JPWO2017145389A1 - Node equipment - Google Patents

Abstract

A node device configured to include a plurality of edge nodes (1) and operating as an edge node (1) of a communication system in which the edge nodes (1) cooperate to provide a service, and information transmitted from a user terminal The edge server (40) that processes the packet and, when receiving the information packet, determines the transfer destination of the received packet that is the received information packet, and outputs the received packet to the route toward the determined transfer destination A processing unit (10), and the edge communication processing unit (10) implements a process for determining a transfer destination of the received packet and an output process of the received packet to the route toward the determined transfer destination with programmable hardware. In the circuit.

Description

  The present invention relates to a node device that forms a communication network.

  In recent years, with cloud computing technology, services that store information on servers that do not own specific information processing functions and information on the user side and that use information on the servers have become widespread. Yes. Cloud computing is information that uses services provided by these devices via a network without the user being aware of the physical configuration and location of information and communication devices such as servers and storage deployed in data centers. It is a processing form. In addition, distributed information communication processing that links multiple information communication devices distributed on the network, shares the information processing required for service provision among the multiple information communication devices, and improves the processing load and communication volume. A form using the system is also being studied. By introducing this form of distributed information communication processing, a service that responds to information changes that occur on the user terminal, in particular on information communication equipment located near the user terminal, that responds in a short time Is also considered to be able to respond. In general, an information communication device arranged near a user terminal as described above is called an edge node or an edge server.

  An example of a conventional distributed information communication processing system is described in Patent Document 1. The information communication processing system described in Patent Document 1 is a service in which a plurality of information communication devices provide services via a network, improves response speed and power consumption, and further improves reliability. In the information communication processing system described in Patent Document 1, an entrance node that executes filter processing in the vicinity of terminals, and an intelligent node that executes information processing and communication processing instead of a data center by changing the information processing position And the management node that manages them cooperate to realize real-time information processing.

  Patent Document 2 discloses a configuration that can realize load distribution of a network when virtualizing a network function. A virtual machine arrangement design device described in Patent Literature 2 includes a means for inputting a requested resource, and a virtual machine arrangement destination calculating means for selecting a physical machine that arranges a virtual machine that virtualizes a network function based on the inputted requested resource The virtual machine placement destination calculation means predicts and predicts the amount of traffic flowing to the network to which the physical machine is connected when each virtual machine is placed on a physical machine that meets the conditions specified by the requested resource. Based on the traffic volume, a physical machine that balances network link utilization is selected as the virtual machine location.

Japanese Patent No. 5544006 International Publication No. 2014/208661

  The invention described in Patent Document 1 includes a communication control unit that selects a device that performs information processing and transfers a data packet to be processed by the selected device to the selected device. However, the data packet is reliably transmitted with minimum delay. There is no mechanism or function to transfer to the selected device. The communication control unit is configured by software or hardware, and when configured by software, the data packet transfer processing time is uncertain. On the other hand, the hardware configuration lacks versatility and cannot be applied to various services.

  The invention described in Patent Document 2 can balance network utilization, but does not have a mechanism and function for guaranteeing a data packet transfer time. Therefore, the invention described in Patent Document 2 cannot be applied to a service that requires a high-speed response, that is, a service that requires a response with a low delay.

  The present invention has been made in view of the above, and an object of the present invention is to obtain a node device that can reach a transfer destination within a predetermined time after a data packet is transferred.

  In order to solve the above-described problems and achieve the object, the node device according to the present invention includes a plurality of edge nodes, and operates as an edge node of a communication system in which the edge nodes cooperate to provide a service. . The node device determines the transfer destination of the received packet that is the received information packet when receiving the information packet and the edge server that processes the information packet transmitted from the user terminal, and the route toward the determined transfer destination The received packet is output to In addition, the node device performs a process for determining a transfer destination of the received packet and a process for outputting the received packet to the route toward the determined transfer destination by a circuit realized by programmable hardware.

  The node device according to the present invention has an effect that the information packet can reach the transfer destination within a predetermined time.

The figure which shows the structural example of the communication system with which the node apparatus concerning Embodiment 1 of this invention is applied. The figure which shows the structural example of the edge node which is a node apparatus concerning Embodiment 1. FIG. The figure which shows the structural example of the edge communication process part with which the edge node concerning Embodiment 1 is provided. 1 is a diagram illustrating an example of a hardware configuration of an edge communication processing unit according to the first embodiment; 1 is a flowchart illustrating an example of a programmable hardware change processing procedure according to the first embodiment; 1 is a flowchart illustrating an example of a programmable hardware change processing procedure according to the first embodiment; 1 is a flowchart showing an example of operation of a multiplexing priority control setting unit according to the first exemplary embodiment; 10 is a flowchart showing an example of the operation of the distribution pattern setting unit according to the first embodiment. The figure which shows the structural example of the edge node concerning Embodiment 2. FIG. The figure which shows the structural example of the edge communication process part concerning Embodiment 2. FIG. The figure which shows an example of the hardware constitutions of the edge communication process part concerning Embodiment 2. FIG. The figure which shows the structural example of the edge communication process part of the edge node concerning Embodiment 3. FIG. The figure which shows an example of the hardware constitutions of the edge communication process part concerning Embodiment 3. FIG. 10 is a flowchart illustrating an example of an operation of a resource allocation parameter setting unit according to the third embodiment. The figure which shows the structural example of the edge communication process part of the edge node concerning Embodiment 4. FIG. The figure which shows an example of the hardware constitutions of the edge communication process part concerning Embodiment 4. FIG.

  A node device according to an embodiment of the present invention will be described below in detail with reference to the drawings. Note that the present invention is not limited to the embodiments.

Embodiment 1 FIG.
FIG. 1 is a diagram illustrating a configuration example of a communication system to which the node device according to the first exemplary embodiment of the present invention is applied.

  The communication system to which the node device according to the first embodiment is applied includes a plurality of edge nodes 1 that are node devices according to the first embodiment, and a plurality of information processing devices 101 that are servers or the like. Yes. The edge node 1 and the information processing apparatus 101 are connected to the network 100 to realize cloud computing. The network 100 is a communication network configured to include various networks such as a core network and a monitoring control network. The monitoring control network is a network for each device such as the edge node 1 and the information processing apparatus 101 to transmit and receive control information. A plurality of devices cooperate to distribute a load and realize one function, that is, a service. It is used when transmitting / receiving control information necessary for the transmission.

  Each edge node 1 has an interface unit for communicating with the terminal 201 via the access network which is the optical access network 200 or the radio access network 300, and transmits / receives information packets to / from various terminals 201. . An information packet is a packet for transmitting data of various types of applications to a communication partner, and is also called a data packet. Each edge node 1 provides a service to the terminal 201 while distributing the load in cooperation with another edge node 1 or another device that is the information processing apparatus 101. Each edge node 1 processes the information packet received from the terminal 201 if it should be processed in its own device, and the received packet is processed by another device, that is, another edge node 1 or the information processing apparatus 101. If so, the information packet is transferred to another device via the core network. The terminal 201 is various types of user terminals that receive provision of various services from a communication network that includes the edge node 1 and the information processing apparatus 101.

  The configuration illustrated in FIG. 1 is an example, and the number of edge nodes 1, information processing apparatuses 101, and terminals 201 is not limited to that illustrated.

  FIG. 2 is a diagram of a configuration example of the edge node 1 that is the node device according to the first embodiment. The edge node 1 includes an edge communication processing unit 10, a communication control unit 20, a switch unit 30, an edge server 40, an optical interface unit 50, and a wireless interface unit 60. In FIG. 2, the optical interface unit is described as an optical IF unit, and the wireless interface unit is described as a wireless IF unit. Also in this specification, hereinafter, the optical interface unit is described as an optical IF unit, and the wireless interface unit is described as a wireless IF unit.

  The optical IF unit 50 is connected to the optical access network 200 illustrated in FIG. 1, and transmits and receives information packets storing various types of data to and from the terminal 201 via the optical access network 200. The wireless IF unit 60 is connected to the wireless access network 300 shown in FIG. 1 and transmits / receives information packets storing various types of data to / from the terminal 201 via the wireless access network 300.

  The edge communication processing unit 10 performs transfer processing of information packets received from other devices. Specifically, when an information packet from the terminal 201 is input via the optical IF unit 50 or the wireless IF unit 60, the edge communication processing unit 10 analyzes the input information packet and determines a transfer destination. The information packet is output to the switch unit 30 or the edge server 40 according to the determination result. That is, when receiving the information packet, the edge communication processing unit 10 determines the transfer destination and outputs the information packet to the route toward the determined transfer destination. Further, when an information packet addressed to the user terminal is input from the switch unit 30 or the edge server 40, the edge communication processing unit 10 transmits the information packet to the destination terminal 201 via the optical IF unit 50 or the wireless IF unit 60. Further, the edge communication processing unit 10 outputs the information packet to be processed by the own device, that is, the own edge node 1 to the edge server 40 when the information packet is transmitted from the core network.

  The communication control unit 20 is connected to the monitoring control network and sends resource management information and connection management information to the edge communication processing unit 10 based on the control information stored in the control packet received from the monitoring control network. The processing related to the operation and maintenance of the entire edge node 1 is performed.

  The resource management information is, for example, information regarding each device that implements cloud computing, that is, the hardware resource and software resource of the edge node 1 or the information processing apparatus 101. The resource management information includes a service provided by each device that implements cloud computing, that is, information related to an application that can be processed by each device. The connection management information is information used when communicating with each device that implements cloud computing, for example. The connection management information includes an IP address, a type of priority control used when transferring the information packet, a multiplexing execution condition when transferring the information packet, that is, a condition for combining two or more information packets into one packet, Etc. are included. In this embodiment, the resource management information and the connection management information are connected to a monitoring control network such as another edge node 1, an information processing apparatus 101, and a network management apparatus that implements cloud computing. It is assumed that it is transmitted as control information stored in the control packet from another device. If the control information stored in the control packet received from the monitoring control network is resource management information or connection management information, the communication control unit 20 extracts the control information and outputs it to the edge communication processing unit 10.

  The switch unit 30 is connected to the core network, and transmits and receives information packets between the other edge nodes 1 and the information processing apparatus 101 arranged in the core network.

  When the edge server 40 receives the information packet from the edge communication processing unit 10, the edge server 40 processes the information packet, stores the processing result in the information packet, and returns the information packet to the edge communication processing unit 10. Prepare. The edge server 40 receives information packets transmitted from a plurality of terminals 201 and information packets transmitted from devices in the core network, that is, other edge nodes 1 or information processing apparatuses 101, from the plurality of information processing units 41. It is possible to process simultaneously using two or more of 43. Also, the edge server 40 uses a plurality of information packets sent from a single terminal 201 or a single device in the core network in parallel using two or more of the plurality of information processing units 41 to 43. It is also possible to process. In the present embodiment, the edge server 40 includes the information processing units 41 to 43, but the number of information processing units is not limited to this.

  FIG. 3 is a diagram illustrating a configuration example of the edge communication processing unit 10 provided in the edge node 1. The edge communication processing unit 10 includes a demultiplexing circuit 11, a distribution circuit 12, a hardware configuration setting unit 13, a multiplexing priority control setting unit 14, and a distribution pattern setting unit 15. The demultiplexing circuit 11 and the distribution circuit 12 are realized by programmable hardware 70 that is a device capable of changing the circuit configuration. The programmable hardware 70 is an existing general programmable logic device.

  The demultiplexing circuit 11 transmits and receives information packets to and from the optical IF unit 50, the wireless IF unit 60, the edge server 40, and the switch unit 30. At this time, if there are a plurality of information packets with the same destination in the information packets waiting for transmission, the demultiplexing circuit 11 follows the processing rules set in advance, and a plurality of information with the same destination A part or all of the packets are combined into one information packet, that is, multiplexed and transmitted. The distribution circuit 12 determines the transmission destination of the information packet based on the identification information included in the information packet. Therefore, when receiving the information packet, the demultiplexing circuit 11 extracts the identification information from the information packet and outputs it to the distribution circuit 12. When the demultiplexing circuit 11 receives an information packet in which a plurality of information packets are combined into one, that is, an information packet in which a plurality of information packets are multiplexed, Return to multiple information packets. When demultiplexing and returning to the original plurality of information packets, the demultiplexing circuit 11 extracts identification information from each of the plurality of information packets after demultiplexing and outputs the identification information to the distribution circuit 12.

  When the identification information of the information packet is input from the demultiplexing circuit 11, the distribution circuit 12 determines the transfer destination of the information packet based on the input identification information and a preset processing rule, and the determined transfer destination To the demultiplexing circuit 11.

  The multiplexing priority control setting unit 14 determines the priority when the demultiplexing circuit 11 transfers a plurality of information packets to one route and the plurality of information packets based on the information input from the communication control unit 20. A processing rule for combining the information packets is generated, and the generated priority order and processing rule are transmitted to the demultiplexing circuit 11. The demultiplexing circuit 11 performs a multiplexing process, which is a process of combining a plurality of information packets into one information packet, and an information packet transfer process, according to the processing rule received from the multiplexing priority control setting unit 14.

  Based on the information input from the communication control unit 20, the distribution pattern setting unit 15 generates a processing rule when the distribution circuit 12 determines the transfer destination of the information packet, and transmits the generated processing rule to the distribution circuit 12. . When determining the transfer destination of the information packet, the distribution circuit 12 determines the transfer destination according to the processing rule received from the distribution pattern setting unit 15.

  The hardware configuration setting unit 13 determines the circuit configuration of the programmable hardware 70 based on the information input from the communication control unit 20, and performs settings for the programmable hardware 70 so that the programmable hardware 70 can operate as an actual processing circuit. Do.

  Subsequently, a hardware configuration for realizing the hardware configuration setting unit 13, the multiplexing priority control setting unit 14, and the distribution pattern setting unit 15 of the edge communication processing unit 10 will be described. FIG. 4 is a diagram illustrating an example of a hardware configuration of the edge communication processing unit 10. As described above, the demultiplexing circuit 11 and the distribution circuit 12 are realized by the programmable hardware 70.

  The hardware configuration setting unit 13, the multiplexing priority control setting unit 14, and the distribution pattern setting unit 15 of the edge communication processing unit 10 are realized by software. Each of these units can be realized by a processing circuit 80 including a processor 81, a memory 82, a register 83, and a DPRAM (Dual Port Random Access Memory) 84.

  Software for realizing the hardware configuration setting unit 13, the multiplexing priority control setting unit 14, and the distribution pattern setting unit 15 is described as a program and stored in the memory 82. The hardware configuration setting unit 13, the multiplexing priority control setting unit 14, and the distribution pattern setting unit 15 are realized by the processor 81 reading out from the memory 82 and executing programs for realizing these units. That is, the processing circuit 80, when executed by the processor 81, determines a setting value for multiplexing priority control processing and a setting value for distribution pattern processing from the communication control unit 20, and determines information packet transfer priority. Storing a program in which the steps of generating the information packet processing rule and the distribution processing rule, and transmitting the priority and the rule to the demultiplexing circuit 11 or the distribution circuit 12 are executed as a result. The memory 82 is provided. In addition, it can be said that these programs cause the computer to execute the procedures and methods of the hardware configuration setting unit 13, the multiplexing priority control setting unit 14, and the distribution pattern setting unit 15.

  Here, the processor 81 is a CPU (Central Processing Unit, a central processing unit, a processing unit, an arithmetic unit, a microprocessor, a microcomputer, a processor, or a DSP), a system LSI (Large Scale Integration), or the like. The memory 82 is a nonvolatile or volatile semiconductor such as a RAM (Random Access Memory), a ROM (Read Only Memory), a flash memory, an EPROM (Erasable Programmable Read Only Memory), or an EEPROM (Electrically Erasable Programmable Read-Only Memory). Memory, magnetic disk, flexible disk, optical disk, compact disk, mini disk, DVD (Digital Versatile Disc) and the like.

  The register 83 and the DPRAM 84 are used when the circuit configuration of the programmable hardware 70 is changed.

  The configuration circuit 90 illustrated in FIG. 4 is an electronic circuit for changing the setting of the programmable hardware 70 so that the circuit configuration determined by the hardware configuration setting unit 13 is obtained, and is included in the hardware configuration setting unit 13. .

  Next, an operation for changing the circuit configuration of the programmable hardware 70 will be described. FIG. 5 is a flowchart illustrating an example of a change processing procedure of the programmable hardware 70. The operation illustrated in FIG. 5 is started, for example, when the communication control unit 20 receives a control packet including hardware configuration information indicating the configuration of the programmable hardware 70 from the monitoring control network. When the communication control unit 20 receives a control packet from the supervisory control network, the communication control unit 20 can analyze the received control packet and determine whether or not hardware configuration information is included. Whether or not hardware configuration information is included is determined, for example, by storing information indicating that hardware configuration information is included in a predetermined area in the area for storing the packet header or data. It can be so.

  In the operation of changing the circuit configuration of the programmable hardware 70, first, the communication control unit 20 inputs hardware configuration information to the hardware configuration setting unit 13 (step S11). In the hardware configuration setting unit 13, the hardware configuration information received from the communication control unit 20 is input to the DPRAM 84. The hardware configuration information is generated using a development tool provided from a vendor of the programmable hardware 70 or the like. Note that the communication control unit 20 is configured to input the hardware configuration information to the hardware configuration setting unit 13, that is, the configuration in which the hardware configuration information is input to the edge node 1 via the monitoring control network. is not. The edge node 1 may include a connector for connecting a communication cable, and the hardware configuration information may be input from a device directly connected to the edge node 1 using the communication cable.

  Next, application change instruction information is input from the communication control unit 20 to the hardware configuration setting unit 13 (step S12). In the hardware configuration setting unit 13, the application change instruction information received from the communication processing unit 20 is written into the register. The application change instruction information is information that instructs to start changing the circuit configuration of the programmable hardware 70.

  When the application change instruction information is input, the hardware configuration setting unit 13 executes a change process of the programmable hardware 70 (step S13). The detailed procedure of the change process executed in step S13 is shown in FIG.

  FIG. 6 is a flowchart illustrating an example of a change processing procedure of the programmable hardware 70. In the description of the processing procedure illustrated in FIG. 6, “hardware configuration setting unit 13” means “processor 81 that is executing a program for operating as hardware configuration setting unit 13”. When the application change instruction information is input, the hardware configuration setting unit 13 accesses the DPRAM 84, confirms that the hardware configuration information has been written (step S131), and sets the DPRAM 84 to update prohibition (step S132). ). Next, the hardware configuration setting unit 13 reads the hardware configuration information from the DPRAM 84 and transfers it to the configuration circuit 90 (step S133). The configuration circuit 90 converts the hardware configuration information into data for actually changing the circuit and then transfers the data to the programmable hardware 70. When the transfer of the hardware configuration information is completed, the hardware configuration setting unit 13 cancels the update prohibition of the DPRAM 84 and permits the DPRAM 84 to be updated (step S134).

  Subsequently, processing procedures of the multiplexing priority control setting unit 14 and the distribution pattern setting unit 15 will be described with reference to FIGS. 7 and 8. FIG. 7 is a flowchart showing an example of the operation of the multiplexing priority control setting unit 14, and FIG. 8 is a flowchart showing an example of the operation of the distribution pattern setting unit 15.

  When the resource management information or the connection management information is input from the communication control unit 20, the multiplexing priority control setting unit 14 starts the process illustrated in FIG. 7. Similarly, when the resource management information or the connection management information is input from the communication control unit 20, the distribution pattern setting unit 15 starts the processing illustrated in FIG.

  When information is input from the communication control unit 20, the multiplexing priority control setting unit 14 first updates a setting value for multiplexing priority control processing based on the input information (step S21). That is, the multiplexing priority control setting unit 14 sets the setting value for multiplexing priority control processing set based on information previously input from the communication control unit 20 to information newly input from the communication control unit 20. Update based on. The setting value for multiplexing priority control processing includes a value indicating the type of priority control to be performed, a value indicating the priority for each type of information stored in the information packet, and a condition for executing the multiplexing processing of the information packet , A value indicating the condition of the information packet to be multiplexed, and the like. When information is input from the communication control unit 20, the multiplexing priority control setting unit 14, based on the input information, part or all of various values included in the setting value for the multiplexing priority control process Update. Depending on the content of information input from the communication control unit 20, there may be no setting value that needs to be updated. In that case, the multiplexing priority control setting unit 14 does not update the setting value for the multiplexing priority control process. Also, steps S22 to S24 described later are not executed.

  Next, the multiplexing priority control setting unit 14 generates information packet transfer priority (A) and information packet processing rules (A) based on the setting value for multiplexing priority control processing updated in step S21. B) is generated (steps S22 and S23). In step S22, for example, a priority for each type of information packet, that is, a transfer priority for each type of information stored in the information packet is generated. In step S23, the multiplexing priority control setting unit 14 sets a processing rule including, for example, the type of priority control to be performed, the presence / absence of the packet multiplexing process, and the conditions of the information packet to be multiplexed. Generate. The information packet conditions to be multiplexed include the type of information packet to be multiplexed and the size of the information packet to be multiplexed.

  Next, the multiplexing priority control setting unit 14 transmits the transfer priority (A) generated in step S22 and the processing rule (B) generated in step S23 to the demultiplexing circuit 11 (step S24). The demultiplexing circuit 11 that has received the transfer priority (A) and the processing rule (B) changes the setting so as to operate according to the received transfer priority (A) and the processing rule (B).

  Moving to an explanation of the operation of the distribution pattern setting unit 15, when information is input from the communication control unit 20, the distribution pattern setting unit 15 first updates the setting value of the distribution pattern processing based on the input information (step). S31). That is, the distribution pattern setting unit 15 updates the setting value of the distribution pattern process set based on information previously input from the communication control unit 20 based on information newly input from the communication control unit 20. The setting value of the distribution pattern process includes a distribution destination for each type of information stored in the information packet, that is, a value indicating a transfer destination. A value indicating the distribution destination, that is, the transfer destination for each type of various information stored in the information packet is updated when, for example, the number of edge nodes 1 forming the communication system changes. When information is input from the communication control unit 20, the distribution pattern setting unit 15 updates some or all of various values included in the setting value of the distribution pattern process based on the input information. Depending on the content of information input from the communication control unit 20, there may be no setting value that needs to be updated. In this case, the distribution pattern setting unit 15 does not update the setting value of the distribution pattern process. Also, steps S32 to S33 described later are not executed.

  Next, the distribution pattern setting unit 15 generates a distribution process rule (C) based on the set value of the distribution pattern process updated in step S31 (step S32). In step S32, for example, a processing rule including a condition for transferring an information packet storing information that can be processed by the own edge node 1 to another edge node 1 without being processed by the own edge node 1 is generated. The distribution pattern setting unit 15 is based on, for example, the number of other edge nodes 1 having the same function as the own edge node 1, the hardware resources and software resources of these other edge nodes 1, and the like. Thus, there are a plurality of conditions for transferring an information packet storing information that can be processed by the own edge node 1 to another edge node 1 without being processed by the own edge node 1, and a plurality of other edge nodes 1 that are transfer destination candidates. Decide how to select the forwarding destination if it exists.

  Next, the distribution pattern setting unit 15 transmits the processing rule (C) generated in step S32 to the distribution circuit 12 (step S33). The distribution circuit 12 that has received the processing rule (C) changes the setting so as to operate according to the received processing rule (C).

  As described above, in the edge node 1 according to the present embodiment, the edge communication processing unit 10 uses the demultiplexing circuit 11 and the distribution circuit 12 that are configured by the programmable hardware 70 that can change the circuit configuration. Packet transfer processing and information packet multiplexing processing and separation processing are performed. Thereby, in the edge node 1, the edge server 40 included in the own edge device 40 or another edge node 1 receives the information packet received from each terminal 201 via the optical IF unit 50 or the wireless IF unit 60. Since the hardware circuit performs the process of transferring to the terminal 201 via the optical IF unit 50 or the wireless IF unit 60 and the process of transferring the information packet processed by the edge server 40 between the terminal and the edge server Information packets can be transferred from the edge server to the terminal in a predetermined design time. That is, according to the edge node 1 according to the present embodiment, the information packet can reach the transfer destination within a predetermined time. Further, the edge node 1 according to the present embodiment changes various circuit types by changing the circuit configuration of the programmable hardware 70 and changing the scale of the demultiplexing circuit 11 and the distribution circuit 12 and the number of connection destinations. It can be applied to services. Therefore, the edge node 1 according to the present embodiment can constitute a distributed processing system that can support various applications.

  In addition, since the demultiplexing circuit 11 performs a process of collecting a plurality of information packets into one, the amount of communication data is reduced, and the load in the network and the edge node 1 can be reduced.

Embodiment 2. FIG.
FIG. 9 is a diagram of a configuration example of the edge node according to the second embodiment. The edge node 1a according to the second embodiment is obtained by replacing the edge communication processing unit 10 and the communication control unit 20 of the edge node 1 according to the first embodiment with an edge communication processing unit 10a and a communication control unit 20a. Since the other components are the same as those of the edge node 1 of the first embodiment, description thereof is omitted.

  The communication control unit 20a of the edge node 1a includes processing units # 1, # 2, and # 3 that perform processing of the communication control unit 20 of the first embodiment. The communication control unit 20a can simultaneously send three different control instructions, that is, the above-described resource management information and connection management information to the edge communication processing unit 10a. Since each operation | movement of process part # 1, # 2, and # 3 is the same as that of the communication control part 20 of Embodiment 1, detailed description is abbreviate | omitted.

  FIG. 10 is a diagram of a configuration example of the edge communication processing unit 10a according to the second embodiment. The edge communication processing unit 10a includes a demultiplexing circuit 11a, a distribution circuit 12a, a hardware configuration setting unit 13, a multiplexing priority control setting unit 14a, and a distribution pattern setting unit 15a. The demultiplexing circuit 11a and the distribution circuit 12a are realized by programmable hardware 70a. The programmable hardware 70a is the same as the programmable hardware 70 of the first embodiment. In the present embodiment, parts different from the edge communication processing unit 10 of the first embodiment will be described.

  The demultiplexing circuit 11a includes an overall processing circuit 110 and a plurality of processing circuits 111, 112, and 113. The processing circuits 111, 112, and 113 are circuits similar to the multiprocessing circuit 11 of the first embodiment. The demultiplexing circuit 11a can perform in parallel the processing performed by the demultiplexing circuit 11 of the first embodiment, and can simultaneously process a plurality of information packets. The overall processing circuit 110 determines which of the processing circuits 111, 112, and 113 is to process when an information packet is input. For example, every time an information packet is input, the processing circuits 111, 112, and 113 are caused to process the information packet in order.

  The distribution circuit 12a includes a plurality of processing circuits 121, 122, and 123. The processing circuits 121, 122, and 123 are the same circuits as the distribution circuit 12 of the first embodiment. The distribution circuit 12a can perform the processing performed by the distribution circuit 12 of the first embodiment in parallel. The processing circuits 121, 122, and 123 are connected one-to-one with any one of the processing circuits 111, 112, and 113 of the demultiplexing circuit 11a. When the processing circuits 121, 122, and 123 receive the identification information of the information packet from the connected processing circuits 111, 112, or 113, the processing circuits 121, 122, and 123 determine the transfer destination of the information packet.

  The multiplexing priority control setting unit 14a includes an overall processing unit 140 and a plurality of processing units 141, 142, and 143. The processing units 141, 142, and 143 execute the same processing as that of the multiplexing priority control setting unit 14 of the first embodiment. The multiplexing priority control setting unit 14a can perform the processing performed by the multiplexing priority control setting unit 14 of the first embodiment in parallel. The overall processing unit 140 determines which of the processing units 141, 142, and 143 is to process when an information packet is input from the processing unit # 1, # 2, or # 3 of the communication control unit 20a. For example, each time information is input, the processing units 141, 142, and 143 are caused to execute processing in order.

  The distribution pattern setting unit 15a includes a plurality of processing units 151, 152, and 153. The processing units 151, 152, and 153 execute the same processing as the distribution pattern setting unit 15 of the first embodiment. The distribution pattern setting unit 15a can perform the processing performed by the distribution pattern setting unit 15 of the first embodiment in parallel. The processing circuits 151, 152, and 153 are connected one-to-one with any one of the processing circuits 141, 142, and 143 of the multiplexing priority control setting unit 14a. The processing circuits 151, 152, and 153 start processing when information is input from the communication control unit 20a and the connected processing circuit 141, 142, or 143 starts processing.

  In addition, the overall processing unit 140 provided in the multiplexing priority control setting unit 14a and the overall processing circuit 110 provided in the demultiplexing circuit 11a include three units that operate in cooperation with the processing function of the communication control unit 20a. A process for collecting the results of the processing unit and the processing circuit is performed. That is, the processes corresponding to the three different services are executed in parallel at the same time, but the information packet transfer process needs to be summarized. The overall processing unit 140 and the overall processing circuit 110 of the demultiplexing circuit 11a perform the processing.

  FIG. 11 is a diagram illustrating an example of a hardware configuration of the edge communication processing unit 10a according to the second embodiment. The hardware configuration setting unit 13, the multiplexing priority control setting unit 14a and the distribution pattern setting unit 15a of the edge communication processing unit 10a are the same as the hardware configuration setting unit 13, the multiplexing priority control setting unit 14 and the distribution pattern of the first embodiment. Similar to the setting unit 15, it is realized by software. Each of these units can be realized by the processing circuit 80 including the processor 81, the memory 82, the register 83, and the DPRAM 84 shown in FIG. The processing circuit 80 is the same as the processing circuit 80 shown in FIG. That is, the hardware configuration setting unit 13, the multiplexing priority control setting unit 14a, and the distribution pattern setting unit 15a of the edge communication processing unit 10a are read by the processor 81 from the memory 82 and executed by the processor 81. Is realized.

  As described above, the edge node 1a according to the present embodiment is configured to be able to simultaneously execute the processes executed by the edge node 1 according to the first embodiment in parallel. Thereby, for example, it is possible to realize processing corresponding to a plurality of different services using a single system.

  In addition, although the structure which can perform three processes in parallel was shown and demonstrated, the number of processes which can be performed in parallel is not limited to this.

Embodiment 3 FIG.
FIG. 12 is a diagram of a configuration example of the edge communication processing unit of the edge node according to the third embodiment. The overall configuration of the edge node according to the third embodiment is the same as that of the edge node 1 according to the first embodiment except for the edge communication processing unit 10b illustrated in FIG. In this embodiment, parts different from those in Embodiment 1 will be described.

  The edge communication processing unit 10b is obtained by adding a resource allocation circuit 16 and a resource allocation parameter setting unit 17 to the edge communication processing unit 10 included in the edge node 1 according to the first embodiment. The resource allocation circuit 16 and the resource allocation parameter setting unit 17 are components for performing allocation processing of communication resources, that is, wavelengths, time slots, frequencies, and the like in the optical IF unit 50 and the wireless IF unit 60.

  The resource allocation circuit 16 is realized by the programmable hardware 70 b as in the demultiplexing circuit 11 and the distribution circuit 12. The programmable hardware 70b is the same as the programmable hardware 70 of the first embodiment.

  Based on information input from the communication control unit 20, the resource allocation parameter setting unit 17 sets resources such as wavelengths, time slots, and frequencies used when the optical IF unit 50 and the wireless IF unit 60 communicate with the terminal 201 as resources. A rule for assignment by the assignment circuit 16 is generated. The rules created by the resource allocation parameter setting unit 17 are rules used when the resource allocation circuit 16 allocates communication resources used by the edge node in communication with the terminal 201. When the rule is determined, the resource allocation parameter setting unit 17 transmits the rule to the resource allocation circuit 16. The resource allocation circuit 16 generates resource allocation information according to the data amount of the information packet transferred to the optical IF unit 50 and the wireless IF unit 60 according to the rule received from the resource allocation parameter setting unit 17 and generates the demultiplexing circuit 11. Send to. The demultiplexing circuit 11 transmits an information packet using the resource indicated by the information received from the resource allocation circuit 16. At this time, the demultiplexing circuit 11 multiplexes information packets as necessary, as in the first embodiment.

  FIG. 13 is a diagram illustrating an example of a hardware configuration of the edge communication processing unit 10b according to the third embodiment. The hardware configuration setting unit 13, the multiplexing priority control setting unit 14, the distribution pattern setting unit 15, and the resource allocation parameter setting unit 17 of the edge communication processing unit 10 b are the same as the hardware configuration setting unit 13, multiplexing priority of the first embodiment. Similar to the control setting unit 14 and the distribution pattern setting unit 15, it is realized by software. Each of these units can be realized by the processing circuit 80 configured to include the processor 81, the memory 82, the register 83, and the DPRAM 84 shown in FIG. The processing circuit 80 is the same as the processing circuit 80 shown in FIG. That is, the hardware configuration setting unit 13, the multiplexing priority control setting unit 14, the distribution pattern setting unit 15, and the resource allocation parameter setting unit 17 of the edge communication processing unit 10 b are programmed by the processor 81 to realize these units. This is realized by reading from the memory 82 and executing it.

  FIG. 14 is a flowchart showing an example of the operation of the resource allocation parameter setting unit 17. The resource allocation parameter setting unit 17 starts the process illustrated in FIG. 14 when information related to the communication resource is input from the communication control unit 20.

  When the information related to the communication resource is input from the communication control unit 20, the resource allocation parameter setting unit 17 first updates the setting value of the resource allocation parameter process based on the input information (step S 41). In other words, the resource allocation parameter setting unit 17 updates the setting value of the resource allocation parameter processing set based on the information input in the past from the communication control unit 20 based on the information newly input from the communication control unit 20. . The set values of the resource allocation parameter processing include usable wavelengths, frequencies, QoS (Quality of Service) of each terminal 201 connected to the edge node 1, and each terminal 201 connected to the edge node 1 as a contract. This includes the types of services that are available. When the information is input from the communication control unit 20, the resource allocation parameter setting unit 17 updates some or all of the various values included in the setting values of the resource allocation parameter processing based on the input information. . Depending on the content of information input from the communication control unit 20, there may be no setting value that needs to be updated. In that case, the resource allocation parameter setting unit 17 does not update the setting value of the resource allocation parameter process. Also, steps S42 to S43 described later are not executed.

  Next, the resource allocation parameter setting unit 17 generates a resource allocation rule (D) based on the setting value of the resource allocation parameter process updated in step S41 (step S42). In step S42, for example, the bandwidth allocated to each terminal 201 connected to its own edge node 1, the wavelength and frequency for each terminal 201 used in communication with each terminal 201 connected to its own edge node 1, A resource allocation rule including information such as a time slot allocation method is generated.

  Next, the resource allocation parameter setting unit 17 transmits the resource allocation rule (D) generated in step S42 to the resource allocation circuit 16 (step S43). The resource allocation circuit 16 that has received the resource allocation rule (D) changes the setting so as to operate according to the received resource allocation rule (D).

  In general, when using a system in which a distributed processing method is applied to a service that requires a high-speed response, the points for realizing high-speed performance are the transfer time of information packets between the terminal and the edge node and between the age node and the terminal, and The processing time is within a target range. Therefore, depending on the service, scheduling is performed in anticipation that information is transmitted to a terminal after being processed in the edge server 1 by looking at the type of information packet transmitted from the terminal. It is possible. If the contents of this scheduling are incorporated into the resource allocation rule (D) generated by the resource allocation parameter setting unit 17, transmission from the edge server to the terminal is performed based on the type of information packet that is always identified by the distribution circuit 12. The resources required for transferring the information packet can be secured in advance for the optical IF unit 50 or the wireless IF unit 60 accommodating the corresponding terminal.

  As described above, the edge communication processing unit 10b of the information management apparatus according to the third embodiment includes the resource allocation parameter setting unit 17 that generates a resource allocation rule for allocating resources for communication with the terminal 201, and the resource allocation rule. A resource allocation circuit 16 for allocating communication resources is further provided. As a result, it is possible to appropriately secure resources necessary for transferring information packets transmitted from the edge server to the terminal 201 without waste.

Embodiment 4 FIG.
FIG. 15 is a diagram of a configuration example of the edge communication processing unit of the edge node according to the fourth embodiment. The overall configuration of the edge node according to the fourth embodiment is the same as that of the edge node 1 according to the first embodiment except for the edge communication processing unit 10c illustrated in FIG. In the present embodiment, portions different from the first and third embodiments will be described.

  The edge communication processing unit 10c deletes the hardware configuration setting unit 13 from the edge communication processing unit 10b of the third embodiment, and implements the demultiplexing circuit 11, the distribution circuit 12, and the resource allocation circuit 16 with hardware 71 that is not programmable. It has become the composition. The processes executed by the demultiplexing circuit 11, the distribution circuit 12, the multiplexing priority control setting unit 14, the distribution pattern setting unit 15, the resource allocation circuit 16 and the resource allocation parameter setting unit 17 are the edge communication processing unit 10 of the first embodiment. Or it is the same as the process which the circuit to which the same code | symbol of the edge communication process part 10b of Embodiment 3 attached | subjected, or the setting part performs.

  FIG. 16 is a diagram of an example of a hardware configuration of the edge communication processing unit 10c according to the fourth embodiment. The hardware configuration of the edge communication processing unit 10c is obtained by deleting the configuration circuit 90 from the hardware configuration of the edge communication processing unit 10b according to the third embodiment illustrated in FIG. Since the configuration is the same as that of the third embodiment except that the configuration circuit 90 is deleted, description of each hardware is omitted.

  The edge communication processing unit 10c according to the fourth embodiment is difficult to deal with various services and network environments because the demultiplexing circuit 11, the distribution circuit 12, and the resource allocation circuit 16 are not programmable. By integrating these circuits in an IC (Integrated Circuit) as a wear, the cost of the apparatus can be reduced. In addition, although the structure which implement | achieves the edge communication process part 10b concerning Embodiment 3 with the hardware 71 which is not programmable was demonstrated, the edge communication process part 10 concerning Embodiment 1, and the edge communication process concerning Embodiment 2 Even if the unit 10a is realized by non-programmable hardware 71, the cost of the apparatus can be reduced.

  The configuration described in the above embodiment shows an example of the contents of the present invention, and can be combined with another known technique, and can be combined with other configurations without departing from the gist of the present invention. It is also possible to omit or change the part.

  1 edge node, 10 edge communication processing unit, 11 demultiplexing circuit, 12 distribution circuit, 13 hardware configuration setting unit, 14 multiplexing priority control setting unit, 15 distribution pattern setting unit, 16 resource allocation circuit, 17 resource allocation parameter setting Unit, 20 communication control unit, 30 switch unit, 40 edge server, 41 to 43 information processing unit, 50 optical interface unit, 60 wireless interface unit, 70, 70a, 70b programmable hardware, 80, 111 to 113, 121 to 123 , 141 to 143, 151 to 153 processing circuit, 81 processor, 82 memory, 83 register, 84 DPRAM, 90 configuration circuit, 100 network, 101 information processing device, 110 overall processing circuit, 140 overall processing unit, 200 optical access network, 201 terminal, 300 wireless access network.

In order to solve the above-described problems and achieve the object, the node device according to the present invention includes a plurality of edge nodes, and operates as an edge node of a communication system in which the edge nodes cooperate to provide a service. . The node device determines the transfer destination of the received packet that is the received information packet when receiving the information packet and the edge server that processes the information packet transmitted from the user terminal, and the route toward the determined transfer destination And an edge communication processing unit for outputting a received packet to the network. In addition, the node device performs a process for determining a transfer destination of the received packet and a process for outputting the received packet to the route toward the determined transfer destination by a circuit realized by programmable hardware. The edge communication processing unit multiplexes a plurality of distribution packets and a plurality of distribution packets that execute a process of determining a transfer destination of the received packet as an edge server or another edge node based on the identification information of the received packet as a determination process. When a packet in the state is input, it is demultiplexed and separated into a plurality of information packets. If there is an information packet that can be multiplexed, the information packets that can be multiplexed And when the information packet that can be multiplexed does not exist, the transfer determined by the distribution circuit without multiplexing the information packet. And a plurality of demultiplexing circuits that execute, as an output process, a process for outputting to the path toward the destination. Further, the contents of the determination processing by the plurality of distribution circuits are different, and the contents of the output processing by the plurality of demultiplexing circuits are different.

Claims (6)

A node device configured to include a plurality of edge nodes and operating as the edge node of a communication system in which the edge nodes cooperate to provide a service,
An edge server for processing information packets transmitted from user terminals;
An edge communication processing unit that, when receiving the information packet, determines a transfer destination of the received packet that is the received information packet, and outputs the received packet to a route toward the determined transfer destination;
With
The edge communication processing unit performs a process of determining the transfer destination of the received packet and a process of outputting the received packet to a route toward the determined transfer destination by a circuit realized by programmable hardware.
A node device characterized by that. The edge communication processing unit
A distribution circuit that executes, as the determination process, a process of determining the transfer destination of the received packet to the edge server or another edge node based on identification information of the received packet;
When a packet in which a plurality of information packets are multiplexed is input, it is demultiplexed and separated into a plurality of information packets, and if there is an information packet that can be multiplexed, it is multiplexed. Information packets that can be multiplexed and output to the path toward the transfer destination determined by the distribution circuit. If there is no information packet that can be multiplexed, the information packet is multiplexed A demultiplexing circuit that executes, as the output process, a process of outputting to the path toward the transfer destination determined by the distribution circuit
The node device according to claim 1, further comprising: The edge communication processing unit
A plurality of the distribution circuit and the demultiplexing circuit, respectively,
The node device according to claim 2. The edge communication processing unit
A resource allocation circuit realized by the programmable hardware, which determines communication resources to be used in communication with a user terminal based on a predetermined resource allocation rule;
The node device according to claim 2, further comprising: A node device configured to include a plurality of edge nodes and operating as the edge node of a communication system in which the edge nodes cooperate to provide a service,
An edge server for processing information packets transmitted from user terminals;
A distribution circuit that determines a transfer destination to the edge server or another edge node based on identification information of the information packet when the information packet is received;
A demultiplexing circuit that outputs the input information packet to a path toward a transfer destination determined by the distribution circuit when the information packet is input;
A resource allocation circuit for determining a communication resource to be used for communication with the user terminal based on a predetermined resource allocation rule;
With
The distribution circuit, the demultiplexing circuit, and the resource allocation circuit are realized by dedicated hardware.
A node device characterized by that. The demultiplexing circuit includes:
When a packet in which a plurality of information packets are multiplexed is input, it is demultiplexed and separated into a plurality of information packets. If there are a plurality of information packets that can be multiplexed, multiplexing is performed. Multiplexes a plurality of information packets that can be output and outputs the information packet to the route toward the transfer destination determined by the distribution circuit,
The node device according to claim 5, wherein:

Images