each leaf device 220 and the corresponding device module 219 (eg, device module 1 219a , device module 2 219b ) ) can be installed. The edge device 210 is connected to the IoT hub server 250 by executing the edge runtime 216 in the provisioning process, and the at least one module is additionally installed according to the type of the leaf device 220 and can be executed The edge device 210 may activate or deactivate the edge mode according to a command received from the IoT hub server 250 or the IoT management server 240 . When the edge mode is deactivated, the edge device 210 performs only a unique function (eg, an image output function of the TV), and the device module 219 and the service module 218 may not be executed.

According to various embodiments, the leaf device 220 (eg, the leaf device 120 of FIG. 1 ) transmits data acquired using a sensor to the connected edge device 210 or a cloud network (eg, IoT management server 240 ); It can be transmitted to the IoT hub server (250). For example, in the case of an IP (internet protocol) camera operating as the leaf device 220 , it may be connected to the edge device 210 to transmit video streaming to the edge device 210 .

According to various embodiments, the user device 230 may be a device including a display capable of executing various applications, such as a smart phone and a tablet PC, and displaying a user interface (UI). The user device 230 may install and/or execute an application for an edge computing service, and receive content and a notification generated by the leaf device 220 through the corresponding application. When the edge device 210 and the leaf device 220 are connected, the content or notification generated by the leaf device 220 may be transmitted to the user device 230 through the edge device 210 .

According to various embodiments, the functions of the IoT hub server 250 and the IoT management server 240 may be performed by one server device (eg, the IoT server 260 of FIG. 2B ). For example, referring to FIG. 2B , the IoT server 260 includes the IoT hub 261 (eg, the IoT hub 252 of FIG. 2A ) that is a configuration of the IoT hub server 250 and the IoT management server 240 described above. ), module registry 262 (eg, module registry 254 in FIG. 2A ), provision manager 263 (eg, provision manager 242 in FIG. 2A ), module manager 264 (eg, FIG. 2A ). of the module manager 244) and the edge-leaf manager 265 (eg, the edge-leaf manager 246 of FIG. 2A).

Alternatively, the functions may be performed by three or more plurality of server devices. For example, each configuration of the IoT hub server 250 and the IoT management server 240 of FIG. 2A is distributedly arranged by three or more plurality of server devices existing on the network, or some operations performed in each configuration It may also be distributed by several server devices.

3 is a block diagram of a user device within a network environment, in accordance with various embodiments. Hereinafter, a user device of the edge computing system (eg, the user device 130 of FIG. 1 and the user device 230 of FIG. 2A ) may be referred to as an electronic device 301 .

Referring to FIG. 3 , in the network environment 300 , the user device (or electronic device) 301 communicates with the electronic device 302 through a first network 398 (eg, a short-range wireless communication network), or 2 may communicate with the electronic device 304 or the server 308 through the network 399 (eg, a remote wireless communication network). According to an embodiment, the electronic device 301 may communicate with the electronic device 304 through the server 308 . According to an embodiment, the electronic device 301 includes a processor 320 , a memory 330 , an input module 350 , a sound output module 355 , a display module 360 , an audio module 370 , and a sensor module ( 376 , interface 377 , connection terminal 378 , haptic module 379 , camera module 380 , power management module 388 , battery 389 , communication module 390 , subscriber identification module 396 ) , or an antenna module 397 . In some embodiments, at least one of these components (eg, the connection terminal 378 ) may be omitted or one or more other components may be added to the electronic device 301 . In some embodiments, some of these components (eg, sensor module 376 , camera module 380 , or antenna module 397 ) are integrated into one component (eg, display module 360 ). can be

The processor 320, for example, executes software (eg, a program 340) to execute at least one other component (eg, a hardware or software component) of the electronic device 301 connected to the processor 320 . It can control and perform various data processing or operations. According to one embodiment, as at least part of data processing or computation, the processor 320 converts commands or data received from other components (eg, the sensor module 376 or the communication module 390 ) to the volatile memory 332 . may be stored in , process commands or data stored in the volatile memory 332 , and store the result data in the non-volatile memory 334 . According to an embodiment, the processor 320 is a main processor 321 (eg, central processing unit or application processor) or a secondary processor 323 (eg, a graphics processing unit, a neural network processing unit) a neural processing unit (NPU), an image signal processor, a sensor hub processor, or a communication processor). For example, when the electronic device 301 includes a main processor 321 and a sub-processor 323 , the sub-processor 323 uses less power than the main processor 321 or is set to be specialized for a specified function. can The auxiliary processor 323 may be implemented separately from or as a part of the main processor 321 .

The coprocessor 323 may be, for example, on behalf of the main processor 321 while the main processor 321 is in an inactive (eg, sleep) state, or when the main processor 321 is active (eg, executing an application). ), together with the main processor 321, at least one of the components of the electronic device 301 (eg, the display module 360, the sensor module 376, or the communication module 390) It is possible to control at least some of the related functions or states. According to one embodiment, the coprocessor 323 (eg, image signal processor or communication processor) may be implemented as part of another functionally related component (eg, camera module 380 or communication module 390). there is. According to an embodiment, the auxiliary processor 323 (eg, a neural network processing unit) may include a hardware structure specialized for processing an artificial intelligence model. Artificial intelligence models can be created through machine learning. Such learning may be performed, for example, in the electronic device 301 itself on which artificial intelligence is performed, or may be performed through a separate server (eg, the server 308 ). The learning algorithm may include, for example, supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning, but in the above example not limited The artificial intelligence model may include a plurality of artificial neural network layers. Artificial neural networks include deep neural networks (DNNs), convolutional neural networks (CNNs), recurrent neural networks (RNNs), restricted boltzmann machines (RBMs), deep belief networks (DBNs), bidirectional recurrent deep neural networks (BRDNNs), It may be one of deep Q-networks or a combination of two or more of the above, but is not limited to the above example. The artificial intelligence model may include, in addition to, or alternatively, a software structure in addition to the hardware structure.

The memory 330 may store various data used by at least one component (eg, the processor 320 or the sensor module 376 ) of the electronic device 301 . The data may include, for example, input data or output data for software (eg, the program 340 ) and instructions related thereto. The memory 330 may include a volatile memory 332 or a non-volatile memory 334 .

The program 340 may be stored as software in the memory 330 , and may include, for example, an operating system 342 , middleware 344 , or an application 346 .

The input module 350 may receive a command or data to be used in a component (eg, the processor 320 ) of the electronic device 301 from the outside (eg, a user) of the electronic device 301 . The input module 350 may include, for example, a microphone, a mouse, a keyboard, a key (eg, a button), or a digital pen (eg, a stylus pen).

The sound output module 355 may output a sound signal to the outside of the electronic device 301 . The sound output module 355 may include, for example, a speaker or a receiver. The speaker can be used for general purposes such as multimedia playback or recording playback. The receiver may be used to receive an incoming call. According to one embodiment, the receiver may be implemented separately from or as part of the speaker.

The display module 360 may visually provide information to the outside (eg, a user) of the electronic device 301 . The display module 360 may include, for example, a control circuit for controlling a display, a hologram device, or a projector and a corresponding device. According to an embodiment, the display module 360 may include a touch sensor configured to sense a touch or a pressure sensor configured to measure the intensity of a force generated by the touch.

The audio module 370 may convert a sound into an electric signal or, conversely, convert an electric signal into a sound. According to an embodiment, the audio module 370 obtains a sound through the input module 350 or an external electronic device (eg, a sound output module 355 ) connected directly or wirelessly with the electronic device 301 . The electronic device 302 may output sound through (eg, a speaker or headphones).

The sensor module 376 detects an operating state (eg, power or temperature) of the electronic device 301 or an external environmental state (eg, a user state), and generates an electrical signal or data value corresponding to the sensed state. can do. According to one embodiment, the sensor module 376 may include, for example, a gesture sensor, a gyro sensor, a barometric pressure sensor, a magnetic sensor, an acceleration sensor, a grip sensor, a proximity sensor, a color sensor, an IR (infrared) sensor, a biometric sensor, It may include a temperature sensor, a humidity sensor, or an illuminance sensor.

The interface 377 may support one or more specified protocols that may be used by the electronic device 301 to directly or wirelessly connect with an external electronic device (eg, the electronic device 302 ). According to an embodiment, the interface 377 may include, for example, a high definition multimedia interface (HDMI), a universal serial bus (USB) interface, an SD card interface, or an audio interface.

The connection terminal 378 may include a connector through which the electronic device 301 can be physically connected to an external electronic device (eg, the electronic device 302 ). According to an embodiment, the connection terminal 378 may include, for example, an HDMI connector, a USB connector, an SD card connector, or an audio connector (eg, a headphone connector).

The haptic module 379 may convert an electrical signal into a mechanical stimulus (eg, vibration or movement) or an electrical stimulus that the user can perceive through tactile or kinesthetic sense. According to an embodiment, the haptic module 379 may include, for example, a motor, a piezoelectric element, or an electrical stimulation device.

The camera module 380 may capture still images and moving images. According to one embodiment, the camera module 380 may include one or more lenses, image sensors, image signal processors, or flashes.

The power management module 388 may manage power supplied to the electronic device 301 . According to an embodiment, the power management module 388 may be implemented as, for example, at least a part of a power management integrated circuit (PMIC).

The battery 389 may supply power to at least one component of the electronic device 301 . According to one embodiment, battery 389 may include, for example, a non-rechargeable primary cell, a rechargeable secondary cell, or a fuel cell.

The communication module 390 is a direct (eg, wired) communication channel or a wireless communication channel between the electronic device 301 and an external electronic device (eg, the electronic device 302, the electronic device 304, or the server 308). It can support establishment and communication performance through the established communication channel. The communication module 390 may include one or more communication processors that operate independently of the processor 320 (eg, an application processor) and support direct (eg, wired) communication or wireless communication. According to one embodiment, the communication module 390 is a wireless communication module 392 (eg, a cellular communication module, a short-range wireless communication module, or a global navigation satellite system (GNSS) communication module) or a wired communication module 394 (eg, : It may include a LAN (local area network) communication module, or a power line communication module). A corresponding communication module among these communication modules is a first network 398 (eg, a short-range communication network such as Bluetooth, wireless fidelity (WiFi) direct, or infrared data association (IrDA)) or a second network 399 (eg, legacy It may communicate with the external electronic device 304 through a cellular network, a 5G network, a next-generation communication network, the Internet, or a computer network (eg, a telecommunication network such as a LAN or a WAN). These various types of communication modules may be integrated into one component (eg, a single chip) or may be implemented as a plurality of components (eg, multiple chips) separate from each other. The wireless communication module 392 uses the subscriber information (eg, International Mobile Subscriber Identifier (IMSI)) stored in the subscriber identification module 396 within a communication network, such as the first network 398 or the second network 399 . The electronic device 301 may be identified or authenticated.

The wireless communication module 392 may support a 5G network after a 4G network and a next-generation communication technology, for example, a new radio access technology (NR). NR access technology includes high-speed transmission of high-capacity data (eMBB (enhanced mobile broadband)), minimization of terminal power and access to multiple terminals (mMTC (massive machine type communications)), or high reliability and low latency (URLLC (ultra-reliable and low-latency) -latency communications)). The wireless communication module 392 may support a high frequency band (eg, mmWave band) to achieve a high data rate, for example. The wireless communication module 392 uses various techniques for securing performance in a high frequency band, for example, beamforming, massive multiple-input and multiple-output (MIMO), all-dimensional multiplexing. It may support technologies such as full dimensional MIMO (FD-MIMO), an array antenna, analog beam-forming, or a large scale antenna. The wireless communication module 392 may support various requirements specified in the electronic device 301 , an external electronic device (eg, the electronic device 304 ), or a network system (eg, the second network 399 ). According to an embodiment, the wireless communication module 392 may include a peak data rate (eg, 20 Gbps or more) for realizing eMBB, loss coverage (eg, 164 dB or less) for realizing mMTC, or U-plane latency for realizing URLLC ( Example: downlink (DL) and uplink (UL) each 0.5 ms or less, or round trip 1 ms or less).

The antenna module 397 may transmit or receive a signal or power to the outside (eg, an external electronic device). According to an embodiment, the antenna module 397 may include an antenna including a conductor formed on a substrate (eg, a PCB) or a radiator formed of a conductive pattern. According to an embodiment, the antenna module 397 may include a plurality of antennas (eg, an array antenna). In this case, at least one antenna suitable for a communication scheme used in a communication network such as the first network 398 or the second network 399 is connected from the plurality of antennas by, for example, the communication module 390 . can be selected. A signal or power may be transmitted or received between the communication module 390 and an external electronic device through the selected at least one antenna. According to some embodiments, other components (eg, a radio frequency integrated circuit (RFIC)) other than the radiator may be additionally formed as a part of the antenna module 397 .

According to various embodiments, the antenna module 397 may form a mmWave antenna module. According to one embodiment, the mmWave antenna module comprises a printed circuit board, an RFIC disposed on or adjacent to a first side (eg, bottom side) of the printed circuit board and capable of supporting a designated high frequency band (eg, mmWave band); and a plurality of antennas (eg, an array antenna) disposed on or adjacent to a second side (eg, top or side) of the printed circuit board and capable of transmitting or receiving signals of the designated high frequency band. can do.

At least some of the components are connected to each other through a communication method between peripheral devices (eg, a bus, general purpose input and output (GPIO), serial peripheral interface (SPI), or mobile industry processor interface (MIPI)) and a signal ( eg commands or data) can be exchanged with each other.

According to an embodiment, the command or data may be transmitted or received between the electronic device 301 and the external electronic device 304 through the server 308 connected to the second network 399 . Each of the external

electronic devices

302 or 304 may be the same as or different from the electronic device 301 . According to an embodiment, all or part of the operations executed by the electronic device 301 may be executed by one or more external

electronic devices

302 , 304 , or 308 . For example, when the electronic device 301 is to perform a function or service automatically or in response to a request from a user or other device, the electronic device 301 may perform the function or service itself instead of executing the function or service itself. Alternatively or additionally, one or more external electronic devices may be requested to perform at least a part of the function or the service. One or more external electronic devices that have received the request may execute at least a part of the requested function or service, or an additional function or service related to the request, and transmit a result of the execution to the electronic device 301 . The electronic device 301 may process the result as it is or additionally and provide it as at least a part of a response to the request. For this, for example, cloud computing, distributed computing, mobile edge computing (MEC), or client-server computing technology may be used. The electronic device 301 may provide an ultra-low latency service using, for example, distributed computing or mobile edge computing. In another embodiment, the external electronic device 304 may include an Internet of things (IoT) device. The server 308 may be an intelligent server using machine learning and/or neural networks. According to an embodiment, the external electronic device 304 or the server 308 may be included in the second network 399 . The electronic device 301 may be applied to an intelligent service (eg, smart home, smart city, smart car, or health care) based on 5G communication technology and IoT-related technology.

According to various embodiments, the processor 320 connects an edge device (eg, the edge device 210 of FIG. 2A ) and a leaf device (eg, the leaf device 220 of FIG. 2A ) in the home network using the application 346 ). Control related to the edge computing service used can be performed.

According to various embodiments, the application 346 may provide a function of registering the edge device and the leaf device with the IoT server (eg, the IoT management server 240 of FIG. 2A ). For example, the processor 320 may discover at least one edge device and a leaf device in the home network using the communication module 390 and receive device information (eg, identification information, network information) of each device. .

The processor 320 may display a list of identified devices on the application. The processor 320 may request registration by transmitting device information of the edge device or the leaf device selected based on the user input to the IoT server. In addition, the processor 320 may receive the name and/or location information of each device on the application 346 .

According to various embodiments, the processor 320 may receive data (eg, image streaming, sound data) obtained from a sensor of the leaf device from the leaf device from the cloud network while the edge mode of the edge device is deactivated. Thereafter, when the edge computing service is started, the data acquired from the leaf device is transmitted to the edge device, and the user device (eg, the user device 130 of FIG. 1 , the user device 230 of FIG. 2A , or the electronic device) 301 ) may receive sensor data and analysis data directly from the edge device or through a cloud network (eg, the cloud network 140 of FIG. 1 ) from the edge device.

According to various embodiments, the processor 320 may display information related to connection or disconnection between the edge device and the leaf device on an application displayed on the display. For example, when the leaf device changes the connection from the first edge device to the second edge device according to a handover event, the user device 301 selects one of the leaf device, the first edge device, the second edge device, or the IoT server. Information related to the update of the edge-leaf connection may be received from at least one. The user device 301 may display updated edge-leaf connection information through an application based on the received information.

According to various embodiments, at least one of the components of the edge device or the leaf device may be configured to be at least partially identical to or similar to components of the electronic device 301 (eg, a user device). For example, the sensor of the leaf device may perform substantially the same function and/or operation as the sensor module 376 of the electronic device 301 . In addition, the communication module of the edge device (eg, the communication module 420 of FIG. 4 ) is the communication module 190 of the electronic device 301 , and the interface (eg, the interface 212 of FIG. 2A ) is the electronic device 301 . ) may perform substantially the same function and/or operation as that of the interface 377 .

The edge device 400 shown in FIG. 4 is a first edge device (eg, the first edge device 1010 of FIG. 10 ) or a second edge device (eg, the second edge device of FIG. 10 ) according to various embodiments. 1020)) can be operated. For example, a handover event occurs while the edge device 400 is connected to a leaf device (eg, the leaf device 220 of FIG. 2A ) and performs an edge computing service, so that the leaf device is handed over to another edge device. If possible, the edge device 400 may operate as a first edge device, and a handover event occurs while another edge device 400 is connected to a leaf device to perform an edge computing service, so that the leaf device becomes an edge device ( 400), the edge device 400 may operate as a second edge device.

In an edge computing system according to various embodiments, a plurality of edge devices (eg, the tablet PC 111 and TV 112 of FIG. 1 ) may exist, and each edge device may be a different type of device. can For example, the edge device 400 may be implemented as a TV, a tablet PC, a laptop PC, or the like. Hereinafter, descriptions of features for the edge device 400 to execute device-specific functions will be omitted, and only operations necessary to operate as the edge device 400 in the edge computing system will be described.

According to various embodiments, the communication module 420 supports wireless communication (eg, short-range communication (Wi-Fi), cellular communication), a leaf device (eg, the leaf device 220 of FIG. 2A ), a user device ( For example: the user device 230 of FIG. 2A ) and an external server (eg, the IoT management server and the IoT hub server of FIG. 2A ) may transmit/receive data. According to an embodiment, the communication module 420 is short-range wireless communication, near field communication (NFC), Bluetooth, bluetooth low energy (BLE), WiFi Direct, and a mesh network (eg, zigbee, z-wave). ) and/or UWB (ultra-wideband), and cellular communication, may be connected to a 4G network, and/or a 5G network (eg, standalone (SA), non-standalone (NSA)).

According to various embodiments, the sensor 440 may detect a movement of the electronic device. For example, the edge device 400 may be a device portable by a user (eg, a tablet PC, a laptop PC), and a gyroscope sensor to detect movement (or movement) of the edge device 400 , It may include at least one motion detection sensor such as an acceleration sensor. The edge device 400 includes a sensor hub (not shown) that collects and processes data of various sensors 440 , and sensor data collected from the sensor hub may be provided to the processor 410 .

According to various embodiments, the power management module 450 may check the power state of the edge device 400 and may be implemented as at least a part of a power management integrated circuit (PMIC). For example, the power management module 450 detects the power state of the edge device 400, such as whether the edge device 400 is connected to an external power source, the amount of charge of the battery (not shown), and sends it to the processor 410 . can transmit

According to various embodiments, the memory 430 may include a volatile memory and/or a non-volatile memory, and may store various data used in at least one component (eg, the processor 410 ) of the edge device 400 . It may be temporarily and/or permanently stored. The memory 430 may store various instructions that may be executed by the processor 410 . Such instructions may include various control commands including arithmetic and logical operations, data movement, and input/output that can be recognized by the processor 410 .

According to various embodiments, the memory 430 may store device information, an edge runtime, a basic module, a device module, and a service module in relation to an edge computing service.

According to various embodiments, the device information may include identification information of the edge device 400 , for example, device ID, manufacturer, model name, capability, and device type. In addition, the device information may further include at least some of location information (eg, a room, living room) and network information (eg, an IP address) of the edge device 400 . At least some of the device information (eg, location information) may be input by the user on an application of the user device (eg, the electronic device 301 of FIG. 3 or the user device 301 of FIG. 3 ).

According to various embodiments, the edge runtime may include a daemon program for interworking with the IoT server. The edge runtime is not executed when the edge mode of the edge device 400 is deactivated. When receiving a connection string from the IoT server (eg, the IoT management server 240 of FIG. 2A ), this value is It can be implemented using

According to various embodiments, the basic module may be configured as a container as a program necessary for communication with the IoT server. A basic module for edge runtime and edge computing may be installed in the edge device 400 through a process process or software upgrade of the edge device 400 . According to an embodiment, the edge device 400 may perform an over the air (OTA) software update as a software upgrade. For example, the OTA software update may include an open mobile alliance (OMA) download, a firmware OTA (FOTA), or a plain FTP (FTP).

According to various embodiments, the edge device 400 may store a device module and a service module as a module required for an edge computing service. The device module may correspond to each connected leaf device, and the service module may correspond to each service to be performed. For example, a plurality of device modules and/or service modules may be installed according to the number of connected leaf devices and the number of services to be performed. (Example: device module 1 (219a) and device module 2 (219b) in FIG. 2A)

According to various embodiments, the device module converts data received according to the first protocol from the leaf device according to the second protocol (eg, message queue telemetry transport (MQTT)) and transmits it to an external server. can According to an embodiment, the first protocol and the second protocol are protocols related to a control channel for the edge device 400 to communicate with the IoT server, and the first protocol is a web socket. may include For example, the control channel is a channel for providing and/or processing device information, and the edge device 400 may communicate with the IoT server using the control channel. In addition, the service module may include programs that process and/or analyze the received data.

During the process or software upgrade of the edge device 400 , only the edge runtime and the basic module may be installed, and the device module and the service module may not be installed. Thereafter, when the edge device 400 is connected to the leaf device, the device module and the service module may be downloaded and installed from the IoT server (eg, the module registry 254 of FIG. 2A ).

In addition to the illustrated configuration, the memory 430 may further store various programs for executing a unique function of the edge device 400 (eg, an image output function of a TV).

According to various embodiments, the processor 410 is a configuration capable of performing an operation or data processing related to control and/or communication of each component of the edge device 400 , and includes a communication module 420 and a memory 430 . It may be operatively, functionally, and/or electrically coupled to each component of the back edge device 400 .

According to various embodiments, there will be no limitations on the arithmetic and data processing functions that the processor 410 can implement within the edge device 400 , but below, the edge device 400 is the first edge device (eg, in FIG. 10 ). When operating as the first edge device 1010) and the second edge device (eg, the second edge device 1020 of FIG. 10 ), a handover event is detected and an edge connection change process is performed according to the handover event. In this case, various operations will be described.

Hereinafter, operations of the edge device 400 when the edge device 400 operates as the first edge device will be described.

According to various embodiments, the edge device 400 is connected to a leaf device (eg, the leaf device 220 of FIG. 2A ) through a home network, and may perform an edge computing service based on data received from the leaf device. there is. For example, when the leaf device is an IP camera, the edge device 400 uses an audio-video (AV) module and an artificial intelligence (AI) vision module to stream video transmitted from the leaf device to an IoT server (eg: The data may be transmitted to the IoT management server 240 of FIG. 2A ) and image analysis (eg, object recognition, face recognition) may be performed to transmit the analysis data to the leaf device and/or the IoT server.

Examples of edge computing services that can be implemented through the edge device 400 and the leaf device and modules required accordingly are as follows.

리프 장치leaf device	엣지 컴퓨팅 서비스Edge Computing Services	디바이스 모듈device module	서비스 모듈service module
카메라camera	Face Recognition, Object DetectionFace Recognition, Object Detection	MQTT Broker av stream gatewayMQTT Broker av stream gateway	Face AI, Vision AI (Doorbell Service, Delivery notification)Face AI, Vision AI (Doorbell Service, Delivery notification)
카메라camera	Daily SummaryDaily Summary	MQTT Broker av stream gatewayMQTT Broker av stream gateway	Face AI, Pet AI (Daily Summary Video Clip)Face AI, Pet AI (Daily Summary Video Clip)
AI 스피커AI speaker	Speaker RecognitionSpeaker Recognition	MQTT Broker av stream gatewayMQTT Broker av stream gateway	Speaker AI (Personized Service)Speaker AI (Personized Service)
TVTV	Contents RecognitionContents Recognition	MQTT Broker av stream gatewayMQTT Broker av stream gateway	Contents AI (AD Service, Shopping Service)Contents AI (AD Service, Shopping Service)
Robot Vaccum CleanerRobot Vacuum Cleaner	Pet Recognition, Bark detectionPet Recognition, Bark detection	MQTT Broker av stream gatewayMQTT Broker av stream gateway	Pet AI (Pet Service)Pet AI (Pet Service)

In Table 1, the MQTT broker may be a module that provides a channel for exchanging commands and/or events between the leaf device and the edge device 400 . For example, the message queuing telemetry transport (MQTT) protocol includes a broker, a publisher, and a subscriber, and when an MQTT broker is installed in the edge device 400 , the MQTT broker of the edge device 400 receives the topic published by the publisher. It can perform the function of relaying to a subscriber.

The AV stream gateway may perform a function of relaying audio and/or video streaming transmitted from the leaf device to the AI module.

According to various embodiments, the processor 410 is connected to the leaf device to perform edge computing service while the edge device 400 state information (eg, resource status, network connection status, connected leaf device information, service being performed) ) to another device (eg, a second edge device) and/or an IoT server located in the home network.

According to various embodiments, the processor 410 may detect a handover event of an edge computing service being performed. For example, the processor 410 detects a handover event based on at least one of a movement (or movement) of the electronic device acquired using the sensor 440 or the strength of a signal received through the communication module 420 . can detect Alternatively, the processor 410 may detect a handover event based on at least one of available resources of the processor 410 and/or the memory 430 or the power state of the electronic device obtained from the power management module.

The processor 410 monitors information such as movement, resource shortage, or power state change during execution of the edge computing service, detects a handover event in advance before a situation in which the edge computing service is impossible to perform, and other devices can be forwarded to

A method for the processor 410 to detect a handover event will be described in more detail with reference to FIGS. 7 to 9 .

According to various embodiments, before the edge device 400 detects a handover event in advance and transmits it to another device, a situation in which the edge computing service is suddenly impossible, such as disconnection of a network or power off, may occur. In this case, the edge device 400 may transmit a handover event to the IoT server through another network (eg, a cellular network).

According to various embodiments, the processor 410 may identify the second edge device 400 located in the home network to handover the edge computing service. According to an embodiment, the edge device 400 may identify the second edge device 400 through a discovery process or based on information received from the IoT server before the handover event occurs, or When an over event occurs, the second edge device 400 may be checked through discovery, or information related to the second edge device 400 located on the home network may be requested from the IoT server.

According to various embodiments, the processor 410 may check whether another identified edge device has a capability to receive an edge computing service handover with a leaf device. Here, the capability of the edge device includes whether the checked edge mode of the second edge device is activated, what services it can provide, whether it can be additionally connected to the leaf device, and the physical resources of the second edge device (eg, a processor). , memory available resources), an IP address, and may include at least some of OCF (open connectivity foundation) capability.

According to various embodiments, when a handover event is detected and a second edge device to handover a service is determined, the processor 410 transmits the handover event to at least one of the second edge device, the leaf device, or the IoT server. can In this case, the processor 410 may transmit at least some of information on the connected leaf device, the type of service being performed, a module used for the service, and information on the second edge device to be handed over together with the handover event.

According to various embodiments, when the second edge device and the leaf device are connected, the processor 410 may terminate the edge computing service by disconnecting the leaf device. The processor 410 notifies the IoT server of handover of the edge computing service and disconnection with the leaf device, and accordingly, the IoT server may update edge-leaf connection information.

Hereinafter, operations of the edge device 400 when the edge device 400 operates as the second edge device will be described.

According to various embodiments, the processor 410 may check a handover event of the edge computing service of the first edge device and the leaf device. For example, the processor 410 may receive information related to the handover event from the first edge device, and even if information related to the handover event is not received from the first edge device, the edge computing service delivered by the leaf device Based on a change request or a alive signal that the second edge device periodically exchanges with the first edge device, the occurrence of a handover event is confirmed and/or an operation for handover of the edge computing service to the second edge device is initiated. can

According to various embodiments, the processor 410 may check whether the edge device 400 can perform an edge computing service in response to a handover event. For example, the processor 410 is at least among the available resources of the processor 410 and/or memory, whether the edge mode is activated, or whether a module corresponding to the edge computing service being performed between the first edge device and the leaf device is installed. Based on some, it may be confirmed whether the edge device 400 can perform the edge computing service.

According to various embodiments, when it is determined that the edge device 400 can receive a service handover, the processor 410 may transmit the result to at least one of the first edge device, the leaf device, and the IoT server.

According to various embodiments, when it is determined that the edge device 400 cannot perform the edge computing service, the leaf device is connected to another edge device (eg, a third edge device in the network) or an IoT server to provide a service to at least one of another edge device, leaf device, or IoT server to perform

According to various embodiments, the processor 410 releases a connection with the first edge device to the leaf device in response to a handover event, and requests an edge computing service change including establishing a connection between the edge device 400 and the edge computing service. can be transmitted. According to another embodiment, when an edge connection request is received from the leaf device, the processor 410 may perform a connection process for an edge computing service.

5 is a block diagram of a leaf device according to various embodiments.

Referring to FIG. 5 , the leaf device 500 according to various embodiments may include a communication module 520 , a processor 510 , and a sensor 540 , and even if some of the illustrated components are omitted or replaced, this document Various embodiments of can be implemented.

In an edge computing system according to various embodiments, a plurality of leaf devices (eg, 120 in FIG. 1 ) may exist, and each leaf device may be a different type of device. For example, the leaf device 500 may be implemented as a camera, a refrigerator, a light bulb, a digital thermometer, or the like. Hereinafter, descriptions of features for the leaf device 500 to execute device-specific functions will be omitted, and only operations necessary to operate as the leaf device 500 in the edge computing system will be described.

According to various embodiments, the communication module 520 supports wireless communication (eg, Wi-Fi), an edge device (eg, the edge device 210 of FIG. 2A , the edge device 400 of FIG. 4 ), a user A device (eg, the user device 230 of FIG. 2A , the user device 301 of FIG. 3 ) and an external server (eg, the IoT management server 240 of FIG. 2A , and the IoT hub server 250 ) can

According to various embodiments, the leaf device 500 may include at least one sensor 540 . For example, if the leaf device 500 is an IP camera, it may include an image sensor for acquiring surrounding image data, and if it is an AI speaker, it may include a microphone for detecting surrounding sound. Alternatively, a sensor 540 for sensing various data such as temperature, pressure, and impact amount may be provided according to the type of the leaf device 500 .

According to various embodiments, the processor 510 is a configuration capable of performing an operation or data processing related to control and/or communication of each component of the leaf device 500 , and a communication module 520 , a sensor 540 . It may be operatively, functionally, and/or electrically coupled with each component of the back leaf device 500 .

According to various embodiments, the leaf device 500 may be connected to a first edge device in the home network (eg, the first edge device 1010 of FIG. 10 ) to perform an edge computing service, and according to a handover event The connection with the first edge device may be released and the edge computing service may be performed by being connected to the second edge device (eg, the second edge device 1020 of FIG. 10 ).

According to various embodiments, the processor 510 may perform an edge computing service by transmitting data (eg, image streaming) acquired through the sensor 540 to the first edge device through the communication module 520 .

According to various embodiments, the processor 510 may check a handover event of the edge computing service. For example, the processor 510 may receive information related to a handover event from at least one of the first edge device, the second edge device, and the IoT server.

According to various embodiments, the processor 510 makes it impossible for the first edge device to perform an edge computing service when socket communication is not performed or when a connection termination on a transmission protocol is detected as an alive packet does not arrive. can be confirmed as

According to various embodiments, when detecting a handover event, the processor 510 may transmit handover event information to the second edge device.

According to various embodiments, the processor 510 may identify a connectable second edge device for an edge computing service in response to a handover event. For example, the processor 510 may check information on the second edge device included in information related to a handover event received from at least one of the first edge device, the second edge device, and the IoT server. According to another embodiment, the second edge device may be identified through discovery on the home network.

According to various embodiments, the processor 510 may check whether the checked second edge device can perform the edge computing service. For example, the processor 510 is based on at least a part of the available resources of the processor 510 and/or memory of the second edge device, whether the edge mode is activated, or whether a module corresponding to the edge computing service is installed, It may be checked whether the second edge device can perform the edge computing service.

According to various embodiments, when it is determined that the second edge device can receive a service handover, the processor 510 may request a connection between the second edge device and the edge computing service.

According to various embodiments, when it is determined that the second edge device cannot perform the edge computing service, the processor 510 may transmit a request for an edge computing service or a cloud computing service to the IoT server. In this case, the processor 510 may be connected to another edge device (eg, a third edge device) based on information received from the IoT server to perform an edge computing service or to perform a cloud computing service through the IoT server. there is.

Referring to FIG. 6 , the first edge device is an edge device that is connected to the current leaf device (eg, the leaf device 500 of FIG. 5 ) to perform edge computing services, and the second edge device is located on the home network. It may be a device that can be connected to a leaf device when a handover event occurs. The same edge device (eg, edge device 400 in FIG. 4 ) may use a first edge device (eg, first edge device 1010 in FIG. 10 ) or a second edge device (eg, in FIG. 10 ) depending on the service execution state. It can operate as the second edge device 1020), and when a handover event occurs again on the second edge device after handover from the first edge device to the second edge device, it previously operated as the first edge device. The edge device may operate as the second edge device, and the edge device that has operated as the second edge device may operate as the first edge device.

The operation shown in FIG. 6 is not limited to operating in a specific subject (eg, a first edge device, a second edge device, a leaf device, and an IoT server). For example, a particular operation may be performed by a plurality of devices on the edge computing system, or may be performed by a device other than that described.

According to various embodiments, in operation 610, the first edge device may be connected to the leaf device on a home network to perform an edge computing service. For example, if the leaf device is an IP camera, the edge device uses an audio-video (AV) module and an artificial intelligence (AI) vision module to stream video transmitted from the leaf device to an IoT server (eg, in FIG. 2A ). The IoT management server 240 and the IoT hub server 250 may be transmitted, and the image analysis data may be transmitted to the leaf device and/or the IoT server.

According to various embodiments, the first edge device is connected to the leaf device and while performing the edge computing service, the state information of the first edge device (eg, resource status, network connection status, information of the connected leaf device, service being performed) can be transmitted to another device (eg, a second edge device) and/or an IoT server located in the home network.

According to various embodiments, in operation 620, the first edge device, the second edge device, or the leaf device may detect a handover event.

For example, the first edge device may be a device that a user can carry and move (eg, a tablet PC, a laptop PC), and the coverage of a Wi-Fi signal connectable to an access point (AP) of a home network is within several tens of meters. Since it is short, when the user takes the first edge device outdoors, the first edge device leaves the home network, and thus the edge computing service cannot be performed. In addition, since the first edge device performs edge computing services using some of the hardware and/or software resources, resources Occupying , there may be a shortage of resources for edge computing services. Also, when the power of the first edge device is insufficient, it may be impossible to provide the edge computing service. According to various embodiments, as described above, a handover event may be generated by determining a situation in which the first edge device cannot smoothly perform the edge computing service.

According to various embodiments, the first edge device may determine a handover event based on at least one of a movement of the first edge device, a resource shortage, or a change in a power state. The first edge device may monitor the information while the edge computing service is being performed, and may generate a handover event in advance before a situation in which the edge computing service cannot be performed occurs.

According to various embodiments, when a handover event is detected, the first edge device may transmit the handover event to at least one of the second edge device, the leaf device, and the IoT server.

According to various embodiments, before the first edge device detects a handover event in advance and transmits it to another device, a situation in which the edge computing service is suddenly impossible, such as disconnection from a network or power off, may occur. In this case, the first edge device may transmit a handover event to the IoT server through another network (eg, a cellular network). In addition, the leaf device and/or the second edge device may detect a handover event by detecting that the signal transmitted from the first edge device is no longer transmitted.

A method for the first edge device to determine a handover event will be described in more detail with reference to FIGS. 7 to 9 .

According to various embodiments, in operation 630, the first edge device may identify the second edge device located in the home network. According to an embodiment, the first edge device may identify the second edge device through a discovery process or based on information received from the IoT server before the handover event occurs, or the handover event occurs In this case, the second edge device may be identified through discovery, or information related to the second edge device located on the home network may be requested from the IoT server to be transmitted.

According to various embodiments, operation 630 may be performed by a leaf device or an IoT server. For example, when the leaf device receives a handover event from the first edge device or the IoT server or detects a handover event according to a change in a network signal, the second device based on the discovery process or information received from the IoT server You can check the edge device.

According to various embodiments, in operation 640 , the first edge device may check whether the second edge device checked in operation 630 has a capability to receive an edge computing service handover with the leaf device. Here, the capability of the second edge device includes whether the checked edge mode of the second edge device is activated, what services it can provide, whether it can be additionally connected to the leaf device, and the physical resources of the second edge device (e.g. : processor, memory available resources), IP address, physical and/or software resources supported by the device, and methods of controlling the resources (eg, defined in IoT resource related standards such as open connectivity foundation (OCF), M2M, Connected Home over IP) capability) may include at least some of them. According to an embodiment, the first edge device may determine that the edge mode is activated when the edge runtime of the second edge device is operating (or running). In addition, when the second edge device is connected to another leaf device to perform an edge computing service or has performed it before, the first edge device may confirm that the corresponding service can be provided. Alternatively, the first edge device may check the service that the second edge device can perform, the device module installed in the second edge device, and the service module based on the device information received from the second edge device (or IoT server). . In addition, as the second edge device executes its own function and/or is connected to other leaf devices to perform edge computing services, the first edge device has sufficient hardware and/or software resources to receive the leaf device and provide the service. can be checked to determine if it can be further connected with a leaf device.

According to various embodiments, the first edge device can synchronize and check the capability of the second edge device in advance before the handover event occurs, or the capability information can be uploaded to the IoT server in advance, or when a handover event occurs The first edge device may be identified through the discovery process. Here, the discovery may be in the form of receiving a response by transmitting it in the network as a broadcasting message as a query on whether the edge computing service is supported. According to another embodiment, the first edge device checks information that can be confirmed in advance among the capabilities of the second edge device (eg, a service that can be provided, OCF capability, etc.) through synchronization and requires confirmation in real time. Information (eg, physical resource, etc.) can be confirmed by requesting the second edge device when a handover event occurs.

According to various embodiments, when a plurality of edge devices satisfying a handover condition are identified in the home network, the first edge device may select one of them to handover the edge computing service. For example, the first edge device may determine one edge device suitable for receiving an edge computing service handover based on device information (or cloud parameters) and/or operation state information (or local parameters) of a plurality of edge devices. can Here, the device information includes account, location information, edge computing service list, user weight information, device model information, service performance, online status, battery status, central processing unit (CPU) or random access memory (RAM) usage, edge service status may include at least one of, and the operation state information may include at least one of whether the device wakes up or sleeps, an application running in the foreground, a connection state of a local network, and IP address information. According to an embodiment, the IoT server primarily selects a part of a plurality of edge devices as a candidate device using at least a part of the device information and the operation state information, and the first edge device is a candidate device selected by the IoT server By establishing a connection with and checking the remaining part of device information and operation state information, one of the candidate devices may be finally determined as the second edge device.

According to various embodiments, operation 640 may be performed by a leaf device and/or an IoT server.

According to various embodiments, if the second edge device satisfies the handover condition in operation 640, in operation 650, the first edge device may perform a handover operation of the edge computing service to the second edge device. The process of handover of the edge computing service to the second edge device may be initiated by the first edge device, the second edge device, the leaf device, or the IoT server. Detailed embodiments will be described in more detail with reference to FIGS. 10-16. do it with

According to various embodiments, in operation 660, the second edge device may be connected to the leaf device to perform an edge computing service. Accordingly, the leaf device may transmit data (eg, image streaming) acquired through the sensor to the second edge device, and data analysis (eg, image analysis) may be performed in the second edge device. The first edge device may pass data that has not been provided to the leaf device, but which has already been processed, to the second edge device.

According to various embodiments, when the handover process of the edge computing service is started (or completed), the first edge device may release the connection with the leaf device. In addition, when the handover is completed (or initiated), the second edge device and/or the leaf device notifies the IoT server of a connection change, and the IoT server may update edge-leaf connection information.

According to various embodiments, the edge device (eg, the edge device 400 of FIG. 4 ) includes at least one sensor (eg, the sensor 440 of FIG. 4 ) capable of detecting a motion of the edge device, and the sensor can be used to detect the motion of edge devices in real time.

According to various embodiments, in operation 710 , the edge device may be connected to a leaf device (eg, the leaf device 500 of FIG. 5 ) to perform an edge computing operation. For example, if the leaf device is an IP camera, the edge device uses an audio-video (AV) module and an artificial intelligence (AI) vision module to transmit video streaming from the leaf device to the IoT server, and analyze the video. Data can be sent to leaf devices and/or IoT servers.

According to various embodiments, in operation 720, the edge device may determine whether the motion of the edge device detected through a sensor (eg, a gyro sensor or an acceleration sensor) is equal to or greater than a reference value. For example, the edge device may determine that the motion of the edge device is equal to or greater than a reference value when the motion of the edge device is equal to or greater than a predetermined speed and/or distance, or the number of times that the motion is sensed is greater than or equal to a predetermined value.

According to various embodiments, in operation 730, the edge device may determine whether the strength of a signal received from the AP through the communication module decreases. Here, the signal strength may be a received signal strength indicator (RSSI) and may be detected by a network chipset (eg, Wi-Fi chipset).

According to various embodiments, when the motion of the edge device is equal to or greater than the reference value and the strength of a signal received from the AP is decreasing, in operation 740 , the edge device (eg, the processor of FIG. 4 ) determines the mobility of the edge device. is determined to have occurred, and it is possible to monitor whether an edge handover event has occurred.

According to various embodiments, when monitoring of a handover event is started, the edge device may transmit information related to monitoring of the handover event to a connected leaf device, an external edge device connected to a home network, or an IoT server. Even while the edge device is monitoring the handover event, the edge computing service can continue to be performed by connecting with the leaf device.

According to various embodiments, in operation 750 , the edge device may determine whether the detected motion of the edge device is greater than or equal to a predetermined distance and/or speed, and may determine whether the strength of a signal received from the AP is less than or equal to a predetermined value. According to an embodiment, the edge device may check only one of the motion of the edge device or the strength of a signal.

For example, if a continuous motion is detected in the edge device and the signal received from the AP is weakened, it can be viewed as a situation in which the user moves the portable edge device from the room where the edge device and the leaf device are installed to another space. Since the AP has limited coverage, in this case, it can be seen that the edge device can no longer perform the function of the edge device on the home network.

According to various embodiments, when the movement of the edge device is greater than a certain distance and/or speed and the strength of a signal received from the AP is less than or equal to a certain value, in operation 760, the edge device determines that an edge handover event has occurred, An operation for handover of an edge computing service to an external edge device (eg, the second edge device of FIG. 10 ) may be executed.

A process in which an edge device handovers a leaf device and an edge computing service being performed to another edge device will be described in more detail with reference to FIGS. 10-16 .

In operation 770, the edge device checks whether the change in motion and/or signal strength is lower than a predetermined level while monitoring the handover event, in this case, ends monitoring of the handover event, and edge computing service with the leaf device can continue to be performed.

According to various embodiments, the edge device (eg, edge device 400 of FIG. 4 ) may include a processor (eg, processor 410 of FIG. 4 ) and/or memory (eg, memory 420 of FIG. 4 ) of the edge device ) can determine whether to handover the edge computing service based on the available resources. Edge device must perform its own functions (eg, tablet PC application, TV video transmission) other than edge computing service , it is possible to handover a leaf device to another edge device capable of edge computing services.

According to various embodiments, the edge device may check whether a situation that may change the resource state of the edge device, such as a user input or an alarm on the system, occurs, and monitor an edge handover event.

According to various embodiments, in operation 810 , the edge device may be connected to a leaf device to perform an edge computing operation.

According to various embodiments, in operation 822 , the edge device may detect whether a user input on the touch screen is generated. Since the user input on the touch screen is for performing an application or function provided by the edge device, available resources of a processor and/or memory required for an edge computing service may be reduced.

According to various embodiments, in operation 824 , the edge device may detect whether a key (eg, hard key, soft key) input of the edge device occurs.

According to various embodiments, in operation 828 , the edge device may detect whether an input using a remote control is received.

According to various embodiments, in operation 826, the edge device may determine whether an alarm is generated in the operating system (OS). For example, it is possible to check the notification for the user provided by the operating system of the edge device, such as an emergency text message, SNS, system alarm, and the like.

According to various embodiments, when at least one condition among

operations

822, 824, 826, and 828 is satisfied, in operation 830, the edge device may start resource monitoring. Here, operation 830 may be performed when any one of

operations

822, 824, 826, and 828 is satisfied, and according to an embodiment, operation 830 may be performed when two or more conditions are satisfied.

For example, the edge device may check how much of the hardware and/or software resources of the edge device required for the edge computing service are being used according to the execution of other functions or the occurrence of an event.

According to various embodiments, in operation 840, the edge device may determine whether the currently available resource is lower than a threshold value. Here, the threshold value may be determined according to the minimum amount of processor and/or memory required for the edge computing service.

According to various embodiments, when the currently available resource is lower than the threshold, in operation 860, the edge device determines that an edge handover event has occurred, and provides an edge to an external edge device (eg, the second edge device of FIG. 10 ). An operation for handover of a computing service may be performed.

On the other hand, if the currently available resource maintains a value higher than the threshold, and in operation 850, it is determined that there is no operation other than the edge computing operation (eg, application of a tablet PC, providing an image of a TV), the edge device is The monitoring of the over event is terminated, and edge computing services with the leaf device can be continued.

According to various embodiments, whether the edge device (eg, the edge device 400 of FIG. 4 ) is connected to an external power source using a power management module (the power management module 450 of FIG. 4 ), The power state of the edge device can be detected.

According to various embodiments, in operation 910 , the edge device may be connected to a leaf device to perform an edge computing operation.

According to various embodiments, in operation 920 , the edge device may determine whether the edge device operates in a low power mode. For example, depending on the setting of the edge device, the edge device may be set to operate in a low power mode when the edge device is not connected to an external power source and uses the power of the battery, or when the remaining amount of the battery is less than a predetermined value while the battery is not being charged. . If the edge device operates in low power mode or the remaining battery level is below a predetermined level, the edge device may be turned off due to insufficient power. Computing services may be continuously performed.

According to various embodiments, in operation 930 , the edge device may determine whether a resource of a processor and/or a memory of the edge device is insufficient.

According to various embodiments, when the conditions of

operations

920 and 930 are satisfied, in operation 940, the edge device determines that an edge handover event has occurred, and provides an edge to an external edge device (eg, the second edge device of FIG. 10 ). An operation for handover of a computing service may be performed.

10 illustrates an embodiment in which the first edge device 1010 and the second edge device 1020 operate as subjects of handover when a handover event can be detected in advance.

According to various embodiments, in operation 1050 , the first edge device 1010 may be connected to the leaf device 1030 on a home network to perform an edge computing service.

According to various embodiments, in operation 1060 , the first edge device 1010 may detect a handover event. For example, the first edge device 1010 includes the movement of the first edge device 1010 acquired using a sensor (eg, the sensor 440 of FIG. 4 ), and a communication module (eg, the communication module of FIG. 4 ) 420)), the resource status of the processor (eg, the processor 410 of FIG. 4 ) and/or the memory (eg, the memory 430 of FIG. 4 ), and the power management module (eg, FIG. 4 ) The handover event may be detected based on at least one of the power states detected through the power management module 450 of the . Various embodiments in which the first edge device 1010 detects a handover event have been described above with reference to FIGS. 7 to 9 .

According to various embodiments, in operation 1062 , the first edge device 1010 may identify the second edge device 1020 in the network to which the edge computing service is to be handed over. According to an embodiment, the first edge device 1010 checks the second edge device 1020 through a discovery process or based on information received from the IoT server 1040 before the handover event occurs. Alternatively, when a handover event occurs, the second edge device 1020 is checked through discovery, or information related to the second edge device 1020 located on the home network is transmitted to the IoT server 1040. you can request

According to various embodiments, the first edge device 1010 may check whether the checked second edge device 1020 has the capability to receive the edge computing service handover. Here, the capability of the second edge device 1020 is whether the checked edge mode of the second edge device 1020 is activated, what services it can provide, whether it can be additionally connected to the leaf device 1030, The second edge device 1020 may include at least some of physical resources (eg, processor, memory available resources), an IP address, and open connectivity foundation (OCF) capability.

According to various embodiments, in operation 1064 , the first edge device 1010 may transmit a handover event to at least one of the second edge device 1020 , the leaf device 1030 , and the IoT server 1040 . In this case, the first edge device 1010 may transmit information including information on the currently connected leaf device 1030 and edge computing service, or may transmit only information on the occurrence of a handover event. According to an embodiment, the first edge device 1010 may broadcast a handover event to devices on a home network.

According to various embodiments, in operation 1066 , the second edge device 1020 may identify a handover event according to handover event information transmitted (or broadcast) from the first edge device 1010 .

According to an embodiment, even if a handover event is not transmitted from the first edge device 1010, the second edge device 1020 may request a change of the edge computing service delivered by the leaf device 1030 or the second edge device ( The generation of the handover event may be confirmed based on the alive packet exchanged periodically by the 1020 with the first edge device 1010 . In this case, operation 1064 may be omitted.

According to various embodiments, information on the leaf device 1030 has not been obtained in advance through connection with the first edge device 1010, or the handover event information transmitted from the first edge device 1010 (operation 1064). If information related to the leaf device 1030 is not included, in operation 1070 , the second edge device 1020 may identify the leaf device 1030 through discovery. Contrary to this, when the second edge device 1020 acquires information on the leaf device 1030 through handover event information or a signal periodically exchanged, operation 1070 may be omitted.

According to various embodiments, in operation 1072 , the second edge device 1020 may transmit an edge computing connection change request to the leaf device 1030 .

According to various embodiments, in operation 1074 , the leaf device 1030 may transmit an edge connection request to the second edge device 1020 in response to the request of the second edge device 1020 . Also, in operation 1076 , the leaf device 1030 may release the connection with the first edge device 1010 . According to an embodiment, the first edge device 1010 may pass data that has not been provided to the leaf device 1030 but has already been processed (eg, image analysis data) to the second edge device 1020 . Although operation 1076 is shown to be performed after operation 1074 in FIG. 10 , the order in which

operations

1074 and 1076 are performed may be changed, and each operation may be performed at least partially simultaneously.

According to various embodiments, in operation 1080, the second edge device 1020 may be connected to the leaf device 1030 to perform an edge computing service. Here, the edge computing service may be the same service as the edge computing service in operation 1050 .

According to various embodiments, when the handover is completed (or initiated), the second edge device 1020 and/or the leaf device 1030 notifies the IoT server 1040 of a connection change, and in operation 1090 , the IoT server 1040 may update edge-leaf connection information.

11 illustrates an embodiment in which the first edge device 1110 and the second edge device 1120 operate as subjects of handover when a handover event cannot be detected in advance.

According to various embodiments, in operation 1150 , the first edge device 1110 may be connected to the leaf device 1130 on a home network to perform an edge computing service.

According to various embodiments, in operation 1160 , a handover event may occur in the first edge device 1110 . In this embodiment, the handover event may occur in a situation in which the first edge device 1110 cannot detect it in advance, unlike the embodiment of FIG. 10 described above. For example, before the first edge device 1110 detects a handover event in advance and transmits it to another device, a situation in which the edge computing service is suddenly impossible, such as disconnection of a network or power off, may occur. According to an embodiment, the first edge device 1110 transmits handover event information to the IoT server 1140 by connecting to another network (eg, a cellular network) when communication with an access point (AP) is impossible after moving outdoors. can be transmitted

According to various embodiments, the leaf device 1130 may detect a handover event according to whether a signal transmitted from the first edge device 1110 is received. For example, when the leaf device 1130 does not perform socket communication or when a connection termination on a transmission protocol is detected as an alive packet does not arrive, the first edge device 1110 performs an edge computing service. It can be verified that this is impossible.

According to various embodiments, in operation 1162 , when detecting a handover event, the leaf device 1130 and/or the IoT server 1140 may transmit handover event information to the second edge device 1120 .

According to various embodiments, in operation 1164 , the second edge device 1120 may check a handover event according to handover event information transmitted from the leaf device 1130 and/or the IoT server 1140 . According to another embodiment, the second edge device 1120 may check the occurrence of a handover event based on the alive packet exchanged periodically with the first edge device 1110 . In this case, operation 1162 may be omitted.

According to various embodiments, information on the leaf device 1130 is not obtained in advance through connection with the first edge device 1110 , or a handover event received from the leaf device 1130 and/or the IoT server 1140 . If the information (operation 1162) does not include information related to the leaf device 1130, in operation 1170, the second edge device 1120 may identify the leaf device 1130 through discovery. Contrary to this, when the second edge device 1120 acquires the information of the leaf device 1130 through handover event information or a signal exchanged periodically, operation 1170 may be omitted.

According to various embodiments, in operation 1172 , the second edge device 1120 may transmit an edge computing connection change request to the leaf device 1130 .

According to various embodiments, in operation 1174 , the leaf device 1130 may transmit an edge connection request to the second edge device 1120 in response to the request of the second edge device 1120 .

According to various embodiments, in operation 1180 , the second edge device 1120 and the first edge device 1110 are connected to the leaf device 1130 to perform an edge computing service. Here, the edge computing service may be the same service as the edge computing service in operation 1150 .

According to various embodiments, when the handover is completed (or initiated), the second edge device 1120 and/or the leaf device 1130 notifies the IoT server 1140 of a connection change, and in operation 1190 , the IoT server 1140 may update edge-leaf connection information.

12 illustrates an embodiment in which the leaf device 1230 operates as a handover subject when a handover event can be detected in advance.

According to various embodiments, in operation 1250 , the first edge device 1210 may be connected to the leaf device 1230 on a home network to perform an edge computing service.

According to various embodiments, in operation 1260 , the first edge device 1210 may detect a handover event and transmit handover event information to the leaf device 1230 . For example, the first edge device 1210 may include among the movement of the first edge device 1210 acquired using a sensor, the strength of a signal received through the communication module, the resource status of the processor and/or memory, and the power status. A handover event may be detected based on at least one. Various embodiments in which the first edge device 1210 detects a handover event have been described above with reference to FIGS. 7 to 9 .

According to various embodiments, in operation 1262 , the leaf device 1230 may identify a handover event according to handover event information transmitted (or broadcast) from the first edge device 1210 . According to another embodiment, when the leaf device 1230 does not perform socket communication with the first edge device 1210 or a connection termination on a transmission protocol is sensed as an alive packet does not arrive, the first edge It may be determined that the device 1210 is unable to perform the edge computing service. In this case, operation 1260 may be omitted.

According to various embodiments, when the handover event information (operation 1260) does not include information related to the second edge device 1220, in operation 1270, the leaf device 1230 performs a handover of the edge computing service. The two-edge device 1220 may be discovered.

According to various embodiments, in operation 1272 , the leaf device 1230 may check whether the second edge device 1220 identified through discovery has a capability to receive an edge computing service handover. Here, the capability of the second edge device 1220 is whether the checked edge mode of the second edge device 1220 is activated, what services it can provide, whether it can be additionally connected to the leaf device 1230, The second edge device 1220 may include at least some of physical resources (eg, processor and memory available resources), an IP address, and open connectivity foundation (OCF) capability.

In operation 1272 , the leaf device 1230 may identify the second edge device 1220 . According to an embodiment, device information and capability information of the second edge device 1220 may be included in the handover event information, and in this case, operations 1270 and/or operation 1272 may be omitted. According to an embodiment, when a plurality of edge devices exist on the home network, the leaf device 1230 may attempt a handover by identifying an edge device in which the same service (eg, vision, NLU, etc.) is activated. there is.

According to various embodiments, in operation 1274 , the leaf device 1230 may transmit an edge computing connection request to the second edge device 1220 . In operation 1276 , the leaf device 1230 may release the connection with the first edge device 1210 .

According to various embodiments, in operation 1280 , the leaf device 1230 may be connected to the second edge device 1220 to perform an edge computing service.

According to various embodiments, in operation 1282, the leaf device 1230 and/or the second edge device 1220 notifies the IoT server 1240 of a connection change, and in operation 1290, the IoT server 1240 is edge- You can update leaf connection information.

13 illustrates an embodiment in which the leaf device 1330 operates as a handover subject when a handover event can be detected in advance.

According to various embodiments, in operation 1350 , the first edge device 1310 may be connected to the leaf device 1330 on a home network to perform an edge computing service.

According to various embodiments, in operation 1360 , the first edge device 1310 may detect a handover event and transmit handover event information to the leaf device 1330 .

According to various embodiments, in operation 1362 , the leaf device 1330 may identify a handover event according to handover event information transmitted (or broadcast) from the first edge device 1310 . According to another embodiment, when the leaf device 1330 does not perform socket communication with the first edge device 1310 or a connection termination on a transmission protocol is sensed as an alive packet does not arrive, the first edge device 1330 It may be determined that the device 1310 cannot perform the edge computing service. In this case, operation 1360 may be omitted.

According to various embodiments, in operation 1370 , the leaf device 1330 may confirm that the first edge device 1310 cannot perform the edge computing service, and may transmit a service request to the IoT server 1340 . For example, when the leaf device 1330 is an IP camera, an artificial intelligence (AI) service, which is a service related to image data acquired from the leaf device 1330, is performed on the edge device and/or IoT server 1340 in the network. can The leaf device 1330 may transmit a request for an edge computing service or a cloud computing service to the IoT server 1340 .

According to various embodiments, in operation 1372 , the IoT server 1340 checks at least one edge device registered with the same account and/or location as the leaf device 1330 in the database, and checks the operating state of the corresponding edge device. can Here, the operation state is whether the checked edge mode of the second edge device 1320 is activated, what services can be provided, whether it can be additionally connected to the leaf device 1330, and the second edge device 1320 of the physical resource (eg, processor, memory available resource), IP address, and capability of the second edge device 1320 such as open connectivity foundation (OCF) capability.

According to various embodiments, the IoT server 1340 is located in the same home network as the leaf device 1330, and when a plurality of edge devices capable of edge computing services are identified, device information (or cloud parameters) of each edge device and /or it is possible to determine one edge device suitable for receiving an edge computing service handover based on the operation state information (or local parameter). Alternatively, a list of a plurality of edge devices capable of edge computing service may be transmitted to the user device, and one device may be determined as the second edge device 1320 according to the selection of the user device.

According to various embodiments, in operation 1380 , the IoT server 1340 may check whether the second edge device 1320 can perform the service requested by the leaf device 1330 . When the second edge device 1320 can perform the service, in operation 1382 , the IoT server 1340 transmits device information of the second edge device 1320 to the leaf device 1330 , and the second edge device In connection with 1320 , it may notify to perform edge computing services.

According to various embodiments, in operation 1384 , the leaf device 1330 may transmit an edge connection request to the second edge device 1320 . In operation 1386 , the leaf device 1330 may be connected to the second edge device 1320 to perform an edge computing service.

On the other hand, if the second edge device 1320 cannot perform the service requested by the leaf device 1330, in operation 1390, the IoT server 1340 connects to the leaf device 1330 as the IoT server 1340. It may notify you to perform cloud computing services. In operation 1392, the leaf device 1330 is connected to the IoT server 1340, and without transmitting the acquired data (eg, video streaming) to the edge device, it is transmitted directly to the IoT server 1340 to provide a cloud computing service. can

14 illustrates an embodiment in which the leaf device 1430 or the IoT server 1440 operates as a subject of handover when a handover event cannot be detected in advance.

According to various embodiments, in operation 1450 , the first edge device 1410 may be connected to the leaf device 1430 on a home network to perform an edge computing service.

In the present embodiment, a situation in which an edge computing service is suddenly impossible occurs in the first edge device 1410, such as disconnection of a network connection or power off, and thus a handover event may not be detected in advance.

According to various embodiments, in operation 1460, when the first edge device 1410 is disconnected from the network (eg, Wi-Fi network) used for the edge computing service, it uses another network (eg, cellular network) Handover event information may be transmitted to the IoT server 1440 . According to another embodiment, when the first edge device 1410 is in a situation in which access to another network is impossible, such as when the power is turned off, operation 1460 may be omitted, and the second edge device 1420, the leaf device 1430, or A handover event may be detected by the IoT server 1440 .

According to various embodiments, in operation 1462, the IoT server 1440 checks at least one edge device registered with the same account and/or location as the leaf device 1430 in the database, and checks the operating state of the corresponding edge device. can Here, the operating state may include the capability of the second edge device 1420 .

According to various embodiments, in operation 1470 , the IoT server 1440 may check whether the second edge device 1420 can perform the service requested by the leaf device 1430 . When the second edge device 1420 can perform the service, in operation 1472 , the IoT server 1440 transmits device information of the second edge device 1420 to the leaf device 1430 , and the second edge device In connection with 1420, it may notify to perform edge computing service.

According to various embodiments, in operation 1474 , the leaf device 1430 may transmit an edge connection request to the second edge device 1420 . In operation 1476 , the leaf device 1430 may be connected to the second edge device 1420 to perform an edge computing service. In operation 1480 , the IoT server 1440 may update leaf-edge connection information as the leaf device 1430 is connected to the second edge device 1420 .

On the other hand, if the second edge device 1420 cannot perform the service requested by the leaf device 1430, in operation 1490, the IoT server 1440 connects to the leaf device 1430 as the IoT server 1440. It may notify you to perform cloud computing services. In operation 1492, the leaf device 1430 is connected to the IoT server 1440, and without transmitting the acquired data (eg, video streaming) to the edge device, it is transmitted directly to the IoT server 1440 to provide a cloud computing service. can

According to another embodiment, when the leaf device 1430 is not connected to the second edge device 1420 or there is no response from the IoT server 1440, the leaf device 1430 is an edge device found after local discovery. A service connection may be requested, or information of the discovered edge device may be transmitted to the IoT server 1440 to request a service connection.

According to various embodiments, some of the edge computing services being performed between the first edge device 1510 and the leaf device 1530 are handed over to the second edge device 1520 according to a handover event, and the remaining part is handed over to the first edge device 1520. It may continue to be performed on the edge device 1510 .

According to various embodiments, in operation 1550 , the first edge device 1510 may be connected to the leaf device 1530 on a home network to perform an edge computing service. For example, the leaf device 1530 may be an IP camera device that acquires image data in real time, and services that can be provided through the acquired image data include a vision recognition service and a natural language understanding service. can do.

According to various embodiments, in operation 1560 , the second edge device 1520 may be connected to the home network, and an edge mode may be activated. Here, the second edge device 1520 may perform at least some of the services being performed by the first edge device 1510 , and may be a device in which a module necessary for the corresponding service is installed.

According to various embodiments, in operation 1562 , the first edge device 1510 may identify the second edge device 1520 . The first edge device 1510 may detect a broadcasting signal from the second edge device 1520 and check whether the second edge device 1520 has connected to the home network or activated the edge mode.

According to various embodiments, in operation 1570 , the first edge device 1510 may transmit information on the first edge device 1510 and information on the edge computing service being performed to the second edge device 1520 . For example, the first edge device 1510 may broadcast functions and device performance capabilities that can be supported by the first edge device 1510 on a network.

According to various embodiments, in operation 1572 , the second edge device 1520 may transmit information of the second edge device 1520 to the first edge device 1510 . For example, the second edge device 1520 may transmit capability information of the second edge device 1520 to the first edge device 1510 in response to a signal broadcast from the first edge device 1510 . there is.

According to various embodiments, in operation 1574 , the first edge device 1510 and the second edge device 1520 are configured based on the capability information of the first edge device 1510 and the capability information of the second edge device 1520 . You can decide which service to perform on each device. For example, among the vision recognition service and natural language understanding service being performed by the first edge device 1510 , the vision recognition service is continuously performed by the first edge device 1510 , and the natural language understanding service is transferred to the second edge device 1520 . It can be decided by handover. In this case, the first edge device 1510 and the second edge device 1520 perform each service based on available resources of each device, installed modules (eg, device modules, service modules), mobility, power status, etc. You can decide which service is more suitable for each device.

According to various embodiments, in operation 1578 , the first edge device 1510 makes an edge connection change request for some of the services being performed (eg, natural language understanding service) along with the information of the second edge device 1520 and the leaf device. 1530 may be sent.

According to various embodiments, in operation 1578 , the leaf device 1530 transmits an edge connection request for a service (eg, natural language understanding service) determined to the second edge device 1520 according to the edge connection change request, and operation 1580 . , the second edge device 1520 and the leaf device 1530 may be connected to each other to perform a predetermined service. In operation 1582, the first edge device 1510 and the leaf device 1530 continue to perform in the first edge device 1510 except for the service (eg, natural language understanding service) handed over to the second edge device 1520 . It can continue to perform the service it has decided to do (eg, a vision recognition service).

According to various embodiments, in operation 1584, the first edge device 1510 and/or the second edge device 1520 notifies the IoT server 1540 that the edge connection has been changed, and in operation 1590, the IoT server 1540 ) can update edge-leaf connections.

According to various embodiments, in operation 1650 , the first edge device 1610 may be connected to the leaf device 1630 on a home network to perform an edge computing service. For example, the leaf device 1630 may be an IP camera device that acquires image data in real time, and services that can be provided through the acquired image data include a vision recognition service and a natural language understanding service. can do.

According to various embodiments, in operation 1660 , the second edge device 1620 may be connected to the home network, and an edge mode may be activated.

According to various embodiments, in operation 1662 , the second edge device 1620 may transmit information on the second edge device 1620 to the IoT server 1640 . For example, the second edge device 1620 may transmit information including device information of the second edge device 1620 , resource status, installed modules, and edge mode activation status to the IoT server 1640 .

According to various embodiments, in operation 1664 , the IoT server 1640 may check information of the first edge device 1610 and the second edge device 1620 . In operation 1666 , the IoT server 1640 may determine a service to be performed by each device based on capability information of the first edge device 1610 and capability information of the second edge device 1620 . For example, among the vision recognition service and natural language understanding service being performed by the first edge device 1610, the vision recognition service is continuously performed by the first edge device 1610, and the natural language understanding service is transferred to the second edge device 1620. It can be decided by handover. The IoT server 1640 includes the first edge device 1610 and the second edge device 1620 based on available resources of each device, installed modules (eg, device modules, service modules), mobility, power status, etc. , it is possible to determine which of the services is more suitable for each device.

According to various embodiments, in operation 1670 , the IoT server 1640 may transmit information about a service to be performed by each device to the leaf device 1630 . In operation 1672, the leaf device 1630 transmits an edge connection request for a predetermined service (eg, natural language understanding service) to the second edge device 1620 according to the edge connection change request, and in operation 1674, the second edge device 1620 and the leaf device 1630 may be connected to each other to perform a predetermined service. In operation 1676, the first edge device 1610 and the leaf device 1630 continue to perform in the first edge device 1610 except for a service handed over to the second edge device 1620 (eg, natural language understanding service). It can continue to perform the service it has decided to do (eg, a vision recognition service). In operation 1680, the IoT server 1640 may update the edge-leaf connection.

According to various embodiments, the processor may be configured to receive the handover event from at least one of the first external device, the second external device, and the external server through the communication module.

According to various embodiments, the processor receives a predetermined signal from the first external device using the communication module while the first external device performs the edge computing service with the second external device, and When the predetermined signal is not received from the first external device, it may be configured to determine that the handover event has occurred.

According to various embodiments, the processor, in response to the handover event, disconnects the connection from the first external device to the second external device and an edge including the electronic device and the establishment of a connection for the edge computing service Computing service may be configured to send a change request.

According to various embodiments, the processor may include available resources of the processor and/or the memory, whether an edge mode is activated, or a module corresponding to an edge computing service being performed between the first external device and the second external device. It may be configured to check whether the electronic device can perform the edge computing service based on at least a part of whether or not it is installed.

According to various embodiments, when it is determined that the electronic device cannot perform the edge computing service, the processor is configured to connect the second external device to another edge device or an external server to perform the service. It may be configured to transmit to at least one of an external device, the second external device, or an external server.

According to various embodiments, the processor may be configured to perform some of edge computing services being performed between the first external device and the second external device.

According to various embodiments, when the processor is connected to the second external device to perform the edge computing service, the processor may be configured to notify an external server of an edge computing service change.

According to various embodiments of the present disclosure, further comprising a sensor for detecting a movement of the electronic device, wherein the processor includes at least one of the movement of the electronic device acquired using the sensor or the strength of a signal received through the communication module Based on one, it may be configured to detect the handover event.

According to various embodiments, the processor may be configured to detect the handover event based on at least one of an available resource of the processor and/or the memory or a power state of the electronic device.

According to various embodiments, the processor is configured to enable the second external device to be configured based on at least a part of available resources of the second external device, whether an edge mode is activated, or whether a module corresponding to the edge computing service is installed. It may be configured to check whether the edge computing service can be performed.

According to various embodiments, the processor may be configured to receive information related to whether the second external device can perform the edge computing service from the second external device or the external server.

According to various embodiments, when the processor is disconnected from the first network used for the edge computing service, information related to the second external device identified through a second network and information related to the handover event may be set to be transmitted to the external server.

An electronic device according to various embodiments includes a communication module, a sensor, and a processor operatively connected to the communication module and the sensor, wherein the processor transmits data obtained through the sensor to the communication module transmits to the first external device to perform the edge computing service, checks the handover event of the edge computing service, and responds to the handover event and to request a connection for the edge computing service to the second external device.

According to various embodiments, the processor may be configured to identify the handover event based on the strength of a signal transmitted from the first external device through the communication module.

According to various embodiments, the processor may be configured to receive information related to the handover event from at least one of the first external device, the second external device, and the IoT server through the communication module.

According to various embodiments, the processor may be configured to request a connection to some of the edge computing services being performed from the second external device based on the received information related to the handover event.

According to various embodiments, the processor transmits a service connection request to the IoT server through the communication module in response to the handover event, and the second external device to perform the edge computing service from the IoT server. may be configured to receive information.

According to various embodiments, when receiving a notification from the IoT server to connect to the cloud computing service, the processor may be configured to stop the edge computing service and transmit data obtained through the sensor to the IoT server there is.

Claims

In an electronic device,

communication module;

Memory; and

a processor operatively coupled to the communication module and the memory;

The processor is

Check the handover event of the edge computing service being performed by the first external device and the second external device on the local network,

check whether the electronic device can perform the edge computing service; and

An electronic device configured to perform the edge computing service in connection with the second external device operating as a leaf device of the edge computing service when the electronic device can perform the edge computing service.
The method of claim 1,

The processor is

an electronic device configured to receive the handover event from at least one of the first external device, the second external device, and an external server through the communication module.
The method of claim 1,

The processor is

While the first external device performs the edge computing service with the second external device, receiving a predetermined signal from the first external device using the communication module, and

An electronic device configured to determine that the handover event has occurred when the predetermined signal is not received from the first external device.
The method of claim 1,

The processor is

In response to the handover event, an electronic device configured to transmit an edge computing service change request including disconnecting the connection from the first external device and establishing a connection between the electronic device and the edge computing service to the second external device .
The method of claim 1,

The processor is

Based on at least a part of available resources of the processor and/or the memory, whether an edge mode is activated, or whether a module corresponding to the edge computing service being performed between the first external device and the second external device is installed. An electronic device configured to check whether the electronic device can perform the edge computing service.
6. The method of claim 5,

The processor is

When it is determined that the electronic device cannot perform the edge computing service, the first external device, the second external device, or an external device connects the second external device to another edge device or an external server to perform the service. An electronic device configured to transmit to at least one of the servers.
The method of claim 1,

The processor is

An electronic device configured to perform some of the edge computing services being performed between the first external device and the second external device.
The method of claim 1,

The processor is

An electronic device configured to notify an external server of an edge computing service change when connected to the second external device to perform the edge computing service.
In an electronic device,

communication module;

Memory; and

a processor operatively coupled to the communication module and the memory;

The processor is

performing an edge computing service based on data received from a first external device connected through the communication module;

detecting a handover event of the edge computing service,

In response to the detection of the handover event, a second external device connected to the first external device through the communication module and capable of performing the edge computing service is identified, and

an electronic device configured to transmit the checked information related to the second external device and information related to the handover event to at least one of the first external device, the second external device, and an external server.
10. The method of claim 9,

Further comprising a sensor for detecting the movement of the electronic device,

The processor is

An electronic device configured to detect the handover event based on at least one of a movement of the electronic device acquired using the sensor or a strength of a signal received through the communication module.
10. The method of claim 9,

The processor is

an electronic device configured to detect the handover event based on at least one of an available resource of the processor and/or the memory or a power state of the electronic device.
10. The method of claim 9,

The processor is

Whether the second external device can perform the edge computing service based on at least a part of available resources of the second external device, whether an edge mode is activated, or whether a module corresponding to the edge computing service is installed Electronic devices set up to verify.
In an electronic device,

communication module;

sensor; and

a processor operatively connected to the communication module and the sensor;

The processor is

An edge computing service is performed by transmitting data acquired through the sensor to a first external device through the communication module,

Check the handover event of the edge computing service,

In response to the handover event, identify a connectable second external device for the edge computing service, and

An electronic device configured to request a connection for the edge computing service to the second external device.
14. The method of claim 13,

The processor is

The electronic device is configured to receive information related to the handover event from at least one of the first external device, the second external device, and the IoT server through the communication module.
14. The method of claim 13,

The processor is

In response to the handover event, transmit a service connection request to the IoT server through the communication module,

An electronic device configured to receive information on the second external device to perform the edge computing service from the IoT server.