JP6982639B2 - Multi-edge cloud network communication control method and edge computing system - Google Patents

Description

The present invention relates to a network communication control method, and more particularly to a multi-edge cloud network communication control method.

With the popularity of mobile devices and the proliferation of Internet services such as deostreaming, virtual reality, and self-driving, and the expansion of business services to Internet services in various industries, the demand for mobile network traffic continues to increase and therefore. The load traffic of a typical backhaul network is not sufficient, and the remote cloud computing center cannot handle a huge amount of computing. Traditional network architectures face significant challenges in the case of increasingly advanced communication technologies.

In response to the above situations, mobile edge computing (MEC) architectures have been proposed to solve problems that increase traffic demand and computational complexity. Literally, mobile edge computing provides an environment for cloud computing and information technology (IT) services at the edge of mobile networks. The main concept of mobile edge computing is to reduce the computing load of core network equipment and provide a platform for mobile operators to create specific mobile experiences for their customers. However, when anomalous situations occur in mobile edge computing architectures, the entire communication environment often needs to be rebuilt, which takes a lot of time and therefore the user experience should not be good.

Therefore, the present invention provides a multi-edge cloud network communication control method and an edge computing system for solving the above-mentioned problems.

According to one embodiment of the present invention, the network communication control method of the multi-edge cloud is applied to the first edge computing platform, the second edge computing platform, and the central control platform, and the central control platform is the first edge. Communicates with the computing platform and the second edge computing platform. In the network communication control method, the target service is provided to the terminal device by the first edge computing platform, the central control platform determines that the first edge computing platform has a service abnormality status, and the service abnormality status, the target service, And according to the operational information of the 2nd edge computing platform, the target service is reassigned to the 2nd edge computing platform, the offload information and the target service location are generated, and the offload information is transferred to the 2nd edge by the central control platform. By transmitting to the computing platform and transmitting the target service location to the terminal device by the first edge computing platform or the second edge computing platform, the terminal device performs the second edge computing platform according to the target service position. Includes having a communication connection with. Offload information includes at least terminal device identification and target service identification.

According to one embodiment of the present invention, the edge computing system includes an edge computing device and a central control device having a communication connection with the edge computing device. The edge computing device provides a target service to the terminal device. When the central controller determines that an edge computing device has a service anomaly state, it performs another edge computing of the target service according to the service anomaly state, the target service, and the operation information of another edge computing device. Reassign to the device, generate offload information and target service location, send offload information to another edge computing device, and terminal the target service location to the edge computing device or another edge computing device. Includes making the terminal device have a communication connection with another edge computing device depending on the target service location by instructing to transmit to. Offload information includes at least terminal device identification and target service identification.

In view of the above, the multi-edge cloud network communication control method and edge computing system provided by the present invention can reassign the edge computing platform that provides the service according to various service abnormal conditions. .. Therefore, it is not necessary to reconfigure the entire communication environment when a service abnormal state occurs. The edge computing system, the edge computing device, and the network communication control method of the multi-edge cloud provided in the present invention may have a dynamic allocation function without business interruption, and have a load balancing function and a remote backup function. May have.

The present invention is more fully understood from the detailed description and accompanying drawings given below, which are provided merely by way of illustration and thus are not intended to limit the invention.

It is a schematic diagram of the communication environment of the edge computing system which concerns on one Embodiment of this invention. It is a functional block diagram of the edge computing system which concerns on one Embodiment of this invention. It is a flowchart of the network communication control method of the multi-edge cloud which concerns on one Embodiment of this invention. It is a schematic diagram of the signal transmission in the network communication control method of the multi-edge cloud which concerns on one Embodiment of this invention. It is a schematic diagram of the signal transmission in the network communication control method of the multi-edge cloud which concerns on another embodiment of this invention. It is a partial flowchart of the network communication control method of the multi-edge cloud which concerns on one Embodiment of this invention. It is a functional block diagram of the edge computing apparatus which concerns on another embodiment of this invention.

In the following detailed description, a number of specific details are provided for purposes of explanation and to provide a complete understanding of the disclosed embodiments. However, it is clear that one or more embodiments may be implemented without these specific details. In other examples, well-known structures and devices are schematically shown to simplify the drawings.

The present invention provides an edge computing system. See FIGS. 1 and 2. Here, FIG. 1 is a schematic diagram of the communication environment of the edge computing system according to the embodiment of the present invention, and FIG. 2 is a functional configuration diagram of the edge computing system according to the embodiment of the present invention. .. As shown in FIG. 1, the edge computing system 1 includes a first edge computing device 11 and a central control device 13 having communication connections with each other. The edge computing system 1 can have a communication connection with the terminal device 21 and can also have a communication connection with the second edge computing device 31. In particular, the first edge computing device 11 can have a communication connection with the terminal device 21, and the central control device 13 can have a communication connection with the second edge computing device 31. Note that the number of terminal devices 21 connected to the edge computing system 1 and the number of second edge computing devices 31 connected to the edge computing system 1 shown in FIG. 1 are merely examples. There is a need to. The edge computing system 1 is also connected to a plurality of terminal devices 21 and is connected to a plurality of second edge computing devices 31. Further, the second edge computing device 31 can be connected to one or more terminal devices 21.

The first edge computing device 11 can be a mobile edge computing (MEC) cloud, which can be abbreviated as "edge cloud". The first edge computing device 11 is configured to provide one or more types of services to the terminal device 21. The first edge computing device 11 can be connected to the terminal device 21 via a base station. With respect to the network architecture, the first edge computing device 11 is located at the network edge and is relatively close to the user end terminal device 21. More specifically, the cloud server or the Internet can be the network core in the network architecture, and the terminal device 21 is located around the network architecture and can connect to the cloud server or the Internet via the network. The network edge can represent, but is not limited to, the boundary with the local area network in which the terminal device 21 is located. In particular, the first edge computing device 11 may be a single server having computing power, or may be composed of a plurality of servers having different functions and connected to each other. The terminal device 21 is a portable electronic device such as a smartphone, a tablet, or a laptop, and is not limited thereto.

More specifically, as shown in FIG. 2, the first edge computing device 11 includes a user plan function (UPF) module 111, a domain name service (DNS) module 112, a resource management module 113, and a service management module 114. , The first service module 115 and the second service module 116 can be provided. The user plan function module 111 of the first edge computing device 11 can be connected to the first service module 115 and the second service module 116 via the N6 interface, respectively, and can also be connected to the base station via the N3 interface. It can also be connected to the terminal device 21 via a base station. The domain name service module 112 can respond to a service location request from the terminal device 21 and activate the corresponding service. For example, when the user sends a request for the service location of "www.youtube®.com" via the terminal device 21, the domain name service module 112 sends "10.14.188.xxx" to the terminal device 21. In response, launch the YouTube® service. The resource management module 113 can monitor, organize, and manage the resource conditions of the first edge computing device 11. The service management module 114 can monitor the operating status of the first service module 115 and the second service module 116, monitor the service execution status, return a report when an error occurs, and further, a new service module (that is, a new service module). , Service modules other than the first and second service modules 115 and 116) can be created or enabled. The first service module 115 and the second service module 116 can each provide one or more network services.

The modules described above can be implemented by multiple servers that are independently configured but connected to each other, or by multiple applications running on one or more servers. The present invention does not limit the number of physical servers for implementing the aforementioned modules. Further, FIG. 2 schematically shows that the first edge computing device 11 includes two service modules (first service module 115 and second service module 116), but the first edge computing device 11 In other embodiments, one or more service modules can be provided, the enable state of the service module can be dynamically adjusted, and the enable state is, for example, whether or not a service can be provided. Note that By providing the service to the terminal device 21 by the service module of the first edge computing device 11, more complicated operations can be executed on the first edge computing device 11, and the calculation load of the terminal device 21 is reduced. be able to. The first edge computing device 11 can also provide a service for storing or processing information available to the terminal device 21. The above services are merely examples, and the services that the first edge computing device 11 can provide are not limited to these.

For example, the central control device 13 is an orchestrator, particularly a 5G core data center, that transmits and receives information to and from the first edge computing device 11 and the second edge computing device 31. The second edge computing device 31 can have the same configuration and function as the first edge computing device 11 described above. The second edge computing device 31 can be a mobile edge computing cloud configured to provide one or more services to the terminal device. In particular, the second edge computing device 31 may be a single server having computing power, or may be composed of a plurality of servers having different functions and connected to each other. As described above, the second edge computing device 31 can include a user plan function module, a domain name service module, a resource management module, a service management module, and one or more maintenance modules. The second edge computing device 31 has a resource condition (for example, the amount of resources), the number and types of services that can be provided, and the waiting time generated when providing a service to a certain terminal device. May differ from.

In addition to having communication connections with the first and second edge computing devices 11 and 31, the central control device 13 can provide device identification (ID), device location (eg, IP of the edge computing device). It collects information about each edge computing device, such as the ID of the service, the location of the service it can provide (eg, the IP of the corresponding service module), the ID of the connected terminal device, resource conditions, and latency, especially these. Each may have a communication connection with more edge computing devices to collect type information on a regular basis. The central control device 13 can set a communication connection relationship between a plurality of terminal devices and a plurality of edge computing devices according to the collected contents. In particular, the central control device 13 of the present invention can allocate a terminal device to a predetermined edge computing device according to the requirements of the terminal device, and can reallocate the terminal device according to the operating state of the edge computing device. Will be described later.

Further, to explain the configuration of the central control device 13, as shown in FIG. 2, the central control device 13 includes a user plan function module 131, a domain name service module 132, a service location management module 133, and a service redirection module 134. And the resource management module 135 can be provided. The user plan function module 131 of the central control device 13 can be connected to the user plan function module 111 of the first edge computing device 11 via the N9 interface. Similarly, the user plan function module 131 can also be connected to one or more other edge computing devices via the N9 interface. Since the domain name service module 132 has the same function as the domain name service module 112 described above, detailed description thereof will be omitted here. The service location management module 133 can have a database for recording services that can be provided by each edge computing device connected to the central control device 13, and the recording method is, for example, to record the ID of each service. Is. The service location management module 133 can execute service reassignment in cooperation with the service redirection module 134 or the resource management module 135, and further implementation of the reassignment will be described later. The modules described above may be configured independently, but may be multiple servers connected to each other, or may be multiple applications running on one or more servers. The present invention does not limit the number of physical servers for executing the above-mentioned modules. That is, the central control device 13 may be realized by one server, or may be configured by a plurality of servers having different functions. In another embodiment, the central control device 13 may be a mobile edge computing cloud having a central control function, connected to the terminal device 21 via a base station, and one or more services to the terminal device 21. Can be provided. In this embodiment, in addition to the many modules described above, the central controller 13 may further include a service management module and one or more maintenance modules.

The present invention also provides a method for controlling network communication in a multi-edge cloud. Referring to FIGS. 1 to 3, FIG. 3 is a flowchart of a network communication control method for a multi-edge cloud according to an embodiment of the present invention. As shown in FIG. 3, the multi-edge cloud network communication control method provides a target service to a terminal device by a first edge computing platform (step S11), and a first edge computing platform by a central control platform. (Step S12), the central control platform reassigns the target service to the second edge computing platform according to the service abnormality status, the target service, and the operation information of the second edge computing platform. , Offload information and target service location generated (step S13), step S14: send offload information to the second edge computing platform by the central control platform (step 14), step S15: first edge computing. By transmitting the target service location to the terminal device by the wing platform or the second edge computing platform, it is possible for the terminal device to have a communication connection with the second edge computing platform according to the target service position (step S15). Can include that.

In one embodiment, the first edge computing platform, the second edge computing platform, and the central control platform described above are the above-mentioned first edge computing device 11 and the second edge computing device 31 of FIGS. 1 and 2, respectively. , And can be carried out by the central controller 13. In another embodiment, the first edge computing platform, the second edge computing platform, and the central control platform can be applications run by virtual machines in the server, respectively. Hereinafter, the first edge computing platform, the second edge computing platform, and the central control platform of the network communication control method of the multi-edge cloud shown in FIG. 3 will be illustrated and described, and the first edge computing device 11 and the second edge computing device 11 and the second will be described, respectively. It is realized by the edge computing device 31 and the central control device 13.

In S11, the first edge computing device 11 provides the terminal device 21 with a target service. For example, target services include artificial intelligence, virtual reality, augmented reality, autonomous driving, or other application services. The present invention is not intended to limit the types of the Target Service. In particular, the communication connection between the first edge computing device 11 and the terminal device 21 is predetermined by the central control device 13 according to the operation information of the first edge computing device 11, and the operation information is when the target service is provided. Includes resource conditions and latency for the operation of the first edge computing device 11. In step S12, the central control device 13 determines that a service abnormal state has occurred in the first edge computing device 11, and the service abnormal state means that the target service is interrupted (referred to as “service down”). It can indicate that the target service has been swapped out (referred to as "service swapped out") or the platform has been disabled (referred to as "MEC down"). In response to this service abnormality state, in steps S13 to S15, the central control device 13 first sends the target service (that is, the first edge computing device 11) to another edge computing device (second edge computing device 31). Reassignment is performed to instruct the terminal device 21 to provide the provided service).

FIGS. 1 to 4 are referred to for further explaining steps S12 to S15 according to another service abnormal state. Here, FIG. 4 is a schematic diagram of signal transmission in the network communication control method of the multi-edge cloud according to the embodiment of the present invention. In the operating state in which the service abnormal state indicates service down or service swap-out, as shown in A11 of FIG. 4, the central control device 13 receives the service invalidation signal related to the service abnormal state from the first edge computing device 11. As a result, it can be determined that an abnormality has occurred in the first edge computing device 11.

More specifically, since the service module is disabled, the service down can represent a state in which the service module that originally provided the target service to the terminal device 21 can no longer provide the target service. can. In this case, the service management module 114 can generate the corresponding service invalidation signal and supply the corresponding service invalidation signal to the service location management module 133 of the central controller 13. On the other hand, in the service swap-out, when the resource management module 113 of the first edge computing device 11 determines that the resources are insufficient, the service management module 114 of the first edge computing device 11 selects a service having a lower priority. It can indicate that they are replaced in order of priority. For example, the service management module 114 can switch services by disabling the service module corresponding to the service or by instructing the service module to provide another service. The priorities can be set according to actual requirements and are not limited in the present invention. If the service that the service management module 114 decides to swap out is the first target service provided to the terminal device 21, the service management module 114 generates the corresponding service invalidation signal and the corresponding service invalidation. The signal is provided to the service position management module 133 of the central control device 13. The service invalidation signal corresponding to the service down or service swap-out is the ID of the first edge computing device 11 first connected to the edge computing platform where the anomaly occurred, the ID of the target service, and the terminal device 21. ID can be included.

When the service location management module 133 of the central control device 13 receives the service invalidation signal and learns that a service abnormality state has occurred in the first edge computing device 11, the service location management module 133 and the service redirection module 134 Reassignment can be performed accordingly. In this embodiment, the reassignment includes a relocation procedure and a redirection procedure. The relocation procedure (step A12) involves selecting an edge computing device capable of providing a target service that is a candidate for an edge computing platform, and a target edge computing platform according to the operation information of each candidate edge computing platform. Can include determining. As described above, the central control device 13 can periodically collect the resource conditions of the edge computing device connected to the central control device 13, the waiting time generated at the time of provision, and the like. Specifically, an edge computing device including a service module in which the service location management module 133 of the central control device 13 acquires the ID of the target service from the service invalidation signal and has the ID of the target service that is a candidate for the edge computing platform. You can select and then select the edge computing platform candidate with the best operational information to be the target edge computing device, and the target edge computing device will take over the task of providing the target service to the terminal device 21. It is an edge computing platform excluding.

The determination of the best operational information can have different criteria depending on the type of target service. For example, in the case of virtual reality services, bandwidth resource conditions can be a major consideration, but the invention is not limited to this. Further, the number of terminal devices 21 requesting the target service is also one of the important considerations. The service location management module 133 acquires the number of the terminal device 21 requesting the target service from the ID of the terminal device 21 included in the service invalidation signal, and the resource condition of each edge computing platform candidate is the target service to the terminal device 21. Can be determined if it is sufficient to provide. More specifically, in a mobile edge computing environment, the latency generated to provide the target service can be a major consideration. In particular, the service location management module 133 can select the edge computing platform candidate having the lowest waiting time from the edge computing platform candidates satisfying a certain standard with resource conditions. More specifically, a standard can refer to the lowest threshold for providing a target service to the terminal device 21.

When the service location management module 133 determines the target edge computing platform by the above relocation procedure, the service location management module 133 generates a redirect request and sends it to the service redirect module 134 (A13). The redirect request includes the ID of the target edge computing platform, the ID of the target service, and the ID of the terminal device 21. In the embodiment of FIG. 3 described above, the second edge computing device 31 is selected by the service location management module 133 so that it is the target edge computing platform. Therefore, in the present embodiment, the redirect request includes the ID of the second edge computing device 31. The service redirection module 134 transmits redirection information to the first edge computing device 11 in response to the redirection request which is the redirection procedure described above (A14). The redirect information can include the ID of the second edge computing device 31, the ID of the terminal device 21, and the ID of the target service. In particular, the user plan function module 111 of the first edge computing device 11 has the first second edge computing for the terminal device 21 with respect to the user plan function module of the second edge computing device 31 based on this redirect information. A request for establishing a connection between devices 11 and 31 can be proposed, the connection being specifically between the first second edge computing devices 11 and 31 for the terminal device 21. Is a session connection for the terminal device 21 established via the N9 interface of. Specifically, in order to indicate that the first edge computing device 11 has succeeded in transmitting the redirect information, an acknowledgment (ACK) is returned to the service redirect module 134 as the receive redirect information.

As described above, the central control device 13 reassigns the target service to the second edge computing device 31 to generate the offload information and position (referred to as “target service position”) of the target service, and the second edge. Offload information is transmitted to the computing device 31, and the target service position is transmitted to the terminal device 21. Specifically, the service redirection module 134 of the central control device 13 transmits offload information to the second edge computing device 31 (A15). More specifically, the service redirection module 134 does not perform step A15 until the first edge computing device 11 returns an acknowledgment message corresponding to step A14. In this embodiment, the offload information includes the ID of the first edge computing device 11, the ID of the terminal device 21, and the ID of the target service. The second edge computing device 31 may agree to the above-mentioned request for establishing a connection between the first second edge computing device 11 and 31 for the terminal device 21 according to the offload information. can. That is, the first edge computing device 11 and the second edge computing device 31 can acquire the redirect information and the offload information from the central control device 13, respectively, and are associated with the terminal device 21 and the target service. Connection can be established. Further, when the second edge computing device 31 receives the offload information, the second edge computing device 31 acquires the location information (for example, IP) of the service module corresponding to the ID of the target service in the offload information. , The location information can be regarded as the target service location and an acknowledgment message can be returned to the service redirect module 134 to indicate that the offload information was successfully transmitted. Specifically, the acknowledgment message corresponding to this A15 includes the target service location.

The service redirection module 134 of the central control device 13 transmits the target service position to the terminal device 21 via the first edge computing device 11. Specifically, after the service redirection module 134 waits for the second edge computing device 31 to return the acknowledgment message corresponding to step A15, the service redirection module 134 acquires the target service position from the target service position, and the terminal device 21 The ID and target service location can be transmitted to the first edge computing device 11 (step A16). The first edge computing device 11 can acquire the target service position from the central control device 13 and transmit the target service position to the terminal device 21 according to the ID of the terminal device 21 (A17). Specifically, the information transmission in steps A16 and A17 can be performed by the domain name service notification (DNS Notify), HTTP 301, and HTTP 302. After the terminal device 21 has acquired the target service location, the terminal device 21 is the target of the second edge computing device 31 via the connection between the first edge computing device 11 and the second edge computing device 31. It is possible to connect to a service module capable of providing a service (steps A18, A19).

In addition to handling the service down or service swap out service anomaly as described above, the network communication control method shown in FIG. 3 can further handle the MEC down service anomaly. Referring to FIGS. 1-3 and 5, FIG. 5 is a schematic diagram of signal transmission in a multi-edge cloud network communication control method according to another embodiment of the present invention. In the embodiment of FIG. 5, the resource management module 135 of the central control device 13 can periodically acquire the information of the first edge computing device 11 from the first edge computing device 11. When the resource management module 135 determines that the resource management module 135 has not received information from the first edge computing device 11 for a certain period of time (step A21), the resource management module 135 is the first edge computing device. It is determined that 11 is invalid. Then, the central control device 13 can perform reassignment. In the present embodiment, the resource management module 135 generates a relocation request according to the service abnormality state and sends it to the service location management module 133 (A22). In particular, the relocation request can include the ID of the first edge computing device 11 and the ID of the terminal device 21 first connected to the first edge computing device 11.

The service location management module 133 executes the relocation procedure according to the relocation request, generates a relocation response, and returns the relocation response to the resource management module 135 (A23). As described above, the service location management module 133 can store the ID of the business owned by the edge computing device connected to the central control device 13. Therefore, the relocation procedure includes determining the service that the first edge computing device 11 first owns according to the ID of the first edge computing device 11 and considering each of the services as a target service. Can be done. Subsequent implementation of selecting the edge computing platform candidate and the target edge computing platform is the same as the embodiment of FIG. 4 described above, and is not repeated here. The relocation response generated by the service location management module 133 can include the ID of the target edge computing platform, the ID of the target service, and the ID of the terminal device 21. As described above, in the embodiment of FIG. 3, the second edge computing device 31 is selected as the target edge computing platform by the service location management module 133, so that the rearrangement response in the present embodiment is the second edge computing device. Contains 31 IDs.

As described above, the central control device 13 reassigns the target service to the second edge computing device 31 to generate the offload information and position (referred to as “target service position”) of the target service, and the second edge. Offload information is transmitted to the computing device 31, and the target service position is transmitted to the terminal device 21. Specifically, the resource management module 135 of the central control device 13 generates offload information including the ID of the terminal device 21 and the ID of the target service in response to the relocation response, and causes the second edge computing device 31 to generate offload information. Offload information is transmitted (A24). Therefore, it can be known that the second edge computing device 31 is trying to provide the target service to the terminal device 21 according to the offload information, and when the second edge computing device 31 receives the offload information, the second edge The computing device 31 has acquired the location information (for example, IP) of the service module corresponding to the ID of the target service in the offload information, regarded the location information as the target service location, and normally transmitted the offload information. An acknowledgment message can be returned to the resource management module 135 to indicate. More specifically, this acknowledgment message includes the target service location.

The resource management module 135 of the central control device 13 transmits the target service position to the terminal device 21 via the second edge computing device 31. Specifically, the resource management module 135 waits for the second edge computing device 31 to return an acknowledgment message, acquires the target service position from the target service position, and obtains the ID of the terminal device 21 and the target service position. It is transmitted to the second edge computing device 31 (A25). The second edge computing device 31 can acquire the target service position from the central control device 13 and transmit the target service position to the terminal device 21 according to the ID of the terminal device 21 (A26). More specifically, the information transmission in steps A25 and A26 can be performed by DNS Notify, HTTP 301, or HTTP 302. After the terminal device 21 has acquired the target service position, the terminal device 21 can be connected to a service module capable of providing the target service of the second edge computing device 31 accordingly (step A27). More specifically, in the present embodiment, the first edge computing device 11 and the second edge computing device 31 are connected to the terminal device 21 before changing the edge computing platform that provides the target service. More specifically, the base station connected to the terminal device 21 is originally connected to the first edge computing device 11 and the second edge computing device 31, and the first edge computing device 11 is the main edge computing device. It functions as a platform, and the second edge computing device 31 functions as a backup edge computing platform for taking over the base station in the event of a failure of the main edge computing platform.

In one embodiment, before the first edge computing device 11 provides the target service to the terminal device (that is, step S11 in FIG. 3), the network communication control method of the multi-edge cloud registers the edge computing platform / device. A procedure and a procedure for assigning a service request from the terminal device 21 can be further included. Referring to FIGS. 1, 3, and 6, FIG. 6 is a partial flowchart of a multi-edge cloud network communication control method according to an embodiment of the present invention. Prior to step S11 shown in FIG. 3, the multi-edge cloud network communication control method may further include the step shown in FIG. 6, step S21 is a step of sending a registration request to the central control platform by the first edge computing platform. Step S22 is a step of providing the operation information of the first edge computing platform to the central control platform by the first edge computing platform, and step S23 is a step of receiving a service request from the terminal device by the central control platform. , A step of determining that the service request corresponds to the target service, and a step of assigning the target service to the first edge computing platform by the central control platform according to the target service and operation information of the first edge computing platform in step S24. include.

In particular, the communication environment shown in FIG. 1 can be established by steps S21 to S24. As shown in FIGS. 1, in steps S21 and S22, the first edge computing device 11 sends a registration request to the central control device 13, and the central control device 13 responds to the first edge computing device 11 and the central control device. A connection with 13 can be established. After the first edge computing device 11 is registered, the first edge computing device 11 can provide the central control device 13 with its operation information including resource conditions, standby time, and the like. More specifically, the first edge computing device 11 periodically supplies the operation information to the central control device 13. Further, the second edge computing device 31 may submit a registration request to the central control device 13 before the reassignment procedure is executed, and provide the operation information to the central control device 13 after the registration. Further, more edge computing devices can send registration requests and their operational information to the central control device 13, but this is not limited in the present invention.

When the edge computing system 1 receives the service request from the terminal device 21, in steps S23 and S24, the central control device 13 determines that the service request is the target service, and determines that the service request is the target service of the registered edge computing device. Allocate the target service according to the operation information. In particular, the domain name service module of the first edge computing device 11, the second edge computing device 31, or another edge computing device registered in the central control device 13 receives a service request from the terminal device 21 within the communication range. For example, the edge computing device capable of receiving the service location inquiry) and executing the reception process transfers the ID, the ID of the service, and the ID of the terminal device 21 to the service position management module 133 of the central control device 13. Can be sent. In the present embodiment, since the operation information of the first edge computing device 11 is the best operation information corresponding to the target service, the central control device 13 allocates the target service to the first edge computing device 11. The example and description of the determination of the best operation information are the same as the determination of the best operation information in the reassignment procedure in the previous embodiment, and therefore are not repeated here.

Further, as described above, in one embodiment, the central control device 13 can be a mobile edge computing cloud having a central control function, connected to the terminal device 21 via a base station, and one or more. The service can be provided to the terminal device 21. In this embodiment, when the central controller 13 performs the allocation or reassignment procedure as described in the previous embodiment, the central controller 13 may consider itself as one of the target edge computing platform choices. can. More specifically, after the central controller 13 can set its priority to the lowest, i.e., the central controller 13 determines that not all edge computing devices are suitable for providing the target service. , Determine if it is suitable for providing the target service. Further, when the central control device 13 determines that the edge computing device cannot provide the target service, the central control device 13 can generate an allocation failure signal and transmit it to the terminal device 21.

The present invention further provides a configuration for an edge computing device. More specifically, the first edge computing device 11 and the central control device 13 can have such a device configuration. FIG. 7 is a functional configuration diagram of an edge computing device according to another embodiment of the present invention. As shown in FIG. 7, the edge computing device 10 includes a memory 101 and a processor 103, and the processor 103 is electrically connected to the memory 101. For example, the memory 101 is a flash memory, a read-only memory, a magnetic memory, or another non-volatile storage medium. The memory 101 stores a plurality of instructions. Specifically, the plurality of instructions include at least the instructions corresponding to the steps executed by the first edge computing device 11 / central control device 13, as described in the above embodiments. The processor 103 is, for example, a central processing unit, a microcontroller, a programmable logic controller, or the like. By executing the instruction stored in the memory 101, the processor 103 can execute the step executed by the first edge computing device 11 / central control device 13 as described in the above-described embodiment.

In view of the above, the present invention applies to centralized communication environments and is used for edge computing systems, edge computing devices, and multi-edge clouds that reassign edge computing platforms that provide services in response to various service anomalies. It provides a network communication control method, which eliminates the need to reconfigure the entire communication environment when a service error occurs. The edge computing system, edge computing device, and network communication control method of the multi-edge cloud of the present invention may have a function of dynamic allocation without business interruption, and also have a function of load balancing and remote backup. You may.

Claims (20)

A multi-edge cloud network communication control method applied to a first edge computing platform, a second edge computing platform, and a central control platform that transmits information to the first edge computing platform and the second edge computing platform. And
The first edge computing platform provides the target service to the terminal device.
The central control platform determines that the first edge computing platform has a service anomaly.
The central control platform reassigns the target service to the second edge computing platform according to the service anomaly state, the target service, and the operational information of the second edge computing platform, and offload information and Generate a target service location and
The central control platform transmits the offload information to the second edge computing platform.
By transmitting the target service position to the terminal device by the first edge computing platform or the second edge computing platform, the terminal device and the second edge computing platform according to the target service position. Including having a communication connection
The offload information, possess the ID and ID of the target services for at least the terminal device, the target service location, network communication control method is the IP address of providable service modules the target service. Reassigning the target service to the second edge computing platform according to the service abnormal state, the target service, and the operation information of the second edge computing platform by the central control platform is possible.
The second edge computing platform is selected from the one or more edge computing platform candidates according to the target service and the operation information of each of the one or more edge computing platform candidates.
The network communication control method according to claim 1, wherein the redirect information is generated according to the service abnormality state and the result of the selection, and the redirect information is transmitted to the first edge computing platform. The offload information further includes the ID of the first edge computing platform, and the network communication control method further includes.
The network communication control method according to claim 2, wherein the first edge computing platform establishes a connection with the second edge computing platform in response to the redirect information. Transmitting the target service location to the terminal device by the first edge computing platform or the second edge computing platform
The network communication control method according to claim 1, wherein the target service position is acquired from the central control platform by the first edge computing platform, and the target service position is transmitted to the terminal device. The step of determining that the service abnormality state is present in the first edge computing platform by the central control platform is
The central control platform receives a service invalidation signal associated with the service anomaly from the first edge computing platform.
The network communication control method according to claim 1, wherein the service invalidation signal is generated when the first edge computing platform determines to swap out the target service according to a priority. Determining that the first edge computing platform has the service anomaly by the central control platform can be determined.
The central control platform receives a service invalidation signal associated with the service anomaly from the first edge computing platform.
The network communication control method according to claim 1, wherein the service invalidation signal is generated by the first edge computing platform when the target service is stopped. The service abnormal state indicates that the first edge computing platform is invalid, and the target service position may be transmitted to the terminal device by the first edge computing platform or the second edge computing platform. ,
The network communication control method according to claim 1, wherein the target service position is acquired from the central control platform by the second edge computing platform, and the target service position is transmitted to the terminal device. Determining that the first edge computing platform has the service anomaly by the central control platform can be determined.
When the central control platform determines that the central control platform has not received information from the first edge computing platform for a certain period of time, the central control platform is invalid for the first edge computing platform. The network communication control method according to claim 1, which comprises determining that. Reassigning the target service to the second edge computing platform according to the service abnormal state, the target service, and the operation information of the second edge computing platform by the central control platform is possible.
One or a plurality of edge computing platform candidates capable of providing the target service are selected, each of the one or a plurality of edge computing platform candidates has operation information, and the second edge computing platform is the said. Included in one or more edge computing platform candidates, the operational information includes resource conditions and latency corresponding to the target service.
A claim including selecting the second edge computing platform from the one or more edge computing platform candidates by determining that the operation information of the second edge computing platform is the optimum operation information. Item 1. The network communication control method according to Item 1. Before the target service is provided to the terminal device by the first edge computing platform, further
The first edge computing platform sends a registration request to the central control platform.
The first edge computing platform provides operation information of the first edge computing platform to the central control platform.
The central control platform receives a service request from the terminal device and receives a service request.
The network communication control according to claim 1, wherein the central control platform allocates the target service to the first edge computing platform according to the operation information of the target service and the first edge computing platform. Method. It ’s an edge computing system.
Edge computing devices that provide target services to terminal devices, and
Including the edge computing device and a central control device having a communication connection.
When the central control device determines that the edge computing device has a service abnormal state, the central control device responds to the operation information of the service abnormal state, the target service, and another edge computing device, and the target service. To the other edge computing device, generate offload information and target service locations, send the offload information to the other edge computing device, and the edge computing device or the other edge. By instructing the computing device to transmit the target service location to the terminal device, the terminal device is made to have a communication connection with the other edge computing device according to the target service position.
The offload information includes ID of ID and the target service of at least the terminal device, the target service position, the edge computing system is the IP address of providable service modules the target service. Reassigning the target service to another edge computing device in response to the service anomaly state, the target service, and the operational information of the other edge computing device performed by the central control unit is possible.
The other edge computing device is selected from the one or more edge computing platform candidates according to the operation information of each of the target service and the one or more edge computing platform candidates.
The edge computing system according to claim 11, which comprises generating redirect information according to the service abnormal state and the result of the selection, and transmitting the redirect information to the edge computing device. The edge computing device according to claim 12, wherein the offload information further includes an ID of the edge computing device, and the edge computing device further establishes a connection with the other edge computing device in response to the redirect information. Ing system. Instructing the edge computing device or another edge computing device, which is executed by the central control device, to transmit the target service position to the terminal device is the target service position and the terminal device. 11. The edge computing system according to claim 11, which is executed by transmitting the ID of the above to the edge computing device. The edge computing device further generates a service invalidation signal when determining to swap out the target service according to priority, and the central control unit further generates the service to the edge computing device. The edge computing system according to claim 11, wherein the service invalidation signal is received from the edge computing device to determine that there is an abnormal state. The edge computing device further generates a service invalidation signal when the target service is stopped, and the central control device further determines that the edge computing device has the service abnormal state. The edge computing system according to claim 11, wherein the service invalidation signal is received from the edge computing device. The service abnormal state indicates that the edge computing device is invalid, and the target service position is set to the terminal device to the edge computing device or the other edge computing device executed by the central control device. 11. The edge computing system of claim 11, which is performed by instructing the edge computing device to transmit the target service location to the other edge computing device. The eleventh aspect of claim 11 further determines that the edge computing device is invalid when the central control device determines that the central control device has not received information from the edge computing device for a certain period of time. The described edge computing system. Reassigning the target service to another edge computing device in response to the service anomaly state, the target service, and the operational information of the other edge computing device performed by the central control unit is possible.
One or more edge computing platform candidates capable of providing the target service are selected, each of the one or more edge computing platform candidates has operation information, and the other edge computing system is one or more. Included in multiple edge computing platform candidates, the operational information includes resource conditions and latency corresponding to the target service.
A claim comprising selecting the other edge computing device from the one or more edge computing platform candidates by determining that the operation information of the other edge computing device is the optimum operation information. Item 11. The edge computing system according to Item 11. The edge computing device further sends a registration request to the central control device, provides operation information of the edge computing device to the central control device before providing the target service to the terminal device, and provides the central control device. Further receives a service request from the terminal device, determines the service request corresponding to the target service, and before the edge computing device provides the target service to the terminal device, the target service and the target service. The edge computing system according to claim 11, wherein the target service is assigned to the edge computing device according to the operation information of the edge computing device.

Images